{"id":"https://openalex.org/W2266664921","doi":"https://doi.org/10.1186/s13321-016-0113-y","title":"The development of models to predict melting and pyrolysis point data associated with several hundred thousand compounds mined from PATENTS","display_name":"The development of models to predict melting and pyrolysis point data associated with several hundred thousand compounds mined from PATENTS","publication_year":2016,"publication_date":"2016-01-22","ids":{"openalex":"https://openalex.org/W2266664921","doi":"https://doi.org/10.1186/s13321-016-0113-y","mag":"2266664921","pmid":"https://pubmed.ncbi.nlm.nih.gov/26807157"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-016-0113-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0113-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0113-y","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0113-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067679577","display_name":"Igor V. Tetko","orcid":"https://orcid.org/0000-0002-6855-0012"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Igor V. Tetko","raw_affiliation_strings":["Institute of Structural Biology, Helmholtz Zentrum M\u00fcnchen f\u00fcr Gesundheit und Umwelt (HMGU), Ingolst\u00e4dter Landstra\u00dfe 1, b. 60w, 85764 Neuherberg, Germany ; BigChem GmbH, 85764 Neuherberg, Germany","Institute of Structural Biology, Helmholtz Zentrum M\u00fcnchen f\u00fcr Gesundheit und Umwelt (HMGU), Ingolst\u00e4dter Landstra\u00dfe 1, b. 60w, 85764, Neuherberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Structural Biology, Helmholtz Zentrum M\u00fcnchen f\u00fcr Gesundheit und Umwelt (HMGU), Ingolst\u00e4dter Landstra\u00dfe 1, b. 60w, 85764 Neuherberg, Germany ; BigChem GmbH, 85764 Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Institute of Structural Biology, Helmholtz Zentrum M\u00fcnchen f\u00fcr Gesundheit und Umwelt (HMGU), Ingolst\u00e4dter Landstra\u00dfe 1, b. 60w, 85764, Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021129795","display_name":"Daniel M. Lowe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107830","display_name":"Nerve Centre","ror":"https://ror.org/01r7ewj84","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210107830"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel M. Lowe","raw_affiliation_strings":["NextMove Software Limited, Innovation Centre (Unit 23), Cambridge Science Park, Cambridge, CB4 0EY UK","NextMove Software Limited, Innovation Centre (Unit 23), Cambridge Science Park, Cambridge, CB4 0EY, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software Limited, Innovation Centre (Unit 23), Cambridge Science Park, Cambridge, CB4 0EY UK","institution_ids":["https://openalex.org/I4210107830"]},{"raw_affiliation_string":"NextMove Software Limited, Innovation Centre (Unit 23), Cambridge Science Park, Cambridge, CB4 0EY, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062051745","display_name":"Antony Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I2751430930","display_name":"Royal Society of Chemistry","ror":"https://ror.org/025sbr097","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2751430930"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antony J. Williams","raw_affiliation_strings":["ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC 27587 USA","ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC, 27587, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC 27587 USA","institution_ids":["https://openalex.org/I2751430930"]},{"raw_affiliation_string":"ChemConnector Inc., 904 Tamaras Circle, Wake Forest, NC, 27587, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067679577"],"corresponding_institution_ids":["https://openalex.org/I3018134672"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":9.46,"has_fulltext":true,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98054042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"1","first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.5184999704360962,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.5184999704360962,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.41280001401901245,"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/T13180","display_name":"Chemistry and Chemical Engineering","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/2304","display_name":"Environmental