14 - 16 July 2022
Barcelona MMSML Workshop
METHODS IN MOLECULAR SIMULATIONS AND MACHINE LEARNING
On site — Barcelona Biomedical Research Park
A three-day get together of discussions, activities and short talks
Molecular simulations are changing. converging quantum and classical simulations, accurate machine learning potentials for richer physics, chemical representations and quantum computers. THIS WORKSHOP is about shaping this future.
Speakers
Rafael Gómez-Bombarelli
MIT, USA
John Chodera
MSKCC, USA
Peter Eastman
U. Stanford, USA
Gianni
De Fabritiis
De Fabritiis
UPF, Spain
Cecilia Clementi
FU Berlin, Germany
Raimondas Galvelis
Acellera, Spain
Paolo Carloni
Jülich Research Center, Germany
Chris Chipot
U. Lorraine and U. Illinois, Urbana-Champaign, USA
Kristof T. Schütt
TU Berlin, Germany
Michael Gastegger
TU Berlin, Germany
Olexandr Isayev
Carnegie Mellon University, USA
Loche Philip Robin
EPFL, Switzerland
Elizabeth Decolvenaere
D.E. Shaw Research, USA
Matthias Rupp
U. Konstanz, Germany
Olga Kononova
Roivant, USA
Alexander Wade
U. College London, UK
Tristan Bereau
UvA, Netherlands
Tess
Smidt
Smidt
MIT, USA
Julien
Michel
Michel
U. Edinburgh, UK
Jonathan Godwin
DeepMind, UK
Frank
Noe
Noe
FU Berlin, Germany
Hanwen Zhang
University of Oxford, UK
Justin
Smith
Smith
Nvidia, USA
Gábor
Csányi
Csányi
University of Cambridge, UK
Rianne van den Berg
Microsoft Research, Netherlands
Robin
Winter
Winter
Bayer
Germany
Daniel
Cole
Cole
Newcastle University, UK
Jose
Jimenez
Jimenez
Microsoft Research, UK
Luis Itza Vazquez-Salazar
University Basel, Switzerland
Ryota Tomioka
Microsoft Research, UK
Research topics
How to develop new ML potentials in the context of physics-based molecular modelling and simulations.
What software infrastructure is required to support hybrid ML- and physics-based simulations.
How to handle charges and long-range interactions.
How to extend machine learning potentials to charge transfer and reactions.
How to optimize neural network calculations, latency, CUDA graphs, tensor cores.
What is the role of quantum computers and special hardware in quantum chemistry.
Description
Nature and the fundamental equations that govern physics at atomistic scales are well understood, i.e. quantum mechanics and the Schrodinger equation. However, solving such equations is possible only for very simple systems such as the hydrogen atom. While advances have been made by using a quantum computer, the field of quantum chemistry is devoted to finding approximations for solving the quantum problem on classical computers but even these approximations remain slow for biological applications and inaccurate in certain conditions.
Machine learning potentials, as universal many-body function approximators, might be capable of delivering the next generation of force fields when used together with physics-based potentials, blurring the boundary between quantum mechanics, molecular mechanics and coarse-grained simulations into a cohesive methodology.
In recent years, incredible progress has been made in transferable molecular representations which can learn effective potential functions. New methods for learning such potentials and even the energetics of the underlying physical systems are now available. Applications using differentiable molecular simulations offer a further way to create force-fields. The possibility to have molecular mechanics simulations with changing molecular identity seems now reachable as well as reactivity. However, there are still problems in extending the generalizability of such potentials, lack of accurate datasets, handling of charges and charged molecules, all within a speed bound which must be able to handle large systems like protein complexes. This workshop is expected to get us together to discuss and advance these scientific problems towards next generation molecular simulations.
The Venue
Barcelona Biomedical Research Park
C/Doctor Aiguader, 88
E-08003 Barcelona, Spain
E-08003 Barcelona, Spain
The meeting will be held at the Barcelona Biomedical Research Park (PRBB), a large scientific hub that brings together several research centres to promote research in the field of life sciences, human health, and biomedicine.
Organizers and Contacts
Gianni De Fabritiis, UPF, Spain (@gdefabritiis)
Rafael Gómez-Bombarelli, MIT, USA
Contact: irene.escolar@upf.edu
Industrial sponsor: Acellera (@acellera)
CompBioMed
The MMSML Workshop is organized as part of the training activities of CompBioMed2, a European Commission H2020 funded Centre of Excellence focused on the use and development of computational methods for biomedical applications.
Comprising members from academia, industry and the healthcare sector, CompBioMed2 has established itself as a hub for practitioners in the field, successfully nucleating a substantial body of research, education, training, innovation and outreach within the nascent field of Computational Biomedicine.