Francisco M. Couto

The paper develops a text mining pipeline to create a ncRNA-phenotype relational corpus and evaluates a large language model for relation extraction, achieving high accuracy.

DGH-GO is an application that uses Gene Ontology to cluster disease-causing genes and identify genetic heterogeneity in complex diseases like ASD and NDDs.

This paper develops a deep learning NERL system and a parallel oncology corpus for Portuguese and Spanish, addressing the lack of language support in biomedical text mining tools.

This paper develops a machine learning classifier to automate biomarker curation in the Exposome-Explorer database, reducing manual screening by 90% with 70.1% F2-score.

This study uses machine learning to identify biological mechanisms underlying ASD subgroups based on clinical and genetic data, finding distinct processes in mild and severe cases.

BO-LSTM uses biomedical ontologies with LSTM networks to improve drug-drug interaction classification in text, achieving better performance with limited annotations.

This study uses machine learning with gene functional similarities to identify novel ASD genes, achieving higher accuracy than existing methods.

The paper introduces a novel filtering method to identify privacy-sensitive nucleotides in genomic data, improving accuracy and reducing false positives compared to previous approaches.

This paper introduces a multi-level sensitivity classification for genomic variations to optimize privacy-preserving DNA alignment performance by adapting alignment algorithms to sensitivity levels.