Yu Zhang
@yu-zh.bsky.social
Postdoctoral Fellow, Collins Lab @ Broad Institute and Wyss Institute at Harvard and MIT | AI in drug discovery
Reposted by Yu Zhang
A study in Nature Communications used AI to mine global venom proteomes and discovered novel peptides with antimicrobial activity. Several candidates showed efficacy against drug-resistant bacteria in laboratory and animal tests. go.nature.com/4f0zYb4 #medsky 🧪
July 26, 2025 at 1:16 AM
A study in Nature Communications used AI to mine global venom proteomes and discovered novel peptides with antimicrobial activity. Several candidates showed efficacy against drug-resistant bacteria in laboratory and animal tests. go.nature.com/4f0zYb4 #medsky 🧪
Reposted by Yu Zhang
The Open Molecules 2025 dataset is out! With >100M gold-standard ωB97M-V/def2-TZVPD calcs of biomolecules, electrolytes, metal complexes, and small molecules, OMol is by far the largest, most diverse, and highest quality molecular DFT dataset for training MLIPs ever made 1/N
May 14, 2025 at 8:52 PM
The Open Molecules 2025 dataset is out! With >100M gold-standard ωB97M-V/def2-TZVPD calcs of biomolecules, electrolytes, metal complexes, and small molecules, OMol is by far the largest, most diverse, and highest quality molecular DFT dataset for training MLIPs ever made 1/N
Reposted by Yu Zhang
Interesting work on a computational approach to develop orthogonal aminoacyl-tRNA synthetase/tRNA pairs in E. coli www.nature.com/articles/s41...
Automated orthogonal tRNA generation - Nature Chemical Biology
Genetic code expansion and reprogramming require orthogonal tRNAs. Methods have now been developed for the automated generation of chimeric orthogonal tRNAs and discovery of their cognate synthetases....
www.nature.com
December 20, 2024 at 2:04 PM
Interesting work on a computational approach to develop orthogonal aminoacyl-tRNA synthetase/tRNA pairs in E. coli www.nature.com/articles/s41...
Reposted by Yu Zhang
1/n New paper alert 🚨 We're thrilled to share our just published paper in #CancerCell
Do you ever wonder how the #TME in #HGSC changes during chemotherapy? Check it here: www.sciencedirect.com/science/arti... and let’s dive into the highlights together #spatialbiology #ovariancancer #cancerresarch
Do you ever wonder how the #TME in #HGSC changes during chemotherapy? Check it here: www.sciencedirect.com/science/arti... and let’s dive into the highlights together #spatialbiology #ovariancancer #cancerresarch
Chemotherapy induces myeloid-driven spatially confined T cell exhaustion in ovarian cancer
Anti-tumor immunity is crucial for high-grade serous ovarian cancer (HGSC) prognosis, yet its adaptation upon standard chemotherapy remains poorly und…
www.sciencedirect.com
December 10, 2024 at 11:48 AM
1/n New paper alert 🚨 We're thrilled to share our just published paper in #CancerCell
Do you ever wonder how the #TME in #HGSC changes during chemotherapy? Check it here: www.sciencedirect.com/science/arti... and let’s dive into the highlights together #spatialbiology #ovariancancer #cancerresarch
Do you ever wonder how the #TME in #HGSC changes during chemotherapy? Check it here: www.sciencedirect.com/science/arti... and let’s dive into the highlights together #spatialbiology #ovariancancer #cancerresarch
Reposted by Yu Zhang
Excellent new paper (with code) by my former colleagues Steven Kearnes and Patrick Riley describing a procedure for associating confidence levels with regression model predictions in drug discovery. pubs.acs.org/doi/10.1021/...
Ordinal Confidence Level Assignments for Regression Model Predictions
We present a simple method for assigning accurate confidence levels to molecular property predictions from regression models. These confidence levels are easy to interpret and useful for making decisi...
pubs.acs.org
December 10, 2024 at 1:02 PM
Excellent new paper (with code) by my former colleagues Steven Kearnes and Patrick Riley describing a procedure for associating confidence levels with regression model predictions in drug discovery. pubs.acs.org/doi/10.1021/...
Reposted by Yu Zhang
Cell Painting: a decade of discovery and innovation in cellular imaging
"Cell Painting has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects."
www.nature.com/articles/s41...
"Cell Painting has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects."
www.nature.com/articles/s41...
Cell Painting: a decade of discovery and innovation in cellular imaging - Nature Methods
This Review synthesizes the literature from over 10 years of Cell Painting for image-based profiling and highlights how advances in this technology enable new biological discovery of cellular phenotyp...
www.nature.com
December 8, 2024 at 2:53 PM
Cell Painting: a decade of discovery and innovation in cellular imaging
"Cell Painting has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects."
www.nature.com/articles/s41...
