{"id":"https://openalex.org/W4408907996","doi":"https://doi.org/10.1101/2025.03.24.644668","title":"ConfuseNN: Interpreting convolutional neural network inferences in population genomics with data shuffling","display_name":"ConfuseNN: Interpreting convolutional neural network inferences in population genomics with data shuffling","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408907996","doi":"https://doi.org/10.1101/2025.03.24.644668","pmid":"https://pubmed.ncbi.nlm.nih.gov/40196528","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11974698"},"language":"en","primary_location":{"id":"doi:10.1101/2025.03.24.644668","doi":"https://doi.org/10.1101/2025.03.24.644668","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.03.24.644668","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1101/2025.03.24.644668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003286107","display_name":"Linh N. Tran","orcid":"https://orcid.org/0000-0003-0574-0887","observed_orcids":["https://orcid.org/0000-0003-0574-0887"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linh N. Tran","raw_affiliation_strings":["Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ, USA","University of Arizona"],"raw_orcid":"https://orcid.org/0000-0003-0574-0887","affiliations":[{"raw_affiliation_string":"Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024480613","display_name":"David Castellano","orcid":"https://orcid.org/0000-0001-8778-6007","observed_orcids":["https://orcid.org/0000-0001-8778-6007"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Castellano","raw_affiliation_strings":["Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","University of Arizona"],"raw_orcid":"https://orcid.org/0000-0001-8778-6007","affiliations":[{"raw_affiliation_string":"Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056381387","display_name":"Ryan N. Gutenkunst","orcid":"https://orcid.org/0000-0002-8659-0579","observed_orcids":["https://orcid.org/0000-0002-8659-0579"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan N. Gutenkunst","raw_affiliation_strings":["Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","University of Arizona"],"raw_orcid":"https://orcid.org/0000-0002-8659-0579","affiliations":[{"raw_affiliation_string":"Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056381387"],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10012","display_name":"Genetic diversity and population structure","score":0.3107999861240387,"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/T10012","display_name":"Genetic diversity and population structure","score":0.3107999861240387,"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/T10751","display_name":"Forensic and Genetic Research","score":0.30880001187324524,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.164900004863739,"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/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8740000128746033},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.5849999785423279},{"id":"https://openalex.org/keywords/data-shuffling","display_name":"data shuffling","score":0.8560000061988831},{"id":"https://openalex.org/keywords/haplotype-data","display_name":"haplotype data","score":0.8299999833106995},{"id":"https://openalex.org/keywords/linkage-disequilibrium","display_name":"linkage disequilibrium","score":0.8930000066757202},{"id":"https://openalex.org/keywords/allele-frequency","display_name":"allele frequency","score":0.9779999852180481},{"id":"https://openalex.org/keywords/demographic-inference","display_name":"demographic inference","score":0.8510000109672546},{"id":"https://openalex.org/keywords/selection-inference","display_name":"selection inference","score":0.7089999914169312},{"id":"https://openalex.org/keywords/population-genomics","display_name":"population genomics","score":0.8130000233650208},{"id":"https://openalex.org/keywords/feature-attribution","display_name":"feature attribution","score":0.4440000057220459},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.5329999923706055}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7188737392425537},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7086933851242065},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.6657569408416748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6349461674690247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182169318199158},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.598613977432251},{"id":"https://openalex.org/C35605836","wikidata":"https://www.wikidata.org/wiki/Q2064311","display_name":"Linkage disequilibrium","level":5,"score":0.5351202487945557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5153509974479675},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19694048166275024},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15959474444389343},{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.14882048964500427},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.12907066941261292},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1101/2025.03.24.644668","doi":"https://doi.org/10.1101/2025.03.24.644668","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.03.24.644668","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:40196528","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40196528","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:10787382","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11974698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:11974698","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11974698","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,"listed_in":[],"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":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1101/2025.03.24.644668","doi":"https://doi.org/10.1101/2025.03.24.644668","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.03.24.644668","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5761011415","display_name":"Joint inferences of natural selection between sites and populations","funder_award_id":"R01GM127348","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G9000920171","display_name":"Population genomic inferences of history and selection across populations and time","funder_award_id":"R35GM149235","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2015159529","https://openalex.org/W2134599124","https://openalex.org/W2140449543","https://openalex.org/W2150883566","https://openalex.org/W2783880833","https://openalex.org/W2950327064","https://openalex.org/W2953082877","https://openalex.org/W2963306315","https://openalex.org/W2989915159","https://openalex.org/W3042023486","https://openalex.org/W3134364710","https://openalex.org/W3136528618","https://openalex.org/W3164117052","https://openalex.org/W4294376238","https://openalex.org/W4300862723","https://openalex.org/W4365442883","https://openalex.org/W4386417162","https://openalex.org/W4389042252","https://openalex.org/W4392023818","https://openalex.org/W4411053089"],"related_works":["https://openalex.org/W4414872234","https://openalex.org/W4417171272","https://openalex.org/W2950327064","https://openalex.org/W4389042252","https://openalex.org/W6989887789","https://openalex.org/W4322489059","https://openalex.org/W7152096067","https://openalex.org/W4400236160","https://openalex.org/W4404413444","https://openalex.org/W4365442883"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"become":[5],"powerful":[6,128],"tools":[7],"for":[8,79,113],"population":[9,36,57,121,134],"genomic":[10,15],"inference,":[11,84],"yet":[12],"understanding":[13],"which":[14],"features":[16,38,91],"drive":[17],"their":[18,41],"performance":[19],"remains":[20],"challenging.":[21],"We":[22,72],"introduce":[23],"ConfuseNN,":[24],"a":[25],"method":[26],"that":[27],"systematically":[28],"shuffles":[29],"input":[30],"haplotype":[31],"matrices":[32],"to":[33,43,69,75],"disrupt":[34],"specific":[35,89],"genetic":[37,58,135],"and":[39,55,82,92,98,102,132],"evaluate":[40,64],"contribution":[42],"CNN":[44,70,115],"performance.":[45,71],"By":[46],"sequentially":[47],"removing":[48],"signals":[49],"from":[50],"linkage":[51],"disequilibrium,":[52],"allele":[53],"frequency,":[54],"other":[56],"patterns":[59],"in":[60,120],"test":[61],"data,":[62],"we":[63],"how":[65],"each":[66],"feature":[67],"contributes":[68],"applied":[73],"ConfuseNN":[74,106],"three":[76],"published":[77],"CNNs":[78],"demographic":[80],"history":[81],"selection":[83],"confirming":[85],"the":[86,125],"importance":[87],"of":[88,95,99],"data":[90,104],"identifying":[93],"limitations":[94],"network":[96],"architecture":[97],"simulated":[100],"training":[101],"testing":[103],"design.":[105],"provides":[107],"an":[108],"accessible":[109],"biologically":[110],"motivated":[111],"framework":[112],"interpreting":[114],"behavior":[116],"across":[117],"different":[118],"tasks":[119],"genetics,":[122],"helping":[123],"bridge":[124],"gap":[126],"between":[127],"deep":[129],"learning":[130],"approaches":[131],"traditional":[133],"theory.":[136]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-03-28T00:00:00"}
