🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🎉 Exciting News! 🎉 We are thrilled to announce that Dr. Suphavilai Chayaporn has been awarded the GIS Innovation Fellow FY24! 🏆 Dr. Suphavilai is spearheading an innovative project at GIS, aiming to develop clinical-grade metagenomic diagnostic systems for effective

🎓PhD Opportunity: AI x Genomics at A*STAR Genome Institute of Singapore (A*STAR GIS) 🧬🤖 Are you passionate about pushing the boundaries of science with cutting-edge technology? Join us for a transformative PhD journey at the intersection of Artificial Intelligence and

biorxiv.org/content/10.110…

ChatGPT now can analyze, manipulate, and visualize molecules and chemical information via the RDKit library. Useful for scientific work across health, biology, and chemistry.

stTrace: Detecting Spatial-Temporal Domains from spatial transcriptome to Trace Developmental Path biorxiv.org/content/10.110… #biorxiv_bioinfo

Announcing myloasm, a new long-read (ONT R10/PacBio) metagenome assembler. With Heng Li. myloasm-docs.github.io

Our most recent work on sphingolipids is now published in Cell Host & Microbe! cell.com/cell-host-micr… Here we discovered a mechanism by which bacterial sphingolipids in outer membrane vesicles promote anti-inflammatory responses in immune cells, through activation of the mevalonate

Residue conservation and solvent accessibility are (almost) all you need for predicting mutational effects in proteins １．A simple model called RSALOR achieves performance on par with or better than most state-of-the-art tools in predicting the effects of mutations on proteins

An atlas of transcription factor-driven gene programs across human cells Teichlab biorxiv.org/content/10.110…

MolTextNet: A Two-Million Molecule-Text Dataset for Multimodal Molecular Learning １．MolTextNet introduces a dataset of 2.5 million molecule-text pairs, designed to support large-scale multimodal learning between molecular graphs and natural language. Each entry provides

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Congratulations to Lanyue Zhang for leading this effort in the context of her PhD studies and thanks to all co-authors. 🔗link to preprint: researchsquare.com/article/rs-683…

All-Atom Protein Sequence Design using Discrete Diffusion Models １．This paper presents the first application of discrete diffusion models to protein design using an all-atom representation. Instead of relying on the standard 20 amino acids, the authors use SELFIES to model

Whole-Genome Phenotype Prediction with Machine Learning: Open Problems in Bacterial Genomics academic.oup.com/bioinformatics… 🧬🖥️🧪 gitlab.com/leoisl/dbgwas

(1/n) Sampling from the Boltzmann density better than Molecular Dynamics (MD)? It is possible with PITA 🫓 Progressive Inference Time Annealing! A spotlight GenBio Workshop @ ICML25 of ICML Conference 2025! PITA learns from "hot," easy-to-explore molecular states 🔥 and then cleverly "cools"

I often post how studying the effects of genetic variation on gene expression can reveal disease mechanisms & novel drug targets🧬-->💊 Our paper at AJHG links disease GWASs with single-cell gene expression to uncover cell-specific drivers of atherosclerosis👇[1/9]

Very excited to share our latest work in Nature Genetics w/ Christopher Smillie’s lab: a spatial transcriptomics atlas of stricturing #Crohns disease that offers new insights into mechanisms driving fibrotic complications in chronic gut inflammation...(cont.) nature.com/articles/s4158…

MegaFold: System-Level Optimizations for Accelerating Protein Structure Prediction Models １．MegaFold targets AlphaFold3’s key training bottlenecks and delivers substantial memory savings and speedups, enabling training on 1.35× longer protein sequences without out-of-memory

Eyebrows raised when I see Xanthomonadales, Burkholderia...

Did a quick experiment with the data from PRJNA1101467. I ran Sylph on the reads and was ONLY able to detect bacterium from SRR32957579 (positive control - Stenotrophomonas maltophilia detected in the 4 isolate samples SRR32957488-SRR32957579).