diff --git a/tests/pipeline.ipynb b/tests/pipeline.ipynb index cd7c4df..b1dad91 100644 --- a/tests/pipeline.ipynb +++ b/tests/pipeline.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "initial_id", "metadata": { "collapsed": true @@ -17,24 +17,2687 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "f49f7691a27aa7b4", "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The file at ../data/lovd/lovd_data.txt already exists.\n" + ] + } + ], "source": [ "store_database_for_eys_gene(\"lovd\", override=False)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "cf5c45c0f7b9de0f", "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Genes\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idnamechromosomechrom_bandimprintingrefseq_genomicrefseq_UDreferenceurl_homepageurl_external...headerheader_alignfooterfooter_aligncreated_bycreated_dateedited_byedited_dateupdated_byupdated_date
0EYSeyes shut homolog (Drosophila)6q12unknownNG_023443.2UD_132085377375http://www.LOVD.nl/EYS...<font color=\\\"#FF0000\\\">This database is one o...-1-1000012012-02-13 00:00:00000062023-08-30 13:08:19000002024-04-19 20:27:30
\n", + "

1 rows × 34 columns

\n", + "
" + ], + "text/plain": [ + " id name chromosome chrom_band imprinting \n", + "0 EYS eyes shut homolog (Drosophila) 6 q12 unknown \\\n", + "\n", + " refseq_genomic refseq_UD reference url_homepage \n", + "0 NG_023443.2 UD_132085377375 http://www.LOVD.nl/EYS \\\n", + "\n", + " url_external ... header \n", + "0 ... This database is one o... \\\n", + "\n", + " header_align footer footer_align created_by created_date edited_by \n", + "0 -1 -1 00001 2012-02-13 00:00:00 00006 \\\n", + "\n", + " edited_date updated_by updated_date \n", + "0 2023-08-30 13:08:19 00000 2024-04-19 20:27:30 \n", + "\n", + "[1 rows x 34 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Transcripts\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idgeneidnameid_mutalyzerid_ncbiid_ensemblid_protein_ncbiid_protein_ensemblid_protein_uniprotremarksposition_c_mrna_startposition_c_mrna_endposition_c_cds_endposition_g_mrna_startposition_g_mrna_endcreated_bycreated_dateedited_byedited_date
000007329EYStranscript variant 1001NM_001142800.1NP_001136272.1-53810051943566417118644298760000-00-00 00:00:00
\n", + "
" + ], + "text/plain": [ + " id geneid name id_mutalyzer id_ncbi \n", + "0 00007329 EYS transcript variant 1 001 NM_001142800.1 \\\n", + "\n", + " id_ensembl id_protein_ncbi id_protein_ensembl id_protein_uniprot remarks \n", + "0 NP_001136272.1 \\\n", + "\n", + " position_c_mrna_start position_c_mrna_end position_c_cds_end \n", + "0 -538 10051 9435 \\\n", + "\n", + " position_g_mrna_start position_g_mrna_end created_by created_date \n", + "0 66417118 64429876 0000-00-00 00:00:00 \\\n", + "\n", + " edited_by edited_date \n", + "0 " + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Diseases\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idsymbolnameinheritanceid_omimtissuesfeaturesremarkscreated_bycreated_dateedited_byedited_date
000012PSORSpsoriasis, pustular, generalized (PSORS)000062012-07-06 21:50:32000062019-08-12 13:38:21
100058CORDdystrophy, cone-rod (CORD)000062012-09-22 11:31:25000062020-08-30 09:43:59
200112RPretinitis pigmentosa (RP)268000000012013-02-21 17:12:36000062021-01-18 09:53:26
300139IDintellectual disability (ID)000842013-06-04 18:18:07000062015-02-09 10:02:49
400173SLOSSmith-Lemli-Opitz syndrome (SLOS)AR270400000062013-08-01 11:16:14000062021-12-10 21:51:32
500198?unclassified / mixed000062013-09-13 14:21:47000062016-10-22 17:54:40
602156-retinitis pigmentosa, X-linked, and sinorespir...300455000062014-09-25 23:29:40000062021-12-10 21:51:32
702440RP25retinitis pigmentosa, type 25 (RP25)AR602772000062014-09-25 23:29:40000062021-12-10 21:51:32
804211RParretinitis pigmentosa, autosomal recessive (RPar)000062015-02-27 18:58:57
904214-retinal disease000062015-02-27 19:48:07000012023-03-09 14:26:26
1004249macular dystrophydystrophy, macular000062015-05-04 22:10:58000062024-02-15 21:18:39
1105086HLhearing loss (HL)000062015-10-23 11:41:05000062015-10-23 11:43:00
1205415USHUsher syndrome (USH)000062018-04-02 16:40:44
1305468uveitisuveitis000062018-08-22 09:47:04
1406906DEEencephalopathy, developmental and epileptic000062022-04-07 09:24:23
\n", + "
" + ], + "text/plain": [ + " id symbol \n", + "0 00012 PSORS \\\n", + "1 00058 CORD \n", + "2 00112 RP \n", + "3 00139 ID \n", + "4 00173 SLOS \n", + "5 00198 ? \n", + "6 02156 - \n", + "7 02440 RP25 \n", + "8 04211 RPar \n", + "9 04214 - \n", + "10 04249 macular dystrophy \n", + "11 05086 HL \n", + "12 05415 USH \n", + "13 05468 uveitis \n", + "14 06906 DEE \n", + "\n", + " name inheritance id_omim \n", + "0 psoriasis, pustular, generalized (PSORS) \\\n", + "1 dystrophy, cone-rod (CORD) \n", + "2 retinitis pigmentosa (RP) 268000 \n", + "3 intellectual disability (ID) \n", + "4 Smith-Lemli-Opitz syndrome (SLOS) AR 270400 \n", + "5 unclassified / mixed \n", + "6 retinitis pigmentosa, X-linked, and sinorespir... 300455 \n", + "7 retinitis pigmentosa, type 25 (RP25) AR 602772 \n", + "8 retinitis pigmentosa, autosomal recessive (RPar) \n", + "9 retinal disease \n", + "10 dystrophy, macular \n", + "11 hearing loss (HL) \n", + "12 Usher syndrome (USH) \n", + "13 uveitis \n", + "14 encephalopathy, developmental and epileptic \n", + "\n", + " tissues features remarks created_by created_date edited_by \n", + "0 00006 2012-07-06 21:50:32 00006 \\\n", + "1 00006 2012-09-22 11:31:25 00006 \n", + "2 00001 2013-02-21 17:12:36 00006 \n", + "3 00084 2013-06-04 18:18:07 00006 \n", + "4 00006 2013-08-01 11:16:14 00006 \n", + "5 00006 2013-09-13 14:21:47 00006 \n", + "6 00006 2014-09-25 23:29:40 00006 \n", + "7 00006 2014-09-25 23:29:40 00006 \n", + "8 00006 2015-02-27 18:58:57 \n", + "9 00006 2015-02-27 19:48:07 00001 \n", + "10 00006 2015-05-04 22:10:58 00006 \n", + "11 00006 2015-10-23 11:41:05 00006 \n", + "12 00006 2018-04-02 16:40:44 \n", + "13 00006 2018-08-22 09:47:04 \n", + "14 00006 2022-04-07 09:24:23 \n", + "\n", + " edited_date \n", + "0 2019-08-12 13:38:21 \n", + "1 2020-08-30 09:43:59 \n", + "2 2021-01-18 09:53:26 \n", + "3 2015-02-09 10:02:49 \n", + "4 2021-12-10 21:51:32 \n", + "5 2016-10-22 17:54:40 \n", + "6 2021-12-10 21:51:32 \n", + "7 2021-12-10 21:51:32 \n", + "8 \n", + "9 2023-03-09 14:26:26 \n", + "10 2024-02-15 21:18:39 \n", + "11 2015-10-23 11:43:00 \n", + "12 \n", + "13 \n", + "14 " + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Genes_To_Diseases\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
geneiddiseaseid
0EYS00112
1EYS02440
\n", + "
" + ], + "text/plain": [ + " geneid diseaseid\n", + "0 EYS 00112\n", + "1 EYS 02440" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Individuals\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idfatheridmotheridpanelidpanel_sizelicenseowned_byIndividual/ReferenceIndividual/RemarksIndividual/GenderIndividual/ConsanguinityIndividual/Origin/GeographicIndividual/Age_of_deathIndividual/VIPIndividual/Data_avIndividual/TreatmentIndividual/Origin/PopulationIndividual/Individual_ID
000000135300006{PMID:Marrakchi 2011:21848462}5-generation family, 3 affecteds (M)MyesTunisia
100000210100039{PMID:Abu-Safieh-2013:23105016}(Saudi Arabia)
200001962100025M?Germanywhite
3000166051005520
400033096100229{PMID:Neveling 2012:22334370}Mno0
.........................................................
144500447702100006{PMID:Weisschuh 2024:37734845}patient, no family historyFGermany0SRP-1105
144600447707100006{PMID:Weisschuh 2024:37734845}patient, no family historyMGermany0SRP-1167
144700447716100006{PMID:Weisschuh 2024:37734845}patient, no family historyFGermany0SRP-1249
144800447718100006{PMID:Weisschuh 2024:37734845}patient, no family historyMGermany0SRP-1274
144900447720100006{PMID:Weisschuh 2024:37734845}patientMGermany0SRP-1299
\n", + "

