Lightnews — Scholar-powered news

Reposted by Michael Jendrusch

Josh Hardy @joshuamhardy.bsky.social · 10d

I am thrilled to release ProteinDJ: a high-performance and modular protein design pipeline. Our open-source workflow incorporates #RFdiffusion, #ProteinMPNN, #FAMPNN, #AlphaFold2 and #Boltz-2. It is a fast, free, and fun way to design proteins (1/5)
doi.org/10.1101/2025.09.24.678028 #proteindesign

2 31 87

Reposted by Michael Jendrusch

Joe Grove @grovearmada.bsky.social · 13d

🚨 New Web Resource Alert! 🚨 We're delighted to share Viro3D a database of >85000 viral protein structure predictions from >4400 human & animal viruses.

🔗 viro3d.cvr.gla.ac.uk
📄 www.embopress.org/doi/full/10....

@molsystbiol.org @cvrinfo.bsky.social @uofgmvls.bsky.social #Virology #AlphaFold 🧪 🦠

Viro3D

viro3d.cvr.gla.ac.uk

1 19 34

Reposted by Michael Jendrusch

Ulad Litvin @ulad-litvin.bsky.social · 12d

Viro3D paper is out! We predicted 85,000 protein structures from human & animal viruses. 1/5 🧵

📑 Paper doi.org/10.1038/s443...
🔭 Explore virosphere viro3d.cvr.gla.ac.uk

Viro3D: a comprehensive database of virus protein structure predictions | Molecular Systems Biology

imageimageViro3D provides proteome-level, high confidence AI-protein structure predictions for >4,400 viruses, allowing mapping of form and function across the human and animal virosphere. Viro3D i...

doi.org

1 24 55

Michael Jendrusch @mjendrusch.bsky.social · 14d

Thank you!

Michael Jendrusch @mjendrusch.bsky.social · 15d

Also, shoutout to @blender.org and @bradyajohnston.bsky.social for making it so easy to turn protein structures into nice images!
5/5

Protein structures colored teal and purple floating above a reflective surface on a dark background. The protein structures spell out the word "SALAD" in all-capital letters.

1 1 4

Michael Jendrusch @mjendrusch.bsky.social · 15d

While I was working on salad as part of my PhD at Korbel group at EMBL, it was very much a passion project. So it makes me very happy to see @embl.org feature this paper!
Thanks again to Jan and the team supporting me on my more non-standard projects!
4/🧵

1 3

Michael Jendrusch @mjendrusch.bsky.social · 15d

Compared to the preprint, we have added comparisons to Proteína (openreview.net/forum?id=TVQLu34…) in terms of unconditional design. Here, salad compares favorably in terms of both runtime per design and designability of generated structures.
3/🧵

Graph of runtime comparisons of diffusion models (per design: top; per iteration: botton). This panel compares the runtimes of previous protein diffusion models (RFdiffusion, Genie, Proteína, Chroma) to two versions of the salad model. Salad outperforms all previous models in terms of runtime across protein lengths between 50 and 1,000 amino acid residues.

Boxplot of self-consistent RMSDs (scRMSDs) for salad models with different noise schedules (variance preserving, variance expanding, shaped) and the previous state of the art (RSO, Proteína), for proteins of length between 50 and 1,000 residues.
Variance expanding and shaped noise salad models consistently exhibit lower (better) scRMSDs compared to previous approaches across all sizes. While Proteína produces comparable results to salad all the way up to 800 residues, it surprisingly fails for 1,000 residue proteins.

1 2

Michael Jendrusch @mjendrusch.bsky.social · 15d

The preprint and code have been out for a while - if you want a quick overview, have a look at the thread we did back in February:
bsky.app/profile/mjendrus…
If you want to try salad in your browser, you can load up this Colab notebook:
colab.research.google.com/github/mjendrusc…
2/🧵

Michael Jendrusch @mjendrusch.bsky.social · Feb 6

New protein ML preprint from my PhD project.
We describe salad (sparse all-atom denoising), a family of efficient protein structure diffusion models and show that it works well on a bunch of protein design task previously described in the literature.

Preprint: www.biorxiv.org/content/10.1...

