ChemBERTa-3: an open source training framework for chemical foundation models

Digital Discovery 2026 Open access

Read full text
Authors: Riya Singh, Aryan Amit Barsainyan, Rida Irfan, Connor Joseph Amorin, Stewart He, Tony Davis, Arun Thiagarajan, Shiva Sankaran, Seyone Chithrananda, Walid Ahmad, Derek Jones, Kevin McLoughlin
+6 more Hyojin Kim, Anoushka Bhutani, Shreyas Vinaya Sathyanarayana, Venkat Viswanathan, Jonathan Allen, Bharath Ramsundar
DOI: 10.1039/d5dd00348b
Cited by: 14
References: 20

Abstract

An overview of ChemBERTa-3, an open-source training and benchmarking framework designed to train and fine-tune large-scale chemical foundation models.

Fields of Study & Subjects

Machine Learning in Materials Science Computational Drug Discovery Methods Advanced Physical and Chemical Molecular Interactions

Publication details

Journal / source
Digital Discovery
Publisher
Royal Society of Chemistry (RSC)
Volume
5
Issue
2
Pages
662–685
Publication date
1 January 2026
Language
EN