BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Memento EPFL// BEGIN:VEVENT SUMMARY:Mini-Symposium for Machine Learning in Chemistry DTSTART:20260512T151500 DTEND:20260512T170000 DTSTAMP:20260513T001316Z UID:138a2074e8b179d8e40191af8a441fd3b973d34bcddca13e78517bdd CATEGORIES:Conferences - Seminars DESCRIPTION:Lucia Morán\, Paula Torren Peraire\nThe ML Seminars Series is hosting a mini-symposium to celebrate the end of the semester! Join us fo r excellent talks on data-driven approaches in transition metal catalysis and drug discovery. \n\nLucia Moran\nData-Driven Approaches to Transition -Metal Catalysis\nThe application of machine learning to homogeneous catal ysis is transforming the field\, with computational methods addressing key challenges in catalyst design\, mechanistic understanding\, and reaction optimization. In this talk\, I will present recent work on how the combina tion of data-driven approaches and quantum chemistry can improve the model ling and discovery of transition-metal (TM) catalysts.\nI will first outli ne the current landscape of AI in homogeneous catalysis\, focusing on rece nt advances in chemical representations and computational workflows. I wil l then present our recent developments in TM descriptors\, highlighting th eir transferability across different chemical motifs. Finally\, I will sho wcase the application of these methods to the discovery of bifunctional ca talysts for CO₂ hydrogenation to methanol. By combining high-throughput virtual screening with machine learning surrogate models\, we explore larg e chemical spaces to identify and prioritize candidates for experimental v alidation.\n\nBiography\nLucía Morán is a computational chemist working at the interface of homogeneous catalysis and machine learning. She obtain ed her MSc and PhD at the Institute of Chemical Research of Catalonia unde r the supervision of Prof. Feliu Maseras\, where her research focused on o rganometallic reaction mechanisms and the development of data-driven chemi cal descriptors. During her doctoral studies\, she conducted a short stay at the University of Oslo (UiO) with Res. Prof. David Balcells. Following a postdoctoral period at UiO with Prof. Ainara Nova\, she was awarded a Ma rie Skłodowska-Curie Fellowship. Her current research focuses on the desi gn of bifunctional catalysts for CO₂ hydrogenation\, utilizing quantum m ethods and machine learning models.\n\nPaula Torren Peraire\nAligning Mach ine Learning Methods with Drug Discovery Objectives\nMachine learning is i ncreasingly shaping drug discovery\, with computational methods addressing challenges in molecular design\, synthesis planning\, and optimization. I n this talk\, I will present recent work on how computational choices infl uence discovery outcomes\, from retrosynthesis to generative chemistry. I will first examine how different combinations of single-step and multi-ste p retrosynthesis models guide exploration of retrosynthetic space and can enable convergent synthesis planning. I will then discuss de-novo molecula r design\, highlighting how multi objective optimization strategies shape molecular exploration in many objective design settings. This talk undersc ores the importance of aligning algorithmic decisions with practical disco very objectives and explores opportunities for integrating data driven met hods into medicinal chemistry workflows\n\nBiography\nPaula Torren Peraire is a Data Science Innovation Fellow at Novartis in Basel\, where she work s on machine learning driven methods for drug discovery\, with a focus on generative chemistry. She studied Pharmacy at the University of Barcelona\ , followed by a Master’s in Bioinformatics for Health Sciences at Univer sitat Pompeu Fabra. Paula received her PhD from the Technical University o f Munich with a joint project between Helmholtz Munich and Johnson & Johns on\, focusing on computer-aided synthesis planning. Overall\, her work aim s to develop robust computational frameworks that support molecular design and decision-making in drug discovery\, bridging methodological innovatio n with real-world pharmaceutical applications.\n\n\n\n  LOCATION:CH B3 30 https://plan.epfl.ch/?room==CH%20B3%2030 STATUS:CONFIRMED END:VEVENT END:VCALENDAR