Mini-Symposium for Machine Learning in Chemistry
Event details
| Date | 12.05.2026 |
| Hour | 15:15 › 17:00 |
| Speaker | Lucia Morán, Paula Torren Peraire |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
The ML Seminars Series is hosting a mini-symposium to celebrate the end of the semester! Join us for excellent talks on data-driven approaches in transition metal catalysis and drug discovery.
Lucia Moran
Data-Driven Approaches to Transition-Metal Catalysis
The application of machine learning to homogeneous catalysis 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 combination of data-driven approaches and quantum chemistry can improve the modelling and discovery of transition-metal (TM) catalysts.
I will first outline the current landscape of AI in homogeneous catalysis, focusing on recent advances in chemical representations and computational workflows. I will then present our recent developments in TM descriptors, highlighting their transferability across different chemical motifs. Finally, I will showcase the application of these methods to the discovery of bifunctional catalysts for CO₂ hydrogenation to methanol. By combining high-throughput virtual screening with machine learning surrogate models, we explore large chemical spaces to identify and prioritize candidates for experimental validation.
Biography
Lucía Morán is a computational chemist working at the interface of homogeneous catalysis and machine learning. She obtained her MSc and PhD at the Institute of Chemical Research of Catalonia under the supervision of Prof. Feliu Maseras, where her research focused on organometallic reaction mechanisms and the development of data-driven chemical 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 Marie Skłodowska-Curie Fellowship. Her current research focuses on the design of bifunctional catalysts for CO₂ hydrogenation, utilizing quantum methods and machine learning models.
Paula Torren Peraire
Aligning Machine Learning Methods with Drug Discovery Objectives
Machine learning is increasingly shaping drug discovery, with computational methods addressing challenges in molecular design, synthesis planning, and optimization. In this talk, I will present recent work on how computational choices influence discovery outcomes, from retrosynthesis to generative chemistry. I will first examine how different combinations of single-step and multi-step retrosynthesis models guide exploration of retrosynthetic space and can enable convergent synthesis planning. I will then discuss de-novo molecular design, highlighting how multi objective optimization strategies shape molecular exploration in many objective design settings. This talk underscores the importance of aligning algorithmic decisions with practical discovery objectives and explores opportunities for integrating data driven methods into medicinal chemistry workflows
Biography
Paula Torren Peraire is a Data Science Innovation Fellow at Novartis in Basel, where she works 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 Universitat Pompeu Fabra. Paula received her PhD from the Technical University of Munich with a joint project between Helmholtz Munich and Johnson & Johnson, focusing on computer-aided synthesis planning. Overall, her work aims to develop robust computational frameworks that support molecular design and decision-making in drug discovery, bridging methodological innovation with real-world pharmaceutical applications.
Lucia Moran
Data-Driven Approaches to Transition-Metal Catalysis
The application of machine learning to homogeneous catalysis 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 combination of data-driven approaches and quantum chemistry can improve the modelling and discovery of transition-metal (TM) catalysts.
I will first outline the current landscape of AI in homogeneous catalysis, focusing on recent advances in chemical representations and computational workflows. I will then present our recent developments in TM descriptors, highlighting their transferability across different chemical motifs. Finally, I will showcase the application of these methods to the discovery of bifunctional catalysts for CO₂ hydrogenation to methanol. By combining high-throughput virtual screening with machine learning surrogate models, we explore large chemical spaces to identify and prioritize candidates for experimental validation.
Biography
Lucía Morán is a computational chemist working at the interface of homogeneous catalysis and machine learning. She obtained her MSc and PhD at the Institute of Chemical Research of Catalonia under the supervision of Prof. Feliu Maseras, where her research focused on organometallic reaction mechanisms and the development of data-driven chemical 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 Marie Skłodowska-Curie Fellowship. Her current research focuses on the design of bifunctional catalysts for CO₂ hydrogenation, utilizing quantum methods and machine learning models.
Paula Torren Peraire
Aligning Machine Learning Methods with Drug Discovery Objectives
Machine learning is increasingly shaping drug discovery, with computational methods addressing challenges in molecular design, synthesis planning, and optimization. In this talk, I will present recent work on how computational choices influence discovery outcomes, from retrosynthesis to generative chemistry. I will first examine how different combinations of single-step and multi-step retrosynthesis models guide exploration of retrosynthetic space and can enable convergent synthesis planning. I will then discuss de-novo molecular design, highlighting how multi objective optimization strategies shape molecular exploration in many objective design settings. This talk underscores the importance of aligning algorithmic decisions with practical discovery objectives and explores opportunities for integrating data driven methods into medicinal chemistry workflows
Biography
Paula Torren Peraire is a Data Science Innovation Fellow at Novartis in Basel, where she works 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 Universitat Pompeu Fabra. Paula received her PhD from the Technical University of Munich with a joint project between Helmholtz Munich and Johnson & Johnson, focusing on computer-aided synthesis planning. Overall, her work aims to develop robust computational frameworks that support molecular design and decision-making in drug discovery, bridging methodological innovation with real-world pharmaceutical applications.
Practical information
- General public
- Free
Organizer
- Sarina Kopf, Victor Sabanza-Gil, Philippe Schwaller