[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121879-en":3,"doc-seo-121879-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121879,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","ACCELERATING MOLECULAR DYNAMICS SIMULATIONS AND PREDICTING REACTION PATHWAYS WITH FREE ENERGY SURFACE GRADIENTS - Derived from Machine Learning Models - Dissertation Overview","Molecular Dynamics (MD) simulations enable study of atomic interactions in proteins and molecular systems, but their slow sampling rate can make many biological processes impractical to access. This dissertation develops machine learning methods to infer reaction coordinates from molecular descriptors and to use the resulting free-energy information to bias the system and reduce energy barriers. A new approach trains on MD trajectories and extracts free energy surface (FES) gradients. Using LINES with invertible neural networks, the method accelerates MD sampling, learns reaction pathways, and enables applications including protein-peptide binding site discovery and characterization of stabilizing inter-residue interactions.","ACCELERATING MOLECULAR DYNAMICS SIMULATIONS AND PREDICTING  \nREACTION PATHWAYS WITH FREE ENERGY SURFACE GRADIENTS  \nDERIVED FROM MACHINE LEARNING MODELS  \nBy  \nRYAN E. ODSTRCIL  \nA dissertation submitted in partial fulfillment of  \nthe requirements for the degree of  \nDOCTOR OF PHILOSOPHY  \nWASHINGTON STATE UNIVERSITY  \nSchool of Mechanical and Materials Engineering  \nMAY 2024  \n© Copyright by RYAN E. ODSTRCIL, 2024  \nAll Rights Reserved  \n© Copyright by RYAN E. ODSTRCIL, 2024 All Rights Reserved  \nTo the Faculty of Washington State University:  \nThe members of the Committee appointed to examine the dissertation of RYAN E. ODSTRCIL find it satisfactory and recommend that it be accepted.  \nJin Liu, Ph.D., Co-Chair Prashanta Dutta, Ph.D., Co-Chair Soumik Banerjee, Ph.D.  \nACKNOWLEDGMENT  \nI am delighted to recognize the people in my life without whom this work would not have been possible. First, words cannot express my gratitude to Professor Jin Liu, my PhD supervisor, who offered me guidance on countless occasions and mentored me on my journey of learning how to research. I am also grateful to Professor Prashanta Dutta, whose insightful support and direction in the field of biological simulation and machine learning helped me along the way. I would like to extend my sincere thanks to my lab members–Chunhua and Muhtasim – as well as other friends in graduate school for their camaraderie over the last several years. Finally, I am deeply indebted to my parents for their unwavering support and confidence in me which propelled me throughout life.  \nACCELERATING MOLECULAR DYNAMICS SIMULATIONS AND PREDICTING  \nREACTION PATHWAYS WITH FREE ENERGY SURFACE GRADIENTS DERIVED  \nFROM MACHINE LEARNING MODELS  \nAbstract  \nby Ryan E. Odstrcil, Ph.D.  \nWashington State University  \nMay 2024  \nCo-Chairs: Jin Liu and Prashanta Dutta  \nMolecular Dynamics (MD) simulations are a computational tool to investigate atomic interactions in proteins and molecular systems. However, the slow rate of simulation renders many biological processes inaccessible to study. To combat this, machine learning techniques are underdevelopment to identify reaction coordinates as a function of molecular descriptors (a.k.a. molecular coordinates). Once relevant reaction coordinates are known, the energy of the molecular system can be biased to reduce energy barriers that inhibit conformational sampling.  \nIn this work, a machine learning approach is developed to discover reaction pathways by training a machine learning model on trajectories of MD simulations and extract gradients of the free energy surface (FES) . With these gradients, trends or patterns in the reaction pathways can be identified – sometimes even before a reaction has been fully sampled.  \nThe developed algorithm log-probability estimation via invertible neural networks for enhanced sampling (LINES) is validated on several small systems that showcase the approach’s ability to learn the FES and produce reaction coordinates that significantly accelerate sampling during MD  \nsimulations. The method is later applied to discover protein-peptide binding sites, explore novel protein conformations, and evaluate the strength of inter-residue interactions that stabilize protein complexes.  \nTABLE OF CONTENTS  \nPage  \nACKNOWLEDGMENT................................................................................................................ iii  \nABSTRACT................................................................................................................................... iv  \nLIST OF TABLES ......................................................................................................................... ix  \nLIST OF FIGURES ........................................................................................................................ x  \nCHAPTERS  \nCHAPTER 1: INTRODUCTION TO MOLECULAR DYNAMICS AND ENHANCED SAMPLING ........................................................................","cbCaijP7B7h1IJlH","https://ap.wps.com/l/cbCaijP7B7h1IJlH","pdf",5221410,1,150,"English","en",105,"# Acknowledgment\n# Abstract\n# List of Tables\n# List of Figures\n# Chapter 1: Introduction to Molecular Dynamics and Enhanced Sampling\n## Strengths and Limitations of Molecular Dynamics\n## Methods to Predict Reaction Coordinates\n# Chapter 2: LINES Method - Machine Learning Model to Identify Reaction Pathways\n## Biased MD Simulation\n## Invertible Neural Networks\n## Neural Network Architecture and Training\n## Reaction Coordinate Prediction\n## Biasing Potential Prediction\n## LINES iterative algorithm\n# Chapter 3: Alanine Dipeptide Case Study - Free Energy Surface Estimation with a Normalizing Flow\n## Introduction\n## Model Inputs\n## Results\n## Conclusions\n# Chapter 4: Cyclodextrin Case Study - Accelerating Sampling with a Reaction Coordinate Predicted by LINES\n## Introduction\n## Model Inputs","[{\"question\":\"Why do molecular dynamics simulations struggle to study many biological processes?\",\"answer\":\"MD sampling is slow, so key biological processes may not be fully observed within feasible simulation times, limiting accessibility for study.\"},{\"question\":\"How does the work use machine learning to improve enhanced sampling?\",\"answer\":\"It learns reaction coordinates from molecular descriptors, then uses free energy surface gradients to bias the system and reduce energy barriers that hinder conformational sampling.\"},{\"question\":\"What is the role of free energy surface (FES) gradients and the LINES method?\",\"answer\":\"The method estimates FES gradients from learned models; LINES uses invertible neural networks to validate and generate reaction coordinates that accelerate sampling and reveal reaction pathway structure.\"}]","ACCELERATING MOLECULAR DYNAMICS SIMULATIONS AND PREDICTING REACTION PATHWAYS WITH FREE ENERGY SURFACE GRADIENTS - Derived from Machine Learning Models - Dissertation Overview | PDF",1785807413,378,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"accelerating-molecular-dynamics-simulations-and-predicting-reaction-pathways-with-free-energy-surface-gradients-derived-from-machine-learning-models-dissertation-overview","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/accelerating-molecular-dynamics-simulations-and-predicting-reaction-pathways-with-free-energy-surface-gradients-derived-from-machine-learning-models-dissertation-overview/121879/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do molecular dynamics simulations struggle to study many biological processes?","Question",{"text":75,"@type":76},"MD sampling is slow, so key biological processes may not be fully observed within feasible simulation times, limiting accessibility for study.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the work use machine learning to improve enhanced sampling?",{"text":80,"@type":76},"It learns reaction coordinates from molecular descriptors, then uses free energy surface gradients to bias the system and reduce energy barriers that hinder conformational sampling.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of free energy surface (FES) gradients and the LINES method?",{"text":84,"@type":76},"The method estimates FES gradients from learned models; LINES uses invertible neural networks to validate and generate reaction coordinates that accelerate sampling and reveal reaction pathway structure.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]