(1/N)

Five generated protein structures coloured with a gradient from purple to teal. The structures are shaped and positioned to spell out the word "salad" – the name of the software described in the mentioned preprint – in all-capital letters.

1 3

Michael Jendrusch @mjendrusch.bsky.social · 15d

With this, the last bit of my PhD at @embl.org is finally out!
We developed salad (sparse all-atom denoising), a family of blazing fast protein structure diffusion models.
Paper: nature.com/articles/s42256-…
Code: github.com/mjendrusch/salad
Data: zenodo.org/records/14711580
1/🧵

EMBL @embl.org · 15d

‘Salad’ – a new AI model from EMBL scientists – offers major improvements in synthetic protein design.

Salad is significantly faster than comparable methods, and designing proteins that don't exist in nature can have applications in many scientific fields.

www.nature.com/articles/s42...

1 9 23

Reposted by Michael Jendrusch

TJ McCorvie @allostericstate.bsky.social · 17d

Part of something that we have been working on for a while-A 3.1 Å map of a flexibly tethered 38 kDa domain. Hopefully preprinted soon along with a few other structures. #CryoEM

5 9 75

Reposted by Michael Jendrusch

Ben Engel @cellarchlab.com · 18d

A molecular-resolution look into the near-native architecture of the spinach chloroplast🌱. This one was a long time in the oven, but we're happy to finally share our "version of record". What long-standing debates did we settle? Check back for a short thread🧵 on Monday. #TeamTomo #PlantScience 🧪🧶🧬🔬🌾

eLife @elife.bsky.social · 18d

🌱 Using ‘compelling’ methods, including #CryoET, researchers mapped spinach thylakoid membranes at single-molecule precision, revealing how photosynthetic complexes are organised and settling long-standing debates on chloroplast architecture.
buff.ly/j3TSIkn

3 46 140

Reposted by Michael Jendrusch

Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 18d

MMseqs2-GPU sets new standards in single query search speed, allows near instant search of big databases, scales to multiple GPUs and is fast beyond VRAM. It enables ColabFold MSA generation in seconds and sub-second Foldseek search against AFDB50. 1/n
📄 www.nature.com/articles/s41...
💿 mmseqs.com

GPU-accelerated homology search with MMseqs2 - Nature Methods

Graphics processing unit-accelerated MMseqs2 offers tremendous speedups for homology retrieval from metagenomic databases, query-centered multiple sequence alignment generation for structure predictio...

www.nature.com

4 64 170

Reposted by Michael Jendrusch

Harry M. Williams @harrywilliams.bsky.social · 21d

❄️ NEW PRE-PRINT ❄️ Happy to see our latest work online. Here we present a super simple solution to the preferred orientation problem in single particle cryo-EM: the use of ultrasonic excitation during vitrification! Details in the 🧵 below... #cryoEM #structuralbiology

bioRxiv Biophysics @biorxiv-biophys.bsky.social · 21d

Overcoming Preferred Orientation in Cryo-EM With Ultrasonic Excitation During Vitrification https://www.biorxiv.org/content/10.1101/2025.09.14.676144v1

1 12 24

Reposted by Michael Jendrusch

Oli Clarke @olibclarke.bsky.social · 26d

This one is a bit of a departure from the usual and definitely a work in progress!

We found that by using ab initio reconstruction at very high res, in very small steps, we could crack some small structures that had eluded us - e.g. 39kDa iPKAc (EMPIAR-10252), below.

Read on for details... 1/x

18 81 260

Reposted by Michael Jendrusch

paulschanda.bsky.social @paulschanda.bsky.social · Aug 25

📢 New preprint: Aromatic Ring Flips Reveal Reshaping of Protein Dynamics in Crystals and Complexes.

We addressed a long-standing question that people debated already in the 1970s - but it still remained open:
Do proteins in crystals move as they do in solution? We used ring flips to find out.
1/n

2 17 45

Reposted by Michael Jendrusch

Daniel Fox @danielrfox.bsky.social · Sep 2

Quite proud of this one. Our review on AI-designed de novo binders out now in Structure. We give a brief history, outline the current ecosystem, highlight some standout applications and discuss the need for regulatory discussions. 🤖🧪🔬

Code to complex: AI-driven de novo binder design

The application of artificial intelligence to structural biology has transformed protein design from a conceptual challenge into a practical approach …

www.sciencedirect.com

1 5 19

Reposted by Michael Jendrusch

Martin Pacesa @martinpacesa.bsky.social · Aug 27

Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.

www.nature.com/articles/s41...