1450 rows × 18 columns

\n", + "
" + ], + "text/plain": [ + " id fatherid motherid panelid panel_size license owned_by \n", + "0 00000135 3 00006 \\\n", + "1 00000210 1 00039 \n", + "2 00001962 1 00025 \n", + "3 00016605 1 00552 \n", + "4 00033096 1 00229 \n", + "... ... ... ... ... ... ... ... \n", + "1445 00447702 1 00006 \n", + "1446 00447707 1 00006 \n", + "1447 00447716 1 00006 \n", + "1448 00447718 1 00006 \n", + "1449 00447720 1 00006 \n", + "\n", + " Individual/Reference Individual/Remarks \n", + "0 {PMID:Marrakchi 2011:21848462} 5-generation family, 3 affecteds (M) \\\n", + "1 {PMID:Abu-Safieh-2013:23105016} \n", + "2 \n", + "3 \n", + "4 {PMID:Neveling 2012:22334370} \n", + "... ... ... \n", + "1445 {PMID:Weisschuh 2024:37734845} patient, no family history \n", + "1446 {PMID:Weisschuh 2024:37734845} patient, no family history \n", + "1447 {PMID:Weisschuh 2024:37734845} patient, no family history \n", + "1448 {PMID:Weisschuh 2024:37734845} patient, no family history \n", + "1449 {PMID:Weisschuh 2024:37734845} patient \n", + "\n", + " Individual/Gender Individual/Consanguinity Individual/Origin/Geographic \n", + "0 M yes Tunisia \\\n", + "1 (Saudi Arabia) \n", + "2 M ? Germany \n", + "3 \n", + "4 M no \n", + "... ... ... ... \n", + "1445 F Germany \n", + "1446 M Germany \n", + "1447 F Germany \n", + "1448 M Germany \n", + "1449 M Germany \n", + "\n", + " Individual/Age_of_death Individual/VIP Individual/Data_av \n", + "0 \\\n", + "1 \n", + "2 \n", + "3 0 \n", + "4 0 \n", + "... ... ... ... \n", + "1445 0 \n", + "1446 0 \n", + "1447 0 \n", + "1448 0 \n", + "1449 0 \n", + "\n", + " Individual/Treatment Individual/Origin/Population \n", + "0 \\\n", + "1 \n", + "2 white \n", + "3 \n", + "4 \n", + "... ... ... \n", + "1445 \n", + "1446 \n", + "1447 \n", + "1448 \n", + "1449 \n", + "\n", + " Individual/Individual_ID \n", + "0 \n", + "1 \n", + "2 \n", + "3 \n", + "4 \n", + "... ... \n", + "1445 SRP-1105 \n", + "1446 SRP-1167 \n", + "1447 SRP-1249 \n", + "1448 SRP-1274 \n", + "1449 SRP-1299 \n", + "\n", + "[1450 rows x 18 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Individuals_To_Diseases\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
individualiddiseaseid
00000013500012
10000021000058
20000196200173
30003309604214
40003310904214
.........
14440044770200198
14450044770700198
14460044771600198
14470044771800198
14480044772000198
\n", + "

1449 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " individualid diseaseid\n", + "0 00000135 00012\n", + "1 00000210 00058\n", + "2 00001962 00173\n", + "3 00033096 04214\n", + "4 00033109 04214\n", + "... ... ...\n", + "1444 00447702 00198\n", + "1445 00447707 00198\n", + "1446 00447716 00198\n", + "1447 00447718 00198\n", + "1448 00447720 00198\n", + "\n", + "[1449 rows x 2 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Phenotypes\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddiseaseidindividualidowned_byPhenotype/InheritancePhenotype/AgePhenotype/AdditionalPhenotype/Biochem_paramPhenotype/Age/OnsetPhenotype/Age/DiagnosisPhenotype/Severity_scorePhenotype/OnsetPhenotype/ProteinPhenotype/Tumor/MSIPhenotype/Enzyme/CPKPhenotype/Heart/MyocardiumPhenotype/LungPhenotype/Diagnosis/DefinitePhenotype/Diagnosis/InitialPhenotype/Diagnosis/Criteria
00000000008000120000013500006Familial, autosomal recessive
10000000026000580000021000039Familial, autosomal recessive
20000000941001730000196200025Familial2-3 toe syndactyly5
30000026525042140003309600229Unknownretinitis pigmentosa
40000026538042140003310900229Unknownretinitis pigmentosa
...............................................................
12660000336901001980044770200006Unknownretinitis pigmentosa, simplex
12670000336906001980044770700006Unknownretinitis pigmentosa, simplex
12680000336915001980044771600006Unknownretinitis pigmentosa, simplex
12690000336917001980044771800006Unknownretinitis pigmentosa, simplex
12700000336919001980044772000006Unknownretinitis pigmentosa, simplex
\n", + "

1271 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id diseaseid individualid owned_by \n", + "0 0000000008 00012 00000135 00006 \\\n", + "1 0000000026 00058 00000210 00039 \n", + "2 0000000941 00173 00001962 00025 \n", + "3 0000026525 04214 00033096 00229 \n", + "4 0000026538 04214 00033109 00229 \n", + "... ... ... ... ... \n", + "1266 0000336901 00198 00447702 00006 \n", + "1267 0000336906 00198 00447707 00006 \n", + "1268 0000336915 00198 00447716 00006 \n", + "1269 0000336917 00198 00447718 00006 \n", + "1270 0000336919 00198 00447720 00006 \n", + "\n", + " Phenotype/Inheritance Phenotype/Age Phenotype/Additional \n", + "0 Familial, autosomal recessive \\\n", + "1 Familial, autosomal recessive \n", + "2 Familial 2-3 toe syndactyly \n", + "3 Unknown \n", + "4 Unknown \n", + "... ... ... ... \n", + "1266 Unknown \n", + "1267 Unknown \n", + "1268 Unknown \n", + "1269 Unknown \n", + "1270 Unknown \n", + "\n", + " Phenotype/Biochem_param Phenotype/Age/Onset Phenotype/Age/Diagnosis \n", + "0 \\\n", + "1 \n", + "2 \n", + "3 \n", + "4 \n", + "... ... ... ... \n", + "1266 \n", + "1267 \n", + "1268 \n", + "1269 \n", + "1270 \n", + "\n", + " Phenotype/Severity_score Phenotype/Onset Phenotype/Protein \n", + "0 \\\n", + "1 \n", + "2 5 \n", + "3 \n", + "4 \n", + "... ... ... ... \n", + "1266 \n", + "1267 \n", + "1268 \n", + "1269 \n", + "1270 \n", + "\n", + " Phenotype/Tumor/MSI Phenotype/Enzyme/CPK Phenotype/Heart/Myocardium \n", + "0 \\\n", + "1 \n", + "2 \n", + "3 \n", + "4 \n", + "... ... ... ... \n", + "1266 \n", + "1267 \n", + "1268 \n", + "1269 \n", + "1270 \n", + "\n", + " Phenotype/Lung Phenotype/Diagnosis/Definite \n", + "0 \\\n", + "1 \n", + "2 \n", + "3 \n", + "4 \n", + "... ... ... \n", + "1266 \n", + "1267 \n", + "1268 \n", + "1269 \n", + "1270 \n", + "\n", + " Phenotype/Diagnosis/Initial Phenotype/Diagnosis/Criteria \n", + "0 \n", + "1 \n", + "2 \n", + "3 retinitis pigmentosa \n", + "4 retinitis pigmentosa \n", + "... ... ... \n", + "1266 retinitis pigmentosa, simplex \n", + "1267 retinitis pigmentosa, simplex \n", + "1268 retinitis pigmentosa, simplex \n", + "1269 retinitis pigmentosa, simplex \n", + "1270 retinitis pigmentosa, simplex \n", + "\n", + "[1271 rows x 20 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idindividualidvariants_foundowned_bycreated_bycreated_dateedited_byedited_dateScreening/TechniqueScreening/TemplateScreening/TissueScreening/Remarks
0000000012600000135100006000062012-07-07 19:04:19000062012-07-07 19:12:08RT-PCR;SEQDNA;RNA
1000000021100000210100039000062012-09-22 11:36:24SEQDNA
2000000164000001962100025000062010-03-11 16:36:41000252012-04-13 15:18:00SEQDNA
3000001655700016605100552005522014-05-23 13:12:43SEQ-NG-IDNA
4000003316400033096100229002292012-02-04 15:20:01000062012-05-18 13:59:33SEQ;SEQ-NG-SDNA
.......................................
1445000044927900447702100006000062024-01-26 10:23:59SEQ-NGDNAWGS
1446000044928400447707100006000062024-01-26 10:23:59SEQ-NGDNAWGS
1447000044929300447716100006000062024-01-26 10:23:59SEQ-NGDNAWGS
1448000044929500447718100006000062024-01-26 10:23:59SEQ-NGDNAWGS
1449000044929700447720100006000062024-01-26 10:23:59SEQ-NGDNAWGS
\n", + "

