Publications

You can also find my articles on my Google Scholar profile.

First Author

How to build machine learning models able to extrapolate from standard to modified peptides

Published in Journal of Cheminformatics, 2025

This paper explores different design choices including learning algorithm and representation technique for building machine learning models that are able to extrapolate from one data distribution (standard peptides) to another (modified peptides). This study opens the door for new drug discovery campaings by allowing scientist to leverage data that is cheaper to acquire to make predictions for more expensive compounds.

Download Paper

BioBrigit, a Hybrid Machine Learning and Knowledge-Based Approach to Model Metal Pathways in Proteins: Application to a Dicopper Tyrosinase

Published in ACS Omega, 2025

This paper presents a new prediction tool for identifying metal ion diffusion pathways within proteins, and demonstrates its capabilities by considering the use case of a dicopper tyrosinase.

Download Paper

A new framework for evaluating model out-of-distribution generalisation for the biochemical domain

Published in The Thirteenth International Conference on Learning Representations, 2025

This paper discusses a new framework for evaluating model performance in new data. It offers metrics for choosing the best similarity function for a given biochemical prediction task and for estimating model performance conditioned on a deployment distribution.

Download Paper

AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors

Published in Bioinformatics, 2024

This paper discusses the design of an AutoML tool for building peptide bioactivity predictors and how to ensure their robust evaluation through homology partitioning.

Download Paper

Raúl Fernández Díaz

Publications

First Author

How to build machine learning models able to extrapolate from standard to modified peptides

BioBrigit, a Hybrid Machine Learning and Knowledge-Based Approach to Model Metal Pathways in Proteins: Application to a Dicopper Tyrosinase

A new framework for evaluating model out-of-distribution generalisation for the biochemical domain

AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors

Co-Author

Molecular Modelling in Bioactive Peptide Discovery and Characterisation

Enhancing foundation models for scientific discovery via multimodal knowledge graph representations

Knowledge enhanced representation learning for drug discovery