Curriculum Vitae

Computational Chemist & Research Software Engineer — Machine Learning & Representation Learning for Chemistry

Eduardo Alberto Aguilar-Bejarano

Nottingham, UK (visiting MIT, Cambridge, MA — from June 2026)  |  eduardo.aguilar-bejarano@nottingham.ac.uk

Download Full CV (PDF)

Profile

Chemistry-trained machine-learning researcher and research software engineer whose work centres on the chemical representation problem — how molecules, materials, and reactions should be encoded for learning, and when geometric deep learning (graph- and geometry-based representations) outperforms classical tabular descriptors. My PhD is a three-part study of this question across transition-metal complexes (asymmetric catalysis), transition-metal carbides (energetics), and polymers (biomaterials), pairing each system with interpretability methods that attribute predictions to chemically meaningful substructures. First author of five articles (Cell Press, RSC) and lead developer of several open-source scientific Python libraries, with full-cycle engineering experience — architecture, CI/CD, automated testing, deployment, documentation, and HPC — consistently in close collaboration with experimental and industrial partners.

Education

  • University of Nottingham, UK — PhD in Chemistry & Artificial Intelligence, AI Doctoral Training Centre (EPSRC, full 4-year scholarship)
    Oct 2022 – Sep 2026  ·  Thesis: Interpretable Graph Neural Networks for Structure–Activity Relationship Discovery  ·  Viva: September 2026
    Supervisors: Prof. Simon Woodward, Prof. Ender Özcan, Dr. Grazziela Figueredo
  • Universidad de Costa Rica — BSc Chemistry with Honors, GPA 9.23/10
    Mar 2018 – Jun 2022  ·  Graduated with Honors (academic excellence)
  • Colegio Científico Costarricense, San Pedro — Bachillerato (science-track secondary diploma)
    Dec 2015 – Nov 2017  ·  Costa Rica's selective science-focused secondary programme

Research & Professional Experience

  • Visiting Researcher — Anderson Lab, Massachusetts Institute of Technology (Jun 2026 – Present)
  • Based at the Koch Institute for Integrative Cancer Research (Cambridge, MA). Developing interpretable computational models for the design and prioritisation of lipid nanoparticles (LNPs) for more efficient drug delivery, extending prior LNP composition-analysis work toward model-guided exploration of lipid chemical space. Continuation of the Nottingham–MIT LNP collaboration with Prof. Daniel Anderson's lab.

  • Data Scientist & Postdoctoral Researcher — University of Nottingham, Digital Research Service (Nov 2024 – Present)
  • On the EPSRC Large Grant: Designing bio-instructive materials for translation-ready medical devices (Advisor: Dr. Grazziela Figueredo). First author and architect of Helix 1.0 (CI/CD-managed framework for reproducible, interpretable ML on tabular scientific data; applied to biomarker discovery of macrophage cell types from high-dimensional metabolomics data). Lead developer of PolyNet (end-to-end Python/Streamlit library for structure-based polymer property prediction) and of LCNet / LNPQuantification (the neural-network model behind the first quantitative Q-Cryo-OrbiSIMS method for LNP characterisation, with MIT's Anderson Lab — curated the 337-spot calibration dataset; predicts the four canonical LNP lipid components to ~14 mol% MAE). Lead modeller on an antibiofilm polymer-discovery programme (ensemble GNNs over ~500 polymer structures against high-throughput biofilm assays for P. aeruginosa, S. aureus, and uropathogenic E. coli). Also delivered in-house data-science and software training and promoted open-source, reproducible research across an interdisciplinary EPSRC team.

  • PhD Researcher — University of Nottingham, Woodward–Figueredo–Özcan Groups (Oct 2022 – Sep 2026)
  • Doctoral thesis studying chemical representation across three systems of increasing difficulty: (1) transition-metal complexes — interpretable GNN pipeline for enantioselective catalyst/ligand optimisation (→ HCat-GNet, iScience; AsymBench, J. Cheminform.; data curation, Molecules); (2) transition-metal carbides — new 3D-masking explainability for crystal-convolution GNNs and machine-learnt interatomic potentials, applied to molybdenum carbides (→ PCCP); (3) polymers — ensemble-GNN methodology for virtual screening and multi-property optimisation of polymer biomaterials (→ PolyNet).

  • Research Assistant — Universidad de Costa Rica, CBIO3 Group (Jan 2021 – Oct 2022)
  • Cheminformatic modelling for in-silico prediction of physicochemical profiles and rational design of bioactive compounds (Advisor: Prof. William Zamora-Ramírez). Built a novel lipophilicity descriptor from toluene/water partition-coefficient prediction (MLR, SVM, random forest, gradient boosting); developed the first multivariable model for tautomer equilibrium constants in water, extended toward organic solvents; and characterised antimicrobial-peptide structures using QM continuum-solvation calculations.

