QUANTUM-TOX - Revolutionizing Computational Toxicology with Electronic Structure Descriptors and Artificial Intelligence

Introduction

Toxicology is at a crossroads. With ever more drugs going to market and more chemicals having an environmental impact, the need for fast, cheap, and accurate technologies to assess toxic effects is pressing.

Computational Toxicology

Computational toxicology provides an array of tools and methods for toxicity prediction using only computer approaches. Conceptually, computational toxicology has significant advantages since testing is fast and cheaper than in vitro methods.

Current Limitations

However, currently, computational toxicology has severe limitations. Predictions typically use Quantitative Structure-Activity Relationship (QSAR) models that rely on large sets of molecular descriptors. This causes severe problems because:

1. The methodologies cannot assess chemicals different from the ones used to develop the QSAR models.
2. When it is possible to assess different chemicals, the very large number of descriptors limits understandability.

Therefore, new methodologies are needed to address these shortcomings.

Project Goals

This project will develop a new type of descriptor, totally based on quantum mechanics, that can cover the whole chemical space and relies on a small number of parameters that are easily interpretable.

Methodology

Starting with meaningful chemical perturbations that extract the behavior of the chemicals in assumed mechanisms of toxic action, the approach will develop specific Electronic SIGNatures (ESigns). ESigns are mathematical invariants that map the results of the quantum chemical calculations.

Integration with Artificial Intelligence

Using Artificial Intelligence, the ESigns will relate to toxicity. The new approach introduces a momentous change in computational toxicology.

Advantages of the New Approach

This new methodology can cover the whole chemical space because:

• It abandons predictions based on molecular structures.
• It uses fewer parameters.
• It can be related to the new trends in toxicology regarding the use of pathways information.

In fact, it is a powerful tool to allow accurate toxicology predictions solely on the basis of biochemical and chemical insight.