Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳
@srijitseal.com
Senior Chemøinformatician at Merck | Postdoc@Broad Institute of MIT and Harvard, Cambridge(MA) | PhD@University of Cambridge(UK) | AI, Image Analysis, bioML, -omics data, and Cell Painting for drug discovery. srijitseal.com/tools
A model evaluated 234 toxic and 596 non-toxic compounds using structural fingerprints and achieved an F1 score of 0.440; what could be wrong?
Of course, one answer is that it’s a great model. What’s another possibility?
Of course, one answer is that it’s a great model. What’s another possibility?
April 10, 2025 at 5:56 PM
A model evaluated 234 toxic and 596 non-toxic compounds using structural fingerprints and achieved an F1 score of 0.440; what could be wrong?
Of course, one answer is that it’s a great model. What’s another possibility?
Of course, one answer is that it’s a great model. What’s another possibility?
pip install infoalign! Add biological information to your chemcial fingerprints, using only SMILES as input!
I'm thrilled to share that our paper "Learning Molecular Representation in a Cell" has been accepted to ICLR 2025! 🎉
I'm thrilled to share that our paper "Learning Molecular Representation in a Cell" has been accepted to ICLR 2025! 🎉
January 22, 2025 at 8:00 PM
pip install infoalign! Add biological information to your chemcial fingerprints, using only SMILES as input!
I'm thrilled to share that our paper "Learning Molecular Representation in a Cell" has been accepted to ICLR 2025! 🎉
I'm thrilled to share that our paper "Learning Molecular Representation in a Cell" has been accepted to ICLR 2025! 🎉
I did the experiment myself! Having an Android phone saves you 25% costs and the phone pays for itself in 10 Uber rides!
Uber and other apps cost up to 30% more on iPhones than on Androids for the same orders. Don’t get me wrong, by all means buy an iPhone! Keep an Android on the side for orders 🤪
Uber and other apps cost up to 30% more on iPhones than on Androids for the same orders. Don’t get me wrong, by all means buy an iPhone! Keep an Android on the side for orders 🤪
December 20, 2024 at 5:47 PM
I did the experiment myself! Having an Android phone saves you 25% costs and the phone pays for itself in 10 Uber rides!
Uber and other apps cost up to 30% more on iPhones than on Androids for the same orders. Don’t get me wrong, by all means buy an iPhone! Keep an Android on the side for orders 🤪
Uber and other apps cost up to 30% more on iPhones than on Androids for the same orders. Don’t get me wrong, by all means buy an iPhone! Keep an Android on the side for orders 🤪
It’s not that large is it… hmm
December 16, 2024 at 1:55 AM
It’s not that large is it… hmm
When the size of test data is 5 compounds and accuracy is 100% 😌
December 6, 2024 at 9:15 PM
When the size of test data is 5 compounds and accuracy is 100% 😌
What is Cell Painting?
It's a microscopy-based, high-content assay that uses six fluorescent dyes to "paint" cells, capturing thousands of features like size, shape, texture, and intensity. The goal? Reveal cellular responses to perturbations in a target-agnostic way.
It's a microscopy-based, high-content assay that uses six fluorescent dyes to "paint" cells, capturing thousands of features like size, shape, texture, and intensity. The goal? Reveal cellular responses to perturbations in a target-agnostic way.
December 5, 2024 at 5:35 PM
What is Cell Painting?
It's a microscopy-based, high-content assay that uses six fluorescent dyes to "paint" cells, capturing thousands of features like size, shape, texture, and intensity. The goal? Reveal cellular responses to perturbations in a target-agnostic way.
It's a microscopy-based, high-content assay that uses six fluorescent dyes to "paint" cells, capturing thousands of features like size, shape, texture, and intensity. The goal? Reveal cellular responses to perturbations in a target-agnostic way.
Do you want to make biological sense of Cell Painting images? Try BioMorph! BioMorph maps CellProfiler features to a new feature space that’s more interpretable and contains the same signal strength. Try it at broad.io/BioMorph !