"Cell Painting has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects."
www.nature.com/articles/s41...
Reposted by Yu Zhang
Thanks! It's rdEditor, the Python and RDKit based molecular editor, that's inside to deliver selection and editing capabilities: github.com/EBjerrum/rde...
GitHub - EBjerrum/rdeditor: Simple RDKit molecule editor GUI using PySide
Simple RDKit molecule editor GUI using PySide. Contribute to EBjerrum/rdeditor development by creating an account on GitHub.
github.com
November 28, 2024 at 2:40 PM
Thanks! It's rdEditor, the Python and RDKit based molecular editor, that's inside to deliver selection and editing capabilities: github.com/EBjerrum/rde...
Reposted by Yu Zhang
E coli are red
S aureus are blue
Hans Christian Gram
Stained them for you
S aureus are blue
Hans Christian Gram
Stained them for you
November 27, 2024 at 2:16 AM
E coli are red
S aureus are blue
Hans Christian Gram
Stained them for you
S aureus are blue
Hans Christian Gram
Stained them for you
Reposted by Yu Zhang
The complete guide for transfer learning with the protein language model ESM-2.
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
Scaling Down for Efficiency: Medium-Sized Transformer Models for Protein Sequence Transfer Learning
Protein language models such as the transformer-based Evolutionary Scale Modeling 2 (ESM2) can offer deep insights into evolutionary and structural properties of proteins. While larger models, such as...
www.biorxiv.org
November 25, 2024 at 2:50 AM
The complete guide for transfer learning with the protein language model ESM-2.
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
Reposted by Yu Zhang
"Productive stupidity" is such a useful concept! The best thing I learned in my (literary) PhD is to say "I don't know." That's the moment you can listen, explore, find out something new.
I often say my PhD has gone unused because I'm not a professor, but in truth I use it every day. It's a gift.
I often say my PhD has gone unused because I'm not a professor, but in truth I use it every day. It's a gift.
Three must read papers for PhD students. #scisky #PhD #science #research #academicsky
1. The importance of stupidity in scientific research
Open Access
journals.biologists.com/jcs/article/...
1. The importance of stupidity in scientific research
Open Access
journals.biologists.com/jcs/article/...
November 26, 2024 at 11:31 AM
"Productive stupidity" is such a useful concept! The best thing I learned in my (literary) PhD is to say "I don't know." That's the moment you can listen, explore, find out something new.
I often say my PhD has gone unused because I'm not a professor, but in truth I use it every day. It's a gift.
I often say my PhD has gone unused because I'm not a professor, but in truth I use it every day. It's a gift.
Reposted by Yu Zhang
Review: The lives of cells, recorded https://www.nature.com/articles/s41576-024-00788-w (read free: https://rdcu.be/d1s8d) 🧬🖥️🧪
November 26, 2024 at 8:14 PM
Review: The lives of cells, recorded https://www.nature.com/articles/s41576-024-00788-w (read free: https://rdcu.be/d1s8d) 🧬🖥️🧪
Reposted by Yu Zhang
A project 10 years in the making w/ Terry Sejnowski, led by @philosophaki.bsky.social
Insights into ryanodine receptor activation & calcium-induced Ca2+ release from a stochastic explicit-particle 3D simulation of cardiac dyad w/ realistic geometry (from TEM)
www.sciencedirect.com/science/arti...
Insights into ryanodine receptor activation & calcium-induced Ca2+ release from a stochastic explicit-particle 3D simulation of cardiac dyad w/ realistic geometry (from TEM)
www.sciencedirect.com/science/arti...
November 26, 2024 at 2:01 PM
A project 10 years in the making w/ Terry Sejnowski, led by @philosophaki.bsky.social
Insights into ryanodine receptor activation & calcium-induced Ca2+ release from a stochastic explicit-particle 3D simulation of cardiac dyad w/ realistic geometry (from TEM)
www.sciencedirect.com/science/arti...
Insights into ryanodine receptor activation & calcium-induced Ca2+ release from a stochastic explicit-particle 3D simulation of cardiac dyad w/ realistic geometry (from TEM)
www.sciencedirect.com/science/arti...
Reposted by Yu Zhang
A vertical takeoff of life science with #AI LLLMs.
Publication of 10 new foundation models of Proteins, DNA, RNA, methylation, cells, and interactions, evolution, and design in the past couple of weeks!
Unprecedented progress, reviewed in the new Ground Truths
erictopol.substack.com/p/learning-t...
Publication of 10 new foundation models of Proteins, DNA, RNA, methylation, cells, and interactions, evolution, and design in the past couple of weeks!
Unprecedented progress, reviewed in the new Ground Truths
erictopol.substack.com/p/learning-t...
November 24, 2024 at 6:12 PM
A vertical takeoff of life science with #AI LLLMs.
