{"id":"https://openalex.org/W4416018139","doi":"https://doi.org/10.1145/3746252.3761663","title":"The Landscape of Foundation Models for Molecular Chemistry","display_name":"The Landscape of Foundation Models for Molecular Chemistry","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416018139","doi":"https://doi.org/10.1145/3746252.3761663"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761663","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120301846","display_name":"Mateusz Praski","orcid":"https://orcid.org/0009-0006-3956-5377"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Mateusz Praski","raw_affiliation_strings":["Faculty of Computer Science, AGH University of Krakow, Krak\u00f3w, Poland"],"raw_orcid":"https://orcid.org/0009-0006-3956-5377","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, AGH University of Krakow, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I686019","https://openalex.org/I126596746"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120301846"],"corresponding_institution_ids":["https://openalex.org/I126596746","https://openalex.org/I686019"],"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":"6805","last_page":"6808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.48420000076293945,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.48420000076293945,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.36579999327659607,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.04989999905228615,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5659000277519226},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.534500002861023},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5041999816894531},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.36739999055862427},{"id":"https://openalex.org/keywords/molecular-model","display_name":"Molecular model","score":0.33880001306533813}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4797999858856201},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C178910836","wikidata":"https://www.wikidata.org/wiki/Q2196961","display_name":"Molecular model","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28940001130104065},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761663","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761663","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2777416523","https://openalex.org/W3009321976","https://openalex.org/W3207161423","https://openalex.org/W4226159083","https://openalex.org/W4313485929","https://openalex.org/W4379184641","https://openalex.org/W4391568364"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"neural":[1],"networks":[2],"have":[3],"recently":[4],"emerged":[5],"as":[6],"powerful":[7],"tools":[8],"for":[9,99],"molecular":[10,43,106],"data":[11],"mining,":[12],"offering":[13,96],"an":[14],"alternative":[15],"to":[16],"classical":[17,74],"approaches.":[18],"However,":[19],"these":[20],"models":[21,45,76,83],"are":[22],"often":[23],"evaluated":[24],"on":[25],"limited":[26],"datasets":[27,49],"with":[28],"narrow":[29],"baselines,":[30],"leaving":[31],"their":[32],"benefits":[33],"unclear.":[34],"We":[35,88],"present":[36],"the":[37,73,86],"first":[38],"large-scale":[39],"benchmark":[40],"comparing":[41],"pre-trained":[42],"embedding":[44],"across":[46],"20":[47],"public":[48],"spanning":[50],"classification":[51],"and":[52,60,102],"regression":[53],"tasks.":[54],"Our":[55],"evaluation":[56],"covers":[57],"text-based,":[58],"graph-based,":[59],"multimodal":[61],"architectures,":[62],"all":[63],"tested":[64],"under":[65],"a":[66,81],"unified":[67],"methodology.":[68],"The":[69],"results":[70],"show":[71],"that":[72],"fingerprint-based":[75],"remain":[77],"highly":[78],"competitive.":[79],"Only":[80],"few":[82],"consistently":[84],"exceeded":[85],"baseline.":[87],"also":[89],"highlight":[90],"key":[91],"factors":[92],"influencing":[93],"model":[94,100],"performance,":[95],"practical":[97],"guidance":[98],"selection":[101],"future":[103],"improvements":[104],"in":[105],"embeddings.":[107]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-11-08T00:00:00"}