AutoPeptideML
Computational tool for building ML models for predicting peptide bioactivity automatically (https://github.com/IBM/AutoPeptideML).
Posts by Collection
portfolio
BioBrigit
Hybrid machine learning and knowledge-based approach for the prediction of metal diffusion pathways through proteins (https://github.com/insilichem/BioBrigit).
Hestia-GOOD
Open source library for evaluating machine learning models in out-of-distribution generalization (https://github.com/IBM/Hestia-GOOD).
publications
Knowledge enhanced representation learning for drug discovery
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2024
AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors
Published in Bioinformatics, 2024
Enhancing foundation models for scientific discovery via multimodal knowledge graph representations
Published in Journal of Web Semantics, 2025
Molecular Modelling in Bioactive Peptide Discovery and Characterisation
Published in Biomolecules, 2025
A new framework for evaluating model out-of-distribution generalisation for the biochemical domain
Published in The Thirteenth International Conference on Learning Representations, 2025
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
How to build machine learning models able to extrapolate from standard to modified peptides
Published in Journal of Cheminformatics, 2025
talks
AutoPeptideML: automated machine learning for building peptide bioactivity predictors leveraging protein language models
Presented at Irish Computational Biology and Genomics Symposium [Talk] 2023, Galway, Ireland,
Modelos que aprenden el lenguaje de las moléculas y cómo utilizarlos para predecir sus propiedades
Presented at Conferencia en Señalización Celullar en Alcalá de Henares (SECUAH) [Keynote], Alcala de Henares, Spain,
Effect of dataset partitioning strategies for evaluating out-of-distribution generalisation for predictive models in biochemistry
Presented at American Chemical Society (ACS) Fall Meeting [Poster] 2024, Denver, Colorado, United States,
A new framework for evaluating machine learning in biochemistry and its application for peptides and small molecules
Presented at IRB AI for Drug Discovery 2025 [Poster], Barcelona, Spain,
A new framework for evaluating model out-of-distribution generalization for the biochemical domain
Presented at International Conference for Learning Representations (ICLR) 2025 [Poster], Singapore,
AutoPeptideML2: An open-source library for democratising machine learning for peptide bioactivity prediction.
Presented at Intelligent Systems for Molecular Biology (ISMB) 2025 [Poster], Liverpool, UK,
AutoPeptideML2: An open-source library for democratising machine learning for peptide bioactivity prediction.
Presented at Intelligent Systems for Molecular Biology (ISMB) 2025 [Talk], Liverpool, UK,
How to generalize machine learning models to both canonical and non-canonical peptides
Presented at American Chemical Society (ACS) Fall Meeting 2025 [Talk], Washington DC, US,
Partitioning, representation, and automation in canonical and non-canonical peptide modelling
Presented at Peptide Computational Methods And Applications Workshop [Talk], Dublin, Ireland,
Evaluation of partitioning algorithms for trustworthy out-of-distribution evaluation of machine learning models in biochemistry.
Presented at Virtual Institute for Bioinformatics and Evolution [Short Talk], Dublin, Ireland,
teaching
Deep learning in biomedicine - SECUAH VII
Workshop, University of Alcala de Henares, Alcala de Henares, Spain,
Demonstrator Bioinformatics UCD (MEIN30240)
Undergraduate teaching, University College Dublin, School of Medicine, Dublin, Ireland,
Deep learning in biomedicine - SECUAH IX
Workshop, University of Alcala de Henares, Alcala de Henares, Spain,
Models that learn biochemistry
Workshop, University of Oviedo, Oviedo, Spain,