{"id":"https://openalex.org/W4390588971","doi":"https://doi.org/10.1186/s12859-023-05586-5","title":"Prop3D: A flexible, Python-based platform for machine learning with protein structural properties and biophysical data","display_name":"Prop3D: A flexible, Python-based platform for machine learning with protein structural properties and biophysical data","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390588971","doi":"https://doi.org/10.1186/s12859-023-05586-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/38177985","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10768222"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05586-5","doi":"https://doi.org/10.1186/s12859-023-05586-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05586-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05586-5","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05586-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068604431","display_name":"Eli J. Draizen","orcid":"https://orcid.org/0000-0002-5645-5050","observed_orcids":["https://orcid.org/0000-0002-5645-5050"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eli J. Draizen","raw_affiliation_strings":["Department of Biomedical Engineering; University of Virginia","School of Data Science; University of Virginia","Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5645-5050","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering; University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"School of Data Science; University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073372312","display_name":"John Readey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210109614","display_name":"The HDF Group","ror":"https://ror.org/024jrkp82","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Readey","raw_affiliation_strings":["The HDF Group","The HDF Group, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The HDF Group","institution_ids":["https://openalex.org/I4210109614"]},{"raw_affiliation_string":"The HDF Group, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210109614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022761529","display_name":"Cameron Mura","orcid":"https://orcid.org/0000-0001-7985-2561","observed_orcids":["https://orcid.org/0000-0001-7985-2561"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cameron Mura","raw_affiliation_strings":["School of Data Science; University of Virginia","Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7985-2561","affiliations":[{"raw_affiliation_string":"School of Data Science; University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075833022","display_name":"Philip E. Bourne","orcid":"https://orcid.org/0000-0002-7618-7292","observed_orcids":["https://orcid.org/0000-0002-7618-7292"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philip E. Bourne","raw_affiliation_strings":["Department of Biomedical Engineering; University of Virginia","School of Data Science; University of Virginia","Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7618-7292","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering; University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"School of Data Science; University of Virginia","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022761529","https://openalex.org/A5068604431","https://openalex.org/A5075833022"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.9208,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.68471612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"25","issue":"1","first_page":"11","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9272000193595886,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9272000193595886,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.06120000034570694,"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/T11162","display_name":"Enzyme Structure and Function","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/protein-structural-features","display_name":"protein structural properties","score":0.7419999837875366},{"id":"https://openalex.org/keywords/protein-domains","display_name":"protein domains","score":0.6840000152587891},{"id":"https://openalex.org/keywords/biophysical-properties","display_name":"biophysical properties","score":0.6800000071525574},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.5839999914169312},{"id":"https://openalex.org/keywords/training-test-split","display_name":"training-test split","score":0.4970000088214874},{"id":"https://openalex.org/keywords/hdf5","display_name":"HDF5","score":0.878000020980835},{"id":"https://openalex.org/keywords/machine-learning-reproducibility","display_name":"machine learning reproducibility","score":0.5519999861717224},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.5090000033378601},{"id":"https://openalex.org/keywords/electrostatics","display_name":"electrostatics","score":0.7329999804496765},{"id":"https://openalex.org/keywords/phylogenetic-conservation","display_name":"phylogenetic