Work

Badapple 2.0: An Empirical Predictor of Compound Promiscuity, Updated, Modernized, and Enhanced for Explainability

Year: 2025

Type: article

Abstract: Modern drug discovery and chemical biology research relies heavily on analyzing bioassay data. One of the many challenges in bioassay data analysis is identifying false trails, i.e., chemical compounds which initially appear to have desirable activity but are found to be problematic upon further investigation. Badapple (BioAssay-Data Associative Promiscuity Pattern Learning Engine) was initially released in 2012, to help researchers identify promiscuous compounds and thus avoid a common source of these false trails, and since then has been well regarded and used by the global scientific community. Through an effort involving software engineering, cheminformatics, and biomedical data science we have developed Badapple 2.0, a major update with a complete code-rewrite, updated and expanded assay data sets, enhanced functionality, scalability, and metadata, supporting improved explainability and richer bioactivity analyses. Badapple 2.0 was motivated and funded by an ongoing AI/ML-empowered antialphaviral discovery program, but has broad applicability for improving the efficiency of many other early stage drug discovery campaigns.

Source: Journal of Chemical Information and Modeling

DOI: 10.1021/acs.jcim.5c02297

Authors: John A. Ringer, Christophe G. Lambert, Steven B. Bradfute, Cristian G. Bologa, Jeremy J. Yang

Institutions: University of New Mexico, University of New Mexico Health Sciences Center, Center for Global Health

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Defense Threat Reduction Agency

Awards: G7263391928, G980028877