{"id":"https://openalex.org/W7154719316","doi":"https://doi.org/10.1093/bioinformatics/btag189","title":"BABAPPAlign: a multiple sequence alignment engine with a learned residue-level scoring function","display_name":"BABAPPAlign: a multiple sequence alignment engine with a learned residue-level scoring function","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154719316","doi":"https://doi.org/10.1093/bioinformatics/btag189","pmid":"https://pubmed.ncbi.nlm.nih.gov/41992497"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag189","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag189","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/bioinformatics/btag189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133865764","display_name":"Krishnendu Sinha","orcid":null},"institutions":[{"id":"https://openalex.org/I61923386","display_name":"Jawaharlal Institute of Post Graduate Medical Education and Research","ror":"https://ror.org/02fq2px14","country_code":"IN","type":"education","lineage":["https://openalex.org/I61923386"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Krishnendu Sinha","raw_affiliation_strings":["Department of Zoology, Jhargram Raj College , Jhargram, West Bengal 721507,"],"raw_orcid":"https://orcid.org/0000-0001-9590-3875","affiliations":[{"raw_affiliation_string":"Department of Zoology, Jhargram Raj College , Jhargram, West Bengal 721507,","institution_ids":["https://openalex.org/I61923386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5133865764"],"corresponding_institution_ids":["https://openalex.org/I61923386"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50641386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.499099999666214,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.499099999666214,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.18219999969005585,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.024000000208616257,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6093999743461609},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.436599999666214},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.38040000200271606},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37529999017715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452999949455261},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6093999743461609},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162000060081482},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.38040000200271606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.32019999623298645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3003000020980835}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag189","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag189","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41992497","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41992497","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13141150","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13141150/","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag189","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag189","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974050623","https://openalex.org/W2046183549","https://openalex.org/W2068448872","https://openalex.org/W2074231493","https://openalex.org/W2106882534","https://openalex.org/W2110241016","https://openalex.org/W2132926880","https://openalex.org/W2143210482","https://openalex.org/W2144362290","https://openalex.org/W2160378127","https://openalex.org/W2163860567","https://openalex.org/W3146944767","https://openalex.org/W4252684946","https://openalex.org/W4327550249","https://openalex.org/W4390590489"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Multiple":[1],"sequence":[2],"alignment":[3,15,65],"(MSA)":[4],"remains":[5],"a":[6,34,44],"core":[7],"problem":[8],"in":[9,106],"bioinformatics,":[10],"yet":[11],"most":[12],"widely":[13],"used":[14],"methods":[16],"still":[17],"rely":[18],"on":[19,49,78],"static":[20,40],"amino":[21],"acid":[22],"substitution":[23,41],"matrices":[24],"that":[25,38],"cannot":[26],"adapt":[27],"to":[28],"sequence-specific":[29],"context.":[30],"RESULTS:":[31],"BABAPPAlign":[32,103],"is":[33,104,120,128,145],"progressive":[35],"MSA":[36],"engine":[37],"replaces":[39],"scoring":[42],"with":[43,74],"trained":[45],"residue-level":[46],"scorer":[47],"operating":[48],"fixed":[50],"protein-language-model":[51],"embeddings,":[52],"while":[53],"retaining":[54],"exact":[55],"affine-gap":[56],"dynamic":[57],"programming.":[58],"It":[59],"also":[60,97],"provides":[61],"an":[62,111],"integrated":[63],"codon-aware":[64],"mode.":[66],"Using":[67],"BAliBASE":[68],"as":[69,110],"the":[70,85,117,124,133],"primary":[71],"inferential":[72],"benchmark,":[73],"supporting":[75],"external":[76],"validation":[77],"deterministic":[79],"subsets":[80],"of":[81],"PREFAB":[82],"and":[83,93,96,108,132],"HOMSTRAD,":[84],"learned":[86],"backend":[87],"outperformed":[88],"matched":[89],"in-engine":[90],"EBA-style":[91],"cosine":[92],"BLOSUM62":[94],"controls,":[95],"exceeded":[98],"MAFFT.":[99],"AVAILABILITY":[100],"AND":[101],"IMPLEMENTATION:":[102],"implemented":[105],"Python":[107],"distributed":[109],"open-source":[112],"command-line":[113],"package":[114],"through":[115],"PyPI;":[116],"source":[118],"code":[119],"available":[121,129,138,146],"at":[122,130,139,147],"https://github.com/sinhakrishnendu/BABAPPAlign,":[123],"archived":[125],"software":[126],"release":[127],"https://doi.org/10.5281/zenodo.17934124,":[131],"pretrained":[134],"model":[135],"weights":[136],"are":[137],"https://doi.org/10.5281/zenodo.18053200.":[140],"SUPPLEMENTARY":[141],"MATERIAL:":[142],"Supplementary":[143],"material":[144],"Bioinformatics":[148],"online.":[149]},"counts_by_year":[],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2026-04-18T00:00:00"}
