Directed evolution is key for unlocking new protein function But is difficult and time consuming So how can we accelerate protein design by 10-100x? With AI! Now introducing EVOLVEpro, an LLM-based model for evolving proteins rapidly and efficiently biorxiv.org/content/10.110…

A small step for a hobby logic designer, but a giant leap for Tiny Tapeout. The first official RISC-V uLinux ASIC, yes, ASIC, you heard that right, is operational and functional. Just dabbling in chip design as a hobbyist. Haha, what an awesome achievement! Thanx to Matthew Venn

🤣🤣🤣🤣

Active Learning-Assisted Directed Evolution - Combine Directed Evolution (DE) with Active Learning and Bayesian Optimization - Test optimal workflow configurations using different encoding methods (e.g., one-hot, ESM2), models (e.g., Gaussian processes, deep kernel Gaussian

🙌🧬It’s official: the first TCR gene therapy for the treatment of cancer received U.S. FDA approval this evening. A milestone event for the oncology community and the 2nd cell therapy approved for solid cancers! Adaptimmune #Tcellpower adaptimmune.com/investors-and-…

A visitor at the Guggenheim Museum took off a shoe and left it in the exhibition area. Other visitors then lined up to take photos and admire 📹 smith_tok

Alejandra Caraballo This problem is much bigger than just Grok! My Apple ][ computer often created harmful content like this. If you typed PRINT “YOU SHOULD EAT ROCKS”, the computer would advise you to eat rocks, which is dangerous from a culinary perspective.

Introducing 𝐇𝐞𝐫𝐦𝐞𝐬 𝟑: The latest version in our Hermes series, a generalist language model 𝐚𝐥𝐢𝐠𝐧𝐞𝐝 𝐭𝐨 𝐲𝐨𝐮. nousresearch.com/hermes3/ Hermes 3 is available in 3 sizes, 8, 70, and 405B parameters. Hermes has improvements across the board, but with particular

MarkovJunior is a probabilistic programming language where programs are combinations of rewrite rules and inference is performed via constraint propagation github.com/mxgmn/MarkovJu…

Ever wanted to use Python and recreate the first Monte Carlo simulations that were made on an IBM 701 in the 50s? That's just 1 of the goal of "Learn molecular simulations with Python". Here, the EoS of argon is computed and compared to experiments: mdcourse.github.io

Fine-tuning protein language models boosts predictions across diverse tasks | Nature Communications - Finetune pLMs (ESM2, ProtT5, Ankh) on different tasks (GB1, GFP, AAV, Location, Meltome, Stability, Disorder Prediction, and Secondary Structure Prediction) - Explore various PEFT

Can tumours be described as complex ecological systems? What is the mathematical description of their dynamics and treatments? Check our iScience journal paper with Guim Aguadé-Gorgorió and Sandy Anderson in cell.com/iscience/fullt…

Tanishq Mathew Abraham, Ph.D. Martin Steinegger 🇺🇦 We fully open sourced AlphaFold3’s model today under an Apache 2.0, and find a few things in the paper that could really mess up the training. Check it out here: github.com/Ligo-Bioscienc…

And this is why code should always be published with papers... This group made an attempt to reproduce AlphaFold3 and found a number of potential issues in the published pseudo-code. See exciting 🧵 👇

4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment 1. This paper introduces a novel 4D diffusion model for dynamic protein structure prediction, focusing on both backbone and side-chain motions, addressing the limitations of static

Target-conditioned diffusion generates potent TNFR superfamily antagonists and agonists Institute for Protein Design 🚀New preprints from David Baker!🚀 1. A groundbreaking approach to protein design! The study demonstrates how target-conditioned diffusion generates high-affinity binders

I take back what I said, the latest Baker lab paper achieves picomolar affinity with two rounds of design, 96 sequences expressed each round.

A reminder that proteins are highly dynamic molecules. ◼ We have made progress in measuring & predicting static protein structures, but the dynamics that animate life remain challenging to measure & model.

Stephen Mansour is now presenting 'Taming Regression using APL' at #Dyalog24. We are learning how Dyalog APL simplifies linear, multiple, and non-linear regression using namespaces and defined operators. #APL #DataScience #LinearRegression #Math #Maths