Publications

First author unless noted. Full list with graphical abstracts on the Publications page.

  • Aguilar-Bejarano, E., et al. (2026). Benchmarking Molecular Representations and Machine Learning Algorithms for Asymmetric Catalysis. J. Cheminform. (accepted). DOI
  • Roberts, J. W.; Kotowska, A.; Aguilar-Bejarano, E.; et al. (2026). Quantitative Cryogenic Orbitrap Secondary Ion Mass Spectrometry for Structural Characterization of Lipid Nanoparticles. ChemRxiv (preprint). Co-author; led the ML model — with the MIT Anderson Lab. DOI
  • Aguilar-Bejarano, E., et al. (2026). Helix 1.0: An Open-Source Framework for Reproducible and Interpretable Machine Learning on Tabular Scientific Data. Patterns (Cell Press) 7, 101536. (IF ~7.4) Read More
  • Aguilar-Bejarano, E., et al. (2025). Explainable GNN-Derived Structure–Property Relationships in Interstitial-Alloy Materials. Phys. Chem. Chem. Phys. (RSC) 27(41), 22240. (IF ~3.7) DOI
  • Aguilar-Bejarano, E., et al. (2025). HCat-GNet (Homogeneous Catalyst Graph Neural Network): A Human-Interpretable GNN Tool for Ligand Optimization in Asymmetric Catalysis. iScience (Cell Press) 28(3), 111881. (IF ~4.1) Read More
  • Aguilar-Bejarano, E.; Deorukhkar, V.; Woodward, S. (2025). Data Checking of Asymmetric Catalysis Literature Using a Graph Neural Network Approach. Molecules 30(2), 355. (IF ~4.6) Read More

Open-Source Software

Lead/first-author role unless noted. Most publications ship with an accompanying public code repository.

  • HCat-GNet — interpretable GNN for model-guided ligand/catalyst optimisation in asymmetric catalysis. (→ iScience 2025)
  • AsymBench — modular benchmark of fingerprints, descriptors, chemical foundation models, and GNNs for asymmetric catalysis with extrapolative splits. (→ J. Cheminform. 2026)
  • Helix — framework for reproducible, interpretable ML on tabular scientific data (CI/CD, automated testing, interpretation modules, GUI). (→ Patterns 2026)
  • PolyNet — end-to-end Python/Streamlit library for polymer property prediction: six GNN architectures, automated HPO, atom/fragment-level explainability.
  • LNPQuantification (LCNet) — neural-network model behind the first quantitative Q-Cryo-OrbiSIMS method for LNP characterisation; Integrated-Gradients interpretation. (→ ChemRxiv 2026; with MIT Anderson Lab)
  • InterstitialAlloys — interstitial-alloy property prediction with explainable GNNs. (→ PCCP 2025)

Conferences & Presentations

  • University of Nottingham School of Chemistry Postgraduate Symposium — Nottingham, UK, July 2024.
    "HCat-GNet: an Interpretable Graph Neural Network for Catalysis Optimization" (poster)
  • The GSK Prosperity Partnership — GSK, Stevenage, UK, March 2024.
    "HCat-GNet: An Interpretable Graph Neural Network for Catalysis Optimization" (invited lecture)
  • Faraday Community Poster Symposium — Burlington House, London, UK, November 2023.
    "Feature Identification in Molybdenum Carbides: Graph Neural Networks vs. Human Empirical Search" (poster)
  • Machine Learning for Atomistic Modelling Autumn School — Daresbury Laboratory, UK, September 2023.
    "Feature Identification in Molybdenum Carbides: Graph Neural Networks vs. Human Empirical Search" (oral + poster)
  • School of Chemistry Seminar Series — Universidad de Costa Rica, San José, Costa Rica, August 2023.
    "Chemistry in the Artificial Intelligence Era" (invited lecture)
  • Sciences Week Scientific Poster Contest — San José, Costa Rica, September 2022.
    "Development of a Novel Lipophilicity Descriptor from Toluene/Water Partition Coefficient Predictions" (poster)
  • University Week Scientific Poster Contest — San José, Costa Rica, April 2022.
    "Machine Learning Methods to Determine the Toluene/Water Partition Coefficient as an Efficient Lipophilic Descriptor" (poster)
  • Gulf Coast Undergraduate Research Symposium (GCURS) — Rice University, Houston, TX, October 2021.
    "Cheminformatic and Quantum Mechanics Approaches for Quantitative Prediction of Tautomerism in Bioactive Molecules" (lecture)

