{"id":"https://openalex.org/W7213498987","doi":"https://doi.org/10.64898/2026.09.04.749112","title":"Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models","display_name":"Integrating Genomic Annotations and Traits Dependencies for single-nucleotide polymorphisms Prioritization with Causal Concept Bottleneck Models","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213498987","doi":"https://doi.org/10.64898/2026.09.04.749112"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.04.749112","doi":"https://doi.org/10.64898/2026.09.04.749112","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.04.749112","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.04.749112.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.04.749112.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119945929","display_name":"Francesco De Santis","orcid":"https://orcid.org/0009-0008-3501-963X","observed_orcids":["https://orcid.org/0009-0008-3501-963X"]},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Francesco De Santis","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","Dipartimento di Automatica e Informatica (DAUIN), Politecnico di Torino, Torino, Italy"],"raw_orcid":"https://orcid.org/0009-0008-3501-963X","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dipartimento di Automatica e Informatica (DAUIN), Politecnico di Torino, Torino, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005818810","display_name":"Daniele Malpetti","orcid":"https://orcid.org/0000-0002-5658-1890","observed_orcids":["https://orcid.org/0000-0002-5658-1890"]},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniele Malpetti","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5658-1890","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043807665","display_name":"Francesco Gualdi","orcid":"https://orcid.org/0000-0003-0449-9884","observed_orcids":["https://orcid.org/0000-0003-0449-9884"]},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Francesco Gualdi","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0449-9884","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012559209","display_name":"Francesca Mangili","orcid":"https://orcid.org/0000-0002-3215-1028","observed_orcids":["https://orcid.org/0000-0002-3215-1028"]},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Francesca Mangili","raw_affiliation_strings":["Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3215-1028","affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Lugano, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics (SIB), Lugano, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012559209"],"corresponding_institution_ids":["https://openalex.org/I12708293","https://openalex.org/I15196421","https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/single-nucleotide-polymorphisms","display_name":"single nucleotide polymorphisms","score":0.9539999961853027},{"id":"https://openalex.org/keywords/genome-annotation","display_name":"genome annotation","score":0.5740000009536743},{"id":"https://openalex.org/keywords/polygenic-traits","display_name":"polygenic traits","score":0.7699999809265137},{"id":"https://openalex.org/keywords/spurious-association","display_name":"spurious association","score":0.5899999737739563},{"id":"https://openalex.org/keywords/explainable-deep-learning","display_name":"explainable deep learning","score":0.7670000195503235},{"id":"https://openalex.org/keywords/shared-genetic-mechanisms","display_name":"shared genetic mechanisms","score":0.7749999761581421},{"id":"https://openalex.org/keywords/indirect-genetic-effects","display_name":"indirect genetic effects","score":0.6349999904632568},{"id":"https://openalex.org/keywords/multi-trait-gwas","display_name":"multi-trait GWAS","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7444000244140625},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5512999892234802},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C9287583","wikidata":"https://www.wikidata.org/wiki/Q5532883","display_name":"Genetic architecture","level":4,"score":0.4851999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.3864000141620636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C81941488","wikidata":"https://www.wikidata.org/wiki/Q853421","display_name":"Quantitative trait locus","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C3020077223","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomic information","level":4,"score":0.3481000065803528},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.30219998955726624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.04.749112","doi":"https://doi.org/10.64898/2026.09.04.749112","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.04.749112","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.04.749112.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.04.749112","doi":"https://doi.org/10.64898/2026.09.04.749112","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.04.749112","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/17/2026.09.04.749112.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G177054408","display_name":null,"funder_award_id":"101136962","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G8279472309","display_name":"NEXT GENERATION TOOLS FOR GENOME-CENTRIC MULTIMODAL DATA INTEGRATION IN PERSONALISED CARDIOVASCULAR MEDICINE","funder_award_id":"101136962","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320314707","display_name":"Government of the United Kingdom","ror":"https://ror.org/05wnh3t63"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320335238","display_name":"Staatssekretariat f\u00fcr Bildung, Forschung und Innovation","ror":"https://ror.org/01kw63t33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213498987.pdf","grobid_xml":"https://content.openalex.org/works/W7213498987.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2942948333","https://openalex.org/W2041448690","https://openalex.org/W4327639718","https://openalex.org/W2098384259","https://openalex.org/W2996300320","https://openalex.org/W2597117390","https://openalex.org/W4387502218","https://openalex.org/W2922543840","https://openalex.org/W3038428099","https://openalex.org/W7070653901"],"abstract_inverted_index":{"Predicting":[0],"common":[1],"traits":[2,76,111,125],"from":[3,73],"single-nucleotide":[4],"polymorphism":[5],"(SNPs)":[6],"data":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,70,79,91],"polygenicity,":[12],"small":[13],"effect":[14],"sizes,":[15],"and":[16,112],"the":[17,55,83,87,102,145],"presence":[18,146],"of":[19,62,86,149],"potentially":[20],"mediated":[21],"or":[22,147,153],"spurious":[23],"cross-trait":[24,37],"associations.":[25],"We":[26,100],"propose":[27],"a":[28,49,60,105],"modeling":[29],"approach":[30,103],"that":[31,53,114,140],"combines":[32],"genomic":[33,80],"annotations":[34],"with":[35],"known":[36],"relations":[38],"by":[39,129],"leveraging":[40],"Causally":[41],"Reliable":[42],"Concept":[43],"Bottleneck":[44],"Models":[45],"(C":[46],"2":[47,116],"BM),":[48],"deep":[50],"learning":[51],"architecture":[52,85],"factors":[54],"joint":[56],"trait":[57,68],"distribution":[58],"over":[59],"graph":[61],"interpretable":[63,84],"concepts.":[64],"This":[65],"design":[66],"allows":[67],"predictions":[69,119],"leverage":[71],"information":[72],"other":[74],"observed":[75],"in":[77,132],"addition":[78],"inputs.":[81],"Furthermore,":[82],"model":[88],"enables":[89],"us":[90],"investigate":[92],"how":[93,133],"specific":[94],"trait\u2013trait":[95,134],"relationships":[96,135],"influence":[97,136],"SNP-level":[98],"predictions.":[99],"evaluate":[101],"on":[104],"multi-trait":[106],"GWAS":[107],"dataset":[108],"covering":[109],"five":[110],"show":[113],"C":[115],"BM":[117],"improves":[118],"when":[120],"ground-truth":[121],"labels":[122],"for":[123],"related":[124],"are":[126],"available.":[127],"Moreover,":[128],"analyzing":[130],"variations":[131],"predictions,":[137],"we":[138],"postulate":[139],"such":[141],"differences":[142],"may":[143],"reflect":[144],"absence":[148],"shared":[150],"genetic":[151],"mechanisms":[152],"indirect":[154],"effects.":[155]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-18T00:00:00"}
