Oh-hyeon Choung
banner
ohhyeon5.bsky.social
Oh-hyeon Choung
@ohhyeon5.bsky.social
ML/AI in biotech
Reposted by Oh-hyeon Choung
Tonight I'm taking the train to Prague for the European edition of the 2025 #RDKit UGM.
I'm really looking forward to meeting a bunch of the community there!
We don't have space for any last-minute in-person registrations, but info on joining the live streams is here:
github.com/rdkit/UGM_20...
GitHub - rdkit/UGM_2025: 2025 RDKit UGM
2025 RDKit UGM. Contribute to rdkit/UGM_2025 development by creating an account on GitHub.
github.com
September 8, 2025 at 2:23 PM
Reposted by Oh-hyeon Choung
This is my second blog post this year! We wanted random art on our walls daily, so we built privacy-focused e-ink picture frames powered by ESP32. Everything is local; no internet.

charnley.github.io/blog/2025/04...

#eink #esp32 #homeassistant #ai
Building Your Own AI & E-Ink Powered Art Gallery: A Local DIY Guide
This blog will contain technical write-ups with very varying contents. We will try to use tags/category as much as possible to avoid mixing everything up. Usually content is about some github project ...
charnley.github.io
April 2, 2025 at 6:11 PM
Reposted by Oh-hyeon Choung
The new #RDKit blog post is an update of an older tutorial on displaying fingerprint bits.
greglandrum.github.io/rdkit-blog/p...
RDKit blog - Rendering fingerprint bits
Visualizing the meaning of fingerprint bits
greglandrum.github.io
March 29, 2025 at 7:49 AM
Reposted by Oh-hyeon Choung
Check out our paper published in @chemicalscience.rsc.org - pubs.rsc.org/en/content/a...

(1) *General-purpose* generative model + retrosynthesis model = design molecules with optimized properties with an *explicit* predicted synthesis pathway

(1/2)
Directly optimizing for synthesizability in generative molecular design using retrosynthesis models - Chemical Science (RSC Publishing) DOI:10.1039/D5SC01476J
pubs.rsc.org
March 24, 2025 at 5:28 AM
Reposted by Oh-hyeon Choung
In a new Practical Cheminformatics post titled "Even More Thoughts on ML Method Comparisons," I share several plots that I find valuable for comparing machine learning methods.
practicalcheminformatics.blogspot.com/2025/03/even...
Even More Thoughts on ML Method Comparisons
Introduction A few things motivated this post.   Some recent discussions about the virtues of LightGBM vs XGBoost Posts on TabPFN by Jon...
practicalcheminformatics.blogspot.com
March 10, 2025 at 12:56 PM
Reposted by Oh-hyeon Choung
This week's #RDKit blog post shows how to use the built-in drawing code to create a more complex figure.

greglandrum.github.io/rdkit-blog/p...
Drawing on drawings – RDKit blog
Making more complex figures with the RDKit molecule drawing code.
greglandrum.github.io
March 7, 2025 at 10:02 AM
Reposted by Oh-hyeon Choung
My experience working remotely (I am lucky to be able to do that occasionally) made me re-evaluate my setup when traveling. Here are some notes on my setup. charnley.github.io/blog/2025/02... #remotework #digitalnomad #travel
Laptop Setup for Travel and Programming (#DigitalNomad)
Are you looking for a traveling office, working abroad, and digital nomad setup? As a weekend digital nomad, I have some recommendations for you.
charnley.github.io
February 23, 2025 at 4:06 PM
Reposted by Oh-hyeon Choung
Tiny TIL: I just figured out how to run pytest with a different Python version against my pyproject.toml/setup.py projects using uv run

uv run --python 3.12 --with '.[test]' pytest

til.simonwillison.net/pytest/pytes...
Running pytest against a specific Python version with uv run
While working on this issue I figured out a neat pattern for running the tests for my project locally against a specific Python version using uv run :
til.simonwillison.net
February 4, 2025 at 10:59 PM
Reposted by Oh-hyeon Choung
The new #RDKit blog post is another tutorial. This time it's about some advanced substructure search functionality.
greglandrum.github.io/rdkit-blog/p...
More on generalized substructure search – RDKit blog
Advanced substructure search features
greglandrum.github.io
February 8, 2025 at 7:45 AM
Reposted by Oh-hyeon Choung
Associate Professor or DTU Tenure Track Assistant Professor in Chemistry - DTU Chemistry 🇩🇰 efzu.fa.em2.oraclecloud.com/hcmUI/Candid... #compchem

