You can apply to participate and find all the relevant information (speakers, abstracts, program,...) on the event website: https://www.cecam.org/workshop-details/from-data-to-dynamics-machine-learning-in-statistical-mechanics-and-molecular-simulations-1487.
\r\n
\r\nRegistration is required to attend the full event, take part in the social activities and present a poster at the poster session (if any). However, the EPFL community is welcome to attend specific lectures without registration if the topic is of interest to their research. Do not hesitate to contact the CECAM Event Manager if you have any question.
\r\n
\r\nDescription
\r\nSince its introduction in the 1970s, molecular dynamics (MD) has become an indispensable computational microscope for studying complex biological systems at atomic resolution. It has enabled detailed investigations into protein folding, conformational dynamics, and ligand binding and unbinding. Over the past decade, increasing computational power has made microsecond-scale simulations routine, producing massive datasets that demand sophisticated analysis strategies [1]. Despite these advances, conventional MD simulations still face a fundamental limitation: many biologically relevant events occur over milliseconds to seconds—timescales largely inaccessible to standard MD.
\r\nTo bridge this gap, researchers increasingly turn to enhanced sampling techniques—such as metadynamics and umbrella sampling [2,3]—and coarse-grained (CG) modeling approaches [4]. These methods enable more comprehensive exploration of the system’s free energy landscape, yet their success critically depends on the selection of appropriate reaction coordinates or collective variables (CVs). CVs must capture the slowest, most functionally relevant motions to accurately reflect thermodynamic and kinetic behavior. However, identifying suitable CVs remains one of the field’s most challenging tasks, typically requiring domain expertise and iterative refinement [5, 6].
\r\nThis complexity has fueled growing interest in machine learning (ML) techniques, which are now transforming how MD simulations are analyzed, interpreted, and even conducted. ML methods have been applied to automate CV discovery, perform dimensionality reduction, build thermodynamic and kinetic models, and enhance sampling efficiency [7]. These models often employ artificial neural networks or graph neural networks to map high-dimensional molecular configurations—such as Cartesian coordinates or molecular descriptors—into low-dimensional representations suitable for analysis [8].
\r\nDepending on the structure and type of data, ML algorithms can be broadly categorized into supervised, unsupervised, and reinforcement learning paradigms [9]. Supervised learning uses labeled input-output pairs to predict properties such as molecular energies or binding affinities [10], while unsupervised learning enables the identification of latent features, such as CVs, directly from data [11].
\r\nA cornerstone of modern ML-driven simulation is the development of symmetry-aware molecular representations. The predictive power of ML models hinges on encoding physical symmetries—like rotation and translation—directly into the model. E(3)-equivariant neural networks have emerged as powerful tools for this purpose, significantly improving data efficiency and generalization in learning potential energy surfaces [12]. Ongoing research continues to explore the optimal balance between enforcing strict symmetry and retaining model flexibility.
\r\nMeanwhile, breakthroughs in structural prediction—most notably the advent of AlphaFold 3—have revolutionized how researchers obtain initial molecular configurations. AlphaFold now provides remarkably accurate models of not only proteins but also their complexes with nucleic acids, ions, and small-molecule ligands [13]. However, these are static snapshots. They cannot capture dynamic behaviors, allosteric transitions, or binding kinetics—areas where physics-based simulations remain indispensable. Initial benchmarks suggest that even state-of-the-art predictors still fall short in modeling protein dynamics and ranking ligand binding affinities, further emphasizing the role of MD [14].
\r\nTo address the dimensionality and sampling bottlenecks, unsupervised ML approaches such as time-lagged autoencoders have reframed CV identification as a data-driven task. More recently, generative models—including diffusion models and variational autoencoders—have emerged as a new frontier. These models can learn the full conformational landscape of biomolecules and enable enhanced sampling, in some cases eliminating the need for predefined CVs altogether [15].
