Eduardo Aguilar-Bejarano

Data Scientist Engineer and Chemistry PhD Student at The University of Nottingham

Welcome to my personal website where I share my research, projects, and publications related to Graph Neural Networks (GNNs) and their applications.

Explore Research

Research Interests

My research revolves around Graph Neural Networks (GNNs) and their use for various cutting-edge applications in Chemical and Materials Sciences. I am driven by the challenge of representing molecules and materials accurately in computational systems. This interest sparked my curiosity in applying cheminformatics to study inorganic compounds, where traditional representations of molecules (e.g. SMILES) are not compatible. I aim to answer key research questions such as: How can we represent molecules and materials more accurately to enable machine learning models with higher predictive power and interpretability?

Research Topics

Driven Ligand Optimization

Cheminformatics

Python

Explainable Deep Learning Models for Interstitial-Alloy

Materials Science

Deep Learning

Ongoing Projects

GNNs-Driven Biopolymers Design

PyTorch

GNNs

Currently working with the EPSRC Large Grant, specializing in GNNs and explainability methods for novel materials discovery.

GNN-Guided Small Molecule Design

Generative AI

Chemistry

Exploring GNNs and XAI methods for generating novel small molecules with targeted properties.

ML Predictions Error Quantification

Uncertainty

Validation

Developing metrics to quantify prediction accuracy based on molecular structure relationships in training data.

Contact

If you'd like to collaborate or discuss my research:

eduardo.aguilar-bejarano@nottingham.ac.uk