Che,Yang

@animesh1977 @BiologyAIDaily @github will soon to update the repo, please stay tuned

@BiologyAIDaily @github link not working 💩

Mapping Targetable Sites on the Human Surfaceome for the Design of Novel Binders 1. A groundbreaking study maps the human surfaceome, identifying 4,500 targetable sites across 2,886 cell-surface proteins. This resource unlocks new therapeutic opportunities for precision medicine. 2. The study leverages MaSIF, a geometric deep-learning framework, to predict protein-protein interaction sites. Nearly 3 billion docking runs were performed to generate high-quality binder "seeds" for targeted design. 3. A novel web platform, SURFACE-Bind, is introduced. It provides open access to predicted binding sites, corresponding binder seeds, and data visualization tools. This resource aids drug discovery and protein design. 4. Experimental validation highlights three critical targets—FGFR2, IFNAR2, and HER3. De novo-designed binders showed high success rates, targeting key interfaces with nanomolar to micromolar affinities. 5. The team optimized protein design pipelines by integrating ProteinMPNN and AlphaFold2, improving biophysical properties like stability and binding affinity, achieving 11-fold higher success rates in subsequent rounds. 6. A peptide design pipeline was also developed. Interface motifs from mini-protein binders were stabilized as cyclized peptides, yielding 5 target-specific peptides with demonstrated binding activity. 7. This work underscores the power of integrating deep learning and physics-based methods to advance de novo protein and peptide design for therapeutic applications, targeting underexplored surfaceome regions. 8. By combining computational innovation with experimental validation, this research sets a new benchmark for precision protein engineering and opens the door to the next generation of biologics. @befcorreia @hamed_khakzad @yangche7 @SiFulle @J_Damjanovic_ 💻Code: github.com/hamedkhakzad/S… 📜Paper: biorxiv.org/content/10.110… #ProteinDesign #DeepLearning #Surfaceome #ComputationalBiology #DrugDiscovery #MachineLearning

The newly-funded VIB.AI Center in Leuven (Belgium) is recruiting 3 (!) group leaders focusing on answering fundamental biological questions with AI/ML. Great opportunity to join a dynamic community, with competitive conditions.

New amazing research from the @befcorreia lab! @zanderharteveld and Alexandra explore protein topologies that have not been found in nature using a novel deep learning pipeline called Genesis

@AjasjaLjubetic @CasperGoverde will also be there as a witness for your new idea again 🫡

@CasperGoverde @yangche7 There is also EU RosettaCon which you might be interested in.

Is it possible to design soluble analogs of integral membrane proteins using deep learning? The answer is yes! In our latest study we've successfully created novel soluble proteins with claudin, rhomboid protease, and GPCR-like topologies. Read more here biorxiv.org/content/10.110…

@CasperGoverde Fantastic work @CasperGoverde and Martin, I thought you guys just had this idea back to the RC last year, and now the works are done 😲what a speed !

@befcorreia @MartinPacesa @jroeltou @CasperGoverde Will second Bruno !! Probably at some point we need to separate de novo structure or de novo sequence as so far they are all in the same category of de novo design ? And great work from you guys, amazing !😁

@MartinPacesa @jroeltou @CasperGoverde But yes de novo is generally used in a relatively loose sense which can refer to either the design process or the end result. It’s clear that here these are natural folds but the sequences design are unrelated to those found in the natural repertoire

Very happy to share the new manuscript from @befcorreia lab! With @CasperGoverde we de novo designed several complex natural folds, including soluble analogues of integral membrane proteins! biorxiv.org/content/10.110…

Our paper with @befcorreia @CirauquiPablo et al on protein design using geometric deep learning is finally in @nature We show experimental results of diverse de novo designed binders nature.com/articles/s4158…

Hi #ProteinDesign and #AI #DrugDesign enthusiasts, please have a look to openings at Novo in US, UK, and DK and join a great team around @GreisenPer @KrisDeibler @yangche7 me and many others! novonordisk.com/careers/career…

@MartinPacesa That is so cool man ! Especially in the second example it suddenly refold to beta propensity, if that holds true perhaps it may be chaperone there 🧐btw how do you make this gif/video, super nice 👍

@MartinPacesa Many people said the language based model will take a lead this year, just curious of which group/team indeed use that 🧐

AlphaFold/ColabFold no longer dominating at this year’s CASP15 😮

@AnastassiaVoro2 It does seems AF2 can better capture the subtle detail that distinguish folded from unfolded sequence even for TM barrel 😀 but ESMfold also does quite amazing prediction with no doubt! Just curious how the landscape of traditional reverse folding prediction looks like here🧐

Can ML predict sequence-structure compatibility and success of de novo designs? We compared single-sequence predictions (no MSA) to experimental data for water-soluble and membrane b-barrels designs. AF2 does a good job, while ESMF folds everything with almost no discrimination.

The @befcorreia lab is looking for a postdoc! As a postdoc there myself, I can tell you that Lausanne is a stunning city, EPFL has a strong collaborative environment, and the lab researchis super exciting! On top of that, Bruno is a really chill dude 😎 recruiting.epfl.ch/Vacancies/2594…

Great nice work from Zander and Jaume is finally out ! Glad to be part of the journey :)

preprint of a new paper with @befcorreia's group on using MaSIF #geometricdeeplearning architecture to build novel protein binders for various targets (oncological and antiviral)--with experimentally confirmed structure

A generic framework for hierarchical de novo protein design biorxiv.org/cgi/content/sh… #biorxiv_bioinfo

Congratulations to our Group Leader @befcorreia ! and great news for #proteindesign 👏

Check this cool protein switch out from our latest paper. Great work from Sailan and teams !!

@befcorreia Grateful and honorable being one of the witnesses to see you go through it, congrats Bruno 🍺🍺

It has been my pleasure to be around such a great crowd of scientists and human beings ! thank you for all the good things throughout the years