1450 rows × 12 columns

\n", + "
" + ], + "text/plain": [ + " id individualid variants_found owned_by created_by \n", + "0 0000000126 00000135 1 00006 00006 \\\n", + "1 0000000211 00000210 1 00039 00006 \n", + "2 0000001640 00001962 1 00025 00006 \n", + "3 0000016557 00016605 1 00552 00552 \n", + "4 0000033164 00033096 1 00229 00229 \n", + "... ... ... ... ... ... \n", + "1445 0000449279 00447702 1 00006 00006 \n", + "1446 0000449284 00447707 1 00006 00006 \n", + "1447 0000449293 00447716 1 00006 00006 \n", + "1448 0000449295 00447718 1 00006 00006 \n", + "1449 0000449297 00447720 1 00006 00006 \n", + "\n", + " created_date edited_by edited_date Screening/Technique \n", + "0 2012-07-07 19:04:19 00006 2012-07-07 19:12:08 RT-PCR;SEQ \\\n", + "1 2012-09-22 11:36:24 SEQ \n", + "2 2010-03-11 16:36:41 00025 2012-04-13 15:18:00 SEQ \n", + "3 2014-05-23 13:12:43 SEQ-NG-I \n", + "4 2012-02-04 15:20:01 00006 2012-05-18 13:59:33 SEQ;SEQ-NG-S \n", + "... ... ... ... ... \n", + "1445 2024-01-26 10:23:59 SEQ-NG \n", + "1446 2024-01-26 10:23:59 SEQ-NG \n", + "1447 2024-01-26 10:23:59 SEQ-NG \n", + "1448 2024-01-26 10:23:59 SEQ-NG \n", + "1449 2024-01-26 10:23:59 SEQ-NG \n", + "\n", + " Screening/Template Screening/Tissue Screening/Remarks \n", + "0 DNA;RNA \n", + "1 DNA \n", + "2 DNA \n", + "3 DNA \n", + "4 DNA \n", + "... ... ... ... \n", + "1445 DNA WGS \n", + "1446 DNA WGS \n", + "1447 DNA WGS \n", + "1448 DNA WGS \n", + "1449 DNA WGS \n", + "\n", + "[1450 rows x 12 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings_To_Genes\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
screeningidgeneid
00000000126IL36RN
10000000211MKS1
20000001640DHCR7
30000033164AHI1
40000033164EYS
.........
13110000437646EYS
13120000437902EYS
13130000437922EYS
13140000443144EYS
13150000443145EYS
\n", + "

1316 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " screeningid geneid\n", + "0 0000000126 IL36RN\n", + "1 0000000211 MKS1\n", + "2 0000001640 DHCR7\n", + "3 0000033164 AHI1\n", + "4 0000033164 EYS\n", + "... ... ...\n", + "1311 0000437646 EYS\n", + "1312 0000437902 EYS\n", + "1313 0000437922 EYS\n", + "1314 0000443144 EYS\n", + "1315 0000443145 EYS\n", + "\n", + "[1316 rows x 2 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Variants_On_Genome\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idalleleeffectidchromosomeposition_g_startposition_g_endtypeaverage_frequencyowned_byVariantOnGenome/DBID...VariantOnGenome/Genetic_originVariantOnGenome/SegregationVariantOnGenome/dbSNPVariantOnGenome/VIPVariantOnGenome/MethylationVariantOnGenome/ISCNVariantOnGenome/DNA/hg38VariantOnGenome/ClinVarVariantOnGenome/ClinicalClassificationVariantOnGenome/ClinicalClassification/Method
0000003642635066449897164498971subst0.00074292200552EYS_000007...Germline0g.63789078A>GVUS
1000005988135566565575865655758subst0.0011529700229EYS_000001...Germlineyes0g.64945865T>GVUS
2000005988311166533614365336143subst0.22418900229EYS_000002...Germlineno0g.64626250G>Abenign
3000005988411566530086965300869subst0.00083792800229EYS_000003...Germline0g.64590976G>Abenign
4000005988511166501699865016999del000229EYS_000004...Germlineyes0g.64307105_64307106delbenign
..................................................................
2536000096421103066576763465767634subst0.24302202330EYS_000248...CLASSIFICATION recordlikely benign
2537000096421203066576764365767643del002330EYS_000926...CLASSIFICATION recordlikely benign
2538000096421505066600592766005927subst0.00011211202327EYS_000253...CLASSIFICATION recordVUS
2539000096421605066604487466044874subst0.000081897402327EYS_000256...CLASSIFICATION recordVUS
2540000097731409066443094364430943subst0.0000065982201804EYS_000060...CLASSIFICATION recordpathogenic
\n", + "