\r\nOnce accurate structural models and CVs are established, ML can significantly improve the estimation of thermodynamic and kinetic properties. In drug discovery, for instance, predicting protein–ligand binding affinity remains a central challenge. ML potentials trained on quantum mechanical data can be combined with enhanced sampling to yield highly accurate free energy landscapes and binding kinetics—results previously unattainable due to computational limitations [16]. However, challenges in data quality, model interpretability, and transferability remain critical areas of ongoing investigation [17].
\r\nFinally, ML is driving a renaissance in CG modeling. Deep neural networks can now learn many-body CG potentials directly from all-atom simulations, capturing emergent properties and enhancing transferability [18]. These models open the door to longer, larger-scale simulations with greater physical accuracy.
\r\nIn this rapidly evolving context, it becomes imperative to critically assess both the promise and limitations of ML in biomolecular simulation. The excitement surrounding these developments must be tempered by careful validation and benchmarking. This workshop thus serves as a timely opportunity—especially for early-career researchers—to explore these cutting-edge methods, engage in constructive dialogue, and chart new directions in the application of machine learning to molecular dynamics and drug discovery.
\r\n
\r\nReferences
\r\n
\r\n[1] J. Behler, M. Parrinello, Phys. Rev. Lett., 98, 146401 (2007)
\r\n[2] P. Sahrmann, G. Voth, Current Opinion in Structural Biology, 90, 102972 (2025)
\r\n[3] K. Kříž, L. Schmidt, A. Andersson, M. Walz, D. van der Spoel, J. Chem. Inf. Model., 63, 412-431 (2023)
\r\n[4] K. Ahmad, A. Rizzi, R. Capelli, D. Mandelli, W. Lyu, P. Carloni, Front. Mol. Biosci., 9, (2022)
\r\n[5] S. Mehdi, Z. Smith, L. Herron, Z. Zou, P. Tiwary, Annual Review of Physical Chemistry, 75, 347-370 (2024)
\r\n[6] H. Zheng, H. Lin, A. Alade, J. Chen, E. Monroy, M. Zhang, J. Wang, AlphaFold3 in Drug Discovery: A Comprehensive Assessment of Capabilities, Limitations, and Applications, 2025
\r\n[7] J. Abramson, J. Adler, J. Dunger, R. Evans, T. Green, A. Pritzel, O. Ronneberger, L. Willmore, A. Ballard, J. Bambrick, S. Bodenstein, D. Evans, C. Hung, M. O’Neill, D. Reiman, K. Tunyasuvunakool, Z. Wu, A. Žemgulytė, E. Arvaniti, C. Beattie, O. Bertolli, A. Bridgland, A. Cherepanov, M. Congreve, A. Cowen-Rivers, A. Cowie, M. Figurnov, F. Fuchs, H. Gladman, R. Jain, Y. Khan, C. Low, K. Perlin, A. Potapenko, P. Savy, S. Singh, A. Stecula, A. Thillaisundaram, C. Tong, S. Yakneen, E. Zhong, M. Zielinski, A. Žídek, V. Bapst, P. Kohli, M. Jaderberg, D. Hassabis, J. Jumper, Nature, 630, 493-500 (2024)
\r\n[8] Fabian B. Fuchs, Daniel E. Worrall, Volker Fischer, Max Welling, NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems, Article No.: 166, Pages 1970 - 1981 (2020)
\r\n[9] H. Sidky, W. Chen, A. Ferguson, Molecular Physics, 118, (2020)
\r\n[10] Y. Wang, J. Lamim Ribeiro, P. Tiwary, Current Opinion in Structural Biology, 61, 139-145 (2020)
\r\n[11] K. Butler, D. Davies, H. Cartwright, O. Isayev, A. Walsh, Nature, 559, 547-555 (2018)
\r\n[12] F. Noé, A. Tkatchenko, K. Müller, C. Clementi, Annu. Rev. Phys. Chem., 71, 361-390 (2020)
\r\n[13] S. Kaptan, I. Vattulainen, Advances in Physics: X, 7, (2022)
\r\n[14] V. Limongelli, WIREs. Comput. Mol. Sci., 10, (2020)
\r\n[15] A. Glielmo, B. Husic, A. Rodriguez, C. Clementi, F. Noé, A. Laio, Chem. Rev., 121, 9722-9758 (2021)
\r\n[16] A. Pak, G. Voth, Current Opinion in Structural Biology, 52, 119-126 (2018)
\r\n[17] M. Lelimousin, V. Limongelli, M. Sansom, J. Am. Chem. Soc., 138, 10611-10622 (2016)
\r\n[18] C. Abrams, G. Bussi, Entropy, 16, 163-199 (2013)\r\n
The 2027 edition of the CROSS program calls upon researchers at EPFL and the University of Lausanne to submit proposals for joint projects that bring the natural sciences and engineering together with the social sciences and humanities.
