{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T05:20:29Z","timestamp":1794633629256,"version":"4.9.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008875","name":"Shanghai Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008875","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computational Biology and Chemistry"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.compbiolchem.2026.109411","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T23:18:41Z","timestamp":1790378321000},"page":"109411","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Evaluation of protein sequence retrieval via protein language model embeddings and FAISS"],"prefix":"10.1016","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9980-198X","authenticated-orcid":false,"given":"Can","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4126-2877","authenticated-orcid":false,"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109411_b1","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol."},{"issue":"8","key":"10.1016\/j.compbiolchem.2026.109411_b2","doi-asserted-by":"crossref","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: A universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"issue":"D1","key":"10.1016\/j.compbiolchem.2026.109411_b3","doi-asserted-by":"crossref","first-page":"D553","DOI":"10.1093\/nar\/gkab1054","article-title":"SCOPe: Improvements to the structural classification of proteins \u2013 extended database","volume":"50","author":"Chandonia","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiolchem.2026.109411_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiolchem.2025.108429","article-title":"ProAttUnet: Advancing protein secondary structure prediction with deep learning via U-Net dual-pathway feature fusion and ESM2 pretrained protein language model","volume":"118","author":"Cheng","year":"2025","journal-title":"Comput. Biol. Chem."},{"issue":"9","key":"10.1016\/j.compbiolchem.2026.109411_b5","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"Eddy","year":"1998","journal-title":"Bioinformatics"},{"issue":"10","key":"10.1016\/j.compbiolchem.2026.109411_b6","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compbiolchem.2026.109411_b7","series-title":"FastAPI documentation","author":"FastAPI Contributors","year":"2024"},{"issue":"6730","key":"10.1016\/j.compbiolchem.2026.109411_b8","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"issue":"7","key":"10.1016\/j.compbiolchem.2026.109411_b9","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1038\/s41587-024-02353-6","article-title":"Fast, sensitive detection of protein homologs using deep dense retrieval","volume":"43","author":"Hong","year":"2025","journal-title":"Nature Biotechnol."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109411_b10","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product quantization for nearest neighbor search","volume":"33","author":"Jegou","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.compbiolchem.2026.109411_b11","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Trans. Big Data"},{"issue":"7873","key":"10.1016\/j.compbiolchem.2026.109411_b12","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"10.1016\/j.compbiolchem.2026.109411_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiolchem.2024.108055","article-title":"DeepPLM_mCNN: An approach for enhancing ion channel and ion transporter recognition by multi-window CNN based on features from pre-trained language models","volume":"110","author":"Le","year":"2024","journal-title":"Comput. Biol. Chem."},{"key":"10.1016\/j.compbiolchem.2026.109411_b14","series-title":"Advances in Neural Information Processing Systems 37","first-page":"35700","article-title":"ProSST: Protein language modeling with quantized structure and disentangled attention","volume":"Vol. 37","author":"Li","year":"2024"},{"issue":"6637","key":"10.1016\/j.compbiolchem.2026.109411_b15","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":"10.1016\/j.compbiolchem.2026.109411_b16","doi-asserted-by":"crossref","first-page":"2775","DOI":"10.1038\/s41467-024-46808-5","article-title":"PLMSearch: Protein language model powers accurate and fast sequence search for remote homology","volume":"15","author":"Liu","year":"2024","journal-title":"Nat. Commun."},{"issue":"4","key":"10.1016\/j.compbiolchem.2026.109411_b17","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","volume":"42","author":"Malkov","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compbiolchem.2026.109411_b18","series-title":"ESM metagenomic atlas","author":"Meta AI","year":"2022"},{"key":"10.1016\/j.compbiolchem.2026.109411_b19","series-title":"TensorRT: High performance deep learning inference optimizer and runtime","author":"NVIDIA Corporation","year":"2024"},{"issue":"15","key":"10.1016\/j.compbiolchem.2026.109411_b20","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"2","key":"10.1016\/j.compbiolchem.2026.109411_b21","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/protein\/12.2.85","article-title":"Twilight zone of protein sequence alignments","volume":"12","author":"Rost","year":"1999","journal-title":"Protein Eng."},{"key":"10.1016\/j.compbiolchem.2026.109411_b22","series-title":"Slurm workload manager documentation","author":"SchedMD LLC","year":"2024"},{"issue":"11","key":"10.1016\/j.compbiolchem.2026.109411_b23","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nature Biotechnol."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109411_b24","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1186\/s13321-024-00884-3","article-title":"PETA: Evaluating the impact of protein transfer learning with sub-word tokenization on downstream applications","volume":"16","author":"Tan","year":"2024","journal-title":"J. Cheminformatics"},{"issue":"16","key":"10.1016\/j.compbiolchem.2026.109411_b25","doi-asserted-by":"crossref","first-page":"6338","DOI":"10.1021\/acs.jcim.4c00689","article-title":"Simple, efficient, and scalable structure-aware adapter boosts protein language models","volume":"64","author":"Tan","year":"2024","journal-title":"J. Chem. Inf. Model."},{"issue":"D1","key":"10.1016\/j.compbiolchem.2026.109411_b26","doi-asserted-by":"crossref","first-page":"D523","DOI":"10.1093\/nar\/gkac1052","article-title":"UniProt: the universal protein knowledgebase in 2023","volume":"51","author":"The UniProt Consortium","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"10.1016\/j.compbiolchem.2026.109411_b27","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.compbiolchem.2026.109411_b28","first-page":"2614","article-title":"Milvus: A purpose-built vector data management system","volume":"14","author":"Wang","year":"2021","journal-title":"Proc. the VLDB Endow."},{"issue":"1","key":"10.1016\/j.compbiolchem.2026.109411_b29","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/s12539-025-00753-z","article-title":"BEST: Basic embedding search tool enhancing discovery of novel enzyme","volume":"18","author":"Wu","year":"2026","journal-title":"Interdiscip. Sci.: Comput. Life Sci."}],"container-title":["Computational Biology and Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005384?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1476927126005384?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T04:20:41Z","timestamp":1794630041000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1476927126005384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":29,"alternative-id":["S1476927126005384"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109411","relation":{},"ISSN":["1476-9271"],"issn-type":[{"value":"1476-9271","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluation of protein sequence retrieval via protein language model embeddings and FAISS","name":"articletitle","label":"Article Title"},{"value":"Computational Biology and Chemistry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiolchem.2026.109411","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109411"}}