2541 rows × 26 columns

\n", + "
" + ], + "text/plain": [ + " id allele effectid chromosome position_g_start position_g_end \n", + "0 0000036426 3 50 6 64498971 64498971 \\\n", + "1 0000059881 3 55 6 65655758 65655758 \n", + "2 0000059883 1 11 6 65336143 65336143 \n", + "3 0000059884 1 15 6 65300869 65300869 \n", + "4 0000059885 1 11 6 65016998 65016999 \n", + "... ... ... ... ... ... ... \n", + "2536 0000964211 0 30 6 65767634 65767634 \n", + "2537 0000964212 0 30 6 65767643 65767643 \n", + "2538 0000964215 0 50 6 66005927 66005927 \n", + "2539 0000964216 0 50 6 66044874 66044874 \n", + "2540 0000977314 0 90 6 64430943 64430943 \n", + "\n", + " type average_frequency owned_by VariantOnGenome/DBID ... \n", + "0 subst 0.000742922 00552 EYS_000007 ... \\\n", + "1 subst 0.00115297 00229 EYS_000001 ... \n", + "2 subst 0.224189 00229 EYS_000002 ... \n", + "3 subst 0.000837928 00229 EYS_000003 ... \n", + "4 del 0 00229 EYS_000004 ... \n", + "... ... ... ... ... ... \n", + "2536 subst 0.243022 02330 EYS_000248 ... \n", + "2537 del 0 02330 EYS_000926 ... \n", + "2538 subst 0.000112112 02327 EYS_000253 ... \n", + "2539 subst 0.0000818974 02327 EYS_000256 ... \n", + "2540 subst 0.00000659822 01804 EYS_000060 ... \n", + "\n", + " VariantOnGenome/Genetic_origin VariantOnGenome/Segregation \n", + "0 Germline \\\n", + "1 Germline yes \n", + "2 Germline no \n", + "3 Germline \n", + "4 Germline yes \n", + "... ... ... \n", + "2536 CLASSIFICATION record \n", + "2537 CLASSIFICATION record \n", + "2538 CLASSIFICATION record \n", + "2539 CLASSIFICATION record \n", + "2540 CLASSIFICATION record \n", + "\n", + " VariantOnGenome/dbSNP VariantOnGenome/VIP VariantOnGenome/Methylation \n", + "0 0 \\\n", + "1 0 \n", + "2 0 \n", + "3 0 \n", + "4 0 \n", + "... ... ... ... \n", + "2536 \n", + "2537 \n", + "2538 \n", + "2539 \n", + "2540 \n", + "\n", + " VariantOnGenome/ISCN VariantOnGenome/DNA/hg38 VariantOnGenome/ClinVar \n", + "0 g.63789078A>G \\\n", + "1 g.64945865T>G \n", + "2 g.64626250G>A \n", + "3 g.64590976G>A \n", + "4 g.64307105_64307106del \n", + "... ... ... ... \n", + "2536 \n", + "2537 \n", + "2538 \n", + "2539 \n", + "2540 \n", + "\n", + " VariantOnGenome/ClinicalClassification \n", + "0 VUS \\\n", + "1 VUS \n", + "2 benign \n", + "3 benign \n", + "4 benign \n", + "... ... \n", + "2536 likely benign \n", + "2537 likely benign \n", + "2538 VUS \n", + "2539 VUS \n", + "2540 pathogenic \n", + "\n", + " VariantOnGenome/ClinicalClassification/Method \n", + "0 \n", + "1 \n", + "2 \n", + "3 \n", + "4 \n", + "... ... \n", + "2536 \n", + "2537 \n", + "2538 \n", + "2539 \n", + "2540 \n", + "\n", + "[2541 rows x 26 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Variants_On_Transcripts\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idtranscriptideffectidposition_c_startposition_c_start_intronposition_c_endposition_c_end_intronVariantOnTranscript/DNAVariantOnTranscript/RNAVariantOnTranscript/ProteinVariantOnTranscript/Exon
0000003642600007329507558075580c.7558T>Cr.(?)p.(Phe2520Leu)38
1000005988100007329552309023090c.2309A>Cr.(?)p.(Gln770Pro)15
2000005988300007329113444-53444-5c.3444-5C>Tr.(?)p.(=)22i
3000005988400007329154891048910c.4891C>Tr.(?)p.(Pro1631Ser)26
4000005988500007329116079-46079-3c.6079-4_6079-3delr.(?)p.(=)29i
....................................
2536000096421100007329302024-142024-14c.2024-14C>Tr.(=)p.(=)
2537000096421200007329302024-152024-15c.2024-15delr.(=)p.(=)
2538000096421500007329501852018520c.1852G>Ar.(?)p.(Gly618Ser)
2539000096421600007329501765017650c.1765A>Gr.(?)p.(Arg589Gly)
2540000097731400007329908984089840c.8984T>Ar.(?)p.(Ile2995Asn)
\n", + "

2541 rows × 11 columns

\n", + "
" + ], + "text/plain": [ + " id transcriptid effectid position_c_start \n", + "0 0000036426 00007329 50 7558 \\\n", + "1 0000059881 00007329 55 2309 \n", + "2 0000059883 00007329 11 3444 \n", + "3 0000059884 00007329 15 4891 \n", + "4 0000059885 00007329 11 6079 \n", + "... ... ... ... ... \n", + "2536 0000964211 00007329 30 2024 \n", + "2537 0000964212 00007329 30 2024 \n", + "2538 0000964215 00007329 50 1852 \n", + "2539 0000964216 00007329 50 1765 \n", + "2540 0000977314 00007329 90 8984 \n", + "\n", + " position_c_start_intron position_c_end position_c_end_intron \n", + "0 0 7558 0 \\\n", + "1 0 2309 0 \n", + "2 -5 3444 -5 \n", + "3 0 4891 0 \n", + "4 -4 6079 -3 \n", + "... ... ... ... \n", + "2536 -14 2024 -14 \n", + "2537 -15 2024 -15 \n", + "2538 0 1852 0 \n", + "2539 0 1765 0 \n", + "2540 0 8984 0 \n", + "\n", + " VariantOnTranscript/DNA VariantOnTranscript/RNA \n", + "0 c.7558T>C r.(?) \\\n", + "1 c.2309A>C r.(?) \n", + "2 c.3444-5C>T r.(?) \n", + "3 c.4891C>T r.(?) \n", + "4 c.6079-4_6079-3del r.(?) \n", + "... ... ... \n", + "2536 c.2024-14C>T r.(=) \n", + "2537 c.2024-15del r.(=) \n", + "2538 c.1852G>A r.(?) \n", + "2539 c.1765A>G r.(?) \n", + "2540 c.8984T>A r.(?) \n", + "\n", + " VariantOnTranscript/Protein VariantOnTranscript/Exon \n", + "0 p.(Phe2520Leu) 38 \n", + "1 p.(Gln770Pro) 15 \n", + "2 p.(=) 22i \n", + "3 p.(Pro1631Ser) 26 \n", + "4 p.(=) 29i \n", + "... ... ... \n", + "2536 p.(=) \n", + "2537 p.(=) \n", + "2538 p.(Gly618Ser) \n", + "2539 p.(Arg589Gly) \n", + "2540 p.(Ile2995Asn) \n", + "\n", + "[2541 rows x 11 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings_To_Variants\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
screeningidvariantid
000000001260000783293
100000002110000790459
200000016400000235838
300000165570000036426
400000331640000059884
.........
214400004492790000959046
214500004492840000959051
214600004492930000959060
214700004492950000959474
214800004492970000959064
\n", + "

