{"id":"https://openalex.org/W4306896934","doi":"https://doi.org/10.1371/journal.pcbi.1009880","title":"Deep mendelian randomization: Investigating the causal knowledge of genomic deep learning models","display_name":"Deep mendelian randomization: Investigating the causal knowledge of genomic deep learning models","publication_year":2022,"publication_date":"2022-10-20","ids":{"openalex":"https://openalex.org/W4306896934","doi":"https://doi.org/10.1371/journal.pcbi.1009880","pmid":"https://pubmed.ncbi.nlm.nih.gov/36265006"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009880","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009880","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009880&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009880&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037926200","display_name":"Stephen Malina","orcid":"https://orcid.org/0000-0002-7383-0094"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephen Malina","raw_affiliation_strings":["Department of Computer Science, Columbia University, New York, New York, United States of America","Dyno Therapeutics, Watertown, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-7383-0094","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, New York, United States of America","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Dyno Therapeutics, Watertown, Massachusetts, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039861104","display_name":"Daniel Cizin","orcid":"https://orcid.org/0000-0002-6908-6792"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4210100942","display_name":"Tri-Institutional PhD Program in Chemical Biology","ror":"https://ror.org/016twdg30","country_code":"US","type":"education","lineage":["https://openalex.org/I4210100942"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Cizin","raw_affiliation_strings":["Department of Computer Science, Columbia University, New York, New York, United States of America","Tri-Institutional Ph.D. Program in Computational Biology and Medicine, Weill Cornell Medicine, New York, New York, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6908-6792","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, New York, United States of America","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Tri-Institutional Ph.D. Program in Computational Biology and Medicine, Weill Cornell Medicine, New York, New York, United States of America","institution_ids":["https://openalex.org/I4210100942","https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012226169","display_name":"David A. Knowles","orcid":"https://orcid.org/0000-0002-7408-146X"},"institutions":[{"id":"https://openalex.org/I4210151462","display_name":"New York Genome Center","ror":"https://ror.org/05wf2ga96","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210151462"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Knowles","raw_affiliation_strings":["Data Science Institute, Columbia University, New York, New York, United States of America","Department of Computer Science, Columbia University, New York, New York, United States of America","Department of Systems Biology, Columbia University, New York, New York, United States of America","New York Genome Center, New York, New York, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-7408-146X","affiliations":[{"raw_affiliation_string":"Data Science Institute, Columbia University, New York, New York, United States of America","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, New York, United States of America","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Systems Biology, Columbia University, New York, New York, United States of America","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"New York Genome Center, New York, New York, United States of America","institution_ids":["https://openalex.org/I4210151462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037926200"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":1.1261,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.76886187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"18","issue":"10","first_page":"e1009880","last_page":"e1009880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10604","display_name":"RNA Research and Splicing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mendelian-randomization","display_name":"Mendelian randomization","score":0.6567552089691162},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6089983582496643},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5237579345703125},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5055248737335205},{"id":"https://openalex.org/keywords/in-silico","display_name":"In silico","score":0.4994666576385498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4494575262069702},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4367252588272095},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.42473796010017395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064645767211914},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3267246186733246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1991797387599945},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.18704089522361755},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1847161054611206},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15062189102172852},{"id":"https://openalex.org/keywords/genetic-variants","display_name":"Genetic variants","score":0.09675627946853638}],"concepts":[{"id":"https://openalex.org/C2779901538","wikidata":"https://www.wikidata.org/wiki/Q6816584","display_name":"Mendelian