About Me
Hi, I'm Parth. I am a PhD candidate at the Laboratory for Biomolecular Modeling at EPFL. My research interests include applications of machine learning in structural bioinformatics, computational biophysics and integrative modeling. I enjoy playing chess, traveling, reading, and building things.
Education
PhD in Computational and Quantitative Biology
September 2024 - Present
Institute of Bioengineering, SV, EPFL, Switzerland
Advisor: Prof. Matteo Dal Peraro
BS-MS (Bachelor's and Master's dual degree) in Biology with a minor in Computational and Data Sciences
2019 - 2024
IISER Kolkata, India
MS Thesis: Applications of Geometric Deep Learning for Biomolecular Structure Modeling
Advisor: Prof. Matteo Dal Peraro
Projects
RISoTTo
RRISoTTo (RIbonucleic acid Sequence design from TerTiary structure) is a parameter-free geometric deep learning approach that generates RNA sequences conditioned on both their backbone scaffolds and the surrounding molecular context. A preprint describing RISoTTo has been recently posted on bioRxiv and I presented a poster about it at NeurIPS AI4D3 workshop 2025. More updates with experimental validation will follow soon.
PeSTo-Carbs
PeSTo-Carbs, published in The Journal of Chemical Theory and Computation, is a geometric transformer model extending our earlier work on PeSTo. It is specifically designed to predict binding interfaces between proteins and carbohydrates, including protein–cyclodextrin interactions, with high accuracy.
Welearn-bot
Welearn-bot is a CLI application to interact with welearn in the IISER Kolkata domain. The bot was created and is actively maintained by Satvik, Abhay, Amarjeet and I. It can be used to download all the necessary files from welearn, list your assignments, etc. It has Google Calendar integrated to directly add due assignments to your calendar.
Moscow Pioneer Home Championship (1935), Moscow URS
Rubinstein Opening (D05) · 0-1