🧬 Protein Engineering & Language

Context-dependent design of induced-fit enzymes using deep learning generates well-expressed, thermally stable and active enzymes
Lior Zimmerman, Noga Alon , Itay Levin , Anna Koganitsky , Nufar Shpigel , Chen Brestel , Gideon D. Lapidoth
PNAS, 5784 2024

We show how to design novel enzymes that have improved properties such as higher solubility, higher melting temperature and higher activity. We even show the ability to design non-natural enzymatic traits. Our system uses AI & computational biology tools. The research was conducted by the Enzymit team.

#protein_language #protein_engineering #science #paper #pnas #5784 #2024

SolvIT GitHub - Protein Solubility Prediction Deep Neural Network
Chen Brestel, Lior Zimmerman
GitHub, 5785 2024

We share our SolvIT tool which is a GNN (Graph Neural Network) model that predicts protein solubility in Escherichia coli and aid in enzyme design by prioritizing high-solubility candidates from large design sets. Research conducted during my tenure at Enzymit. Our small GNN achieves state-of-the-art performance that rivals much larger models. The approach is described in our PNAS paper. Welcome to enjoy it and reference this page.

#protein_engineering #solubility #gnn #code #github #5785 #2024

Context-dependent design of induced-fit enzymes using deep learning generates well-expressed, thermally stable and active enzymes Talk
Chen Brestel
MeDS Club 5785 2025
YouTube
Slides

We show how to design novel enzymes that have improved properties such as higher solubility, higher melting temperature and higher activity. We even show the ability to design non-natural enzymatic traits. Our system use AI & computational biology tools. Research conducted during my tenure at Enzymit.

#protein_language #protein_engineering #science #slides #talk #meds #5785 #2025

Context-dependent design of induced-fit enzymes using deep learning generates well-expressed, thermally stable and active enzymes Slides
Chen Brestel
ISRANALYTICA 5785 2025 Conference

We show how to design novel enzymes that have improved properties such as higher solubility, higher melting temperature and higher activity. We even show the ability to design non-natural enzymatic traits. Our system use AI & computational biology tools. Research conducted during my tenure at Enzymit.

#protein_language #protein_engineering #science #slides #talk #isranalytica #5785 #2025

מחשב, צור לי כבשה
Chen Brestel , Aviad Brestel
מדע גדול, בקטנה, 5784 2024

אנו מתארים את החידושים של השנים האחרונות ומציגים יכולת מלהיבה במיוחד ליצור חלבונים חדשניים ולפענח את המבנה התלת־ממדי ואת מאפייני הפעולה של חלבונים. בזכות חידושים אלו נוכל להאיץ משמעותית את שיפור עולמנו במגוון תחומים: ברפואה, בייצור המזון, באיכות הסביבה, בהפקת אנרגיה ועוד. התיאור מוצג בשפה בהירה ופשוטה השווה לכל נפש. מוזמנים להעשיר את ידיעתכם במדע פופולרי.

#protein_language #protein_engineering #popular_science #review #5783 #2023

Introducing TxGemma: Open models to improve therapeutics development
Shekoofeh Azizi
Google DeepMind
Blog , 5785 2025

TxGemma is a collection of open models designed to improve the efficiency of therapeutic development by leveraging the power of large language models. Building on Google DeepMind's Gemma, a family of lightweight, state-of-the-art open models, TxGemma is specifically trained to understand and predict the properties of therapeutic entities throughout the entire discovery process, from identifying promising targets to helping predict clinical trial outcomes. This can potentially shorten the time from lab to bedside, and reduce the costs associated with traditional methods.

🌷 Thanks to Olga Rapp for sharing with #meds on whatsapp

#drug_discovery #protein_language #protein_engineering #blog #5785 #2025

AlphaFold 3 predicts the structure and interactions of all of life’s molecules
Google DeepMind
Blog , 5784 2024

Introducing AlphaFold 3, a new AI model developed by Google DeepMind and Isomorphic Labs. By accurately predicting the structure of proteins, DNA, RNA, ligands and more, and how they interact, we hope it will transform our understanding of the biological world and drug discovery.

#protein_language #protein_engineering #popular_science #blog #5784 #2024

ESM3: Simulating 500 million years of evolution with a language model
Facebook
Blog, 5784 2024

Update January 2025: We're thrilled to announce the publication of ESM3 in Science Magazine. We’re opening our API for biological intelligence, now in public beta, allowing scientists in academia and industry a free limited time preview of the capabilities of some of our models through Forge.

#protein_language #protein_engineering #popular_science #blog #5784 #2024

A breakthrough unfolds
Google DeepMind
YouTube, 5782 2022

In December 2019, DeepMind’s AI system, AlphaFold, solved a 50-year-old grand challenge in biology, known as the protein-folding problem. A headline in the journal Nature read, “It will change everything” and the President of the UK's Royal Society called it a “stunning advance [that arrived] decades before many in the field would have predicted”. In this episode, Hannah uncovers the inside story of AlphaFold from the people who made it happen and finds out how it could help transform the future of healthcare and medicine.

#protein_language #protein_engineering #popular_science #podcast #5782 #2022

AlphaFold: a solution to a 50-year-old grand challenge in biology
Google DeepMind
Blog, 5781 2020

Proteins are essential to life, supporting practically all its functions. They are large complex molecules, made up of chains of amino acids, and what a protein does largely depends on its unique 3D structure. Figuring out what shapes proteins fold into is known as the “protein folding problem”, and has stood as a grand challenge in biology for the past 50 years. In a major scientific advance, the latest version of our AI system AlphaFold has been recognised as a solution to this grand challenge by the organisers of the biennial Critical Assessment of protein Structure Prediction (CASP). This breakthrough demonstrates the impact AI can have on scientific discovery and its potential to dramatically accelerate progress in some of the most fundamental fields that explain and shape our world.

#protein_language #protein_engineering #popular_science #blog #5781 #2020

Sheba ARC Oncology AI 5785 2025 Conference
Sheba , Israel
04-Nissan-5785 | 02-Apr-2025
Conference

🌷 Thanks to Yuval Avnir for sharing

#oncology #ai #conference #5785 #2025

MeDS - Medical Data Science Israel
Community channels

MeDS Overview
We are an Israeli community of data scientist and clinicians. Our goal is to share information, promote initiatives and connect over the various challenges of data science and machine learning in the healthcare industry.

#ai #data_science #healthcare #medical #community #israel

Webinar: Cracking the Code- How to Successfully Present AI Technologies to Pharma R&D

ScienceAbroad

Mon Apr 7, 2025 19:00 - 20:00 IDT

🌷 Thanks to Yuval Avnir for sharing

#ai #data_science #healthcare #medical #community #israel