2149 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " screeningid variantid\n", + "0 0000000126 0000783293\n", + "1 0000000211 0000790459\n", + "2 0000001640 0000235838\n", + "3 0000016557 0000036426\n", + "4 0000033164 0000059884\n", + "... ... ...\n", + "2144 0000449279 0000959046\n", + "2145 0000449284 0000959051\n", + "2146 0000449293 0000959060\n", + "2147 0000449295 0000959474\n", + "2148 0000449297 0000959064\n", + "\n", + "[2149 rows x 2 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "data = parse_lovd(LOVD_PATH + \"/lovd_data.txt\")\n", "for i in data:\n", @@ -44,12 +2707,449 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "ef07740b2fa63e42", "metadata": { "collapsed": false }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Genes\n", + "\n", + "RangeIndex: 1 entries, 0 to 0\n", + "Data columns (total 34 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 1 non-null string \n", + " 1 name 1 non-null string \n", + " 2 chromosome 1 non-null Int64 \n", + " 3 chrom_band 1 non-null string \n", + " 4 imprinting 1 non-null string \n", + " 5 refseq_genomic 1 non-null string \n", + " 6 refseq_UD 1 non-null string \n", + " 7 reference 1 non-null string \n", + " 8 url_homepage 1 non-null string \n", + " 9 url_external 1 non-null string \n", + " 10 allow_download 1 non-null bool \n", + " 11 id_hgnc 1 non-null Int64 \n", + " 12 id_entrez 1 non-null Int64 \n", + " 13 id_omim 1 non-null Int64 \n", + " 14 show_hgmd 1 non-null bool \n", + " 15 show_genecards 1 non-null bool \n", + " 16 show_genetests 1 non-null bool \n", + " 17 show_orphanet 1 non-null bool \n", + " 18 note_index 1 non-null string \n", + " 19 note_listing 1 non-null string \n", + " 20 refseq 1 non-null string \n", + " 21 refseq_url 1 non-null string \n", + " 22 disclaimer 1 non-null bool \n", + " 23 disclaimer_text 1 non-null string \n", + " 24 header 1 non-null string \n", + " 25 header_align 1 non-null Int64 \n", + " 26 footer 1 non-null string \n", + " 27 footer_align 1 non-null Int64 \n", + " 28 created_by 1 non-null Int64 \n", + " 29 created_date 1 non-null datetime64[ns]\n", + " 30 edited_by 1 non-null Int64 \n", + " 31 edited_date 1 non-null datetime64[ns]\n", + " 32 updated_by 1 non-null Int64 \n", + " 33 updated_date 1 non-null datetime64[ns]\n", + "dtypes: Int64(9), bool(6), datetime64[ns](3), string(16)\n", + "memory usage: 367.0 bytes\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Transcripts\n", + "\n", + "RangeIndex: 1 entries, 0 to 0\n", + "Data columns (total 19 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 1 non-null Int64 \n", + " 1 geneid 1 non-null string \n", + " 2 name 1 non-null string \n", + " 3 id_mutalyzer 1 non-null Int64 \n", + " 4 id_ncbi 1 non-null string \n", + " 5 id_ensembl 1 non-null string \n", + " 6 id_protein_ncbi 1 non-null string \n", + " 7 id_protein_ensembl 1 non-null string \n", + " 8 id_protein_uniprot 1 non-null string \n", + " 9 remarks 1 non-null string \n", + " 10 position_c_mrna_start 1 non-null Int64 \n", + " 11 position_c_mrna_end 1 non-null Int64 \n", + " 12 position_c_cds_end 1 non-null Int64 \n", + " 13 position_g_mrna_start 1 non-null Int64 \n", + " 14 position_g_mrna_end 1 non-null Int64 \n", + " 15 created_by 0 non-null Int64 \n", + " 16 created_date 0 non-null datetime64[ns]\n", + " 17 edited_by 0 non-null Int64 \n", + " 18 edited_date 0 non-null datetime64[ns]\n", + "dtypes: Int64(9), datetime64[ns](2), string(8)\n", + "memory usage: 289.0 bytes\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Diseases\n", + "\n", + "RangeIndex: 15 entries, 0 to 14\n", + "Data columns (total 12 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 15 non-null Int64 \n", + " 1 symbol 15 non-null string \n", + " 2 name 15 non-null string \n", + " 3 inheritance 15 non-null string \n", + " 4 id_omim 4 non-null Int64 \n", + " 5 tissues 15 non-null string \n", + " 6 features 15 non-null string \n", + " 7 remarks 15 non-null string \n", + " 8 created_by 15 non-null Int64 \n", + " 9 created_date 15 non-null datetime64[ns]\n", + " 10 edited_by 11 non-null Int64 \n", + " 11 edited_date 11 non-null datetime64[ns]\n", + "dtypes: Int64(4), datetime64[ns](2), string(6)\n", + "memory usage: 1.6 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Genes_To_Diseases\n", + "\n", + "RangeIndex: 2 entries, 0 to 1\n", + "Data columns (total 2 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 geneid 2 non-null string\n", + " 1 diseaseid 2 non-null Int64 \n", + "dtypes: Int64(1), string(1)\n", + "memory usage: 162.0 bytes\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Individuals\n", + "\n", + "RangeIndex: 1450 entries, 0 to 1449\n", + "Data columns (total 18 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 1450 non-null Int64 \n", + " 1 fatherid 1450 non-null string\n", + " 2 motherid 1450 non-null string\n", + " 3 panelid 6 non-null Int64 \n", + " 4 panel_size 1450 non-null Int64 \n", + " 5 license 1450 non-null string\n", + " 6 owned_by 1450 non-null Int64 \n", + " 7 Individual/Reference 1450 non-null string\n", + " 8 Individual/Remarks 1450 non-null string\n", + " 9 Individual/Gender 1450 non-null string\n", + " 10 Individual/Consanguinity 1450 non-null string\n", + " 11 Individual/Origin/Geographic 1450 non-null string\n", + " 12 Individual/Age_of_death 1450 non-null string\n", + " 13 Individual/VIP 1450 non-null string\n", + " 14 Individual/Data_av 1450 non-null string\n", + " 15 Individual/Treatment 1450 non-null string\n", + " 16 Individual/Origin/Population 1450 non-null string\n", + " 17 Individual/Individual_ID 1450 non-null string\n", + "dtypes: Int64(4), string(14)\n", + "memory usage: 209.7 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Individuals_To_Diseases\n", + "\n", + "RangeIndex: 1449 entries, 0 to 1448\n", + "Data columns (total 2 columns):\n", + " # Column Non-Null Count Dtype\n", + "--- ------ -------------- -----\n", + " 0 individualid 1449 non-null Int64\n", + " 1 diseaseid 1449 non-null Int64\n", + "dtypes: Int64(2)\n", + "memory usage: 25.6 