{"id":"https://openalex.org/W4249356707","doi":"https://doi.org/10.26434/chemrxiv.8796950","title":"A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space","display_name":"A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space","publication_year":2019,"publication_date":"2019-07-08","ids":{"openalex":"https://openalex.org/W4249356707","doi":"https://doi.org/10.26434/chemrxiv.8796950"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.8796950","doi":"https://doi.org/10.26434/chemrxiv.8796950","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.8796950","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/60c742e7702a9b1d4218a4f1/original/a-physics-infused-deep-learning-model-for-the-prediction-of-refractive-indices-and-its-use-for-the-large-scale-screening-of-organic-compound-space.pdf","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/60c742e7702a9b1d4218a4f1/original/a-physics-infused-deep-learning-model-for-the-prediction-of-refractive-indices-and-its-use-for-the-large-scale-screening-of-organic-compound-space.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000952998","display_name":"Mojtaba Haghighatlari","orcid":"https://orcid.org/0000-0002-3779-2246","observed_orcids":["https://orcid.org/0000-0002-3779-2246"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mojtaba Haghighatlari","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012394038","display_name":"Gaurav Vishwakarma","orcid":"https://orcid.org/0000-0002-8049-4754","observed_orcids":["https://orcid.org/0000-0002-8049-4754"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Vishwakarma","raw_affiliation_strings":["Department of Chemical and Biological Engineering, University at Buffalo,","The State University of New York, Buffalo, NY 14260, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, University at Buffalo,","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"The State University of New York, Buffalo, NY 14260, United States","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078984238","display_name":"Mohammad Atif Faiz Afzal","orcid":"https://orcid.org/0000-0001-8261-2024","observed_orcids":["https://orcid.org/0000-0001-8261-2024"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Atif Faiz Afzal","raw_affiliation_strings":["Department of Chemical and Biological Engineering, University at Buffalo,","The State University of New York, Buffalo, NY 14260, United States"],"raw_orcid":"https://orcid.org/0000-0001-8261-2024","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, University at Buffalo,","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"The State University of New York, Buffalo, NY 14260, United States","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033582284","display_name":"Johannes Hachmann","orcid":"https://orcid.org/0000-0003-4501-4118","observed_orcids":["https://orcid.org/0000-0003-4501-4118"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes Hachmann","raw_affiliation_strings":["Computational and Data-Enabled Science and Engineering Graduate Program, University at Buffalo, The State University of New York, Buffalo, NY 14260, United States","Department of Chemical and Biological Engineering, University at Buffalo,","New York State Center of Excellence in Materials Informatics, Buffalo, NY 14203, United States","The State University of New York, Buffalo, NY 14260, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational and Data-Enabled Science and Engineering Graduate Program, University at Buffalo, The State University of New York, Buffalo, NY 14260, United States","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Chemical and Biological Engineering, University at Buffalo,","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"New York State Center of Excellence in Materials Informatics, Buffalo, NY 14203, United States","institution_ids":[]},{"raw_affiliation_string":"The State University of New York, Buffalo, NY 14260, United States","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9672999978065491,"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":0.9672999978065491,"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":0.03009999915957451,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/refractive-index-prediction","display_name":"refractive index prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/organic-compounds","display_name":"organic compounds","score":0.8489999771118164},{"id":"https://openalex.org/keywords/physics-informed-machine-learning","display_name":"physics-informed machine learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.847000002861023},{"id":"https://openalex.org/keywords/compound-screening","display_name":"compound screening","score":0.6439999938011169},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.44600000977516174},{"id":"https://openalex.org/keywords/extrapolation","display_name":"extrapolation","score":0.4410000145435333},{"id":"https://openalex.org/keywords/molecular-property-prediction","display_name":"molecular property prediction","score":0.6150000095367432},{"id":"https://openalex.org/keywords/optoelectronic-materials","display_name":"optoelectronic materials","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.8466503620147705},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7442688345909119},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7069643139839172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6648023724555969},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6217142939567566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6104795336723328},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.5892208814620972},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5347394347190857},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.509874701499939},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.47939467430114746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47738784551620483},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.449219673871994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28265640139579773},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2483055591583252},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.15151569247245789},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12735092639923096},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.09456384181976318},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08623382449150085},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.8796950","doi":"https://doi.org/10.26434/chemrxiv.8796950","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.8796950","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/60c742e7702a9b1d4218a4f1/original/a-physics-infused-deep-learning-model-for-the-prediction-of-refractive-indices-and-its-use-for-the-large-scale-screening-of-organic-compound-space.pdf","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.8796950","doi":"https://doi.org/10.26434/chemrxiv.8796950","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.8796950","pdf_url":"https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/60c742e7702a9b1d4218a4f1/original/a-physics-infused-deep-learning-model-for-the-prediction-of-refractive-indices-and-its-use-for-the-large-scale-screening-of-organic-compound-space.pdf","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G124302402","display_name":"RCN - SEES: Sustainable Cities - People and the Energy-Climate-Water Nexus","funder_award_id":"1140384","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4863676306","display_name":"S2I2: Impl: The Molecular Sciences Software Institute","funder_award_id":"1547580","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7065105558","display_name":"CAREER: Building an Advanced Cyberinfrastructure for the Data-Driven Design of Chemical Systems and the Exploration of Chemical Space","funder_award_id":"1751161","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/F4320338024","display_name":"Center of Excellence in Materials Informatics, University at Buffalo","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4249356707.pdf","grobid_xml":"https://content.openalex.org/works/W4249356707.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1501145371","https://openalex.org/W1953140988","https://openalex.org/W1975147762","https://openalex.org/W1981025032","https://openalex.org/W1988037271","https://openalex.org/W1988091937","https://openalex.org/W2008423326","https://openalex.org/W2008956921","https://openalex.org/W2016979469","https://openalex.org/W2021748110","https://openalex.org/W2044834685","https://openalex.org/W2044990793","https://openalex.org/W2053561221","https://openalex.org/W2069870183","https://openalex.org/W2076063813","https://openalex.org/W2121076213","https://openalex.org/W2131676173","https://openalex.org/W2131686485","https://openalex.org/W2134164499","https://openalex.org/W2139798297","https://openalex.org/W2147527734","https://openalex.org/W2162152880","https://openalex.org/W2167708558","https://openalex.org/W2333872936","https://openalex.org/W2527540728","https://openalex.org/W2761609932","https://openalex.org/W2792348590","https://openalex.org/W2804164439","https://openalex.org/W2807616984","https://openalex.org/W2884430236","https://openalex.org/W2885841934","https://openalex.org/W2889143727","https://openalex.org/W2899667845","https://openalex.org/W2911568489","https://openalex.org/W2911975749","https://openalex.org/W2920098380","https://openalex.org/W2921696539","https://openalex.org/W2933565232","https://openalex.org/W2943486344","https://openalex.org/W2945206293","https://openalex.org/W2948944238","https://openalex.org/W2950128007","https://openalex.org/W2954088480","https://openalex.org/W2980221293","https://openalex.org/W3209042722","https://openalex.org/W4300109386"],"related_works":["https://openalex.org/W4403418595","https://openalex.org/W4387049259","https://openalex.org/W4402974075","https://openalex.org/W3033050301","https://openalex.org/W4400453959","https://openalex.org/W7171353827","https://openalex.org/W2366099055","https://openalex.org/W2320969025","https://openalex.org/W6913069759","https://openalex.org/W2921696539"],"abstract_inverted_index":{"We":[0,30,137,173,200],"present":[1],"a":[2,24,40,55,75,120,158,210,229,247],"multitask,":[3],"physics-infused":[4],"deep":[5],"learning":[6,37,57,86,240],"model":[7,62,128,140,212,221],"to":[8,23,63,110,122,143,196,208],"accurately":[9],"and":[10,19,43,192,250,258],"efficiently":[11],"predict":[12,184],"refractive":[13],"indices":[14],"(RIs)":[15],"of":[16,26,79,84,101,126,133,147,187,217,238,255],"organic":[17,262],"molecules,":[18],"we":[20,59,118,165],"apply":[21],"it":[22,33],"library":[25],"1.5":[27],"million":[28],"compounds.":[29],"show":[31],"that":[32,44,149,175,202,213],"outperforms":[34],"earlier":[35],"machine":[36,85,239],"models":[38,50,87,177],"by":[39,220],"significant":[41],"margin,":[42],"incorporating":[45],"known":[46],"physics":[47],"into":[48],"data-derived":[49,211],"provides":[51],"valuable":[52],"guardrails.":[53],"Using":[54],"transfer":[56],"approach,":[58],"augment":[60],"the":[61,99,102,124,130,134,139,144,153,176,185,188,205,215,224,235,253],"reproduce":[64],"results":[65,233],"consistent":[66,97],"with":[67,74,98,113,141,264],"higher-level":[68],"computational":[69],"chemistry":[70],"training":[71,103],"data,":[72],"but":[73],"considerably":[76],"reduced":[77],"number":[78],"corresponding":[80],"calculations.":[81],"Prediction":[82],"errors":[83],"are":[88,193],"typically":[89],"smallest":[90],"for":[91,266],"commonly":[92],"observed":[93],"target":[94],"property":[95],"values,":[96,117],"distribution":[100],"data.":[104],"However,":[105],"since":[106],"our":[107,127,167],"goal":[108],"is":[109,204],"identify":[111],"candidates":[112],"unusually":[114],"large":[115,230],"RI":[116,135,218],"propose":[119],"strategy":[121],"boost":[123],"performance":[125],"in":[129,152,161,169,179,223,241,251,268],"remoter":[131],"areas":[132],"distribution:":[136],"bias":[138],"respect":[142],"under-represented":[145],"classes":[146],"molecules":[148,263],"have":[150],"values":[151],"high-RI":[154,265],"regime.":[155],"By":[156],"adopting":[157],"metric":[159],"popular":[160],"web":[162],"search":[163],"engines,":[164],"evaluate":[166],"effectiveness":[168],"ranking":[170],"top":[171,189],"candidates.":[172],"confirm":[174],"developed":[178],"this":[180,203],"study":[181,207],"can":[182],"reliably":[183],"RIs":[186],"1,000":[190],"compounds,":[191],"thus":[194],"able":[195],"capture":[197],"their":[198],"ranking.":[199],"believe":[201],"first":[206],"develop":[209],"ensures":[214],"reliability":[216],"predictions":[219],"augmentation":[222],"extrapolation":[225],"region":[226],"on":[227,246],"such":[228,260],"scale.":[231],"These":[232],"underscore":[234],"tremendous":[236],"potential":[237],"facilitating":[242],"molecular":[243],"(hyper)screening":[244],"approaches":[245],"massive":[248],"scale":[249],"accelerating":[252],"discovery":[254],"new":[256],"compounds":[257],"materials,":[259],"as":[261],"applications":[267],"opto-electronics.":[269]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2022-05-12T00:00:00"}