Computational scientist building ML and simulation tools for molecular and materials problems.
PhD, Chemical Engineering (University at Buffalo) · Postdoc at NC State University
I work at the intersection of machine learning, cheminformatics, and molecular simulation — building computational workflows that help experimental scientists prioritize what to test next. Whether that's screening 20M peptide candidates down to a tractable set, or using MD and free-energy methods to rank molecular interactions, I care about making models that are useful, interpretable, and connected to real chemistry.
- 🔬 High-throughput peptide screening pipelines combining unsupervised ML with molecular dynamics
- 🧪 Claude Skills for CHARMM-GUI PDB Reader — AI-assisted automation for protein structure preparation (Force Field Converter skill coming soon)
- 🛠️ Open-source tools for molecular ML (co-developer of ChemML)
- 📄 Protein MD for soft matter and biomaterials — modeling phase behavior in elastin-like polypeptides and silaffin-driven biomineralization (manuscripts in preparation, code repos to follow)
- Molecular property prediction, transfer learning, and GNNs
- Protein language model embeddings (ESM-2, ProtBert) for peptide design
- Molecular dynamics, enhanced sampling, and free-energy methods (GROMACS/PLUMED)
- Cheminformatics (RDKit) and molecular representations
- Model evaluation, uncertainty quantification, and XAI for chemistry (DeepSHAP/LIME/LRP) — see my ML StarterKit
- Scalable unsupervised learning for large sequence and molecular datasets
- Wixson et al. Soft Matter (2026) — Genetic control of morphological transitions in a coacervating protein template
- Vishwakarma, Sonpal et al. Trends in Chemistry (2021) — Metrics for benchmarking and uncertainty quantification in ML for chemistry
- Haghighatlari et al. WIREs Comp. Mol. Sci. (2020) — ChemML: ML and informatics for chemical and materials data
- Afzal, Sonpal et al. Chemical Science (2019) — Deep neural network packing density prediction applied to 1.5M organic molecules
- Sonpal et al. ACS Symposium Series (2022) — Benchmarking ML Descriptors for Crystals