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Phenotypes\n", + "\n", + "RangeIndex: 1271 entries, 0 to 1270\n", + "Data columns (total 20 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 1271 non-null Int64 \n", + " 1 diseaseid 1271 non-null Int64 \n", + " 2 individualid 1271 non-null Int64 \n", + " 3 owned_by 1271 non-null Int64 \n", + " 4 Phenotype/Inheritance 1271 non-null string\n", + " 5 Phenotype/Age 1271 non-null string\n", + " 6 Phenotype/Additional 1271 non-null string\n", + " 7 Phenotype/Biochem_param 1271 non-null string\n", + " 8 Phenotype/Age/Onset 1271 non-null string\n", + " 9 Phenotype/Age/Diagnosis 1271 non-null string\n", + " 10 Phenotype/Severity_score 1271 non-null string\n", + " 11 Phenotype/Onset 1271 non-null string\n", + " 12 Phenotype/Protein 1271 non-null string\n", + " 13 Phenotype/Tumor/MSI 1271 non-null string\n", + " 14 Phenotype/Enzyme/CPK 1271 non-null string\n", + " 15 Phenotype/Heart/Myocardium 1271 non-null string\n", + " 16 Phenotype/Lung 1271 non-null string\n", + " 17 Phenotype/Diagnosis/Definite 1271 non-null string\n", + " 18 Phenotype/Diagnosis/Initial 1271 non-null string\n", + " 19 Phenotype/Diagnosis/Criteria 1271 non-null string\n", + "dtypes: Int64(4), string(16)\n", + "memory usage: 203.7 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings\n", + "\n", + "RangeIndex: 1450 entries, 0 to 1449\n", + "Data columns (total 12 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 1450 non-null Int64 \n", + " 1 individualid 1450 non-null Int64 \n", + " 2 variants_found 1450 non-null Int64 \n", + " 3 owned_by 1450 non-null Int64 \n", + " 4 created_by 1450 non-null Int64 \n", + " 5 created_date 1450 non-null datetime64[ns]\n", + " 6 edited_by 15 non-null Int64 \n", + " 7 edited_date 15 non-null datetime64[ns]\n", + " 8 Screening/Technique 1450 non-null string \n", + " 9 Screening/Template 1450 non-null string \n", + " 10 Screening/Tissue 1450 non-null string \n", + " 11 Screening/Remarks 1450 non-null string \n", + "dtypes: Int64(6), datetime64[ns](2), string(4)\n", + "memory usage: 144.6 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings_To_Genes\n", + "\n", + "RangeIndex: 1316 entries, 0 to 1315\n", + "Data columns (total 2 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 screeningid 1316 non-null Int64 \n", + " 1 geneid 1316 non-null string\n", + "dtypes: Int64(1), string(1)\n", + "memory usage: 22.0 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Variants_On_Genome\n", + "\n", + "RangeIndex: 2541 entries, 0 to 2540\n", + "Data columns (total 26 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 2541 non-null Int64 \n", + " 1 allele 2541 non-null Int64 \n", + " 2 effectid 2541 non-null Int64 \n", + " 3 chromosome 2541 non-null Int64 \n", + " 4 position_g_start 2540 non-null Int64 \n", + " 5 position_g_end 2540 non-null Int64 \n", + " 6 type 2541 non-null string \n", + " 7 average_frequency 2540 non-null float64\n", + " 8 owned_by 2541 non-null Int64 \n", + " 9 VariantOnGenome/DBID 2541 non-null string \n", + " 10 VariantOnGenome/DNA 2541 non-null string \n", + " 11 VariantOnGenome/Frequency 2541 non-null string \n", + " 12 VariantOnGenome/Reference 2541 non-null string \n", + " 13 VariantOnGenome/Restriction_site 2541 non-null string \n", + " 14 VariantOnGenome/Published_as 2541 non-null string \n", + " 15 VariantOnGenome/Remarks 2541 non-null string \n", + " 16 VariantOnGenome/Genetic_origin 2541 non-null string \n", + " 17 VariantOnGenome/Segregation 2541 non-null string \n", + " 18 VariantOnGenome/dbSNP 2541 non-null string \n", + " 19 VariantOnGenome/VIP 2541 non-null string \n", + " 20 VariantOnGenome/Methylation 2541 non-null string \n", + " 21 VariantOnGenome/ISCN 2541 non-null string \n", + " 22 VariantOnGenome/DNA/hg38 2541 non-null string \n", + " 23 VariantOnGenome/ClinVar 2541 non-null string \n", + " 24 VariantOnGenome/ClinicalClassification 2541 non-null string \n", + " 25 VariantOnGenome/ClinicalClassification/Method 2541 non-null string \n", + "dtypes: Int64(7), float64(1), string(18)\n", + "memory usage: 533.6 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Variants_On_Transcripts\n", + "\n", + "RangeIndex: 2541 entries, 0 to 2540\n", + "Data columns (total 11 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 2541 non-null Int64 \n", + " 1 transcriptid 2541 non-null Int64 \n", + " 2 effectid 2541 non-null Int64 \n", + " 3 position_c_start 2540 non-null Int64 \n", + " 4 position_c_start_intron 2541 non-null Int64 \n", + " 5 position_c_end 2540 non-null Int64 \n", + " 6 position_c_end_intron 2541 non-null Int64 \n", + " 7 VariantOnTranscript/DNA 2541 non-null string\n", + " 8 VariantOnTranscript/RNA 2541 non-null string\n", + " 9 VariantOnTranscript/Protein 2541 non-null string\n", + " 10 VariantOnTranscript/Exon 2541 non-null string\n", + "dtypes: Int64(7), string(4)\n", + "memory usage: 235.9 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Screenings_To_Variants\n", + "\n", + "RangeIndex: 2149 entries, 0 to 2148\n", + "Data columns (total 2 columns):\n", + " # Column Non-Null Count Dtype\n", + "--- ------ -------------- -----\n", + " 0 screeningid 2149 non-null Int64\n", + " 1 variantid 2149 non-null Int64\n", + "dtypes: Int64(2)\n", + "memory usage: 37.9 KB\n" + ] + }, + { + "data": { + "text/plain": [ + "None" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "set_lovd_dtypes(data)\n", "for i in data:\n", @@ -59,10 +3159,193 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "d5ee0724", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idalleleeffectidchromosomeposition_g_startposition_g_endtypeaverage_frequencyowned_byVariantOnGenome/DBID...VariantOnGenome/Genetic_originVariantOnGenome/SegregationVariantOnGenome/dbSNPVariantOnGenome/VIPVariantOnGenome/MethylationVariantOnGenome/ISCNVariantOnGenome/DNA/hg38VariantOnGenome/ClinVarVariantOnGenome/ClinicalClassificationVariantOnGenome/ClinicalClassification/Method
15988135566565575865655758subst0.001153229EYS_000001...Germlineyes0g.64945865T>GVUS
\n", + "

