Temporal Prediction of Genetic Associations in ALS Through NLP and Complex Network Analysis

• Grant number: 25/06512-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2025
• End date: June 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Ricardo Cerri
• Grantee: João Pedro Viguini Tolentino Taufner Correa
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Amyotrophic Lateral Sclerosis (ALS) is a progressive and fatal neurodegenerative disease that affects motor neurons responsible for controlling voluntary movements. Despite decades of intensive research and the identification of approximately 50 genes potentially associated with the disease, its etiology remains largely unknown and treatment options are limited for most patients. This proposal aims to uncover latent knowledge within scientific articles on ALS using advanced Natural Language Processing (NLP) techniques. The project will automatically extract mentions and contexts of genes related to ALS, transforming texts into vector representations that capture complex semantic relationships. By temporally comparing these embeddings, it seeks to predict associations between genes and the disease, enabling the identification of potential ALS¿related genes even before their first explicit mention in the literature.Additionally, a co¿occurrence network will be constructed to interconnect the extracted genes, facilitating the identification of emerging patterns and clusters that may suggest new targets for future investigation. This integrated approach not only aims to validate established associations but also to generate innovative hypotheses about the molecular mechanisms underlying ALS, thereby contributing to advances in early diagnosis and the development of more effective therapies. (AU)