Our group is interested in the development of new machine learning approaches for Computational chemistry. We focus on :

  • algorithmic developments, ranging from machine-learning assisted parametrization of force fields and density functional theory,  to the design of neural network potentials and foundation models.
  • real-life high-performance implementations on GPU-accelerated computing systems,

Selected publications in Machine Learning for Computational Chemistry

      1. A Supervised Fitting Approach to Force Field Parametrization with Application to the SIBFA Polarizable Force Field.
        M. Devereux, N. Gresh, J.-P. Piquemal, M. Meuwly, J. Comput. Chem., 2014, 35, 1577-1591 (COVER) [PDF][HAL]
        DOI: 10.1002/jcc.23661
      2. High-Resolution Mining of SARS-CoV-2 Main Protease Conformational Space: Supercomputer-Driven Unsupervised Adaptive Sampling.
        T. Jaffrelot Inizan, F. Célerse, O. Adjoua, D. El Ahdab, L.-H. Jolly, C. Liu, P. Ren, M. Montes, N. Lagarde, L. Lagardère, P. Monmarché, J.-P.Piquemal, Chem. Sci., 2021, 12, 4889 – 4907 (Open Access) [ChemRxiv][HAL]
        Simulation data can be found on the MolSSi/Bioexcel website : [Link]
        DOI: 10.1039/D1SC00145K
      3. Accurate Deep Learning-aided Density-free Strategy for Many-Body Dispersion-corrected Density Functional Theory.
        P. P. Poier, T. Jaffrelot Inizan, O. Adjoua, L. Lagardère, J.-P. Piquemal, J. Phys. Chem. Lett.,  2022, 13, 19, 4381–4388 [HAL] [ArXiv]
        DOI: 10.1021/acs.jpclett.2c00936
      4. Generalized Many-Body Dispersion Correction through Random-phase Approximation for Chemically Accurate Density Functional Theory.
        P. P. Poier, L. Lagardère, J.-P. Piquemal, J. Phys. Chem. Lett., 2023, 14, 6, 1609–1617 (Open Access) [HAL][ArXiv]
        DOI: 10.1021/acs.jpclett.2c03722
      5. Routine Molecular Dynamics Simulations Including Nuclear Quantum Effects: from Force Fields to Machine Learning Potentials.
        T. Plé, N. Mauger, O. Adjoua,T. Jaffrelot-Inizan, L. Lagardère, S. Huppert, J.-P. Piquemal, J. Chem. Theory. Comput., 2023, 19, 5, 1432–1445 (COVER) [HAL][ArXiv]
        DOI: 10.1021/acs.jctc.2c01233
      6. Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects.
        T. Jaffrelot Inizan, T. Plé, O. Adjoua, P. Ren, H. Gökcan, O. Isayev, L. Lagardère, J.-P. Piquemal, Chem. Sci., 2023, 14, 5438-5452 (Open Access) [HAL][ArXiv]
        DOI: 10.1039/D2SC04815A
      7. Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects.
        T. Plé, L. Lagardère, J.-P. Piquemal, Chem. Sci., 2023, 14, 12554-12569 (Open Access) [HAL][ArXiv]
        DOI: 10.1039/D3SC02581K
      8. Incorporating Neural Networks into the AMOEBA Polarizable Force Field.
        X. Wang, T. Jaffrelot Inizan, C. Liu, J.-P. Piquemal, P. Ren, J. Phys. Chem. B, 2024, 128 (10), 2381–2388 [HAL][ChemRxiv]
        DOI: 10.1021/acs.jpcb.3c08166
      9. Advancing Force Fields Parameterization: A Directed Graph Attention Networks Approach
        G. Chen,         T. Jaffrelot Inizan, T. Plé, L. Lagardère, J.-P. Piquemal, Y. Maday, J. Chem. Theory. Comput., 2024, 20 (13), 5558-5569 [HAL][ChemRxiv]
        DOI: 10.1021/acs.jctc.3c01421
      10. FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials.
        T. Plé, O. Adjoua, L. Lagardère, J.-P. Piquemal, J. Chem. Phys., 2024, 161, 4,  042502 [HAL][ArXiv]
        DOI: 10.1063/5.0217688
      11. Targeting RNA with Small Molecules using State-of-the-Art Methods Provides Highly Predictive Affinities of Riboswitch Inhibitors.
        N. Ansari, C. Liu, F. Hédin, J. Hénin, J. W. Ponder, P. Ren, J.-P. Piquemal, L. Lagardère, K. El Hage, Communications Biology, 2025, 8, 1405 (Open Access) [HAL][ChemRxiv]
        DOI: 10.1038/s42003-025-08809-y
      12. A Foundation Model for Accurate Atomistic Simulations in Drug Design.
        T. Plé, O. Adjoua, A. Benali, E. Posenitskiy, C. Villot, L. Lagardère, J.-P.Piquemal, 2025, submitted [HAL][ChemRxiv]
        DOI:10.26434/chemrxiv-2025-f1hgn
      13. Pushing the Accuracy Limit of Foundation Neural Network Models with Quantum Monte Carlo Forces and Path Integrals .
        A. Benali, T. Plé, O. Adjoua,  V. Agarawal, T. Applencourt, M. Blazhynska, R. Clay III, K. Gasperich, K. Hossain, J. Kim, C. Knight, J. T. Krogel, Y. Maday, M. Maria, M. Montes, Y. Luo, E. Posenitskiy, C. Villot, V. Vishwanath, L. Lagardère,  J.-P. Piquemal, 2025, submitted [HAL][ArXiv]
        DOI: 10.48550/arXiv.2504.07948
      14. Accelerating Molecular Dynamics Simulations with Foundation Neural Network Models using Multiple Time-Step and Distillation
        C. Cattin, T. Plé, O. Adjoua, N. Gouraud, L. Lagardère, J.-P. Piquemal, J. Phys. Chem. Lett., 2026, 17 (5), 1288-1295  (COVER) [HAL][ArXiv][PDF]
        DOI: 10.1021/acs.jpclett.5c03720
      15. Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces.
        N. Gouraud, C. Cattin, T. Plé, O. Adjoua, L. Lagardère, J.-P. Piquemal, 2026, submitted [HAL][ArXiv]
        DOI: 10.48550/arXiv.2602.14975
      16. The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing for Next-Generation Drug Discovery.
        N. Ansari, C. Feniou, N. Gouraud, D. Loco, S. Badreddine, B. Claudon, F. Aviat, M. Blazhynska, K. Gasperich, G. Michel, D. Traore, C. Villot, T. Plé, O. Adjoua, L. Lagardère, J.-P. Piquemal, 2026, [HAL][Arxiv]
        DOI: 10.48550/arXiv.2603.17790

 

0 241

Jean-Philip Piquemal