Preliminary program

Talks should be 20+5 minutes long and focus on a single topic. 5 minutes are left for questions.

Day 1

Thursday, July 14

Registration 8:00 - 9:00

Session 1

09:00-9:25 Olexandr Isayev, Neural networks learning quantum chemistry

09:25-9:50 Jonathan Godwin, Methods For Scalable Molecular Representation Learning

09:50-10.15 Kristof Schütt, Unifying machine learning and quantum chemistry with deep neural networks

10:15-10:45 Coffee break and discussions

10:45-11:10 Matthias Rupp, Ultra-Fast Interpretable Machine-Learning Potentials

11:10-12:35 Raimondas Galvelis, Optimization of neural network potentials

12:35-13.00 Justin Smith, Accelerating machine learning methods for chemistry

13:00-14:00 Lunch break offered

Session 2

14:00-14:25 Rafael Gomez-Bombarelli, Active learning of ML potentials with uncertainty differentiation and attribution

14:25-14:50 Luis Itza Vazquez-Salazar, More data or better data? How the training data influences machine learned predictions in Chemistry

14:50-15.15 Jose Jimenez, Δ-quantum ML potentials in realistic drug-like space

15:15-15:45 Coffee break and discussions

15:45-16:10 Elizabeth Decolvenaere, X(FF) Marks the Spot: Forces from Learned Multipoles for an Accurate Map of Condensed Phase Properties

16:10-16:35 Philip Loche, Investigating Electrostatic Interactions with Data-Driven Models

16:35-17.00 Michael Gastegger, Machine Learning for Molecular Spectra and Solvent Effects

17:00-20:00 Posters (light dinner and drinks offered)

Day 2

Friday, July 15

Session 3

09:00-9:25 Tess Smidt, Higher order Statistical Outputs from Euclidean neural networks

09:25-9:50 Robin Winter, Unsupervised Learning of Group Invariant and Equivariant Representations and its Application to Molecular Conformations

09:50-10.15 Gabor Csanyi, Many-body message passing networks

10:15-10:45 Coffee break and discussions

10:45-11:10 Paolo Carloni, Enhanced-sampling simulations for the estimation of drug binding kinetics

11:10-12:35 Alex Wade, Addressing the Challenge of Drug Discovery with Machine Learning and Exascale Computing

12:35-13.00 Christophe Chipot, Recent advances in enhanced-sampling simulations

13:00-14:00 Lunch break offered

Session 4

14:00-14:25 John Chodera, Teaching free energy calculations to learn

14:25-14:50 Julien Michel, Hybrid Alchemical Free Energy/Machine-Learning methodologies for drug discovery

14:50-15.15 Daniel Cole, Bespoke Interaction Potentials for Computer-Aided Drug Design

15:15-15:45 Coffee break and discussions

15:45-16:10 Cecilia Clementi, Machine learning of coarse-grained protein force-fields

16:10-16:35 Gianni De Fabritiis, Coarse-grained potentials for protein thermodynamics

16:35-17.00 Tristan Bereau, Rational discovery of cardiolipin binders by multiscale modeling and machine learning

20:30 Dinner for invited speakers (Sponsored by Acellera)

Day 3

Saturday, July 16

Session 5

09:00-9:25 Rianne van den Berg, Molecular simulation at Microsoft Research

09:25-9:50 Frank Noe, Deep Learning for Molecular Simulation

09:50-10.15 Ryota Tomioka, Timewarp: Transferable Enhanced Sampling of Molecular Dynamics

10:15-10:45 Coffee break and discussions

10:45-11:10 Olga Kononova, Building a Continuous Representation of Atomic Environment for Efficient Estimation of Force Field Parameters

11:10-12:35 Hanwen Zhang, Exploring Chemical Reactions with Machine Learning Potentials

12:35-13.00 Peter Eastman, The SPICE Dataset for Training Machine Learning Potentials

13.00-13.05 Final remarks

13.05 Lunch (on your own)

Free afternoon and future plans discussions