{"id":"https://openalex.org/W7161169547","doi":"https://doi.org/10.1093/bib/bbag233","title":"Shoebill: an interpretable AlphaFold2-informed predictor of protein crystallization propensity using XGBoost","display_name":"Shoebill: an interpretable AlphaFold2-informed predictor of protein crystallization propensity using XGBoost","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7161169547","doi":"https://doi.org/10.1093/bib/bbag233","pmid":"https://pubmed.ncbi.nlm.nih.gov/42132949"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbag233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag233","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bib/bbag233","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089924019","display_name":"Kuan-Ju Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kuan-Ju Liao","raw_affiliation_strings":["Institute of Bioinformatics and Structural Biology, National Tsing Hua University , No. 101, Section 2, Kuang-Fu Road, Hsinchu 300044,"],"raw_orcid":"https://orcid.org/0009-0005-0475-6459","affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics and Structural Biology, National Tsing Hua University , No. 101, Section 2, Kuang-Fu Road, Hsinchu 300044,","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136181253","display_name":"Yuh-Ju Sun","orcid":"https://orcid.org/0000-0003-4734-7848"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yuh-Ju Sun","raw_affiliation_strings":["Institute of Bioinformatics and Structural Biology, National Tsing Hua University , No. 101, Section 2, Kuang-Fu Road, Hsinchu 300044,"],"raw_orcid":"https://orcid.org/0000-0003-4734-7848","affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics and Structural Biology, National Tsing Hua University , No. 101, Section 2, Kuang-Fu Road, Hsinchu 300044,","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089924019","https://openalex.org/A5136181253"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":{"value":3885,"currency":"USD","value_usd":3885},"apc_paid":{"value":3885,"currency":"USD","value_usd":3885},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35848187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.9498999714851379,"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/T11162","display_name":"Enzyme Structure and Function","score":0.9498999714851379,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.039500001817941666,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.003100000089034438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.819599986076355},{"id":"https://openalex.org/keywords/protein-crystallization","display_name":"Protein crystallization","score":0.5631999969482422},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5321000218391418},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/matthews-correlation-coefficient","display_name":"Matthews correlation coefficient","score":0.39879998564720154},{"id":"https://openalex.org/keywords/crystallization","display_name":"Crystallization","score":0.39820000529289246},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.38690000772476196},{"id":"https://openalex.org/keywords/clickstream","display_name":"Clickstream","score":0.36410000920295715},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.819599986076355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384000182151794},{"id":"https://openalex.org/C153064111","wikidata":"https://www.wikidata.org/wiki/Q1281033","display_name":"Protein crystallization","level":3,"score":0.5631999969482422},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.39879998564720154},{"id":"https://openalex.org/C203036418","wikidata":"https://www.wikidata.org/wiki/Q284256","display_name":"Crystallization","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C138744977","wikidata":"https://www.wikidata.org/wiki/Q5132438","display_name":"Clickstream","level":5,"score":0.36410000920295715},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C17923572","wikidata":"https://www.wikidata.org/wiki/Q7250160","display_name":"Propensity score matching","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25189998745918274}],"mesh":[{"descriptor_ui":"D000098404","descriptor_name":"Boosting Machine Learning Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098404","descriptor_name":"Boosting Machine Learning Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098404","descriptor_name":"Boosting Machine Learning Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098404","descriptor_name":"Boosting Machine Learning Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098404","descriptor_name":"Boosting Machine Learning Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003460","descriptor_name":"Crystallization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003460","descriptor_name":"Crystallization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003460","descriptor_name":"Crystallization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003460","descriptor_name":"Crystallization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003460","descriptor_name":"Crystallization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018360","descriptor_name":"Crystallography, X-Ray","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbag233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag233","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42132949","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42132949","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":"Briefings in bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13174273","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13174273/","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbag233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag233","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8671054077","display_name":null,"funder_award_id":"114QF003E1","funder_id":"https://openalex.org/F4320323092","funder_display_name":"National