November 26, 2024 at 3:06 AM
Do you want to make biological sense of Cell Painting images? Try BioMorph! BioMorph maps CellProfiler features to a new feature space that’s more interpretable and contains the same signal strength. Try it at broad.io/BioMorph !
PKSmart v3.0 is now live! pk-predictor.serve.scilifelab.se
PKSmart is an open-source app we built to predict human and animal pharmacokinetic parameters. Publication is coming soon and is also available for local implementation via pip install pksmart.
PKSmart is an open-source app we built to predict human and animal pharmacokinetic parameters. Publication is coming soon and is also available for local implementation via pip install pksmart.
November 23, 2024 at 6:20 PM
PKSmart v3.0 is now live! pk-predictor.serve.scilifelab.se
PKSmart is an open-source app we built to predict human and animal pharmacokinetic parameters. Publication is coming soon and is also available for local implementation via pip install pksmart.
PKSmart is an open-source app we built to predict human and animal pharmacokinetic parameters. Publication is coming soon and is also available for local implementation via pip install pksmart.
Wait this isn’t how you play Catan?
November 23, 2024 at 1:16 AM
Wait this isn’t how you play Catan?
Ask ChatGPT, “based on what you know about me, generate an image of what you think my current life looks like”
I won’t lie, I like Catan.
I won’t lie, I like Catan.
November 22, 2024 at 8:43 PM
Ask ChatGPT, “based on what you know about me, generate an image of what you think my current life looks like”
I won’t lie, I like Catan.
I won’t lie, I like Catan.
Make your own word cloud from Google scholar! shiny.rcg.sfu.ca/u/rdmorin/sc...
November 21, 2024 at 4:10 PM
Make your own word cloud from Google scholar! shiny.rcg.sfu.ca/u/rdmorin/sc...
The Cambridge (MA) Cheminformatics meetings are free to join! broad.io/ccm
Sign up today!
Sign up today!
November 17, 2024 at 5:29 PM
The Cambridge (MA) Cheminformatics meetings are free to join! broad.io/ccm
Sign up today!
Sign up today!
DILIPredictor is now live!
If you want to predict Liver Toxicity from chemical structures try out broad.io/DILiPredictor!
#cheminformatics #toxicity #drugdiscovery #liver
If you want to predict Liver Toxicity from chemical structures try out broad.io/DILiPredictor!
#cheminformatics #toxicity #drugdiscovery #liver
November 16, 2024 at 4:46 AM
DILIPredictor is now live!
If you want to predict Liver Toxicity from chemical structures try out broad.io/DILiPredictor!
#cheminformatics #toxicity #drugdiscovery #liver
If you want to predict Liver Toxicity from chemical structures try out broad.io/DILiPredictor!
#cheminformatics #toxicity #drugdiscovery #liver
Have you ever wondered why we apply ML to biological problems? We propose that conceptions of scientific understanding as information compression, qualitative intelligibility, and dependency relation modelling provide a useful framework for ML in Biology.
March 9, 2024 at 5:10 AM
Have you ever wondered why we apply ML to biological problems? We propose that conceptions of scientific understanding as information compression, qualitative intelligibility, and dependency relation modelling provide a useful framework for ML in Biology.
New Publication Alert! We started with a null library with excellent pharmacokinetics (DMPK) but no initial target potency. By applying MolDQN, a generative model, we successfully integrated activity against α-synuclein aggregation in Parkinson’s disease.
pubs.acs.org/doi/full/10....
pubs.acs.org/doi/full/10....
January 26, 2024 at 9:06 PM
New Publication Alert! We started with a null library with excellent pharmacokinetics (DMPK) but no initial target potency. By applying MolDQN, a generative model, we successfully integrated activity against α-synuclein aggregation in Parkinson’s disease.
pubs.acs.org/doi/full/10....
pubs.acs.org/doi/full/10....