randomization","level":5,"score":0.6567552089691162},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6089983582496643},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5237579345703125},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5055248737335205},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.4994666576385498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4494575262069702},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4367252588272095},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.42473796010017395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064645767211914},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3267246186733246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1991797387599945},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.18704089522361755},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1847161054611206},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15062189102172852},{"id":"https://openalex.org/C2993967602","wikidata":"https://www.wikidata.org/wiki/Q5532932","display_name":"Genetic variants","level":4,"score":0.09675627946853638},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015984","descriptor_name":"Causality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015984","descriptor_name":"Causality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015984","descriptor_name":"Causality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057182","descriptor_name":"Mendelian Randomization Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057182","descriptor_name":"Mendelian Randomization Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057182","descriptor_name":"Mendelian Randomization Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1009880","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009880","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009880&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:36265006","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36265006","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1009880","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009880","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:7664f8cdc158487181484f7abd9ba2cb","is_oa":false,"landing_page_url":"https://doaj.org/article/7664f8cdc158487181484f7abd9ba2cb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 10, p e1009880 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9624391","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9624391","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1009880","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009880","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009880&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306896934.pdf","grobid_xml":"https://content.openalex.org/works/W4306896934.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1531821806","https://openalex.org/W1538131130","https://openalex.org/W1967993709","https://openalex.org/W1972696558","https://openalex.org/W2000484728","https://openalex.org/W2015416439","https://openalex.org/W2017840637","https://openalex.org/W2059699217","https://openalex.org/W2079321730","https://openalex.org/W2080040321","https://openalex.org/W2112484474","https://openalex.org/W2113699335","https://openalex.org/W2128736149","https://openalex.org/W2129795133","https://openalex.org/W2133009026","https://openalex.org/W2149118429","https://openalex.org/W2198606573","https://openalex.org/W2345512687","https://openalex.org/W2560674852","https://openalex.org/W2612690371","https://openalex.org/W2766234610","https://openalex.org/W2805801533","https://openalex.org/W2807005157","https://openalex.org/W2810852503","https://openalex.org/W2891494568","https://openalex.org/W2909194804","https://openalex.org/W2950463913","https://openalex.org/W3006861283","https://openalex.org/W3036809062","https://openalex.org/W3044724994","https://openalex.org/W3102100346","https://openalex.org/W3130819465","https://openalex.org/W3144227021","https://openalex.org/W3163257742","https://openalex.org/W4214608109","https://openalex.org/W4246607039","https://openalex.org/W4287865629","https://openalex.org/W4399548752"],"related_works":["https://openalex.org/W2901309888","https://openalex.org/W2169283889","https://openalex.org/W4210703904","https://openalex.org/W2052821216","https://openalex.org/W4404875725","https://openalex.org/W2036527494","https://openalex.org/W2610080820","https://openalex.org/W4294125588","https://openalex.org/W2416849719","https://openalex.org/W2015148400"],"abstract_inverted_index":{"Multi-task":[0],"deep":[1],"learning":[2],"(DL)":[3],"models":[4,16],"can":[5],"accurately":[6],"predict":[7],"diverse":[8],"genomic":[9,22,40,44],"marks":[10,23,41],"from":[11],"sequence,":[12],"but":[13,98],"whether":[14],"these":[15],"learn":[17],"the":[18,93,103,114],"causal":[19,37,67,80,96,130],"relationships":[20,38,116,136,142],"between":[21,39,69,82,124,137],"is":[24],"unknown.":[25],"Here,":[26],"we":[27],"describe":[28],"Deep":[29],"Mendelian":[30,49],"Randomization":[31],"(DeepMR),":[32],"a":[33,72,119],"method":[34],"for":[35,143],"estimating":[36],"learned":[42,117],"by":[43,118],"DL":[45,121],"models.":[46],"By":[47],"combining":[48],"randomization":[50],"with":[51],"in":[52,102,127],"silico":[53],"mutagenesis,":[54],"DeepMR":[55,86,111],"obtains":[56],"local":[57],"(locus":[58],"specific)":[59],"and":[60,89,139],"global":[61,95,115],"estimates":[62,91,132],"of":[63,78,92,105],"(an":[64],"assumed)":[65],"linear":[66],"relationship":[68],"marks.":[70],"In":[71],"simulation":[73],"designed":[74],"to":[75,112],"test":[76],"recovery":[77],"pairwise":[79],"relations":[81],"transcription":[83],"factors":[84],"(TFs),":[85],"gives":[87],"accurate":[88],"unbiased":[90],"'true'":[94],"effect,":[97],"its":[99],"coverage":[100],"decays":[101],"presence":[104],"sequence-dependent":[106],"confounding.":[107],"We":[108],"then":[109],"apply":[110],"examine":[113],"state-of-the-art":[120],"model,":[122],"BPNet,":[123],"TFs":[125,138],"involved":[126],"reprogramming.":[128],"DeepMR's":[129],"effect":[131],"validate":[133],"previously":[134],"hypothesized":[135],"suggest":[140],"new":[141],"future":[144],"investigation.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}