An open source toolkit, developed by and for the machine learning community, that simplifies molecular processing and featurization workflows.
Joined January 2021
- Tweets142
- Following506
- Followers919
- Likes442
Pinned Tweet
Introducing Medchem, an open source Python library for molecular filtering and prioritization.
It includes hundreds of molecular filters, alerts, and rules, both established and novel.
Read the blog by @HadiM_ for more details: portal.valencelabs.com/blogs…
datamol.io retweeted
Excited to introduce the first steering committee (SC) from Polaris! This group of industry experts is focused on small-molecule, predictive modelling tasks and is collaborating to develop guidelines for benchmarking best practices.
At Polaris, our mission is to bring innovators and practitioners closer together to develop methods that matter.
The first SC publication in @NatMachIntell outlines the common challenges in benchmarking and serves as a call to action for the community emphasizing the importance of cross-industry collaboration. Next, we’ll be releasing a pre-print on method comparison, providing guidance on comparison protocols and domain-appropriate performance metrics to ensure reproducibility in real-world settings. (1/6) 🧵 👇
Read the correspondence letter: rdcu.be/dVZHz
Read the announcement: polarishub.io/blog/introduci…
datamol.io retweeted
1/ 🚀Today, we’re excited to launch Polaris! 🚀
Polaris is a platform where the ML community working on drug discovery problems can easily share and access datasets and benchmarks.
Get started with just a few lines of code: polarishub.io/
Spotted some molfeat users at the @Polaris_HQ hackathon 👀
They're searching for quick and easy ways to test different molecular featurizers.
molfeat.datamol.io/featurize…
datamol.io retweeted
🧵1/6 We're so excited to announce the inaugural machine learning for drug discovery summer school!
🏫 What: Lectures from Yoshua Bengio, @DrAnneCarpenter, @tiwarylab, @rbhar90, and more.
📍Where: @Mila_Quebec
📅 When: June 12th - 21st
Learn more here: portal.ml4dd.com/
datamol.io retweeted
In the latest blog on Portal, @austinjtripp explores the use of genetic algorithms as strong baselines for moelcule generation.
He also presents mol_ga, a simple, lightweight python package for genetic algorithms on molecules.
Read more:
portal.valencelabs.com/blogs…
datamol.io retweeted
A companion piece by @HWaymentSteele to the @Nature paper "Predicting multiple conformations via sequence clustering and AlphaFold2"
Read the blog on Portal: portal.valencelabs.com/blogs…
Catch @ENoutahi @craigmichaelm @TOSSOUPrudencio @jonathanlimsc at #NeurIPS tomorrow!
They'll be presenting the SAFE paper at two workshops between 12:00 and 2:30 CST.
See below for more details.👇
1⃣AI for Accelerated Materials Design
Where: Room 228 -230
When: Poster session from 12:00 - 2:00 pm CST on Friday, December 15th
sites.google.com/view/ai4mat…
2⃣ New Frontiers of AI for Drug Discovery and Development
Where: Room 242
When: Poster session from 1:20 - 2:25 pm CST on Friday, December 15th
ai4d3.github.io/schedule.htm…
datamol.io retweeted
Game changer for cheminformatic analysis! Thank you to the developers.
Introducing Medchem, an open source Python library for molecular filtering and prioritization.
It includes hundreds of molecular filters, alerts, and rules, both established and novel.
Read the blog by @HadiM_ for more details: portal.valencelabs.com/blogs…
datamol.io retweeted
One of the nice things about Medchem is that it's designed for all stages of drug discovery, with a very intuitive API. Please check out the tutorials! #cheminfo
Introducing Medchem, an open source Python library for molecular filtering and prioritization.
It includes hundreds of molecular filters, alerts, and rules, both established and novel.
Read the blog by @HadiM_ for more details: portal.valencelabs.com/blogs…
Medchem is the latest addition to the datamol.io ecosystem - an open source toolkit that simplifies molecular processing and featurization workflows for ML scientists in drug discovery.
Find us on GitHub:
github.com/datamol-io/medche…
Looking for events that bring the TechBio community together?
Check out the mixers happening at Oxford and Cambridge next week.
We’re hosting two TechBio mixer events next week! One co-hosted with @mmbronstein in Oxford, and one hosted on campus @cambridge_uni.
Join us for an evening of dinner, drinks, and discussions on accelerating AI with drug discovery.
RSVP through the event pages below.👇
datamol.io retweeted
Did you know that the legend of Icarus warns us of graph Transformers?👼
Last year, to organize the field of GNN research, I wrote the very popular maze-analogy:
teapawt.org/dom_beaini/status/1499…
It is now revamped into a blogpost, with nicer visuals and more SOTA
portal.valencelabs.com/blogs…
datamol.io retweeted
⏳1 month left until the deadline (10/13) to submit short papers to #MoML! Choose wisely & you may win the @octavianEganea Prize for Best Paper! Winners will give an oral presentation on their award-winning paper to attendees! View submission guidelines: moml.mit.edu/submit
ALT Graphic that reads "MoML Molecular Machine Learning Conference Wednesday, November 8, 2023 Koch Institute @ MIT"
datamol.io retweeted
(7/8) In our paper, we propose a novel protocol for designing representative test sets to narrow the validation-deployment gap.
We also investigate the impact of model design and selection tools.
Read the blog to learn more: m2d2.io/blog/posts/closing-t…
datamol.io retweeted
(1/8) We propose a rigorous framework for investigating Molecular Out-of-Distribution (MOOD) performance in real-world applications of molecular modeling.
It’s time to close the validation-deployment gap! 🎯
Paper: chemrxiv.org/engage/chemrxiv…
Experiments: github.com/valence-labs/mood…
datamol.io retweeted
Here's a quick demo of the nifty new circle_grid Feature in the open source @datamol_io library.
gist.github.com/PatWalters/e…
datamol.io retweeted
The latest Practical Cheminformatics post (with code) presents an interactive tool for exploring structural alerts. This post also shows off the new " lasso_highlight_image" capability in the awesome datamol package.
practicalcheminformatics.blo…