Honors & Awards

  • Christopher J. Moody Synthesis and Catalysis Poster Prize — University of Nottingham School of Chemistry, July 2024.
  • Second Place, PGR Symposium Poster Contest — University of Nottingham, 2024.
  • AI Doctoral Training Centre Scholarship — University of Nottingham, July 2022. Full scholarship (tuition + stipend, 4 years) via competitive programme.
  • CeNAT-CONARE Research Fellowship — National Center for High Technology, Costa Rica, June 2022. Grant (US$4,300) for the project "Cheminformatic and Quantum Mechanics Approaches for Quantitative Prediction of Tautomerism in Bioactive Molecules".
  • Bachelor of Science with Honors — Universidad de Costa Rica, June 2022. Awarded for graduation with academic excellence.
  • Best Scientific Poster — Chemistry Students Association, Universidad de Costa Rica, April 2022.
  • Medalla de Oro (Gold Medal) — Universidad Nacional de Colombia. Winner of the University Iberoamerican Organic Chemistry Olympiad (2021)
  • GCURS Acceptance and Travel Award — Rice University, October 2021. Travel grant to present at the Gulf Coast Undergraduate Research Symposium, Houston, TX.
  • Academic Excellence Scholarship — Universidad de Costa Rica, 2019–2022. Annual scholarship for students with a prior-year GPA of 9.0/10 or above.
  • Medalla de Oro (Gold Medal) & Mención Honorífica (Honourable Mention) — Universidad Nacional de Costa Rica. Winner of the Costa Rican Physics Olympiad and Honourable Mention in Chemistry Olympiad (2017)

Teaching, Supervision & Mentoring

  • Co-Supervisor, MSc Machine Learning in Science — University of Nottingham (May 2023 – Present)
  • Co-supervised three MSc students (2024–2026) on deep-learning projects in the chemical sciences with Dr. Grazziela Figueredo and Dr. Kristaps Ermanis (2023-2024) and Prof. Simon Woodward (2025).

  • Co-Supervisor, Summer Research Intern — Woodward Group, University of Nottingham (Summer 2024; incoming Summer 2026)
  • Designed and delivered in-house Python and ML training to interdisciplinary research teams.

  • Programming, ML & Data Analysis Tutor — CBIO3 Group, Universidad de Costa Rica (Jul 2022 – Sep 2022)
  • Teaching assistant for Prof. William Zamora's Cheminformatics course (programming, data visualisation, ML algorithms, cheminformatic tools).

  • Organic & Analytical Chemistry Tutor — Universidad de Costa Rica, Campus Atlántico (Sep 2021 – Nov 2021)
  • Chemistry Olympiad Tutor — Colegio Científico Costarricense, San Pedro (Mar 2021 – Oct 2021)
  • Chemistry Tutor for New Students — Universidad de Costa Rica (Mar 2021, Mar 2022)
  • Physics Tutor — Colegio Científico Costarricense, San Pedro (Mar 2019 – Jul 2019)
  • Laboratory Teaching Assistant — Universidad de Costa Rica (2019 – 2021)
  • Assisted across seven laboratory courses: Physical Chemistry I & II, Analytical Chemistry I, Organic Chemistry I, Chemical Experimentation II, and General & Qualitative Chemistry.

Professional Memberships

  • Royal Society of Chemistry (RSC) — Member since September 2023.
  • American Chemical Society (ACS) — Member, July 2021 – July 2022.
  • Costa Rica ACS Student Chapter — Member, June 2021 – June 2022.

Technical & Laboratory Skills

  • Representation & molecular modelling: molecular/materials representation design; graph & 3D (geometric) representations vs tabular descriptors; RDKit; SMILES/InChI; QSAR/QSPR; fingerprints, topological & physicochemical descriptors; lipid & polymer (non-small-molecule) modelling; Chemprop; OpenBabel; DataWarrior.
  • Deep learning & ML: PyTorch; PyTorch Geometric; scikit-learn; XGBoost; TensorFlow; Transformers; GNNs (GCN, GAT, MPNN, GraphSAGE); transfer & self-supervised learning; ensemble methods; HPO (Ray Tune).
  • Atomistic & interatomic potentials: machine-learnt interatomic potentials (MACE); ASE; pymatgen; DScribe; quantum chemistry (Gaussian — QM continuum solvation).
  • Foundation models & interpretability: chemical foundation models (ChemBERTa, MolT5, UniMol); LLM APIs (Anthropic Claude, OpenAI GPT); Integrated Gradients; GNNExplainer; GradCAM; atom/fragment-level attribution.
  • Software engineering & MLOps: Python (advanced, OOP); Git & code review; automated/unit testing; GitHub Actions / CI–CD; build automation (Poetry, UV); Docker; Bash; Linux; HPC/SLURM; GPU/CUDA; Weights & Biases; Streamlit.
  • Other programming: C (basic); R (data analysis, visualisation, ML); scientific Python stack (SciPy, NumPy, Pandas, Matplotlib). Other software: MapleSoft, PyMOL.
  • Laboratory (wet-lab) techniques: HPLC; gas chromatography; atomic absorption spectroscopy; UV/Vis spectrophotometry; fluorescence spectrophotometry.
  • Languages: Spanish (native), English (fluent).