{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T12:07:16Z","timestamp":1775909236816,"version":"3.50.1"},"reference-count":7,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T00:00:00Z","timestamp":1559001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100006143","name":"Department of Science and Technology","doi-asserted-by":"publisher","award":["DST\/INT\/SWD\/P-05\/2016"],"award-info":[{"award-number":["DST\/INT\/SWD\/P-05\/2016"]}],"id":[{"id":"10.13039\/501100006143","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Biotechnology, Government of India","award":["BT\/PR16710\/BID\/7\/680\/2016"],"award-info":[{"award-number":["BT\/PR16710\/BID\/7\/680\/2016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Machine learning techniques require various descriptors from protein and nucleic acid sequences to understand\/predict their structure and function as well as distinguishing between disease and neutral mutations. Hence, availability of a feature extraction tool is necessary to bridge the gap.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We developed a comprehensive web-based tool, Seq2Feature, which computes 252 protein and 41 DNA sequence-based descriptors. These features include physicochemical, energetic and conformational properties of proteins, mutation matrices and contact potentials as well as nucleotide composition, physicochemical and conformational properties of DNA. We propose that Seq2Feature could serve as an effective tool for extracting protein and DNA sequence-based features as applicable inputs to machine learning algorithms.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/www.iitm.ac.in\/bioinfo\/SBFE\/index.html.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btz432","type":"journal-article","created":{"date-parts":[[2019,5,23]],"date-time":"2019-05-23T11:23:07Z","timestamp":1558610587000},"page":"4797-4799","source":"Crossref","is-referenced-by-count":29,"title":["Seq2Feature: a comprehensive web-based feature extraction tool"],"prefix":"10.1093","volume":"35","author":[{"given":"Rahul","family":"Nikam","sequence":"first","affiliation":[{"name":"Department of Biotechnology, Bhupat and Jyoti Mehta School of BioSciences, Indian Institute of Technology Madras , Tamil Nadu, Chennai 600036, India"}]},{"given":"M Michael","family":"Gromiha","sequence":"additional","affiliation":[{"name":"Department of Biotechnology, Bhupat and Jyoti Mehta School of BioSciences, Indian Institute of Technology Madras , Tamil Nadu, Chennai 600036, India"},{"name":"Advanced Computational Drug Discovery Unit (ACDD), Institute of Innovative Research, Tokyo Institute of Technology, Midori-ku , Yokohama 226-8501, Kanagawa, Japan"}]}],"member":"286","published-online":{"date-parts":[[2019,5,28]]},"reference":[{"key":"2023013108364780900_btz432-B1","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.mrfmmm.2015.07.005","article-title":"Discrimination of driver and passenger mutations in epidermal growth factor receptor in cancer","volume":"780","author":"Anoosha","year":"2015","journal-title":"Mutat. Res"},{"key":"2023013108364780900_btz432-B2","doi-asserted-by":"crossref","first-page":"2499","DOI":"10.1093\/bioinformatics\/bty140","article-title":"iFeature: a Python package and web server for features extraction and selection from protein and peptide sequences","volume":"34","author":"Chen","year":"2018","journal-title":"Bioinformatics"},{"key":"2023013108364780900_btz432-B3","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"2023013108364780900_btz432-B4","doi-asserted-by":"crossref","first-page":"D37","DOI":"10.1093\/nar\/gkn597","article-title":"DiProDB: a database for dinucleotide properties","volume":"37","author":"Friedel","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023013108364780900_btz432-B5","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1021\/ci049757q","article-title":"A statistical model for predicting protein folding rates from amino acid sequence with structural class information","volume":"45","author":"Gromiha","year":"2005","journal-title":"J. Chem. Inf. Model"},{"key":"2023013108364780900_btz432-B6","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1093\/nar\/gkm998","article-title":"AAindex: amino acid index database, progress report","volume":"36","author":"Kawashima","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023013108364780900_btz432-B7","doi-asserted-by":"crossref","first-page":"73","DOI":"10.4137\/BBI.S38423","article-title":"PDBparam: online resource for computing structural parameters of proteins","volume":"10","author":"Nagarajan","year":"2016","journal-title":"Bioinform. Biol. Insights"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btz432\/28837655\/btz432.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4797\/48979533\/bioinformatics_35_22_4797.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4797\/48979533\/bioinformatics_35_22_4797.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T17:50:16Z","timestamp":1675187416000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/22\/4797\/5499130"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2019,5,28]]},"references-count":7,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz432","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,11,15]]},"published":{"date-parts":[[2019,5,28]]}}}