[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126449-en":3,"doc-seo-126449-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126449,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Advanced simulations with PLUMED - OPES and Machine Learning Collective Variables - chapter","Biological processes often unfold on timescales beyond those accessible to conventional molecular dynamics. A common strategy introduces collective variables (CVs) and an external bias potential to accelerate sampling. This chapter surveys two widely adopted advances within the PLUMED community library. It first presents OPES (On-the-fly Probability Enhanced Sampling) as a unified biasing framework for free-energy convergence, metastable-state discovery, rate estimation, and generalized ensemble simulation. It then addresses machine-learning-driven CV construction using mlcolvar, optimized in Python and used for enhanced sampling via PLUMED’s native interface.","arXiv :2410 . 18019v1 [physics .comp-ph] 23 Oct 2024  \nAdvanced simulations with PLUMED:  \nOPES and Machine Learning Collective Variables  \nEnrico Trizio,1 Andrea Rizzi,1, 2 Pablo M. Piaggi,3, 4 Michele Invernizzi,5 and Luigi Bonati1, a)  \n1) Atomistic Simulations, Italian Institute of Technology, 16156 Genova, Italy  \n2) Computational Biomedicine, Institute of Advanced Simulations IAS-5; Institute for Neuroscience and Medicine INM-9, Forschungszentrum Jülich GmbH, Jülich 52428, Germany  \n3) CIC nanoGUNE BRTA, 20018 Donostia-San Sebastián, Spain  \n4) Ikerbasque, Basque Foundation for Science, 48013 Bilbao, Spain  \n5) Peptone Ltd. , London, NW1 1JD, United Kingdom  \nMany biological processes occur on time scales longer than those accessible to molecular dynamics simulations. Identifying collective variables (CVs) and introducing an external potential to accelerate them is a popular approach to address this problem. In particular, PLUMED is a community-developed library that implements several methods for CV-based enhanced sampling. This chapter discusses two recent developments that have gained popularity in recent years. The first is the On-the-fly Probability Enhanced Sampling (OPES) method as a biasing scheme. This provides a unified approach to enhanced sampling able to cover many different scenarios: from free energy convergence to the discovery of metastable states, from rate calculation to generalized ensemble simulation. The second development concerns the use of machine learning (ML) approaches to determine CVs by learning the relevant variables directly from simulation data. The construction of these variables is facilitated by the mlcolvar library, which allows them to be optimized in Python and then used to enhance sampling thanks to a native interface inside PLUMED. For each of these methods, in addition to a brief introduction, we provide guidelines, practical suggestions and point to examples from the literature to facilitate their use in the study of the process of interest.  \nKeywords: Enhanced sampling, collective variables, machine learning, OPES, PLUMED, mlcolvar  \nPLUMED  \nPLUgin for MolEcular Dynamics  \n[www.plumed.org](www.plumed.org)  \nmlcolvar Machine Learning Collective Variables  \n[mlcolvar.readthedocs.io](mlcolvar.readthedocs.io)  \nopes cvs  \na) Corresponding author: Luigi Bonati (luigi.bonati@iit.it)  \nContents  \nI. Introduction 3  \nII. Enhancing sampling with OPES 4  \nA. Free energies and probability distributions 4  \nB. OPES overview 6  \nC. OPES Variants 7  \n1. OPES-Metad: converging the free energy surface 8  \n2. OPES-Explore: exploring the landscape 10  \n3. OPES-Expanded: generalized ensemble simulations 11  \n4. OPES-Flooding: computing kinetic rates 15  \nD. Assessing convergence 16  \nIII. Machine learning collective variables 17  \nA. Collective variables for enhanced sampling 17  \nB. Ingredients of a data-driven approach 19  \n1. Representation of the system 19  \n2. Model function 21  \n3. Data acquisition 22  \n4. Learning objectives 23  \n5. The computational pipeline with PLUMED and mlcolvar 23  \nC. Representative use cases 25  \n1. Unsupervised learning and exploration with autoencoders 25  \n2. Distinguishing metastable states with DeepTDA 26  \n3. Deep learning the slow modes with DeepTICA 28  \n4. Combining different approaches with Multi-Task CVs 30  \nD. Interpreting and evaluating ML-based CVs 32  \n1. Correlating the CV with physical descriptors 32  \n2. Controlling the degree of extrapolation 32  \n3. Features relevance via sensitivity analysis 32  \n4. Interpretability via sparse linear models 33  \nIV. Concluding remarks 35  \nList of abbreviations  \nAE . . . . . . . . . . Autoencoder  \nCV . . . . . . . . . Collective variable  \nESS . . . . . . . . . Effective sample size FES . . . . . . . . . Free energy surface  \nFFNN . . . . . . . Feedforward neural network GNN . . . . . . . . Graph neural network KDE . . . . . . . . Kernel density estimation  \nLASSO . . . . . . Least absolute shrinkage and s","cbCaiemWh4uzDvZr","https://ap.wps.com/l/cbCaiemWh4uzDvZr","pdf",14558712,5,1,39,"English","en",105,"# Introduction\n## Rare Events and Enhanced Sampling\n# Enhancing sampling with OPES\n## Free energies and probability distributions\n## OPES overview\n## OPES Variants\n## Assessing convergence\n# Machine learning collective variables\n## Collective variables for enhanced sampling\n## Ingredients of a data-driven approach\n## Representative use cases\n## Interpreting and evaluating ML-based CVs\n# Concluding remarks","[{\"question\":\"Why are enhanced sampling methods needed in molecular dynamics?\",\"answer\":\"Metastable states are often separated by large free-energy barriers, so transitions occur on timescales longer than feasible with standard MD. Enhanced sampling addresses this rare-event problem.\"},{\"question\":\"What does OPES provide in PLUMED?\",\"answer\":\"OPES (On-the-fly Probability Enhanced Sampling) acts as a biasing scheme offering a unified approach to enhanced sampling. It supports tasks such as free-energy convergence, metastable-state discovery, rate calculation, and generalized ensemble simulation.\"},{\"question\":\"How are machine learning collective variables constructed and used?\",\"answer\":\"ML approaches learn CVs directly from simulation data, with construction supported by the mlcolvar library. CVs are optimized in Python and then applied to enhance sampling through PLUMED’s native interface.\"}]","Advanced simulations with PLUMED - OPES and Machine Learning Collective Variables - chapter | PDF",1785905119,98,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"advanced-simulations-with-plumed-opes-and-machine-learning-collective-variables","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/advanced-simulations-with-plumed-opes-and-machine-learning-collective-variables/126449/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why are enhanced sampling methods needed in molecular dynamics?","Question",{"text":77,"@type":78},"Metastable states are often separated by large free-energy barriers, so transitions occur on timescales longer than feasible with standard MD. Enhanced sampling addresses this rare-event problem.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What does OPES provide in PLUMED?",{"text":82,"@type":78},"OPES (On-the-fly Probability Enhanced Sampling) acts as a biasing scheme offering a unified approach to enhanced sampling. It supports tasks such as free-energy convergence, metastable-state discovery, rate calculation, and generalized ensemble simulation.",{"name":84,"@type":75,"acceptedAnswer":85},"How are machine learning collective variables constructed and used?",{"text":86,"@type":78},"ML approaches learn CVs directly from simulation data, with construction supported by the mlcolvar library. CVs are optimized in Python and then applied to enhance sampling through PLUMED’s native interface.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]