#predictive-discovery
We're excited to work with @omsf.io OpenADMET and @polarishub.io to bring you this blind predictive modeling community challenge!

If you're developing predictive models for drug discovery---potency or ADMET---here's your chance to test them prospectively on real discovery data from ASAP!
🦠 We’re excited to announce our first competition in partnership with @asapdiscovery.bsky.social and @omsf.io!

Test your skills across three sub-challenges revolving around SARS-CoV-2 and MERS-CoV Mpro🧵

Full details: polarishub.io/competitions
Blog: polarishub.io/blog/antivir...
December 3, 2024 at 4:46 PM
New discovery! Spoiler alert: Neural dynamics are key.
Evidence for predictive computations in a brain hierarchy during a visual search task
doi.org/10.64898/202...
Work led by @pinotsislab.bsky.social
#neuroscience
doi.org
April 9, 2026 at 4:42 PM
🏆 Best Paper — Predictive Coding or Just Feature Discovery? An Alternative Account of Why Language Models Fit Brain Data: doi.org/10.1162/nol_...

Richard Antonello and @alexanderhuth.bsky.social
Predictive Coding or Just Feature Discovery? An Alternative Account of Why Language Models Fit Brain Data
Abstract. Many recent studies have shown that representations drawn from neural network language models are extremely effective at predicting brain responses to natural language. But why do these…
doi.org
September 13, 2025 at 9:40 PM
It's very prevalent in areas of electronic discovery and document review.

Getting through massive volumes of documents all but requires use of predictive coding etc.
October 21, 2024 at 11:41 PM
OpenBind is a new open science effort to dramatically increase the number of protein:ligand structures in the PDB, pairing this with high-quality affinity data to enable a new generation of predictive structure and affinity models for drug discovery. Check it out: openbind.ai
January 12, 2026 at 2:54 PM
I’ve done a short review by blog post of ‘Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery’ DOI: 10.26434/chemrxiv.15000615/v1 which is still at #preprint stage #chemsky 🧪
fbdd-lit.blogspot.com/2026/05/gran...
Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery
In this blog post I’ll be taking a look at  C2026 (Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery) which has bee...
fbdd-lit.blogspot.com
May 27, 2026 at 11:21 AM
In a new @natureportfolio.bsky.social study, Professor Ryan Shenvi (@shenvi.bsky.social) demonstrated how computational tools and predictive modeling could synthesize 25 picrotoxin—complex plant molecules that could inform drug discovery for brain diseases.
Virtual chemistry speeds up drug discovery
www.scripps.edu
January 9, 2025 at 8:49 PM
Working on predictive models for drug discovery? Here's your chance to see how well your models actually work!

Together with @polarishub.io and OpenADMET, we've launched a blind prospective challenge to see how well predictive models for drug discovery can actually predict real drug discovery data!
🏁 The antiviral challenge is live! 🏁

Ready to test your skills on new data? Hosted in partnership with @asapdiscovery.bsky.social and @omsf.io, we've prepared detailed notebooks showcasing how to format your data and submit your solutions. 🧑‍💻
January 15, 2025 at 3:44 PM
AI/ML are increasingly integrated with first-principles models in chemical engineering, spanning atomic-scale simulations, catalyst discovery, and process operations. The work emphasizes predictive accuracy, interpretability, and lifecycle…

#AI #LLM #TechNews
https://arxiv.org/abs/2610.02014
October 2, 2026 at 8:01 AM
Crim Defense friends, include “predictive intelligence disclosure” or some such language in your discovery motions…since we’re a police state now
November 20, 2025 at 6:22 PM
AI-driven predictive biomarker discovery with contrastive learning to improve clinical trial outcomes: Cancer Cell www.cell.com/cancer-cell/...
AI-driven predictive biomarker discovery with contrastive learning to improve clinical trial outcomes
Arango-Argoty et al. introduce the Predictive Biomarker Modeling Framework (PBMF), an AI-driven contrastive learning framework to identify putative predictive, rather than prognostic, biomarkers for c...
www.cell.com
April 22, 2025 at 5:55 AM
We are thrilled to announce a landmark alliance between The Jackson Laboratory (JAX) and The New York Stem Cell Foundation to transform disease research and accelerate the discovery of life-changing therapies and cures. 🧬🧪
Pioneering alliance between The Jackson Laboratory and The New York Stem Cell Foundation ushers in new era of predictive biomedical research
Uniting cutting-edge genomics, stem cell science, and AI-enabled data science to accelerate the discovery of life-changing therapies
www.jax.org
July 9, 2025 at 8:08 PM
So, you want to know what astrology has to say about your creative writing. I’m not an astrologer but I have some clues to share.

