Cloud-Based Real-Time Molecular Screening Platform with MolFormer

2022/08/13 by Belgodere, Brian, Chenthamarakshan, Vijil, Das, Payel +9
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2208.06665

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 \urlwww.ibm.biz/molecular_demo.

Related

• MolMole: Molecule Mining from Scientific Literature
• MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
• Domain-Agnostic Molecular Generation with Chemical Feedback
• Large-Scale Chemical Language Representations Capture Molecular Structure and Properties
• The MolecularWeb Universe: Web-Based, Immersive, Multiuser Molecular Graphics And Modeling, for Education and Work in Chemistry, Structural Biology, and Materials Sciences