Cloud-Based Real-Time Molecular Screening Platform with MolFormer

TL;DR

This paper introduces a cloud-based platform utilizing MolFormer for real-time molecular screening, enabling tasks like molecule retrieval, visualization, and property prediction to accelerate chemical research and drug discovery.

Contribution

The paper presents a novel cloud platform integrating MolFormer for real-time molecular screening, supporting multiple chemical analysis tasks in a user-friendly environment.

Findings

Effective molecular retrieval and visualization demonstrated

Platform supports accurate property prediction

Facilitates automation in chemical research and drug discovery

Abstract

With the prospect of automating a number of chemical tasks with high fidelity, chemical language processing models are emerging at a rapid speed. Here, we present a cloud-based real-time platform that allows users to virtually screen molecules of interest. For this purpose, molecular embeddings inferred from a recently proposed large chemical language model, named MolFormer, are leveraged. The platform currently supports three tasks: nearest neighbor retrieval, chemical space visualization, and property prediction. Based on the functionalities of this platform and results obtained, we believe that such a platform can play a pivotal role in automating chemistry and chemical engineering research, as well as assist in drug discovery and material design tasks. A demo of our platform is provided at \url{www.ibm.biz/molecular_demo}.