conservation","score":0.9769999980926514},{"id":"https://openalex.org/keywords/community-resources","display_name":"community resources","score":0.5379999876022339},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.828000009059906}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.9020524024963379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6263587474822998},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3770439326763153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3578230142593384},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3440623879432678},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3294077515602112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329384982585907},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3260398507118225},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18550068140029907}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-023-05586-5","doi":"https://doi.org/10.1186/s12859-023-05586-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05586-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05586-5","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"doi:10.1101/2022.12.27.522071","doi":"https://doi.org/10.1101/2022.12.27.522071","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.12.27.522071","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/12/30/2022.12.27.522071.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","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":"pmh:oai:pubmedcentral.nih.gov:10768222","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10768222","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10768222/pdf/12859_2023_Article_5586.pdf","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmid:38177985","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38177985","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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:c6bda3fd57b8472a998f3e96bcf243a3","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/c6bda3fd57b8472a998f3e96bcf243a3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 25, Iss 1, Pp 1-24 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05586-5","doi":"https://doi.org/10.1186/s12859-023-05586-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05586-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05586-5","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3827704327","display_name":"CAREER: Experimental & Computational Studies of Ancient Sm-based RNA Assemblies","funder_award_id":"1350957","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/F4320310536","display_name":"University of Virginia","ror":"https://ror.org/0153tk833"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390588971.pdf","grobid_xml":"https://content.openalex.org/works/W4390588971.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1533059251","https://openalex.org/W1607931568","https://openalex.org/W1966127665","https://openalex.org/W1975304761","https://openalex.org/W1993715180","https://openalex.org/W2001900040","https://openalex.org/W2008708467","https://openalex.org/W2017382438","https://openalex.org/W2025859600","https://openalex.org/W2026593599","https://openalex.org/W2030841140","https://openalex.org/W2070318172","https://openalex.org/W2098718123","https://openalex.org/W2102245393","https://openalex.org/W2106648157","https://openalex.org/W2111472630","https://openalex.org/W2124241917","https://openalex.org/W2131417105","https://openalex.org/W2138104170","https://openalex.org/W2158714788","https://openalex.org/W2165565773","https://openalex.org/W2185628700","https://openalex.org/W2253581743","https://openalex.org/W2302501749","https://openalex.org/W2539190955","https://openalex.org/W2604075160","https://openalex.org/W2607211817","https://openalex.org/W2613409207","https://openalex.org/W2617750324","https://openalex.org/W2731784911","https://openalex.org/W2800648160","https://openalex.org/W2890223884","https://openalex.org/W2913820882","https://openalex.org/W2949223833","https://openalex.org/W2950192635","https://openalex.org/W2952811294","https://openalex.org/W2973136764","https://openalex.org/W3005364306","https://openalex.org/W3036737467","https://openalex.org/W3095435122","https://openalex.org/W3104537585","https://openalex.org/W3106745904","https://openalex.org/W3111835451","https://openalex.org/W3112376646","https://openalex.org/W3112468720","https://openalex.org/W3134089816","https://openalex.org/W3162801148","https://openalex.org/W3163595068","https://openalex.org/W3176355504","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W3216616254","https://openalex.org/W3217314753","https://openalex.org/W4211196614","https://openalex.org/W4282834942","https://openalex.org/W4296032638","https://openalex.org/W4296098995","https://openalex.org/W4309862248","https://openalex.org/W4311181469","https://openalex.org/W4327550249","https://openalex.org/W4402596898","https://openalex.org/W6634119514","https://openalex.org/W6786423766","https://openalex.org/W6893649501"],"related