Firstly, I am only talking about natal chart stuff bc I don’t know anything about predictive astrology. It’s all about self discovery for me than forecasting.
March 23, 2026 at 11:49 AM
niche (pronounced "neesh" 🇨🇦) question: can anyone tell me the dates when NSERC Discovery Grant results were announced (by university research offices to applicants) in 2024 and 2025? I want to update my predictive model gist.github.com/bbolker/ce64... for this year ...
projection/prediction of NSERC Discovery award dates
projection/prediction of NSERC Discovery award dates - nserc_dates.R
gist.github.com
February 26, 2026 at 12:37 AM
It's very funny how they gloss over the fact that "AI" (which can mean anything from LLMs to basic shit like support vector regression btw) has accelerated basic research incredibly (think AlphaFold). If anything is predictive of Future Drug Discovery, it's basic research.
August 11, 2026 at 7:19 AM
How can we build better predictive models? And what can AI tell us about complex ecosystem mechanisms?

I’m hiring a PhD student to work with me on applying data-driven discovery methods on high-frequency lake data to begin September 2025. Application is due on May 4.
February 4, 2025 at 8:58 AM
CircaVent is a high-throughput drug screening platform that combines predictive algorithms, preclinical models, and human brain organoids to efficiently identify and test drugs that could treat the underlying causes of bipolar disorder.
CircaVent: A Drug Discovery Platform for Mental Health Conditions
CircaVent is a novel drug discovery platform that combines predictive algorithms, high-throughput preclinical models, and human organoids to identify and test drugs that could treat mental health conditions like bipolar disorder.
wyss.harvard.edu
October 3, 2026 at 3:05 PM
I've used it in cases where the discovery set was so huge that without predictive coding it was just an impossibility.
October 1, 2025 at 6:12 PM
Me when I have been using GenAI and LLM for years to build predictive networks of biological processes in diseases for therapeutic discovery lmao
May 24, 2025 at 4:52 PM
🧬 AI model building is transforming life sciences by turning complex biological data into predictive insights.

From biomarker discovery to precision medicine, intelligent models are shaping the future of research.

Oxford OmicLine

#AI #MachineLearning #Bioinformatics #Genomics
July 2, 2026 at 8:14 AM
With support from @bipolardiscoveries.org the Wyss' CircaVent project is combining predictive algorithms, preclinical models, & human brain organoids to efficiently identify & test drugs that could treat the underlying causes of bipolar disorder.

#WorldBipolarDay #BipolarDisorder
CircaVent: A Drug Discovery Platform for Mental Health Conditions
CircaVent is a novel drug discovery platform that combines predictive algorithms, high-throughput preclinical models, and human organoids to identify and test drugs that could treat mental health…
buff.ly
March 30, 2025 at 3:02 PM
See my new book on Predictive Analytics for Toxicology: Applications in Discovery Science
It covers current topics of how AI is a discovery science tool to help identify toxic chemicals.
www.routledge.com/Predictive-A...
Predictive Analytics for Toxicology: Applications in Discovery Science
Predictive data science is already in use in many fields, but its application in toxicology is new and sought after by non-animal alternative testing initiatives. Predictive Analytics for Toxicology: ...
www.routledge.com
December 8, 2024 at 3:02 AM
It's been a decade since I was steeped in eDiscovery, but using AI as a tool for discovery is nothing new. The key is to use it as a tool, not trust it to do the job for you. But back in the 2010s, "predictive coding" was all the rage, and I think the basic contours remain the same. 1/
June 13, 2026 at 7:10 PM
From pioneering FDA approved therapies to innovative predictive models, Moffitt is redefining what is possible in cancer care. Explore how our discoveries in 2024 are changing lives. 👇 #CancerResearch
Top Moffitt Research Stories of 2024
From FDA approvals to drug discovery, Moffitt led the way this past year
www.moffitt.org
January 6, 2025 at 8:24 PM