Su Datt Lam

Trained in #AMR wet-lab, doing #AMR genome sequencing, but wrangling with bioinformatics coding which is never really your thing? Fret not, AMRColab is here for you! 1) We compiled #AMR analysis (AMRFinderPlus, ResFinder), comparison (hAMRonization) into a GoogleColab - 1/n

Best Practices for Using AI When Writing Scientific Manuscripts (1/3)

Have you ever wanted to design protein binders with ease? Today we present 𝑩𝒊𝒏𝒅𝑪𝒓𝒂𝒇𝒕, a user-friendly and open-source pipeline that allows to anyone to create protein binders de novo with high experimental success rates. @befcorreia @sokrypton biorxiv.org/content/10.110…

Modeling protein-small molecule conformational ensembles with ChemNet @UWproteindesign 🚀 New preprint from David Baker!🚀 - ChemNet is a breakthrough deep learning model that accurately predicts the conformational ensembles of small molecules in complex with proteins. - It outperforms existing methods like AlphaFold and RoseTTAFold by focusing on atomic-level accuracy, generating ensembles rather than single static structures. - The key innovation is ChemNet’s stochastic nature, which allows it to model conformational heterogeneity, making it ideal for protein-small molecule docking. - ChemNet generates diverse structures based on random initializations, providing deep insights into the flexibility of molecules at binding sites. - The model is designed to assess the pre-organization of catalytic sites in enzymes, which is crucial for improving enzyme activity. - In enzyme design applications, ChemNet-guided designs have achieved impressive success rates, including a retroaldolase with a kcat/KM of 11,000 M-1min-1, the highest pre-deep learning design rate for this reaction. - The ability to rapidly generate conformational ensembles makes ChemNet a valuable tool for drug discovery and computational enzyme design. - This system provides a faster, more generalizable alternative to computationally expensive methods like molecular dynamics simulations. - ChemNet is expected to have broad applications in predicting protein-small molecule interactions, and guiding de novo design of enzymes and drug binders. @ikalvet @gyurielee @alchemist_an @JustasDauparas 📜Paper: biorxiv.org/content/10.110…

Automated molecular optimization of a BRD4 inhibitor using #AlphaFold predicted structure with our new #GenerativeAI drug design method, DrugHIVE. paper: pubs.acs.org/doi/10.1021/ac… GitHub: github.com/jssweller/Drug… @RemoRohs lab @qcb_usc. @JCIM_JCTC. #compchem #machinelearning

#AlphaFold3 is out, and good gravy is it a read. Congrats to the @GoogleDeepMind @IsomorphicLabs folks, some seriously compelling results especially for antibody-antigen complex predictions. Has got me thinking a lot!

AF3 server is LIVE! Just tried predicting complex with almost 5K amino acids. TIP: you need to click "continue with google" to access the server (otherwise the "server" is grayed out). alphafoldserver.com

Thrilled to announce AlphaFold 3 which can predict the structures and interactions of nearly all of life’s molecules with state-of-the-art accuracy including proteins, DNA and RNA. Biology is a complex dynamical system so modeling interactions is crucial blog.google/technology/ai/…

Ligand docking is a key component in comp drug discovery. AF-latest outperforms classical systems like AutoDock Vina on the PoseBusters benchmark. This is despite baselines having access to the ground-truth protein structure information that AlphaFold-latest doesn’t get. 4/7

Are there any privileged routes of acquisition of #driver alterations in #cancer? Can they be used to #predict the outcome of treatments at diagnosis? In our latest work, out in @NatureComms, we show that such routes do exist for most cancer types! nature.com/articles/s4146… 1/6

Want to know what a single-residue substitution does to your favorite protein? Together with @TobiasRaisch we wrote a tool to easily visualize pathogenicity scores from the @GoogleDeepMind #AlphaMissense paper: github.com/MPI-Dortmund/p… We hope you find it interesting :-)

ChatGPT can now browse the internet to provide you with current and authoritative information, complete with direct links to sources. It is no longer limited to data before September 2021.

The human genome is gradually unravelling its secrets 🎁 AlphaMissense model @ScienceMagazine: one more path lit up by deep learning in exploring the code of life 🧬 We now know with high confidence if 89% of ALL missense variants are benign or pathogenic Key contributions🧵🧵

PICKLUSTER: A protein-interface clustering and analysis plug-in for UCSF ChimeraX biorxiv.org/cgi/content/sh… #biorxiv_bioinfo

What is an exon??? New paper w/ @ewjwallace and @RNA_julie in @CellGenomics : cell.com/cell-genomics/… Cue 🧵1/8

And it's a wrap!! Thank you for coming! 😍🌷 Many thanks to @sudattlam @angmiayang @sndigregorio zetty and Prof Sheila Nathan, @griffiemma @FinlayM @pha4ge

And, hAMRonization 2.0 workshop is happening now 😃 @sudattlam @angmiayang @sndigregorio @griffiemma @FinlayM @pha4ge Zetty giving opening remarks:

If you are looking for antibiotic summary cards:

MIT Intro to Deep Learning - 2023 Lectures are Live MIT Intro to Deep Learning is one of few concise deep learning courses on the web. The course quickly takes you to the foundations of deep learning, neural net architectures, and applications of DL. introtodeeplearning.com

In a single long MD simulation we saw a loop change from a closed (red) to open (green) state, with many short "false openings" (yellow). In this pre-print, we characterize the loop residues that act as a conformational switch, and see that the motif occurs in other proteins too