Chemistry"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6914991736412048},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6105904579162598},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6097810864448547},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5794433951377869},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5088894367218018},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4571835696697235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20518046617507935},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.18324851989746094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914991736412048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6105904579162598},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6097810864448547},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5794433951377869},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5088894367218018},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4571835696697235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20518046617507935},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.18324851989746094},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-016-0113-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0113-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0113-y","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:26807157","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26807157","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,"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":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4724158","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4724158","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,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:opus-zb.helmholtz-muenchen.de:47758","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=47758","pdf_url":null,"source":{"id":"https://openalex.org/S4377196115","display_name":"Site cant be reached","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"J. Cheminformatics 8:2 (2016)","raw_type":"article"},{"id":"pmh:oai:push-zb.helmholtz-munich.de:47758","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-munich.de/frontdoor.php?source_opus=47758","pdf_url":null,"source":{"id":"https://openalex.org/S7407055352","display_name":"PuSH - Publication Server of Helmholtz Zentrum M\u00fcnchen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"J. Cheminformatics 8:2 (2016)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13321-016-0113-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0113-y","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-016-0113-y","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2266664921.pdf","grobid_xml":"https://content.openalex.org/works/W2266664921.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W29374554","https://openalex.org/W169052826","https://openalex.org/W637575904","https://openalex.org/W655927574","https://openalex.org/W1541037889","https://openalex.org/W1545231783","https://openalex.org/W1567033081","https://openalex.org/W1944134883","https://openalex.org/W1966441763","https://openalex.org/W1967711618","https://openalex.org/W1970593617","https://openalex.org/W1972156862","https://openalex.org/W1972234779","https://openalex.org/W1976917358","https://openalex.org/W1977287658","https://openalex.org/W1978744367","https://openalex.org/W1982462615","https://openalex.org/W1982597534","https://openalex.org/W1988037271","https://openalex.org/W1990399577","https://openalex.org/W1996925740","https://openalex.org/W2006360003","https://openalex.org/W2022283419","https://openalex.org/W2022755995","https://openalex.org/W2026785010","https://openalex.org/W2033511432","https://openalex.org/W2042278642","https://openalex.org/W2045270356","https://openalex.org/W2052723761","https://openalex.org/W2060531713","https://openalex.org/W2075808059","https://openalex.org/W2077736710","https://openalex.org/W2080922998","https://openalex.org/W2085313599","https://openalex.org/W2089578131","https://openalex.org/W2089589794","https://openalex.org/W2091720264","https://openalex.org/W2092076777","https://openalex.org/W2094189642","https://openalex.org/W2094836090","https://openalex.org/W2099538400","https://openalex.org/W2103674568","https://openalex.org/W2103738366","https://openalex.org/W2104742871","https://openalex.org/W2111044246","https://openalex.org/W2115758667","https://openalex.org/W2118981984","https://openalex.org/W2119723273","https://openalex.org/W2133990480","https://openalex.org/W2136794542","https://openalex.org/W2148797284","https://openalex.org/W2153635508","https