{"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/must-cnn-a-multilayer-shift-and-stitch-deep","title":"MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction","arxiv_id":"1605.03004","date":"2016-05-10","proceeding":null,"authors":["Zeming Lin","Jack Lanchantin","Yanjun Qi"],"abstract":"Predicting protein properties such as solvent accessibility and secondary\nstructure from its primary amino acid sequence is an important task in\nbioinformatics. Recently, a few deep learning models have surpassed the\ntraditional window based multilayer perceptron. Taking inspiration from the\nimage classification domain we propose a deep convolutional neural network\narchitecture, MUST-CNN, to predict protein properties. This architecture uses a\nnovel multilayer shift-and-stitch (MUST) technique to generate fully dense\nper-position predictions on protein sequences. Our model is significantly\nsimpler than the state-of-the-art, yet achieves better results. By combining\nMUST and the efficient convolution operation, we can consider far more\nparameters while retaining very fast prediction speeds. We beat the\nstate-of-the-art performance on two large protein property prediction datasets.","url_abs":"http://arxiv.org/abs/1605.03004v1","url_pdf":"http://arxiv.org/pdf/1605.03004v1.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":"must-cnn-a-multilayer-shift-and-stitch-deep","repo_url":"https://github.com/mzweilin/EvadeML-Zoo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"must-cnn-a-multilayer-shift-and-stitch-deep","repo_url":"https://github.com/QData/DeepLearning4-ProteinSequenceProcessing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null},{"paper_slug":"must-cnn-a-multilayer-shift-and-stitch-deep","repo_url":"https://github.com/QData/DeepProtein","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":null,"task_name":"Position"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"protein-structure-prediction","task_name":"Protein Structure Prediction"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"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}