1 rows × 26 columns

\n", + "
" + ], + "text/plain": [ + " id allele effectid chromosome position_g_start position_g_end type \n", + "1 59881 3 55 6 65655758 65655758 subst \\\n", + "\n", + " average_frequency owned_by VariantOnGenome/DBID ... \n", + "1 0.001153 229 EYS_000001 ... \\\n", + "\n", + " VariantOnGenome/Genetic_origin VariantOnGenome/Segregation \n", + "1 Germline yes \\\n", + "\n", + " VariantOnGenome/dbSNP VariantOnGenome/VIP VariantOnGenome/Methylation \n", + "1 0 \\\n", + "\n", + " VariantOnGenome/ISCN VariantOnGenome/DNA/hg38 VariantOnGenome/ClinVar \n", + "1 g.64945865T>G \\\n", + "\n", + " VariantOnGenome/ClinicalClassification \n", + "1 VUS \\\n", + "\n", + " VariantOnGenome/ClinicalClassification/Method \n", + "1 \n", + "\n", + "[1 rows x 26 columns]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "'Variant scoring:'" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ChromPosRefAltRawScorePHRED
0665655758AC0.9175169.431
1665655758AG0.9341189.597
2665655758AT0.6091546.542
\n", + "
" + ], + "text/plain": [ + " Chrom Pos Ref Alt RawScore PHRED\n", + "0 6 65655758 A C 0.917516 9.431\n", + "1 6 65655758 A G 0.934118 9.597\n", + "2 6 65655758 A T 0.609154 6.542" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "from tools import (fetch_cadd_score, fetch_cadd_scores)\n", "import pandas as pd\n", @@ -85,6 +3368,1334 @@ "display(score_df)\n", " " ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c968af1617be40db", + "metadata": { + "ExecuteTime": { + "end_time": "2024-05-13T15:38:25.149624Z", + "start_time": "2024-05-13T15:38:24.807199Z" + } + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING:root:Skipping variant g.64307105_64307106del\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64902422_64902438del\n", + "WARNING:root:Skipping variant g.64902422_64902438del\n", + "WARNING:root:Skipping variant g.64840707_64997105del\n", + "WARNING:root:Skipping variant g.64840707_64997105del\n", + "WARNING:root:Skipping variant g.64840707_64997105del\n", + "WARNING:root:Skipping variant g.65295915del\n", + "WARNING:root:Skipping variant g.65295915del\n", + "WARNING:root:Skipping variant g.65295915del\n", + "WARNING:root:Skipping variant g.65057728_65320715del\n", + "WARNING:root:Skipping variant g.65057728_65320715del\n", + "WARNING:root:Skipping variant g.65057728_65320715del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65384425del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64439165del\n", + "WARNING:root:Skipping variant g.64439165del\n", + "WARNING:root:Skipping variant g.64626122del\n", + "WARNING:root:Skipping variant g.65494867del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65494867del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.63720919_63720920del\n", + "WARNING:root:Skipping variant g.63720668dup\n", + "WARNING:root:Skipping variant g.63720919_63720920del\n", + "WARNING:root:Skipping variant g.63720668dup\n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant g.64591039_64591042del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64822643dup\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.64591505_64591506delinsCT\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65384480dup\n", + "WARNING:root:Skipping variant g.63726599_63726600del\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.63726599_63726600del\n", + "WARNING:root:Skipping variant g.65495005_65495008delinsAAG\n", + "WARNING:root:Skipping variant g.63726599_63726600del\n", + "WARNING:root:Skipping variant g.65335102del\n", + "WARNING:root:Skipping variant g.65335102del\n", + "WARNING:root:Skipping variant g.65335102del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.65321830_65370656del\n", + "WARNING:root:Skipping variant g.63720850_63720853del\n", + "WARNING:root:Skipping variant g.65321830_65370656del\n", + "WARNING:root:Skipping variant g.63720850_63720853del\n", + "WARNING:root:Skipping variant g.65321830_65370656del\n", + "WARNING:root:Skipping variant g.63720850_63720853del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63806240del\n", + "WARNING:root:Skipping variant g.63806240del\n", + "WARNING:root:Skipping variant g.65495332_65495333dup\n", + "WARNING:root:Skipping variant g.65324960_65416038del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65295915del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.65494988_65495003del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65384480dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65344144_65344152delinsCTTTTCG\n", + "WARNING:root:Skipping variant g.63984409_63984410delinsACGAT\n", + "WARNING:root:Skipping variant g.63788163_63788164del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64912603dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590700dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590700dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64591845del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63984390del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63721651_63721652insCA\n", + "WARNING:root:Skipping variant g.64590665_64590666del\n", + "WARNING:root:Skipping variant g.63721651_63721652insCA\n", + "WARNING:root:Skipping variant g.64590665_64590666del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64591466dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64591480del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63788136del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64912603dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590665_64590666del\n", + "WARNING:root:Skipping variant g.63721652_63721655dup\n", + "WARNING:root:Skipping variant g.64590665_64590666del\n", + "WARNING:root:Skipping variant g.63721652_63721655dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64912603dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64591313del\n", + "WARNING:root:Skipping variant g.64439355_64439356insA\n", + "WARNING:root:Skipping variant g.63984543_63984570del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63984537_63984542dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64614795_64939832del\n", + "WARNING:root:Skipping variant g.64614795_64939832del\n", + "WARNING:root:Skipping variant g.64614795_64939832del\n", + "WARNING:root:Skipping variant g.63721576del\n", + "WARNING:root:Skipping variant g.64902132_64902133del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720889dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63721625dup\n", + "WARNING:root:Skipping variant g.65405300dup\n", + "WARNING:root:Skipping variant g.64813506del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63720753_63720754dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.65405325dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.65707136_65707226del\n", + "WARNING:root:Skipping variant g.65495348del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63720845_63720846del\n", + "WARNING:root:Skipping variant g.63726607del\n", + "WARNING:root:Skipping variant g.63721786dup\n", + "WARNING:root:Skipping variant g.63721640del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65344138dup\n", + "WARNING:root:Skipping variant g.65402503del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590699_64590700del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590699_64590700del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65384384_65384387del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65384480dup\n", + "WARNING:root:Skipping variant g.63806228dup\n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65384384_65384387del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64439331del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65494957dup\n", + "WARNING:root:Skipping variant g.63720995del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63721771_63721776del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.65494957dup\n", + "WARNING:root:Skipping variant g.64591977del\n", + "WARNING:root:Skipping variant g.64886728_64886736del\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.63721138del\n", + "WARNING:root:Skipping variant g.65353541del\n", + "WARNING:root:Skipping variant g.65353541del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65494988_65495002del\n", + "WARNING:root:Skipping variant g.65295857dup\n", + "WARNING:root:Skipping variant g.65295856_65295857dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64307105_64307106del\n", + "WARNING:root:Skipping variant g.64307103_64307106del\n", + "WARNING:root:Skipping variant g.63726618_63726622del\n", + "WARNING:root:Skipping variant g.63720642_63720644del\n", + "WARNING:root:Skipping variant g.65295857dup\n", + "WARNING:root:Skipping variant g.64307105_64307106del\n", + "WARNING:root:Skipping variant g.65353541del\n", + "WARNING:root:Skipping variant g.64591918_64591919del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64590525_64590548del\n", + "WARNING:root:Skipping variant g.64388841_64388843del\n", + "WARNING:root:Skipping variant g.64307084_64307085del\n", + "WARNING:root:Skipping variant g.64307105_64307106del\n", + "WARNING:root:Skipping variant g.64307103_64307106del\n", + "WARNING:root:Skipping variant g.64307105_64307106del\n", + "WARNING:root:Skipping variant g.64593097_64593101del\n", + "WARNING:root:Skipping variant g.65384384_65384387del\n", + "WARNING:root:Skipping variant g.63999110_63999111del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64439213del\n", + "WARNING:root:Skipping variant g.63721771_63721776del\n", + "WARNING:root:Skipping variant g.65494957dup\n", + "WARNING:root:Skipping variant g.65494988_65495008delinsAAAAG\n", + "WARNING:root:Skipping variant g.63720799_63720808del\n", + "WARNING:root:Skipping variant g.63726584del\n", + "WARNING:root:Skipping variant g.63726599_63726600del\n", + "WARNING:root:Skipping variant g.63726648del\n", + "WARNING:root:Skipping variant g.64349976_64426764del\n", + "WARNING:root:Skipping variant g.64591505_64591506delinsCT\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720728_63720729del\n", + "WARNING:root:Skipping variant g.63720845_63720846del\n", + "WARNING:root:Skipping variant g.63721162del\n", + "WARNING:root:Skipping variant g.63721237_63721240del\n", + "WARNING:root:Skipping variant g.63721343del\n", + "WARNING:root:Skipping variant g.63721730_63721733del\n", + "WARNING:root:Skipping variant g.63721763_63721767del\n", + "WARNING:root:Skipping variant g.63721787dup\n", + "WARNING:root:Skipping variant g.63726618_63726622del\n", + "WARNING:root:Skipping variant g.63788163_63788164del\n", + "WARNING:root:Skipping variant g.63984389del\n", + "WARNING:root:Skipping variant g.64066348del\n", + "WARNING:root:Skipping variant g.64590909dup\n", + "WARNING:root:Skipping variant g.64591309del\n", + "WARNING:root:Skipping variant g.64591858_64591859del\n", + "WARNING:root:Skipping variant g.64886728_64886736del\n", + "WARNING:root:Skipping variant g.64945814del\n", + "WARNING:root:Skipping variant g.65344143_65344144insCTTT\n", + "WARNING:root:Skipping variant g.65344146_65344151del\n", + "WARNING:root:Skipping variant g.65344181dup\n", + "WARNING:root:Skipping variant g.65384473dup\n", + "WARNING:root:Skipping variant g.65405287del\n", + "WARNING:root:Skipping variant g.65494885_65494887del\n", + "WARNING:root:Skipping variant g.65494961del\n", + "WARNING:root:Skipping variant g.65495205del\n", + "WARNING:root:Skipping variant g.65495296_65495297del\n", + "WARNING:root:Skipping variant g.64590909dup\n", + "WARNING:root:Skipping variant g.65384473dup\n", + "WARNING:root:Skipping variant g.65405287del\n", + "WARNING:root:Skipping variant g.65494885_65494887del\n", + "WARNING:root:Skipping variant g.63762589del\n", + "WARNING:root:Skipping variant g.63720874del\n", + "WARNING:root:Skipping variant g.63721619_63721620insGT\n", + "WARNING:root:Skipping variant g.63788268dup\n", + "WARNING:root:Skipping variant g.63984369_63984392del\n", + "WARNING:root:Skipping variant g.65057740_65057741insA\n", + "WARNING:root:Skipping variant g.65057740_65057741insAA\n", + "WARNING:root:Skipping variant g.65057750dup\n", + "WARNING:root:Skipping variant g.65384384_65384387del\n", + "WARNING:root:Skipping variant g.65402624dup\n", + "WARNING:root:Skipping variant g.65405377dup\n", + "WARNING:root:Skipping variant g.65494957dup\n", + "WARNING:root:Skipping variant g.65494957dup\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.63721625dup\n", + "WARNING:root:Skipping variant g.63721704dup\n", + "WARNING:root:Skipping variant g.65353537dup\n", + "WARNING:root:Skipping variant g.65335105_65335108del\n", + "WARNING:root:Skipping variant g.63721385_63721386del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64439195del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63720867_63720868del\n", + "WARNING:root:Skipping variant g.63721314_63721321del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63765706_63791377del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63781919_63803805del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64892926_64948294del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64591845del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64945857dup\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63721557_63721558insA\n", + "WARNING:root:Skipping variant g.64439319_64439323del\n", + "WARNING:root:Skipping variant g.65296021del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65384425del\n", + "WARNING:root:Skipping variant g.64591039_64591042del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63721599_63721604del\n", + "WARNING:root:Skipping variant g.64902132_64902133del\n", + "WARNING:root:Skipping variant g.65494988_65495008delinsAAAAG\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65495236del\n", + "WARNING:root:Skipping variant g.64590908_64590909insT\n", + "WARNING:root:Skipping variant g.64617409_64617411dup\n", + "WARNING:root:Skipping variant g.65295857dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63720845_63720846del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720668dup\n", + "WARNING:root:Skipping variant g.