Tsing Hua University"}],"funders":[{"id":"https://openalex.org/F4320323092","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1530397352","https://openalex.org/W1901157220","https://openalex.org/W1961177618","https://openalex.org/W1974528330","https://openalex.org/W1977851803","https://openalex.org/W1981076832","https://openalex.org/W2000895111","https://openalex.org/W2001169808","https://openalex.org/W2008708467","https://openalex.org/W2026501972","https://openalex.org/W2028440694","https://openalex.org/W2035779020","https://openalex.org/W2043338013","https://openalex.org/W2052083266","https://openalex.org/W2087543902","https://openalex.org/W2100059462","https://openalex.org/W2118561568","https://openalex.org/W2126103104","https://openalex.org/W2136299394","https://openalex.org/W2137584761","https://openalex.org/W2139775161","https://openalex.org/W2147702777","https://openalex.org/W2156125289","https://openalex.org/W2165581033","https://openalex.org/W2166033246","https://openalex.org/W2295598076","https://openalex.org/W2413365859","https://openalex.org/W2414449756","https://openalex.org/W2440774392","https://openalex.org/W2519625972","https://openalex.org/W2620636699","https://openalex.org/W2757954796","https://openalex.org/W2776730476","https://openalex.org/W2898210859","https://openalex.org/W2909626341","https://openalex.org/W2935958079","https://openalex.org/W2945976633","https://openalex.org/W2951934944","https://openalex.org/W2980279728","https://openalex.org/W3008730383","https://openalex.org/W3022962116","https://openalex.org/W3028277078","https://openalex.org/W3114115943","https://openalex.org/W3177828909","https://openalex.org/W3181374387","https://openalex.org/W3186179742","https://openalex.org/W3195375135","https://openalex.org/W3206913695","https://openalex.org/W3216325381","https://openalex.org/W4280548378","https://openalex.org/W4293475713","https://openalex.org/W4296032638","https://openalex.org/W4308463927","https://openalex.org/W4310653210","https://openalex.org/W4311677627","https://openalex.org/W4327550249","https://openalex.org/W4360829321","https://openalex.org/W4379933377","https://openalex.org/W4388147611","https://openalex.org/W4389235501","https://openalex.org/W4396721167","https://openalex.org/W4401700750","https://openalex.org/W4410604149"],"related_works":[],"abstract_inverted_index":{"X-ray":[0],"crystallography":[1],"is":[2],"a":[3,18,37,96,109,230],"central":[4],"technique":[5],"for":[6,70,202,222],"high-resolution":[7],"protein":[8,33,79],"structure":[9],"determination;":[10],"however,":[11],"the":[12,156,159,172,183,188],"production":[13],"of":[14,32],"diffraction-quality":[15,105],"crystals":[16],"remains":[17],"major":[19],"bottleneck":[20],"due":[21],"to":[22,40,93,103,166,178,181],"high":[23],"experimental":[24,46,71],"cost":[25],"and":[26,43,100,133,153,168,229],"low":[27],"success":[28],"rates.":[29],"Computational":[30],"prediction":[31],"crystallization":[34,80,146,214],"propensity":[35,81,147,215],"offers":[36],"promising":[38],"strategy":[39],"prioritize":[41],"targets":[42],"reduce":[44],"unnecessary":[45],"screening.":[47],"While":[48],"numerous":[49],"computational":[50],"predictors":[51,148],"have":[52],"been":[53],"proposed,":[54],"many":[55],"rely":[56],"primarily":[57],"on":[58],"sequence-derived":[59],"features":[60,211],"or":[61],"provide":[62],"limited":[63],"interpretability,":[64],"thereby":[65],"offering":[66],"little":[67],"practical":[68],"guidance":[69],"design.":[72],"Here,":[73],"we":[74],"present":[75],"Shoebill,":[76],"an":[77,90],"interpretable":[78],"predictor":[82,191],"that":[83,216],"integrates":[84],"AlphaFold2":[85],"(AF2)-derived":[86],"structural":[87,120,126],"descriptors":[88],"with":[89,213],"XGBoost":[91],"framework":[92],"assess":[94],"whether":[95],"protein-assuming":[97],"successful":[98],"expression":[99],"purification-is":[101],"likely":[102],"form":[104],"crystals.":[106],"Shoebill":[107,142,198,226],"leverages":[108],"comprehensive":[110],"feature":[111],"set":[112],"extracted":[113],"directly":[114],"from":[115,164,176],"AF2-predicted":[116],"structures,":[117],"capturing":[118],"complementary":[119],"information":[121],"beyond":[122],"sequence":[123],"alone,":[124],"including":[125],"disorder,":[127],"AF2":[128],"confidence":[129],"metrics,":[130],"molecular":[131],"geometry,":[132],"surface":[134],"physicochemical":[135],"properties.":[136],"On":[137],"our":[138],"primary":[139],"independent":[140],"benchmark,":[141],"outperforms":[143],"existing":[144],"nondeep-learning":[145,185],"while":[149],"maintaining":[150],"balanced":[151],"sensitivity":[152],"specificity,":[154],"improving":[155],"area":[157],"under":[158],"receiver":[160],"operating":[161],"characteristic":[162],"curve":[163],"0.700":[165],"0.804":[167],"more":[169],"than":[170],"doubling":[171],"Matthews":[173],"correlation":[174],"coefficient":[175],"0.123":[177],"0.297":[179],"relative":[180],"DCFCrystal,":[182],"best-performing":[184],"method.":[186],"Although":[187],"deep":[189],"learning-based":[190],"SADeepcry":[192],"achieves":[193],"higher":[194],"overall":[195],"predictive":[196],"accuracy,":[197],"provides":[199],"feature-level":[200],"explanations":[201],"individual":[203],"predictions":[204],"through":[205],"SHAP":[206],"analysis,":[207],"highlighting":[208],"biologically":[209],"meaningful":[210],"associated":[212],"may":[217],"help":[218],"guide":[219],"rational":[220],"strategies":[221],"construct":[223],"optimization.":[224],"The":[225],"source":[227],"code":[228],"user-friendly":[231],"web":[232],"server":[233],"are":[234],"publicly":[235],"available":[236],"at":[237],"https://github.com/KJ-Liao/Shoebill.":[238]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-15T00:00:00"}