{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:11:45Z","timestamp":1779336705454,"version":"3.51.4"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Multiple sequence alignment (MSA) remains a core problem in bioinformatics, yet most widely used alignment methods still rely on static amino acid substitution matrices that cannot adapt to sequence-specific context.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>BABAPPAlign is a progressive MSA engine that replaces static substitution scoring with a trained residue-level scorer operating on fixed protein-language-model embeddings, while retaining exact affine-gap dynamic programming. It also provides an integrated codon-aware alignment mode. Using BAliBASE as the primary inferential benchmark, with supporting external validation on deterministic subsets of PREFAB and HOMSTRAD, the learned backend outperformed matched in-engine EBA-style cosine and BLOSUM62 controls, and also exceeded MAFFT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and Implementation<\/jats:title>\n                    <jats:p>BABAPPAlign is implemented in Python and distributed as an open-source command-line package through PyPI; the source code is available at https:\/\/github.com\/sinhakrishnendu\/BABAPPAlign, the archived software release is available at https:\/\/doi.org\/10.5281\/zenodo.17934124, and the pretrained model weights are available at https:\/\/doi.org\/10.5281\/zenodo.18053200.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary material<\/jats:title>\n                    <jats:p>Supplementary material is available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag189","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T11:33:37Z","timestamp":1776166417000},"source":"Crossref","is-referenced-by-count":0,"title":["BABAPPAlign: a multiple sequence alignment engine with a learned residue-level scoring function"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9590-3875","authenticated-orcid":false,"given":"Krishnendu","family":"Sinha","sequence":"first","affiliation":[{"name":"Department of Zoology, Jhargram Raj College , Jhargram, West Bengal 721507,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"2026052023570139200_btag189-B1","first-page":"345","article-title":"A model of evolutionary change in proteins","volume":"5","author":"Dayhoff","year":"1978","journal-title":"Atlas Protein Sequence Structure"},{"key":"2026052023570139200_btag189-B2","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2026052023570139200_btag189-B3","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1093\/nar\/gkp1196","article-title":"Quality measures for protein alignment benchmarks","volume":"38","author":"Edgar","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2026052023570139200_btag189-B4","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/0022-2836(82)90398-9","article-title":"An improved algorithm for matching biological sequences","volume":"162","author":"Gotoh","year":"1982","journal-title":"J Mol Biol"},{"key":"2026052023570139200_btag189-B5","doi-asserted-by":"crossref","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026052023570139200_btag189-B6","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand J Stat"},{"key":"2026052023570139200_btag189-B7","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol Biol Evol"},{"key":"2026052023570139200_btag189-B8","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026052023570139200_btag189-B9","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","article-title":"A general method applicable to the search for similarities in the amino acid sequence of two proteins","volume":"48","author":"Needleman","year":"1970","journal-title":"J Mol Biol"},{"key":"2026052023570139200_btag189-B10","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1006\/jmbi.2000.4042","article-title":"T-coffee: A novel method for fast and accurate multiple sequence alignment","volume":"302","author":"Notredame","year":"2000","journal-title":"J Mol Biol"},{"key":"2026052023570139200_btag189-B11","doi-asserted-by":"crossref","first-page":"btad786","DOI":"10.1093\/bioinformatics\/btad786","article-title":"Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone","volume":"40","author":"Pantolini","year":"2024","journal-title":"Bioinformatics"},{"key":"2026052023570139200_btag189-B12","doi-asserted-by":"crossref","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning","volume":"118","author":"Rives","year":"2021","journal-title":"PNAS"},{"key":"2026052023570139200_btag189-B13","doi-asserted-by":"crossref","first-page":"D203","DOI":"10.1093\/nar\/gkh027","article-title":"HOMSTRAD: recent developments of the homologous protein structure alignment database","volume":"32","author":"Stebbings","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2026052023570139200_btag189-B14","doi-asserted-by":"crossref","first-page":"W609","DOI":"10.1093\/nar\/gkl315","article-title":"PAL2NAL: robust conversion of protein sequence alignments into the corresponding codon alignments","volume":"34","author":"Suyama","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2026052023570139200_btag189-B15","doi-asserted-by":"crossref","first-page":"4673","DOI":"10.1093\/nar\/22.22.4673","article-title":"CLUSTAL W: improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice","volume":"22","author":"Thompson","year":"1994","journal-title":"Nucleic Acids Res"},{"key":"2026052023570139200_btag189-B16","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1093\/bioinformatics\/15.1.87","article-title":"BAliBASE: A benchmark alignment database for the evaluation of multiple alignment programs","volume":"15","author":"Thompson","year":"1999","journal-title":"Bioinformatics"},{"key":"2026052023570139200_btag189-B17","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biometrics Bulletin"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag189\/68098318\/btag189.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag189\/68098318\/btag189.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag189\/68098318\/btag189.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:57:20Z","timestamp":1779335840000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag189\/8656831"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":17,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag189","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,4,16]]},"article-number":"btag189"}}