14 110 300

Reposted by Michael Jendrusch

Possu Huang Lab @possuhuanglab.bsky.social · Aug 19

We have a new collection of protein structure generative models which we call Protpardelle-1c. It builds on the original Protpardelle and is tailored for conditional generation: motif scaffolding and binder generation.

1 5 22

Reposted by Michael Jendrusch

Martin Pacesa @martinpacesa.bsky.social · Aug 7

"Hey Bob, just dock the AF3 prediction into density and deposit"

3 3 28

Reposted by Michael Jendrusch

David Mills @millsgroupchem.bsky.social · Aug 5

We are recruiting! Two 24 month postdoc positions are available with @m-l-baker.bsky.social and I, one mainly synthesis and the other measurements of lanthanide SMMs. Links below, deadline 19th Aug - please re-post:
www.jobs.manchester.ac.uk/Job/JobDetai...
www.jobs.manchester.ac.uk/Job/JobDetai...

Research Associate in Synthetic Inorganic Chemistry:Manchester

As an equal opportunities employer we welcome applicants from all sections of the community regardless of age, sex, gender (or gender identity), ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.

www.jobs.manchester.ac.uk

13 12

Reposted by Michael Jendrusch

Yo Akiyama @yoakiyama.bsky.social · Aug 5

Excited to share work with
Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org
biorxiv.org/content/10.1...
TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵

Scaling down protein language modeling with MSA Pairformer

Recent efforts in protein language modeling have focused on scaling single-sequence models and their training data, requiring vast compute resources that limit accessibility. Although models that use ...

biorxiv.org

1 43 95

Reposted by Michael Jendrusch

Dominik Niopek @dominikniopek.bsky.social · Aug 4

Our work on rationally engineering allosteric protein switches is now out in Nature Methods: www.nature.com/articles/s41... Thanks a lot to @grunewald.bsky.social and @noahholzleitner.bsky.social for the comprehensive news and views: www.nature.com/articles/s41...

Rational engineering of allosteric protein switches by in silico prediction of domain insertion sites - Nature Methods

ProDomino is a machine leaning-based method, trained on a semisynthetic domain insertion dataset, to guide the engineering of protein domain recombination.

www.nature.com

8 25

Reposted by Michael Jendrusch

Jan Mathony @jmathony.bsky.social · Aug 4

Publication alert: Our paper on domain insertion predictions in proteins is now out in @natmethods.nature.com in its final form: rdcu.be/ey7w3
Also check out the nice perspective by @noahholzleitner.bsky.social and @grunewald.bsky.social : www.nature.com/articles/s41...

Rational engineering of allosteric protein switches by in silico prediction of domain insertion sites

Nature Methods - ProDomino is a machine leaning-based method, trained on a semisynthetic domain insertion dataset, to guide the engineering of protein domain recombination.

rdcu.be

1 4 8

Reposted by Michael Jendrusch

xiuqichen.bsky.social @xiuqichen.bsky.social · Jul 24

🤔 How do proteins fold while they're still being made? As the main project in my PhD, I developed "Arrest Peptide Profiling" to record proteins folding with as they emerge from ribosomes in living cells 🦠 - with single codon resolution! @natcomms.nature.com‬ 🧵 1/6
#ProteinFolding

2 4 10

Reposted by Michael Jendrusch

Sebastian Deorowicz @sdeorowicz.bsky.social · Jul 19

Interested in a tool that aligns millions of proteins in minutes with quality similar to or better than the state-of-the-art utilities? Please take a look at our FAMSA2 paper: www.biorxiv.org/content/10.1...
and GH repo: github.com/refresh-bio/...

FAMSA2 enables accurate multiple sequence alignment at protein-universe scale

We introduce FAMSA2, an algorithm that produces high-accuracy multiple protein sequence alignments with unprecedented speed. Across structural, phylogenetic, and functional benchmarks, FAMSA2 matches ...

www.biorxiv.org

3 28 49