{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/transfer-string-kernel-for-cross-context-dna","title":"Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction","arxiv_id":"1609.03490","date":"2016-09-12","proceeding":null,"authors":["Ritambhara Singh","Jack Lanchantin","Gabriel Robins","Yanjun Qi"],"abstract":"Through sequence-based classification, this paper tries to accurately predict\nthe DNA binding sites of transcription factors (TFs) in an unannotated cellular\ncontext. Related methods in the literature fail to perform such predictions\naccurately, since they do not consider sample distribution shift of sequence\nsegments from an annotated (source) context to an unannotated (target) context.\nWe, therefore, propose a method called \"Transfer String Kernel\" (TSK) that\nachieves improved prediction of transcription factor binding site (TFBS) using\nknowledge transfer via cross-context sample adaptation. TSK maps sequence\nsegments to a high-dimensional feature space using a discriminative mismatch\nstring kernel framework. In this high-dimensional space, labeled examples of\nthe source context are re-weighted so that the revised sample distribution\nmatches the target context more closely. We have experimentally verified TSK\nfor TFBS identifications on fourteen different TFs under a cross-organism\nsetting. We find that TSK consistently outperforms the state-of the-art TFBS\ntools, especially when working with TFs whose binding sequences are not\nconserved across contexts. We also demonstrate the generalizability of TSK by\nshowing its cutting-edge performance on a different set of cross-context tasks\nfor the MHC peptide binding predictions.","url_abs":"http://arxiv.org/abs/1609.03490v1","url_pdf":"http://arxiv.org/pdf/1609.03490v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"transfer-string-kernel-for-cross-context-dna","repo_url":"https://github.com/QData/TransferStringKernel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}