Bambu and its applications in the discovery of active molecules against melanoma

Isadora Leitzke Guidotti; Alessandra Neis; Daniela Peres Martinez; Fabiana Kömmling Seixas; Karina Machado; Frederico Schmitt Kremer

doi:10.1016/j.jmgm.2023.108564

Bambu and its applications in the discovery of active molecules against melanoma

J Mol Graph Model. 2023 Nov:124:108564. doi: 10.1016/j.jmgm.2023.108564. Epub 2023 Jul 11.

Authors

Isadora Leitzke Guidotti¹, Alessandra Neis¹, Daniela Peres Martinez¹, Fabiana Kömmling Seixas¹, Karina Machado², Frederico Schmitt Kremer³

Affiliations

¹ Centro de Desenvolvimento Tecnológico, Universidade Federal de Pelotas, Pelotas, Rio Grande do Sul, Brazil.
² Centro de Ciências Computacionais, Universidade Federal do Rio Grande, Rio Grande, Rio Grande do Sul, Brazil.
³ Centro de Desenvolvimento Tecnológico, Universidade Federal de Pelotas, Pelotas, Rio Grande do Sul, Brazil. Electronic address: fred.s.kremer@gmail.com.

PMID: 37453311
DOI: 10.1016/j.jmgm.2023.108564

Abstract

Purpose or objective: Melanoma is one of the most dangerous forms of skin cancer and the discovery of novel drugs is an ongoing effort. Quantitative Structure Activity Relationship (QSAR) is a computational method that allows the estimation of the properties of a molecule, including its biological activity. QSAR models have been widely employed in the search for potential drug candidates, but also for agrochemicals and other molecules with applications in different branches of the industry. Here we present Bambu, a simple command line tool to generate QSAR models from high-throughput screening bioassays datasets.

Methods: The tool was developed using the Python programming language and relies mainly on RDKit for molecule data manipulation, FLAML for automated machine learning and the PubChem REST API for data retrieval. As a proof-of-concept we have employed the tool to generate QSAR models for melanoma cell growth inhibition based on HTS data and used them to screen libraries of FDA-approved drugs and natural compounds. Additionally, Bambu was compared to QSAR-Co, another automated tool for QSAR model generation.

Results: based on the developed tool we were able to produce QSAR models and identify a wide variety of molecules with potential melanoma cell growth inhibitors, many of which with anti-tumoral activity already described. The QSAR models are available through the URL http://caramel.ufpel.edu.br, and all data and code used to generate its models are available at Zenodo (https://doi.org/10.5281/zenodo.7495214). Bambu source code is available at GitHub (https://github.com/omixlab/bambu-v2). In the benchmark, Bambu was able to produce models with higher accuracy, recall, F1 and ROC AUC when compared to QSAR-Co for the selected datasets.

Conclusions: Bambu is an free and open source tool which facilitates the creation of QSAR models and can be futurely applied in a wide variety of drug discovery projects.

Keywords: Chemoinformatics; Drug discovery; Structural bioinformatics.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Drug Discovery* / methods
High-Throughput Screening Assays
Humans
Machine Learning
Melanoma* / drug therapy
Quantitative Structure-Activity Relationship
Software