{"id":"https://openalex.org/W7224993167","doi":"https://doi.org/10.64898/2026.10.28.762655","title":"EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations","display_name":"EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7224993167","doi":"https://doi.org/10.64898/2026.10.28.762655"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.28.762655","doi":"https://doi.org/10.64898/2026.10.28.762655","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762655","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762655.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762655.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153309115","display_name":"Nicholas Ho","orcid":"https://orcid.org/0009-0008-2689-0271","observed_orcids":["https://orcid.org/0009-0008-2689-0271"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Ho","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":"https://orcid.org/0009-0008-2689-0271","affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric P. Xing","raw_affiliation_strings":["Machine Learning Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626893","display_name":"Jian Ma","orcid":"https://orcid.org/0000-0002-4202-5834","observed_orcids":["https://orcid.org/0000-0002-4202-5834"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Ma","raw_affiliation_strings":["Ray and Stephanie Lane Computational Biology Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA"],"raw_orcid":"https://orcid.org/0000-0002-4202-5834","affiliations":[{"raw_affiliation_string":"Ray and Stephanie Lane Computational Biology Department, Kenneth C. Griffin School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100626893"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3082999885082245,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3082999885082245,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.2842000126838684,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.20499999821186066,"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/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.6019999980926514},{"id":"https://openalex.org/keywords/mtor-inhibition","display_name":"mTOR inhibition","score":0.8859999775886536},{"id":"https://openalex.org/keywords/autophagosome-lysosome-fusion","display_name":"autophagosome-lysosome fusion","score":0.9649999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5954999923706055},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210999846458435},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.489300012588501},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2991772755","wikidata":"https://www.wikidata.org/wiki/Q751748","display_name":"Gene interaction","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2669999897480011},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C2992708514","wikidata":"https://www.wikidata.org/wiki/Q48968323","display_name":"Quantitative biology","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.28.762655","doi":"https://doi.org/10.64898/2026.10.28.762655","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762655","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762655.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.28.762655","doi":"https://doi.org/10.64898/2026.10.28.762655","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762655","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/31/2026.10.28.762655.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.428600013256073,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G5435736845","display_name":null,"funder_award_id":"R01HG007352","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308774","display_name":"John Simon Guggenheim Memorial Foundation","ror":"https://ror.org/0407tnq23"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224993167.pdf","grobid_xml":"https://content.openalex.org/works/W7224993167.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403855585","https://openalex.org/W4403820530","https://openalex.org/W4411948067","https://openalex.org/W7130512363","https://openalex.org/W4402860131","https://openalex.org/W7165123812","https://openalex.org/W7134840684","https://openalex.org/W7166196793","https://openalex.org/W7214436542","https://openalex.org/W7128074008"],"abstract_inverted_index":{"Abstract":[0],"Predicting":[1],"the":[2,92,173],"effects":[3],"of":[4,50,145,175],"individual":[5,106],"and":[6,15,30,70,76,107,122,131,169,178],"combined":[7,108],"perturbations":[8],"is":[9],"central":[10],"to":[11,104,135],"identifying":[12],"context-specific":[13,179],"vulnerabilities":[14],"designing":[16],"targeted":[17],"interventions.":[18],"Yet":[19],"learning":[20,56,83],"gene":[21,81,102,160],"representations":[22,49,114],"that":[23,45],"integrate":[24],"functional":[25,48],"relationships":[26],"with":[27,57],"cellular":[28],"state":[29],"transfer":[31],"across":[32,73],"perturbation":[33,109],"tasks":[34],"remains":[35,95],"challenging.":[36],"Here,":[37],"we":[38],"present":[39],"EMBER,":[40],"a":[41,64,88,143,149],"gene-centric":[42],"foundation":[43],"model":[44],"learns":[46],"context-dependent":[47],"genes.":[51],"EMBER":[52,79,126,138],"combines":[53],"interaction-guided":[54],"contrastive":[55],"masked":[58],"expression":[59],"reconstruction":[60],"during":[61,152],"pretraining":[62],"on":[63],"single-cell":[65],"corpus":[66],"curated":[67],"for":[68,166,181],"diversity":[69],"balanced":[71],"sampling":[72],"cell":[74],"types":[75],"experimental":[77,182],"batches.":[78],"decouples":[80],"representation":[82],"from":[84],"task-specific":[85],"prediction":[86,130],"through":[87],"composable":[89],"embedding":[90],"framework:":[91],"pretrained":[93,113],"encoder":[94],"frozen,":[96],"while":[97],"lightweight":[98],"probes":[99],"combine":[100],"contextualized":[101,159],"embeddings":[103,161],"predict":[105],"effects.":[110],"The":[111],"same":[112],"support":[115],"single-gene":[116],"perturbation-response":[117,129],"prediction,":[118,121],"digenic":[119],"interaction":[120],"multi-target":[123],"drugresponse":[124],"prediction.":[125],"improves":[127],"cross-context":[128],"geneticinteraction":[132],"ranking":[133],"relative":[134],"evaluated":[136],"baselines.":[137],"also":[139],"prioritized":[140],"SCFD1":[141],",":[142],"mediator":[144],"autophagosome\u2013lysosome":[146],"fusion,":[147],"as":[148,162],"candidate":[150],"dependency":[151],"mTOR":[153],"inhibition.":[154],"Together,":[155],"these":[156],"results":[157],"establish":[158],"reusable":[163],"building":[164],"blocks":[165],"modeling":[167],"genetic":[168,176],"pharmacological":[170],"perturbations,":[171],"supporting":[172],"prioritization":[174],"interactions":[177],"interventions":[180],"testing.":[183]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-01T00:00:00"}