🌆 M2D2 Community Round-Up #3: September 2022
Hi everyone 👋
Welcome to the third issue of the Molecular Modelling and Drug Discovery (M2D2) community newsletter! Before we dive into this month’s newsletter, we have a few exciting announcements to share:
📣 We are welcoming Prof. Jian Tang as a keynote speaker to talk about graph representation learning and geometric deep learning for drug discovery on October 4th at 11 am ET!
🎉 This month, we reached 500 members on our Slack! Thank you all for making this community what it is, we're looking forward to some of the discussions and collaborations that will come out of this.
🏁 Congrats to everyone who submitted something for ICLR! Share your paper submissions with us by replying to the newsletter and we might feature them in the next issue 👀
If you enjoy this newsletter, we’d appreciate it if you could forward it to some of your friends 🙏!
Let’s jump right in! 👇
🧵 Tweets of the Month
Here are some of the community’s favorite tweets of the month. Do you have any specific opinions on these threads? Agree or disagree?
Join our Slack community to discuss these topics further!
Can we establish a foundation for understanding which AI methods are most suitable for therapeutic sciences?
What's the best way of capturing dynamic protein-ligand complexes?
GNNs for molecular property prediction from 3D structures, should we use pre-training?
📚 Community Reads
Robust deep learning–based protein sequence design using ProteinMPNN
Benchmarking AlphaFold-enabled molecular docking predictions for antibiotic discovery
Probabilistic Generative Transformer Language Models for Generative Design of Molecules
🔦 Monthly Spotlight: Tools + Shortcuts
This month, we are bringing Datamol back into the spotlight. After re-vamping some of the tutorials on molecular pre-processing, clustering, conformer generation and more, they have been well packaged into Tweet threads!
Check their most recent step-by-step tutorial on clustering and send us a reply to let us know if this was useful!
🎭 M2D2 Member Spotlight
This section is dedicated towards helping you learn more about the people who are a part of the M2D2 community. If you want to be featured, please message Nikhil Shenoy on Slack!
Sang Truong
About: currently a second-year Computer Science Ph.D. student at Stanford University
Research areas: he works on probabilistic and geometric deep learning with various applications in chemistry, material sciences, and social sciences
What’s new: he recently got a fellowship to study Human-centered AI. Ask him about it on Slack
Looking for: collaborators if there are overlapping interests in research areas
Yunchao (Lance) Liu
About: currently a Ph.D. candidate in Computer Science at Vanderbilt University under the department of Computer Science
Research area: he works on geometric deep learning, self-supervised learning, small molecule drug discovery and generative models
What’s new: his new preprint: "Interpretable Chirality-Aware Graph Neural Network for Quantitative Structure-Activity Relationship Modeling in Drug Discovery" was released recently and the accompanying blog is also available on TDS
Looking for: research collaborators in geometric deep learning and small molecule drug discovery
🗃️ In Case You Missed It
Catch up on this month's M2D2 talks here:
Machine Learning for Scientific Discovery - presented by Yoshua Bengio
Bridging Computation and Experimentation with Evidential Deep Learning - presented by Ava Amini
Kernel Methods for Predicting Yields of Chemical Reactions - presented by Jonathan Hirst
M2D2: Molecular Modeling and Drug Discovery — www.youtube.com Share your videos with friends, family, and the world
⭐ Contributors
Thank you to our newsletter lead for the Fall, Nikhil Shenoy, for putting together this month's edition of the newsletter. If you’d like to get involved in helping craft future issues, please hit reply or message us on Slack!
The M2D2 community lives on Slack with 500+ students, professors, researchers and engineers. We aim to demystify the field of AI for drug discovery and merge the vibrant AI & drug discovery communities together to spark new perspectives, provoke discussions, and offer a safe space to share new ideas.
See you next month! 👋