Deep learning of chemical reactions

Descripción del proyecto

Avanzar en la modelización de reacciones químicas

La modelización precisa de las reacciones químicas sigue suponiendo un reto importante en el ámbito de la química, sobre todo en el caso de las reacciones estereoselectivas y regioselectivas. Las técnicas actuales de aprendizaje automático han destacado en la modelización molecular, pero han tenido dificultades para predecir vías de reacción complejas fundamentales para la síntesis sostenible, como la organocatálisis asimétrica y la biocatálisis. En este contexto, el proyecto DeepRxn, financiado por el Consejo Europeo de Investigación, pretende cubrir esta laguna mediante el desarrollo de marcos de aprendizaje profundo innovadores y basados en datos que mejoren la modelización de reacciones orgánicas y enzimáticas. Al centrarse en la quimioselectividad, la regioselectividad y la estereoselectividad, el equipo de DeepRxn empleará redes neuronales de evolución de grafos moleculares y representaciones tridimensionales ocultas, creando en última instancia un conjunto de herramientas de código abierto que predice con precisión las energías de activación e identifica nuevas transformaciones enantioselectivas para la síntesis sostenible.

Objetivo

The exploration of reactions is a central topic in chemistry. Compared to the success of machine learning for molecules, the modeling of reactions is lagging behind, especially for stereo- and regioselective reactions. Since current efforts toward sustainable synthesis such as asymmetric organocatalysis or biocatalysis rely on the accurate prediction of enantio- and regioselective reaction pathways, new modeling approaches are needed. The proposed project aims toward developing new, data-driven deep learning frameworks for modeling organic and enzymatic reactions, focusing on chemo-, regio-, and stereoselectivity arising through intermolecular interactions with the reagent, solvent, or catalyst. In detail, we target the rule-free, stereochemistry-aware modeling and subsequent experimental validation of asymmetric organocatalysis to identify new enantioselective transformations, the exploration of new biocatalytic synthesis pathways including enzymatic cascades, and the accurate prediction of activation energies via developing new deep learning approaches. We will expand molecular graph-convolutional neural networks and graph transformers to reactions in a rule-free manner, and introduce hidden three-dimensional representations to account for stereochemistry and intermolecular interactions, yielding a versatile, open-source toolbox for reaction deep learning. This approach largely surpasses current approaches, which rely on two-dimensional representations, reaction rules, or three-dimensional input data, in offering the opportunity to model three-dimensional aspects and atom-mapping on-the-fly, for the first time, representing a significant breakthrough in this field. Its experimental validation campaign further allows for a direct application to the identification of new asymmetric organocatalytic transformations, as well as enzymatic cascades including cofactor recycling and side-product reduction, addressing the current need for more sustainable synthesis.