đź“Ť Cambridge, MA, US
đź“Ť Cambridge, UK
FCPS AFHEA AMRSC PhD MPhil

Hello, I'm Srijit Seal

I am a researcher in chemoinformatics, centered on using machine learning techniques, particularly modeling, and interpretation of the Cell Painting assay, to predict drug bioactivity, safety, and toxicity.
I am currently a Senior Scientist at Merck US. I completed my postdoc at the Broad Institute of MIT and Harvard where I was advised by Anne Carpenter and Shantanu Singh.
I obtained my PhD from the University of Cambridge where I was advised by Andreas Bender. I also serve on the Board of Directors at the American Society for Cellular and Computational Toxicology.

Scholar Github Twitter
University of Cambridge Homepage Broad Institute Homepage Blog : understanding.bio

Upcoming and Past Talks

Publications

Cell Painting: a decade of discovery and innovation in cellular imaging

Cell Painting: a decade of discovery and innovation in cellular imaging

Srijit Seal, Marianna Trapotsi, Ola Spjuth, Jordi Carreras Puigvert, Nigel Greene, Shantanu Singh, Andreas Bender, Anne E. Carpenter
Nature Methods, 2024

Open Access Publication Journal (Institutional Access)
Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA Drug-Induced Cardiotoxicity Rank

Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA Drug-Induced Cardiotoxicity Rank

Srijit Seal, Ola Spjuth, Layla Hosseini Gerami, Miguel GarcĂ­a-OrtegĂłn, Shantanu Singh, Andreas Bender, Anne E. Carpenter
Journal of Chemical Information and Modeling, 2024

Project Page Open Access Publication Code
Integrating Cell Morphology with Gene Expression and Chemical Structure to aid Mitochondrial Toxicity detection

Integrating Cell Morphology with Gene Expression and Chemical Structure to aid Mitochondrial Toxicity detection

Srijit Seal, Jordi Carreras Puigvert, Marianna Trapotsi, Yang Hongbin, Ola Spjuth, Andreas Bender
Communications Biology, 2022

Open Access Publication
Comparison of Cellular Morphological descriptors and Molecular Fingerprints for the prediction of Cytotoxicity- and Proliferation-related assays

Comparison of Cellular Morphological descriptors and Molecular Fingerprints for the prediction of Cytotoxicity- and Proliferation-related assays

Srijit Seal, Yang Hongbin, Luis Vollmers, Andreas Bender
Chemical Research in Toxicology, 2021

Project Page Paper (Repository Access) Journal (Institutional Access)
Understanding Biology in the Age of Artificial Intelligence

Understanding Biology in the Age of Artificial Intelligence

Elsa Lawrence, Adham El-Shazly, Srijit Seal, Chaitanya Joshi, Pietro Lio, Shantanu Singh, Andreas Bender, Pietro Sormanni, Matthew Greenig
arXiv, 2024

Project Page PDF arXiv
Using Chemical and Biological data to Predict Drug Toxicity

Using Chemical and Biological data to Predict Drug Toxicity

Anika Liu, Srijit Seal, Yang Hongbin, Andreas Bender
SLAS Discovery, 2023

Open Access Publication
Merging Bioactivity Predictions from Cell Morphology and Chemical Fingerprint models using Similarity to Training data

Merging Bioactivity Predictions from Cell Morphology and Chemical Fingerprint models using Similarity to Training data

Srijit Seal, Yang Hongbin, Marianna Trapotsi, Shantanu Singh, Jordi Carreras Puigvert, Ola Spjuth, Andreas Bender
Journal of Cheminformatics, 2023

Open Access Publication Code
From pixels to phenotypes: Integrating image-based profiling with cell health data as BioMorph features improves interpretability

From pixels to phenotypes: Integrating image-based profiling with cell health data as BioMorph features improves interpretability

Srijit Seal, Jordi Carreras Puigvert, Shantanu Singh, Anne E. Carpenter, Ola Spjuth, Andreas Bender
Molecular Biology of the Cell, 2024

Project Page Open Access Publication Code
Using Generative Modeling to Endow with Potency Initially Inert Compounds with Good Bioavailability and Low Toxicity

Using Generative Modeling to Endow with Potency Initially Inert Compounds with Good Bioavailability and Low Toxicity

Robert Horne, Jared Wilson-Godber, Alicia Gonzalez Diaz, Z. Faidon Brotzakis, Srijit Seal, Rebecca C. Gregory, Andrea Possenti, Sean Chia, Michele Vendruscolo
Journal of Chemical Information and Modeling, 2024

Open Access Publication Code
Improved Early Detection of Drug-Induced Liver Injury by Integrating Predicted in Vivo and in Vitro Data

Improved Early Detection of Drug-Induced Liver Injury by Integrating Predicted in Vivo and in Vitro Data

Srijit Seal, Dominic Williams, Layla Hosseini Gerami, Ola Spjuth, Andreas Bender
bioRxiv, 2024

Project Page Code PDF bioRxiv
PKSmart: An Open-Source Computational Model to Predict in vivo Pharmacokinetics of Small Molecules

PKSmart: An Open-Source Computational Model to Predict in vivo Pharmacokinetics of Small Molecules

Srijit Seal, Marianna Trapotsi, Vigneshwari Subramanian, Ola Spjuth, Nigel Greene, Andreas Bender
bioRxiv, 2024

Project Page Code PDF bioRxiv
Calibrated prediction of scarce adverse drug reaction labels with conditional neural processes

Calibrated prediction of scarce adverse drug reaction labels with conditional neural processes

Miguel GarcĂ­a-OrtegĂłn, Srijit Seal, Shantanu Singh, Andreas Bender, Sergio Bacallado
ICLR 2024 DMLR Workshop

Open Access Publication

News

  • Jan 2025: pip install infoalign! Add biological information to your chemcial fingerprints, using only SMILES as input! Our paper Learning Molecular Representation in a Cell has been accepted to ICLR 2025! We introduce InfoAlign, a new approach for learning molecular representations from cellular response data, integrating features like cell morphology and gene expression. By combining information bottleneck methods with context graphs, we’re able to extract minimal yet sufficient representations of molecules that lead to better predictions and generalization in downstream tasks like molecular property prediction and zero-shot molecule-morphology matching.
  • Mar 2024: Calibrated prediction of scarce adverse drug reaction labels with conditional neural processes has been accepted in DMLR at ICLR 2024. This work introduces a meta-learning approach with neural processes to significantly enhance the accuracy and calibration of adverse drug reaction (ADR) classification.