Research and development firm SyntheticGestalt has partnered with Enamine, an integrated drug discovery services provider, to create an artificial intelligence (AI)-based model for drug discovery.
The partnership is intended to develop a suite of AI models to generate synthetically accessible biologically active compounds with optimised physicochemical and ADME/ Tox properties.
According to SyntheticGestalt, these models will be applicable to its compound discovery initiatives along with its service for both academic users and pharmaceutical companies.
Enamine business development director Iaroslava Kos said: “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 collaboration with SyntheticGestalt bringing to the table the talent and expertise of our scientists to realise mutual goals.”
Under the partnership, Enamine will provide access to its enumerated database of make-on-demand compounds, the Enamine REAL database, which comprises 38 billion molecules in its current edition.
The REAL database, which forecasts a compound’s physicochemical and ADME/Tox properties, will be added by SyntheticGestalt to its Drug Discovery Service.
The service instantly suggests better substitute chemicals for compounds that have problems.
To expedite and shorten the discovery cycle, Enamine will synthesis the chosen compounds in only three to four weeks and deliver pharmacological in vitro profiling data through internal testing.
Additionally, SyntheticGestalt will use Enamine’s data to improve its pre-trained AI model.
The model is anticipated to grow into the largest pre-trained model globally based on the 3D structures of the substances. It will also enhance the predictive power of SyntheticGestalt’s machine learning models.
Enamine said that the resulting models will be made available to certain interested parties on a joint research basis.
SyntheticGestalt CEO Koki Shimada said: “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 (LLMs).”