\r\n
\r\nThrough this annual call for projects, CROSS provides competitive grants to support new seed research endeavors that have the potential to grow into full–scale interdisciplinary research projects.
\r\n
\r\nThe 2024 CROSS call is open to all topics.
\r\n
\r\n—————————————————————————————
\r\n
\r\nPROPOSALS:
\r\n
\r\nProposals must come from joint UNIL-EPFL teams, which bring together specialists in the human and social sciences on the one hand, with specialists from life sciences, natural sciences or engineering on the other. Up to six projects will be selected, with a maximum of CHF 60,000 awarded per project.\r\n
EPFL invites its staff and doctoral students to exhibit their artistic works (paintings, ceramics, framed works on paper, textile art, sculpture, mixed media; no photographs or videos) as part of the CREApoly exhibition. This exhibition offers a space for free, creative, and non-judgmental expression where you can share your artistic vision.
\r\n
\r\nA community-focused initiative organized as part of the 2026 Health days and Les Culturelles Festival.
\r\n
\r\nPractical Information:\r\n
You can apply to participate and find all the relevant information (speakers, abstracts, program,...) on the event website: https://www.cecam.org/workshop-details/complex-fluids-at-interfaces-structure-stability-and-molecular-effects-1492.
\r\n
\r\nRegistration is required to attend the full event, take part in the social activities and present a poster at the poster session (if any). However, the EPFL community is welcome to attend specific lectures without registration if the topic is of interest to their research. Do not hesitate to contact the CECAM Event Manager if you have any question.
\r\n
\r\nDescription
\r\n
\r\nComplex fluids are ubiquitous in biology, geophysics, and industry [1]. These materials are challenging to characterize and predict [1–4], particularly when they incorporate multiple interfaces, as in colloidal suspensions [4], foams [5–7], or nanoporous membranes [8–10]. Many of these interfaces are micro- or nano-scale and evolve over short times, which can obscure them to observation and pose challenges to experimentalists [2–5, 11, 12]. This opens exciting opportunities for a strong partnership between the development of novel theoretical, computational, and experimental techniques.
\r\nProbing interfaces presents unique challenges compared to probing complex fluids in the bulk. The interfacial structure and constitutive behavior then depend on the composition of two fluids as well as the interfacial configuration [13, 14]. Translating this increased complexity to a computational framework involves developing reliable models describing molecular interactions near fluid-fluid or fluid-solid interfaces [15–17], as well as models for continuum stresses [18]. Molecular modeling is necessary to reveal the physics of chemically-complex structures [17], but is computationally expensive, and it can be challenging to identify the relevant physics to include [19]. Yet the interface also provides unique opportunities for control: in liquid crystals, for example, interfacial stresses can be transmitted through the bulk, leading to novel pattern formation [20] and optical materials exploiting interfacial control [21]. Finally, interfaces are prone to instabilities, which can make flows unpredictable, but opens opportunities to exploit unstable growth for spontaneous patterning.
\r\nTo underscore the present challenges, even for a “simple” Newtonian fluid, the presence of an interface may hinder understanding of flow mechanics. For example, mechanisms for contact during drop impact are still debated [22]: molecular dynamics (MD) simulations can clarify which effects dominate among interfacial instabilities, electrostatic charge, gas-kinetic effects, and other driving forces [22–26], in addition to liquid/surface chemistry [27, 28]. Diffusive processes at interfaces [29] and nanoscale membrane flows, where osmotic and phoretic effects are significant [11, 30], also require further development in MD or coarse-grained models.
