SyntheticGestalt and Enamine have announced a collaboration to develop a suite of AI models to aid in drug discovery.

The models generate synthetically accessible compounds with enhanced physicochemical and absorption, distribution, metabolism and excretion (ADME/Tox) properties.

The partnership will leverage Enamine's extensive REAL database, which comprises 38 billion molecules for developing make-on-demand compounds.

REAL will be added to SyntheticGestalt's drug discovery service.

Utilising proprietary AI models, the service will predict the physicochemical and ADME/Tox properties of compounds and suggest improved alternatives for problematic ones.

Enamine will expedite the discovery process by synthesising selected compounds in three to four weeks, and offer in vitro pharmacological profiling data.

SyntheticGestalt will boost its pre-trained AI model with data from Enamine, potentially creating the world's largest model based on 3D compound structures.

This enhancement will significantly increase the predictive precision of SyntheticGestalt's machine learning (ML) models.

The models will be available for collaborative research with select parties interested in advancing compound discovery initiatives.

Enamine business development director Iaroslava Kos stated: “The promise provided by AI/ML powered computational designs in the discovery of new drugs cannot be underestimated.

“Finding new active compounds by synthesis of just a handful of novel compounds looks fantastic.

“We are pleased to enter a collaboration with SyntheticGestalt, bringing to the table the talent and expertise of our scientists to realise mutual goals.”

The AI platform employed by SyntheticGestalt is cloud-based and scalable, capable of predicting on large libraries.

It is designed to forecast early toxicity, enzyme functions and compound properties – crucial in the early stages of drug development.

SyntheticGestalt CEO Koki Shimada stated: “The Enamine REAL database is the perfect match for our initiative as the most trusted and the largest make-on-demand set on the market.

“We believe that the ultra-large pre-trained model we are developing will enable a cosmic leap in AI drug discovery, just as the large-scale pre-training made a revolution in large language models.”