iiinova — where your digital self keeps evolving

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Clare Hall, University of Cambridge @clarehallcambridge.bsky.social · 06/05/2025

Former Clare Hall PhD student @srijitseal.com has recently led a landmark collaboration between over 30 scientists to outline the essential pillars for using machine learning (ML) to predict chemical toxicity. Read more ⬇️ www.clarehall.cam.ac.uk/news/dr-srij...

041

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 06/05/2025

This initiative aligns with the FDA's recent announcement to phase out traditional animal testing in favor of more human-relevant methods. Our collective work provides a roadmap for integrating AI, ensuring safer and more efficient drug development processes.

020

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 06/05/2025

We spoke to government experts from the National Institute of Environmental Health Sciences (NIEHS) and thought leaders from academia, including the University of Cambridge, the Broad Institute of MIT, and Harvard. This unprecedented industry-wide effort outlines a unified framework for adopting AI.

100

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 06/05/2025

It’s a strategic blueprint, introducing pillars for success in the real world, drawing from the expertise of scientists from pharma, including GSK, Novartis, Eli Lilly and Company, Merck, AstraZeneca, Bayer | Crop Science, Pfizer, Recursion, Novo Nordisk, Sanofi, Relay Therapeutics, and others.

110

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 06/05/2025

So, you want to replace animal models with AI? We spent the last two years collaboratively exploring AI for toxicology with 33 scientists from 14 leading pharmaceutical companies and 6 research institutes! 🏆 American Chemical Society Editor's Choice! pubs.acs.org/doi/10.1021/...

pubs.acs.org

Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World

Machine learning (ML) is increasingly valuable for predicting molecular properties and toxicity in drug discovery. However, toxicity-related end points have always been challenging to evaluate experim...

170

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 10/04/2025

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?

140

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 10/03/2025

Today I learned that Hedwig actually died in Harry Potter? How did I even miss this? 😭😭

120

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 02/03/2025

Thank you for highlighting our work! Use DILIpred to figure out if your compounds have any DILI risk, with mechanistic features :D DILIPred was bulit with over 15k compounds and covers a large chemcial space!

040

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 26/01/2025

Excited to join Merck US as a Senior Research Scientist! If you are in Philly area, would be happy to catchup!

0110

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 22/01/2025

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.

lnkd.in

This link will take you to a page that’s not on LinkedIn

010

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 22/01/2025

In this work, Gang Liu introduces InfoAlign, a new approach for learning molecular representations from cellular response data, integrating features like cell morphology and gene expression.

lnkd.in

This link will take you to a page that’s not on LinkedIn

100

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 22/01/2025

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! 🎉

2211

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

God @thegodshow.com · 07/01/2025

Thou shalt not promise lower grocery prices and then deliver war against Panama, Canada, and Greenland.

645274815506

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Francesca Grisoni @fragrisoni.bsky.social · 21/12/2024

Open #postdoc position in *Organic/Medicinal Chemistry* for generative #AI in Drug Discovery — join us @tueindhoven.bsky.social 💪🏻 Funded by the European Research Council (ERC). Deadline: Jan 15, 25 jobs.tue.nl/nl/vacature/... Repost appreciated!

jobs.tue.nl

Postdoc In Organic/Medicinal Chemistry for generative AI in Drug Discovery

De TU/e is voortdurend op zoek naar wetenschappelijk en niet-wetenschappelijk personeel om haar ambities waar te maken. Kijk hier voor ons actuele vacatureaanbod.

14425

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 25/12/2024

“Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should”

57511

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Pranav Rajpurkar PhD @rajpurkar.bsky.social · 18/12/2024

I don't think it's widely clear to the #RadiologyAI community just how poorly GPT-4V compares with the top report generation models on chest X-rays, like MedVersa or MAIRA-2. It's clear we need a way to track progress.

194

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Brendan @chemscrapes.bsky.social · 27/12/2024

Atomic orbitals at the beach #chemsky 🧪

some atomic orbitals at the beach. the d, p and s orbitals are all standing on the shore watching sadly as the d-z-squared orbitals play in the water. the d-z-squared orbitals are using their doughnut shaped lobe as a flotation device.