_works":["https://openalex.org/W6921128852","https://openalex.org/W6968472119","https://openalex.org/W3044288453","https://openalex.org/W1981082833","https://openalex.org/W7095988618","https://openalex.org/W7205805777","https://openalex.org/W7133196846","https://openalex.org/W7133205236","https://openalex.org/W7144638295","https://openalex.org/W2083187798"],"abstract_inverted_index":{"BACKGROUND:":[0],"Machine":[1],"learning":[2,42],"(ML)":[3],"has":[4],"a":[5,154,194,200,251,321],"rich":[6],"history":[7],"in":[8,47,88,91,134,221,280],"structural":[9,92],"bioinformatics,":[10],"and":[11,32,71,74,113,131,147,162,173,215,224,231,270,293,361],"modern":[12],"approaches,":[13,43],"such":[14,64,94],"as":[15],"deep":[16],"learning,":[17],"are":[18,104,247],"revolutionizing":[19],"our":[20,207],"knowledge":[21],"of":[22,55,58,119,165,167,277,325,335,348,365],"the":[23,44,53,84,117,159,217,222,237,286,306,316,341,363,370],"subtle":[24],"relationships":[25,372],"between":[26,373],"biomolecular":[27,48],"sequence,":[28],"structure,":[29],"function,":[30],"dynamics":[31],"evolution.":[33],"As":[34,193],"with":[35,142,171,260,300],"any":[36],"advance":[37],"that":[38,79,124,156,176],"rests":[39],"upon":[40],"statistical":[41],"recent":[45],"progress":[46],"sciences":[49],"is":[50],"enabled":[51],"by":[52,205,304],"availability":[54],"vast":[56],"volumes":[57],"sufficiently-variable":[59],"data.":[60,110],"To":[61],"be":[62,67,126,258,276,291],"useful,":[63],"data":[65,95],"must":[66],"well-structured,":[68],"machine-readable,":[69],"intelligible":[70],"manipulable.":[72],"These":[73],"related":[75],"requirements":[76],"pose":[77],"challenges":[78],"become":[80],"especially":[81],"acute":[82],"at":[83,281],"computational":[85],"scales":[86],"typical":[87],"ML.":[89],"Furthermore,":[90],"bioinformatics":[93],"generally":[96],"relate":[97],"to":[98,186,209,229,308],"protein":[99,168,202,326],"three-dimensional":[100],"(3D)":[101],"structures,":[102],"which":[103],"inherently":[105],"more":[106,342],"complex":[107],"than":[108],"sequence-based":[109],"A":[111],"significant":[112],"recurring":[114],"challenge":[115],"concerns":[116],"creation":[118],"large,":[120],"high-quality,":[121],"openly-accessible":[122],"datasets":[123,235,246,360],"can":[125,177,257,275,290,339],"used":[127,259],"for":[128,137,145,158,264,328],"specific":[129],"training":[130,146],"benchmarking":[132],"tasks":[133],"ML":[135,266,349],"pipelines":[136],"predictive":[138],"modeling":[139],"projects,":[140],"along":[141],"reproducible":[143,346],"splits":[144],"testing.":[148],"RESULTS:":[149],"Here,":[150],"we":[151,197],"report":[152],"'Prop3D',":[153],"platform":[155],"allows":[157],"creation,":[160],"sharing":[161],"extensible":[163],"reuse":[164],"libraries":[166],"domains,":[169],"featurized":[170],"biophysical":[172],"evolutionary":[174,371],"properties":[175],"range":[178],"from":[179,369],"detailed,":[180],"atomically-resolved":[181],"physicochemical":[182],"quantities":[183],"(e.g.,":[184,190],"electrostatics)":[185],"coarser,":[187],"residue-level":[188],"features":[189],"phylogenetic":[191],"conservation).":[192],"community":[195],"resource,":[196],"also":[198],"supply":[199],"'Prop3D-20sf'":[201],"dataset,":[203],"obtained":[204],"applying":[206],"approach":[208],"CATH":[210,331],".":[211,314],"We":[212],"have":[213],"developed":[214],"deployed":[216,294],"Prop3D":[218,269,287],"framework,":[219],"both":[220],"cloud":[223],"on":[225,295],"local":[226],"HPC":[227],"resources,":[228],"systematically":[230],"reproducibly":[232],"create":[233],"comprehensive":[234],"via":[236,250,312],"Highly":[238],"Scalable":[239],"Data":[240],"Service":[241],"(":[242],"HSDS":[243,253,313],").":[244],"Our":[245],"freely":[248],"accessible":[249],"public":[252],"instance,":[254],"or":[255],"they":[256],"accompanying":[261],"Python":[262],"wrappers":[263],"popular":[265],"frameworks.":[267],"CONCLUSION:":[268],"its":[271],"associated":[272],"Prop3D-20sf":[273,318],"dataset":[274,319,324],"broad":[278],"utility":[279],"least":[282],"three":[283],"ways.":[284],"Firstly,":[285],"workflow":[288],"code":[289],"customized":[292],"various":[296],"cloud-based":[297],"compute":[298],"platforms,":[299],"scalability":[301],"achieved":[302],"largely":[303],"saving":[305],"results":[307],"distributed":[309],"HDF5":[310],"files":[311],"Secondly,":[315],"linked":[317],"provides":[320],"hand-crafted,":[322],"already-featurized":[323],"domains":[327],"20":[329],"highly-populated":[330],"families;":[332],"importantly,":[333],"provision":[334],"this":[336],"pre-computed":[337],"resource":[338],"aid":[340],"efficient":[343],"development":[344],"(and":[345],"deployment)":[347],"pipelines.":[350],"Thirdly,":[351],"Prop3D-20sf's":[352],"construction":[353],"explicitly":[354],"takes":[355],"into":[356],"account":[357],"(in":[358],"creating":[359],"data-splits)":[362],"enigma":[364],"'data":[366],"leakage',":[367],"stemming":[368],"proteins.":[374]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-01-05T00:00:00"}