\r\n
\r\nThis workshop aims to foster exchanges around the following broad questions:\r\n
You can apply to participate and find all the relevant information (speakers, abstracts, program,...) on the event website: https://www.cecam.org/workshop-details/bridging-biomolecular-simulations-and-experiments-across-time-and-length-scales-from-single-molecules-to-entire-organelles-1493.
\r\n
\r\nRegistration is required to attend the full event, take part in the social activities and present a poster at the poster session (if any). However, the EPFL community is welcome to attend specific lectures without registration if the topic is of interest to their research. Do not hesitate to contact the CECAM Event Manager if you have any question.
\r\n
\r\nDescription
\r\n
\r\nMolecular simulations are firmly established as a central tool in the life sciences over the last few decades. This is evident from the now-standard use of molecular dynamics simulations by molecular biologists and biophysicists, and the remarkable success of AlphaFold, which has convinced even the most skeptical of the critical role of these methods in contemporary biological research.
\r\nHowever, new challenges are emerging. It is increasingly apparent that to understand biomolecular function, we must move beyond studying isolated molecules. The focus is now shifting towards examining large, dynamic complexes of biomolecules within their complex native environments, complete with post-translational modifications. Embracing this complexity is crucial for understanding how biological functions and cellular structures emerge and adapt.
\r\nThis workshop will address existing and emerging frontiers, discussing both current challenges and the future of molecular simulations needed to meet them. It will gather simulation experts that have been actively developing methods that can increase simulation accuracy and extend their applicability range across multiple scales, as well as experimentalists performing advanced studies that can address outstanding challenges occurring at computationally accessible time and length scales. A main aim will be to discuss how to improve the accuracy of simulations, integrate simulations and cutting-edge experiments, and how to best take advantage of innovative enhanced sampling and machine learning-based approaches.
\r\nThe workshop will seize the opportunity to celebrate the outstanding scientific achievements of Gerhard Hummer, a prominent leader in the field, on his sixty’s birthday. Many of the participants that have already expressed their intention to attend and support the workshop or past or current theoretical and experimental scientist that have been either collaborators and co-authors, mentored by, or inspired by Gerhard’s ideas and expertise.
Current research indicates that the role of generative AI in education is a double-edged sword: on one hand it can assist teachers for designing effective learning tasks and resources, on the other hand it can have negative effects on student learning and raises a range of ethical questions.
\r\nIn our new workshop series “Responsible AI skills for education” we will try to navigate these questions by focusing on specific teaching and learning activities and identifying practical skills you can develop for your everyday practice. Through a blend of concise theoretical input and hands-on activities, we will explore both the benefits and the risks of generative AI in education in short 1-hour sessions on campus. The first two workshops in the series focus on quiz design and critical analysis skills.
\r\n
\r\nEffective quiz design:
\r\nIn this 1-hour workshop, we will focus on the design of effective quiz questions for your class with the assistance of LLM tools. We will explore both the ethical and practical questions associated with LLM use for this task through theoretical inputs and hands-on activities.
Current research indicates that the role of generative AI in education is a double-edged sword: on one hand it can assist teachers for designing effective learning tasks and resources, on the other hand it can have negative effects on student learning and raises a range of ethical questions.
\r\nIn our new workshop series “Responsible AI skills for education” we will try to navigate these questions by focusing on specific teaching and learning activities and identifying practical skills you can develop for your everyday practice. Through a blend of concise theoretical input and hands-on activities, we will explore both the benefits and the risks of generative AI in education in short 1-hour sessions on campus. The first two workshops in the series focus on quiz design and critical analysis skills.
\r\n
\r\nTeaching critical analysis:
\r\nIn this 1-hour workshop, we will focus on how to help students develop critical analysis skills for reviewing LLM outputs in the context of learning tasks. The workshop will combine theoretical inputs and hands-on activities, drawing on your disciplinary expertise and fact-checking strategies.
\r\n