2457

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Andreas Bender @andreasbender.bsky.social · 22/12/2024

The next Cambridge Cheminformatics Newsletter, December 2024 Edition is out! Containing upcoming related events, news jobs and resources For details please see: www.drugdiscovery.net/2024/12/22/c... Have a good Christmas/Holiday period everyone! All the best and see you in 2025, Andreas

0316

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 17/11/2024

Here's a Cheminformatics Starter pack! Let me know if you would like to be added! And more importantly, do encourage people to join the blue skies :D

317421

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 20/12/2024

An Android phone offers you more discounts than any subscription model 😂

000

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 20/12/2024

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 🤪

160

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Jess Ewald @ewaldlab.org · 13/12/2024

🎉 I'm starting my own lab at EMBL-EBI (Cambridge, UK; June 2025) 🎉 We will focus on identifying and characterizing chemical hazards to humans and ecosystems using computational biology methods. I am beginning the search for two postdocs now - stay tuned for more details! ewaldlab.org

ewaldlab.org

Ewald Lab

@ EMBL-EBI. We identify and characterize chemical hazards to both humans and ecosystems with cell profiling data, machine learning, and integrative data analysis.

916537

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Beth Cimini 🔬💻📊 @bethcimini.bsky.social · 16/12/2024

New Year, new job? Delighted to announce two early-career-level (post-BA/BS or MA) positions in my lab, and an open call for computational postdocs at the Broad! First, an image analysis associate - work on high content screens for all kinds of cells and dimensionalities! See more at link (1/4)

docs.google.com

Image analysis associate job description

Image Analysis Associate Broad Institute of MIT and Harvard, Cambridge, MA Impact the discovery of new disease therapies in the Cimini laboratory at the Imaging Platform Join our vibrant, world-clas...

24435

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Anne Carpenter @drannecarpenter.bsky.social · 18/12/2024

We've a postdoc opening for our lab at the Broad: Cambridge MA! Must have experience in toxicology + data science Work on the wonderful OASIS dataset we are producing... Cell Painting, transcriptomics, proteomics in various liver cell and tissue models! broad.io/mlcbpostdoc

Image of the job posting (see URL for full text instead)

13023

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 17/12/2024

Pack 3 now up to 69/150!

1102

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 14/12/2024

Note: most MIT professors I know are honest and morally upright

1541

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 12/12/2024

Thinking about implementing the Cell Painting assay? Here’s a guide to how it can help in Drug Discovery! t.co/hW1jOhAg7q

t.co

https://rdcu.be/d2vHH

130

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Chaitanya K. Joshi @chaitjo.bsky.social · 12/12/2024

My (I think funny) take on AlphaFold3 and equivariance: There are many versions of AF3 which may be better at different tasks — The one they publicly released is as diametrically opposite in terms of architecture (no equivariance, no frames, generative) to RosettaFold-AllAtom.

1131

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 10/12/2024

Yup I just realized what happened and deleted the post before your reply, the organizers of an event said 3pm BST so I searched BST time!

110

Reposted by Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳

Daniel Probst @skepteis.bsky.social · 06/12/2024

Due to recent events and such...

The "is this a pidgeon meme?" where the butterfly is interpolation and the guy asks "is this AI?"

0182

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 06/12/2024

When the size of test data is 5 compounds and accuracy is 100% 😌

1151

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

This ofcourse doesn’t hold for the large datasets where rxrx must have seen improvement (or similar signal with BF images), which makes the case for the switch. In the public domain, we don’t see much of these.. especially where studies only involve around a 100 compounds often—many inactive.

010

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

I’m writing a paper on showing case by case where this is true and where it’s probably not enough. As far as I know, there is no systematic study on the differences with respect to protein targets, all studies are confounded by lots of viability assays—assays where simple cell counts suffice!

120

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

What excites you most about the future of Cell Painting? Share your thoughts below!

100

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

Applications that are changing the game: Predicting MoAs: By comparing unknown compounds to landmark ones. Toxicity profiling: From mitochondrial health to drug-induced liver injury. Disease modeling: Creating phenotypic signatures for rare diseases, ...among others

100

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

Why it matters: Cell Painting unlocks phenotypic profiling, helping researchers understand drug mechanisms of action (MoA), predict toxicity, and even design safer, more effective compounds. It's cost-effective, scalable, and widely accessible.

110

Srijit Seal 🇺🇸🇬🇧🇩🇪🇯🇵🇮🇳 @srijitseal.com · 05/12/2024

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.

110