(63741975_63762461)_(63778180_63788105)dup\n", + "WARNING:root:Skipping variant g.65296051_65296052del\n", + "WARNING:root:Skipping variant g.65296051_65296052del\n", + "WARNING:root:Skipping variant g.64439200dup\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.65494885_65494887del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63984390del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65295897del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65494885_65494887del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590615dup\n", + "WARNING:root:Skipping variant g.63721705del\n", + "WARNING:root:Skipping variant g.64081884del\n", + "WARNING:root:Skipping variant g.65405342_65405355delinsAAA\n", + "WARNING:root:Skipping variant g.65490640_65490643dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65296058del\n", + "WARNING:root:Skipping variant g.65405345del\n", + "WARNING:root:Skipping variant g.(65405368_65490593)_(65495411_?)del\n", + "WARNING:root:Skipping variant g.(65353618_65384385)_(65405368_65490593)del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64081885_64081888del\n", + "WARNING:root:Skipping variant g.64591401_64591408dup\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63721237_63721240del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64591256_64591272del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.63721436del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64591039_64591042del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.63720695_63720714del\n", + "WARNING:root:Skipping variant g.65384480dup\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.65495064del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066470_64066473del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066470_64066473del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.63720695_63720714del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720668del\n", + "WARNING:root:Skipping variant g.64912603dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.64902132_64902133del\n", + "WARNING:root:Skipping variant g.63720954dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64066335del\n", + "WARNING:root:Skipping variant g.64886711del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.63778166_63778172del\n", + "WARNING:root:Skipping variant g.64590914dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63726618_63726622del\n", + "WARNING:root:Skipping variant g.64886728_64886736del\n", + "WARNING:root:Skipping variant g.64893157_64947352del\n", + "WARNING:root:Skipping variant g.64797009_64846087del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.63726519del\n", + "WARNING:root:Skipping variant g.64997275_64998015del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64081605_64082252del\n", + "WARNING:root:Skipping variant g.63777755_63789474dup\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.64081605_64082252del\n", + "WARNING:root:Skipping variant g.65353208_65353867del\n", + "WARNING:root:Skipping variant g.63984134_63984854del\n", + "WARNING:root:Skipping variant g.63743557_63907234del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.64662532_64979780del\n", + "WARNING:root:Skipping variant g.64839119_64970113del\n", + "WARNING:root:Skipping variant g.63720872_63720873del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64081885_64081888del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.63720682dup\n", + "WARNING:root:Skipping variant g.63721619dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64388841del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63720649_63720653del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63720695_63720714del\n", + "WARNING:root:Skipping variant g.65384384_65384387del\n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.65335105_65335108del\n", + "WARNING:root:Skipping variant g.64439165del\n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63998527_64002156del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.65495379dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.63721237_63721240del\n", + "WARNING:root:Skipping variant g.63721237_63721240del\n", + "WARNING:root:Skipping variant g.63721237_63721240del\n", + "WARNING:root:Skipping variant g.64081885_64081888del\n", + "WARNING:root:Skipping variant g.65495348dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64439331del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64912705del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64439200dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.65495181del\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.63721625dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.65384480del\n", + "WARNING:root:Skipping variant g.64388841_64388843del\n", + "WARNING:root:Skipping variant g.63998527_64002156del\n", + "WARNING:root:Skipping variant g.64590525_64590550delinsTA\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64081884del\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.216327637C>T\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.215879068C>T\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.215878931del\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.65384480dup\n", + "WARNING:root:Skipping variant g.216073265G>A\n", + "WARNING:root:Skipping variant g.65495206_65495207insTGCCAGTTTA\n", + "WARNING:root:Skipping variant g.63721227dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.63720990_63720991insATAT\n", + "WARNING:root:Skipping variant g.63720728_63720729del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720947_63720948insT\n", + "WARNING:root:Skipping variant g.64590875_64590876insTCTT\n", + "WARNING:root:Skipping variant g.63721432del\n", + "WARNING:root:Skipping variant g.64591501_64591502insAGAA\n", + "WARNING:root:Skipping variant g.64590556_64590566del\n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant g.63720753_63720754dup\n", + "WARNING:root:Skipping variant g.(?_64945792)_(64945915_64997581)del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63720730_63720733del\n", + "WARNING:root:Skipping variant g.63721377_63721384del\n", + "WARNING:root:Skipping variant g.63726524del\n", + "WARNING:root:Skipping variant g.64423168_64798957delinsATGA\n", + "WARNING:root:Skipping variant g.63942752_64337822delinsATTATG\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant g.?\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64423168_64798957delinsATGA\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63942752_64337822delinsATTATG\n", + "WARNING:root:Skipping variant g.63957115_63958454del\n", + "WARNING:root:Skipping variant g.65001113_65005820del\n", + "WARNING:root:Skipping variant g.65550144_65552138del\n", + "WARNING:root:Skipping variant g.65689153_65694794del\n", + "WARNING:root:Skipping variant g.65454073_65454074insN[305]\n", + "WARNING:root:Skipping variant g.64296539_64296632del\n", + "WARNING:root:Skipping variant g.65204982_65205044del\n", + "WARNING:root:Skipping variant g.65564961_65565284del\n", + "WARNING:root:Skipping variant :g.64295412_64295413insN[118]\n", + "WARNING:root:Skipping variant g.65278328_65278329insN[59]\n", + "WARNING:root:Skipping variant g.64590911dup\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64590875_64590876insTCTT\n", + "WARNING:root:Skipping variant g.63720947_63720948insT\n", + "WARNING:root:Skipping variant g.64591501_64591502insAGAA\n", + "WARNING:root:Skipping variant g.63721432del\n", + "WARNING:root:Skipping variant g.64590556_64590566del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.65658176_65718924del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant NM_001142800.2:c.6079-2A>G\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.63999116del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.64986218_65013355del\n", + "WARNING:root:Skipping variant g.64388690_64388840del\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant g.(?_63719980)_(63726681_63762460)dup\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.65274506_65316845delinsAGATCA\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.65494100_65508832del\n", + "WARNING:root:Skipping variant g.65213025_65296862delinsGTTTTCTTTTTA\n", + "WARNING:root:Skipping variant g.64066349del\n", + "WARNING:root:Skipping variant g.64602159_64657461dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63762589del\n", + "WARNING:root:Skipping variant g.65383303_65441305delinsAACTTTTACT\n", + "WARNING:root:Skipping variant g.63720737_63720746del\n", + "WARNING:root:Skipping variant g.65284957_66872862delinsT\n", + "WARNING:root:Skipping variant g.64122444_64129159delins64204448_64235506inv\n", + "WARNING:root:Skipping variant g.64937848_64948401delins[64944099_64944163inv;CAATTTTGTAT]\n", + "WARNING:root:Skipping variant g.63721385_63721386del\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63720654_63720657del\n", + "WARNING:root:Skipping variant g.64591069_64591081del\n", + "WARNING:root:Skipping variant g.64886841del\n", + "WARNING:root:Skipping variant g.64790603_64977512del\n", + "WARNING:root:Skipping variant g.63721625dup\n", + "WARNING:root:Skipping variant g.64591514_64591520del\n", + "WARNING:root:Skipping variant g.63720649_63720653del\n", + "WARNING:root:Skipping variant g.65479942_67131267inv\n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n", + "WARNING:root:Skipping variant \n" + ] + } + ], + "source": [ + "save_lovd_as_vcf(data[\"Variants_On_Genome\"], \"./lovd.vcf\")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c7ff16903e0c52bd", + "metadata": { + "ExecuteTime": { + "end_time": "2024-05-13T15:58:47.868055Z", + "start_time": "2024-05-13T15:58:41.380466Z" + } + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "2024-05-13 18:58:41.794056: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", + "2024-05-13 18:58:41.794769: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2024-05-13 18:58:41.797917: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", + "2024-05-13 18:58:41.857361: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", + "2024-05-13 18:58:42.410244: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n", + "2024-05-13 18:58:42.957291: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n", + "2024-05-13 18:58:42.957684: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2251] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n", + "Skipping registering GPU devices...\n", + "WARNING:absl:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.\n", + "WARNING:absl:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.\n", + "WARNING:absl:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.\n", + "WARNING:absl:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.\n", + "WARNING:absl:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 595ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 554ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 553ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING:tensorflow:5 out of the last 5 calls to .one_step_on_data_distributed at 0x7dee981abf40> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n", + "WARNING:tensorflow:5 out of the last 5 calls to .one_step_on_data_distributed at 0x7dee981abf40> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 548ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n", + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING:root:dede['G|EYS|0.00|0.00|0.00|0.00|3|9|-20|9']\n" + ] + }, + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from subprocess import Popen\n", + "\n", + "\n", + "process = Popen(\"spliceai -I ./lovd.vcf -O ./lovd_output.vcf -R ../tools/spliceai/hg38.fa -A grch38\".split())\n", + "process.wait()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6a424607361ab528", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -96,14 +4707,14 @@ "language_info": { "codemirror_mode": { "name": "ipython", - "version": 3 + "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.12.3" + "pygments_lexer": "ipython2", + "version": "2.7.6" } }, "nbformat": 4,