Publication of 10 new foundation models of Proteins, DNA, RNA, methylation, cells, and interactions, evolution, and design in the past couple of weeks!
Unprecedented progress, reviewed in the new Ground Truths
erictopol.substack.com/p/learning-t...
Publication of 10 new foundation models of Proteins, DNA, RNA, methylation, cells, and interactions, evolution, and design in the past couple of weeks!
Unprecedented progress, reviewed in the new Ground Truths
erictopol.substack.com/p/learning-t...
Reposted by Yu Zhang
MCGAE: unraveling tumor invasion through integrated multimodal spatial transcriptomics #SingleCell 🧬🖥️ academic.oup.com/bib/article/...
MCGAE: unraveling tumor invasion through integrated multimodal spatial transcriptomics
Abstract. Spatially Resolved Transcriptomics (SRT) serves as a cornerstone in biomedical research, revealing the heterogeneity of tissue microenvironments.
academic.oup.com
November 23, 2024 at 10:04 AM
MCGAE: unraveling tumor invasion through integrated multimodal spatial transcriptomics #SingleCell 🧬🖥️ academic.oup.com/bib/article/...
Reposted by Yu Zhang
Our recent report on #AntimicrobialResistance & the need for improved surveillance, testing, infection control, #antibiotic stewardship, funding & global commitments for #AMR solutions in humanitarian settings. #WAAW2024 #MedSky
msfaccess.org/broken-lens-...
msfaccess.org/broken-lens-...
The Broken Lens: Antimicrobial Resistance in Humanitarian Settings
MSF report on treating AMR in people caught in challenging humanitarian settings
msfaccess.org
November 20, 2024 at 2:35 PM
Our recent report on #AntimicrobialResistance & the need for improved surveillance, testing, infection control, #antibiotic stewardship, funding & global commitments for #AMR solutions in humanitarian settings. #WAAW2024 #MedSky
msfaccess.org/broken-lens-...
msfaccess.org/broken-lens-...
Reposted by Yu Zhang
Over 100 postdocs are registered for tomorrow's Postdoc Night Science Boston session! I can't wait to help other places get their own club started.
November 21, 2024 at 12:54 AM
Over 100 postdocs are registered for tomorrow's Postdoc Night Science Boston session! I can't wait to help other places get their own club started.
Reposted by Yu Zhang
Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
Learning on compressed molecular representations
Last year, a preprint gained notoriety, proposing that a k-nearest neighbour classifier is able to outperform large-language models using compressed text as input and normalised compression distance (...
pubs.rsc.org
November 21, 2024 at 12:58 PM
Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
Reposted by Yu Zhang
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
www.owlposting.com/p/why-recurs...
After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read)
first journalism-y piece!
www.owlposting.com/p/why-recurs...
After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read)
first journalism-y piece!
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
5.7k words, 26 minutes reading time
www.owlposting.com
November 8, 2024 at 3:59 PM
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
www.owlposting.com/p/why-recurs...
After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read)
first journalism-y piece!
www.owlposting.com/p/why-recurs...
After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read)
first journalism-y piece!
Reposted by Yu Zhang
There’s a new Practical Cheminformatics post, “Some Thoughts on Dataset Splitting,” (with code and a robot cartoon) at practicalcheminformatics.blogspot.com/2024/11/some... .
November 18, 2024 at 1:34 PM
There’s a new Practical Cheminformatics post, “Some Thoughts on Dataset Splitting,” (with code and a robot cartoon) at practicalcheminformatics.blogspot.com/2024/11/some... .
Reposted by Yu Zhang
If you're building AI models for drug discovery, you should check out the newly open-source #BioNeMo Framework:
code: github.com/NVIDIA/bione...
paper: arxiv.org/abs/2411.10548
docs: docs.nvidia.com/bionemo-fram...
explainer: t.co/7MOamSChGN
code: github.com/NVIDIA/bione...
paper: arxiv.org/abs/2411.10548
docs: docs.nvidia.com/bionemo-fram...
explainer: t.co/7MOamSChGN
GitHub - NVIDIA/bionemo-framework: BioNeMo Framework: For building and adapting AI models in drug discovery at scale
BioNeMo Framework: For building and adapting AI models in drug discovery at scale - NVIDIA/bionemo-framework
github.com
November 19, 2024 at 2:29 PM
If you're building AI models for drug discovery, you should check out the newly open-source #BioNeMo Framework:
code: github.com/NVIDIA/bione...
paper: arxiv.org/abs/2411.10548
docs: docs.nvidia.com/bionemo-fram...
explainer: t.co/7MOamSChGN
code: github.com/NVIDIA/bione...
paper: arxiv.org/abs/2411.10548
docs: docs.nvidia.com/bionemo-fram...
explainer: t.co/7MOamSChGN