BioPrediction: democratizing machine learning in the study of molecular interactions

• Grant number: 24/00830-8
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Start date: September 01, 2024
• End date: February 28, 2029
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: André Carlos Ponce de Leon Ferreira de Carvalho
• Grantee: Bruno Rafael Florentino
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated scholarship(s): 25/01309-2 - Automated Machine Learning to Predict Interaction Between Human-Pathogen Proteins: Exploring Topological Information, BE.EP.DD

Abstract

With the advancement of modern techniques, such as next-generation sequencing, the increasing amount of available biological data has posed challenges in extracting relevant knowledge at the molecular level. One of the most significant challenges is predicting interactions between biological sequences, such as DNA, RNA, and proteins, which play a crucial role in complex processes like gene regulation and immune response, accelerating the study of diseases and therapies. The use of Machine Learning (ML) algorithms in these problems has shown promising prospects; however, it still faces the challenge of finding the appropriate data representation and selecting the best algorithms and parameters. Additionally, the categorical and unstructured nature complicates this process, requiring specialized knowledge.Therefore, the present project proposes an end-to-end framework based on automated ML, called BioPrediction, capable of identifying implicit interactions between sequences without the need for end-to-end ML expertise. The goal is to develop an accessible classification model for researchers in the field of biological sciences, facilitating the application of ML in molecular biology problems. Furthermore, the project aims for result interpretability, allowing researchers to understand the algorithm's decision-making in studies of metabolic network mapping, protein-protein interactions, and non-coding RNA analysis. In summary, BioPrediction aims to boost research in molecular biology, contributing to the development of therapies, such as drug discovery and early cancer detection, becoming a valuable tool for researchers and enabling significant advances in their scientific investigations. (AU)