Vignesh Somnath
Research Scientist at Isomorphic Labs
United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolVignesh Somnath is a research scientist with eight years of experience at the intersection of machine learning, computational biology, and drug discovery, currently working on AI for therapeutics at Isomorphic Labs. He holds a PhD from ETH Zürich and brings hands-on research experience from roles at DeepMind, MIT, and ETH, with peer-reviewed work on multi-scale protein representation learning. Vignesh has a strong engineering footprint in open source—contributing substantive dataset loaders, preprocessing pipelines, and featurization methods to DeepChem’s widely used MolNet benchmarks—bridging practical tooling with cutting-edge models. His background spans chemical engineering to computational biology, enabling him to translate domain chemistry knowledge into scalable ML solutions for protein and molecular problems. Notably, he has interned in Michael Bronstein’s group improving generalization in protein docking, reflecting a rare blend of theoretical research and applied model engineering.
8 years of coding experience
2 years of employment as a software developer
Indian Institute of Technology MadrasDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at ETH ZürichMaster of Science - MS, Computational Biology and Bioinformatics, Master of Science - MS, Computational Biology and Bioinformatics at ETH Zurich
English, Hindi
Github Skills (9)
data-preprocessing10
drug-discovery10
machine-learning10
deep-learning10
python10
modeling10
tensorflow9
quantum-chemistry8
biology8
Programming languages (6)
Github contributions (5)
deepchem/deepchem
Sep 2018 - Jun 2020
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:61 reviews, 121 commits, 68 PRs in 1 year 9 months
Contributions summary:Vignesh made significant contributions by adding and implementing molnet wrappers for UV, Kinase, and Factors datasets, which included the creation of load functions within the `deepchem/molnet` module and integration within the `run_benchmark.py` script. The user also incorporated data preprocessing steps, such as missing entry removal and task definition for various datasets (Kinase, UV, and Factors) and implemented a feature generation method for use with the Bace datasets. These contributions enhanced the MolNet library's capability in processing and analyzing chemical datasets for machine learning tasks.
chemistrysciencedrug-discoverydeep-learningbiology
vsomnath/graphretro
Dec 2021 - Dec 2022
Learning Graph Models for Retrosynthesis Prediction (NeurIPS 2021)
Contributions:1 review, 8 commits, 1 PR in 1 year
geometrygraph-neural-networkmachine-learningmoleculesneurips-2021
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.