Candidates working within automatization, .... and application of ML in chemistry are particularly encouraged to apply.
Associate Professor or DTU Tenure Track Assistant Professor in Chemistry - DTU Chemistry
The Technical University of Denmark (DTU) offers the opportunity to build a research group in advanced and applied chemistry at an internationally esteemed department with an excellent infrastructure.
efzu.fa.em2.oraclecloud.com
February 10, 2025 at 7:30 AM
Reposted by Oh-hyeon Choung
Our paper on computational design of chemically induced protein interactions is out in @natureportfolio.bsky.social. Big thanks to all co-authors, especially Anthony Marchand, Stephen Buckley and Bruno Correia!

t.co/vtYlhi8aQm
January 15, 2025 at 4:37 PM
Reposted by Oh-hyeon Choung
Over the past months, we've been exploring text2cypher agentic flows with @llamaindex.bsky.social . The result? A comprehensive repository featuring multiple @neo4j.bsky.social workflows, a benchmarking framework, and an web UI.

www.llamaindex.ai/blog/buildin...
January 15, 2025 at 6:38 PM
Reposted by Oh-hyeon Choung
📢 Paper + code release 📃💻

After 2 years of work, I'm excited to announce our newest paper, MatterGen, has been published in Nature!
www.nature.com/articles/s41...

We are also releasing all the training data, model weights, model code, and evaluation code on GitHub!
github.com/microsoft/ma...
January 16, 2025 at 10:15 AM
Reposted by Oh-hyeon Choung
I was asked to improve my documentation for my rmsd Python package, which sent me down a rabbit hole. I ended up finding an improvement to the way the package is doing Inertia alignment of the molecule and finding pretty ways in matplotlib to illustrate the concepts github.com/charnley/rmsd #chemsky
January 9, 2025 at 12:34 PM
Reposted by Oh-hyeon Choung
new preprint on chemical synthesis ML models

- showing how to combine multiple models in a principled way
- modern Transformers + GNN to featurize chemical reaction:
- new insights in where the models shine
+ bonus: find the quirky named reaction!

Feedback welcome!

arxiv.org/abs/2412.05269
Chimera: Accurate retrosynthesis prediction by ensembling models with diverse inductive biases
Planning and conducting chemical syntheses remains a major bottleneck in the discovery of functional small molecules, and prevents fully leveraging generative AI for molecular inverse design. While ea...
arxiv.org
December 9, 2024 at 2:19 AM
Reposted by Oh-hyeon Choung
I'm thrilled to announce a new preprint describing collaborative work with Ajay Jain and Ann Cleves Jain, "Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows".

arxiv.org/abs/2412.02889
Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows
The diffusion learning method, DiffDock, for docking small-molecule ligands into protein binding sites was recently introduced. Results included comparisons to more conventional docking approaches, wi...
arxiv.org
December 5, 2024 at 4:21 PM
Reposted by Oh-hyeon Choung
Reposted by Oh-hyeon Choung
Excited to present what we've been up to the last couple years. Introducing BioEmu, a Biomolecular Emulator of protein dynamics: www.biorxiv.org/content/10.1...
Scalable emulation of protein equilibrium ensembles with generative deep learning
Following the sequence and structure revolutions, predicting the dynamical mechanisms of proteins that implement biological function remains an outstanding scientific challenge. Several experimental t...
www.biorxiv.org
December 6, 2024 at 8:22 AM
Reposted by Oh-hyeon Choung
There's a new #RDKit blog post introducing some new functionality that I'm really excited about: doing efficient substructure and similarity searches in very large chemical libraries:
greglandrum.github.io/rdkit-blog/p...
#ChemSky
Introducing Synthon Searching – RDKit blog
Searching unreasonably large chemical spaces in reasonable amounts of time.
greglandrum.github.io
December 3, 2024 at 7:21 AM
Reposted by Oh-hyeon Choung
I finally got the time to clean up `qml`, and translated it to the new pip package `qmllib`, working with numpy2.0 with consistent argument and function naming github.com/qmlcode/qmllib
GitHub - qmlcode/qmllib: Quantum machine learning (QML) Core Fortran Functions
Quantum machine learning (QML) Core Fortran Functions - qmlcode/qmllib
github.com
November 17, 2024 at 12:44 PM
Reposted by Oh-hyeon Choung
We are hiring (resharing appreciated)!

Given recent successful grant applications (I got my SNSF Starting Grant 🚀), we are extending the LIAC team with multiple openings (PhD/postdoc) for 2025.

Apply now (deadline: December 20th) by filling in this form: forms.fillout.com/t/eq5ADAw3kkus.
#ChemSky
December 2, 2024 at 10:33 AM