{"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/visualizing-convolutional-neural-network","title":"Visualizing Convolutional Neural Network Protein-Ligand Scoring","arxiv_id":"1803.02398","date":"2018-03-06","proceeding":null,"authors":["Joshua Hochuli","Alec Helbling","Tamar Skaist","Matthew Ragoza","David Ryan Koes"],"abstract":"Protein-ligand scoring is an important step in a structure-based drug design\npipeline. Selecting a correct binding pose and predicting the binding affinity\nof a protein-ligand complex enables effective virtual screening. Machine\nlearning techniques can make use of the increasing amounts of structural data\nthat are becoming publicly available. Convolutional neural network (CNN)\nscoring functions in particular have shown promise in pose selection and\naffinity prediction for protein-ligand complexes. Neural networks are known for\nbeing difficult to interpret. Understanding the decisions of a particular\nnetwork can help tune parameters and training data to maximize performance.\nVisualization of neural networks helps decompose complex scoring functions into\npictures that are more easily parsed by humans. Here we present three methods\nfor visualizing how individual protein-ligand complexes are interpreted by 3D\nconvolutional neural networks. We also present a visualization of the\nconvolutional filters and their weights. We describe how the intuition provided\nby these visualizations aids in network design.","url_abs":"http://arxiv.org/abs/1803.02398v1","url_pdf":"http://arxiv.org/pdf/1803.02398v1.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":"visualizing-convolutional-neural-network","repo_url":"https://github.com/gnina/gnina","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"drug-design","task_name":"Drug Design"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}