://openalex.org/W2157851318","https://openalex.org/W2192310614","https://openalex.org/W2216412596","https://openalex.org/W2219397146","https://openalex.org/W2241375048","https://openalex.org/W2279004469","https://openalex.org/W2291496596","https://openalex.org/W2333447460","https://openalex.org/W2342596260","https://openalex.org/W2912934387","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W1603736412","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W2734796617","https://openalex.org/W3083218341","https://openalex.org/W2102405864","https://openalex.org/W2366903352"],"abstract_inverted_index":{"BACKGROUND:":[0],"Melting":[1],"point":[2],"(MP)":[3],"is":[4],"an":[5],"important":[6,291],"property":[7],"in":[8,32,54,102,228],"regards":[9],"to":[10,56,68,110,141,144,168,222,280,295,305,345],"the":[11,40,80,94,103,121,155,177,223,265,272,296,325,337,347],"solubility":[12],"of":[13,35,42,82,87,126,162,179,233,264,275,298,313,327,341,349],"chemical":[14,19,51,127,276,328],"compounds.":[15],"Its":[16],"prediction":[17,219],"from":[18,129,213,242,271],"structure":[20,52],"remains":[21],"a":[22,118,247,303,308,332],"highly":[23,224],"challenging":[24],"task":[25,195],"for":[26,62,120,235,255,269,324,336],"quantitative":[27],"structure-activity":[28,350],"relationship":[29,351],"studies.":[30],"Success":[31],"this":[33],"area":[34],"research":[36],"critically":[37],"depends":[38],"on":[39,154,172],"availability":[41],"high":[43,342],"quality":[44,343],"MP":[45,63,88,267],"data":[46,75,89,128,134,181,211,226,234,344,357],"as":[47,49],"well":[48],"accurate":[50],"representations":[53],"order":[55],"develop":[57,111,142,169],"models.":[58,113,352],"Currently,":[59],"available":[60,92,101,153,360],"datasets":[61],"predictions":[64],"have":[65,116,136,319,330],"been":[66,137],"limited":[67],"around":[69],"50k":[70],"molecules":[71,270],"while":[72],"lots":[73],"more":[74,201],"are":[76,90,358],"routinely":[77],"generated":[78],"following":[79],"synthesis":[81],"novel":[83],"materials.":[84],"Significant":[85],"amounts":[86],"freely":[91],"within":[93],"patent":[95],"literature":[96],"and,":[97],"if":[98],"it":[99],"were":[100,165,260,300],"appropriate":[104],"form,":[105],"could":[106],"potentially":[107],"be":[108],"used":[109,140,227],"predictive":[112],"RESULTS:":[114],"We":[115,205,318],"developed":[117,209,354],"pipeline":[119],"automated":[122,322],"extraction":[123,338],"and":[124,139,147,186,253,258,302,339,356],"annotation":[125],"published":[130],"PATENTS.":[131],"Almost":[132],"300,000":[133],"points":[135,150],"collected":[138,212],"models":[143,170,208,254,268,355],"predict":[145,306],"melting":[146,249,314],"pyrolysis":[148,257,297],"(decomposition)":[149],"using":[151,189,196,210],"tools":[152,323],"OCHEM":[156],"modeling":[157],"platform":[158],"(http://ochem.eu).":[159],"A":[160],"number":[161],"technical":[163],"challenges":[164],"simultaneously":[166],"solved":[167],"based":[171],"these":[173],"data.":[174],"These":[175],"included":[176],"handing":[178],"sparse":[180],"matrices":[182],"with":[183],">200,000,000,000":[184],"entries":[185],"parallel":[187],"calculations":[188],"32":[190,285],"\u00d7":[191],"6":[192],"cores":[193],"per":[194],"13":[197],"descriptor":[198],"sets":[199],"totaling":[200],"than":[202,240],"700,000":[203],"descriptors.":[204],"showed":[206],"that":[207,237,244,321],"PATENTS":[214],"had":[215],"similar":[216,279],"or":[217],"better":[218],"accuracy":[220,263],"compared":[221],"curated":[225],"previous":[229],"publications.":[230],"The":[231,262,353],"separation":[232],"chemicals":[236,299],"decomposed":[238],"rather":[239],"melting,":[241],"compounds":[243],"did":[245],"undergo":[246],"normal":[248],"transition,":[250],"was":[251,278,315],"performed":[252],"both":[256],"MPs":[259],"developed.":[261,316],"consensus":[266],"drug-like":[273],"region":[274],"space":[277],"their":[281],"estimated":[282],"experimental":[283],"accuracy,":[284],"\u00b0C.":[286],"Last":[287],"but":[288],"not":[289],"least,":[290],"structural":[292],"features":[293],"related":[294],"identified,":[301],"model":[304],"whether":[307],"compound":[309],"will":[310],"decompose":[311],"instead":[312],"CONCLUSIONS:":[317],"shown":[320],"analysis":[326],"information":[329],"reached":[331],"mature":[333],"stage":[334],"allowing":[335],"collection":[340],"enable":[346],"development":[348],"publicly":[359],"at":[361],"http://ochem.eu/article/99826.":[362]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}