{"entity": "researcher", "timestamp": "2026-09-28T11:18:03.747Z", "family": "M\u00fcllender", "given": "Lukas", "initials": "L", "orcid": "0009-0008-4978-624X", "affiliations": ["Department of Applied Physics, Science for Life Laboratory, KTH Royal Institute of Technology, SE-171 21 Solna, Sweden.", "Computational Biomedicine, Institute of Advanced Simulations IAS-5/Institute for Neuroscience and Medicine INM-9, Forschungszentrum J\u00fclich GmbH, 52428 J\u00fclich, Germany.", "Department of Physics, RWTH Aachen University, 52062 Aachen, Germany."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/e36bc3c46ca24a52b131b185c8156cdb.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/e36bc3c46ca24a52b131b185c8156cdb"}}, "publications": [{"entity": "publication", "iuid": "4c04cd13ac9647acb273e8a58b029eda", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/4c04cd13ac9647acb273e8a58b029eda.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/4c04cd13ac9647acb273e8a58b029eda"}}, "title": "Effective data-driven collective variables for free energy calculations from metadynamics of paths.", "authors": [{"family": "M\u00fcllender", "given": "Lukas", "initials": "L", "orcid": "0009-0008-4978-624X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/e36bc3c46ca24a52b131b185c8156cdb.json"}}, {"family": "Rizzi", "given": "Andrea", "initials": "A", "orcid": "0000-0001-7693-2013", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/c702989756ab453087a6b7fd52406184.json"}}, {"family": "Parrinello", "given": "Michele", "initials": "M", "orcid": "0000-0001-6550-3272", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1447f5e2f0244d8a9787c51ef51ea690.json"}}, {"family": "Carloni", "given": "Paolo", "initials": "P", "orcid": "0000-0002-9010-0149", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/b0d0a3cc3e0a4f38b52e681b8ee0c6c7.json"}}, {"family": "Mandelli", "given": "Davide", "initials": "D", "orcid": "0000-0002-6869-9511", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a5afe194372b485bb25d2e6efca89e2d.json"}}], "type": "journal article", "published": "2024-04-00", "journal": {"title": "PNAS Nexus", "issn": "2752-6542", "volume": "3", "issue": "4", "pages": "pgae159", "issn-l": null}, "abstract": "A variety of enhanced sampling (ES) methods predict multidimensional free energy landscapes associated with biological and other molecular processes as a function of a few selected collective variables (CVs). The accuracy of these methods is crucially dependent on the ability of the chosen CVs to capture the relevant slow degrees of freedom of the system. For complex processes, finding such CVs is the real challenge. Machine learning (ML) CVs offer, in principle, a solution to handle this problem. However, these methods rely on the availability of high-quality datasets-ideally incorporating information about physical pathways and transition states-which are difficult to access, therefore greatly limiting their domain of application. Here, we demonstrate how these datasets can be generated by means of ES simulations in trajectory space via the metadynamics of paths algorithm. The approach is expected to provide a general and efficient way to generate efficient ML-based CVs for the fast prediction of free energy landscapes in ES simulations. We demonstrate our approach with two numerical examples, a 2D model potential and the isomerization of alanine dipeptide, using deep targeted discriminant analysis as our ML-based CV of choice.", "doi": "10.1093/pnasnexus/pgae159", "pmid": "38665160", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC11044970"}, {"db": "pii", "key": "pgae159"}], "notes": [], "created": "2026-09-23T11:26:02.946Z", "modified": "2026-09-23T11:26:03.145Z"}]}