Work

ALMERIA: Boosting Pairwise Molecular Contrasts with Scalable Methods

Year: 2024

Type: article

Abstract: This work introduces ALMERIA, a decision-support tool for drug discovery. It estimates compound similarities and predicts activity, considering conformation variability. The methodology spans from data preparation to model selection and optimization. Implemented using scalable software, it handles large data volumes swiftly. Experiments were conducted on a distributed computer cluster using the DUD-E database. Models were evaluated on different data partitions to assess generalization ability with new compounds. The tool demonstrates excellent performance in molecular activity prediction (ROC AUC: 0.99, 0.96, 0.87), indicating good generalization properties of the chosen data representation and modelling. Molecular conformation sensitivity is also evaluated.

Source: Informatica

DOI: 10.15388/24-infor558

Authors: Rafael Mena-Yedra, Juana López Redondo, Horacio Pérez-Sánchez, Pilar Martinez Ortigosa

Institutions: University of Almería, Universidad Católica de Murcia

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: European Regional Development Fund, Agencia Estatal de Investigación