Deep learning of chemical reactions

This project aims to develop advanced deep learning frameworks for modeling organic and enzymatic reactions to enhance predictions of selectivity and enable sustainable synthesis.

Subsidie
€ 1.499.285
2024

Projectdetails

Introduction

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.

Need for New Approaches

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.

Project Aim

The proposed project aims to develop new, data-driven deep learning frameworks for modeling organic and enzymatic reactions, focusing on:

  1. Chemo-selectivity
  2. Regio-selectivity
  3. Stereoselectivity arising through intermolecular interactions with the reagent, solvent, or catalyst.

Detailed Objectives

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.
  • The accurate prediction of activation energies via developing new deep learning approaches.

Methodology

We will expand molecular graph-convolutional neural networks and graph transformers to reactions in a rule-free manner. Additionally, we will introduce hidden three-dimensional representations to account for stereochemistry and intermolecular interactions. This will yield a versatile, open-source toolbox for reaction deep learning.

Significance of the Approach

This approach largely surpasses current methods, which rely on:

  • Two-dimensional representations
  • Reaction rules
  • Three-dimensional input data

It offers the opportunity to model three-dimensional aspects and atom-mapping on-the-fly, for the first time, representing a significant breakthrough in this field.

Experimental Validation

The 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.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 1.499.285
Totale projectbegroting€ 1.499.285

Tijdlijn

Startdatum1-10-2024
Einddatum30-9-2029
Subsidiejaar2024

Partners & Locaties

Projectpartners

  • TECHNISCHE UNIVERSITAET WIENpenvoerder

Land(en)

Austria

Vergelijkbare projecten binnen European Research Council

ERC Consolid...

Decoding the Biochemistry of Terpene Synthases

The TerpenCode project aims to utilize deep learning models to predict and engineer terpene synthases, enhancing enzyme design for sustainable biotechnological production of novel chemicals.

€ 2.158.732
ERC Consolid...

Machine Learning and Mass Spectrometry for Structural Elucidation of Novel Toxic Chemicals

LearningStructurE aims to enhance the discovery of novel toxic chemical structures by integrating chromatography, mass spectrometry, and machine learning to explore unknown chemical spaces in environmental samples.

€ 1.867.187
ERC Advanced...

Energy Transfer Catalysis: A Highway to Molecular Complexity

HighEnT aims to innovate synthetic methodologies using visible light-mediated EnT catalysis to create complex organic molecules for pharmacological applications, enhancing chemical space and reaction design.

€ 2.499.250
ERC Proof of...

A multiscale Machine Learning based Software for the Simulation of Catalytic Processes

MultiCAT is a machine learning-based framework that enhances catalytic process modeling by reducing computational costs while improving prediction reliability for sustainable chemical manufacturing.

€ 150.000
ERC Starting...

Revolutionizing AI in drug discovery via innovative molecular representation paradigms

ReMINDER aims to revolutionize drug discovery by developing novel molecular representations for AI, enhancing model capabilities and solving complex chemical challenges.

€ 1.494.006

Vergelijkbare projecten uit andere regelingen

EIC Pathfinder

Reaction robot with intimate photocatalytic and separation functions in a 3-D network driven by artificial intelligence

CATART aims to develop autonomous reaction robots using AI and 3-D quantum dot networks to efficiently mimic natural chemical production, enhancing productivity and sustainability in the chemical industry.

€ 2.871.775
EIC Pathfinder

PROCESSING COMPLEX MATRICES: DESCRIPTION, REACTION-SEPARATION, MODELLING

The DREAM project aims to revolutionize chemical processes by developing intensified methods for extracting and valorizing lignin from Kraft black liquor through interdisciplinary approaches and innovative modeling.

€ 3.421.471