Milot Mirdita

Milot Mirdita

@milot.bsky.social

Open source #bioinformatics at Sungkyunkwan University 🇰🇷 | former Steinegger Lab @ SNU, Söding Lab @ MPI-NAT | http://mstdn.science/@milotmirdita

2.5K followers855 following65 posts

Milot Mirdita reposted

EMBL-EBI
@ebi.embl.org

Is the world prepared for a future pandemic? AI-predicted protein complex structures for 2,800 viruses known to infect humans are now openly available in the #AlphaFold Database, which could improve how we respond to emerging infectious disease outbreaks. Learn more: www.embl.org/news/science...

Milot Mirdita reposted

Kieran Didi
@kdidi.bsky.social

Our wet-lab validation campaign for Proteina-Complexa is now on bioRxiv! It includes some new exciting experimental results, from large protein structures (fully codesigned!) to functional carbohydrate binders. biorxiv.org/content/10.6... Thread with some of the additions 🧵1/n

biorxiv.orgLatent generative search unlocks de novo design of untapped biomolecular interactions at scaleDe novo protein design has advanced rapidly, yet designing binders to polar, solvent-exposed epitopes and small, flexible ligands remains challenging. Such hydrated surfaces and flexible molecules, in...

Milot Mirdita reposted

Sergey Ovchinnikov
@sokrypton.org

Introducing highly experimental localfold.org Building on @martinsteinegger.bsky.social af2 webgpu port, @milot.bsky.social optimizations & jax ports of af3-like models by @marielle.bsky.social, Choonghwan Lee, Julia Buhmann. WARNING: runs directly on your 💻, may drain 🪫 & eat data📱 & overheat 🔥💻

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social

Run AlphaFold2 locally in your browser via WebGPU, no installation needed, it's just a static webpage using your own GPU or CPU. Short proteins run in seconds. Larger ones are still slow: a 291-aa protein takes ~7 minutes on my M4 Pro. ❗It's just a PoC. 🌐 martin-steinegger.github.io/alphafold2-w...

Milot Mirdita
@milot.bsky.social

ColabFold 1.6.3 is out! 2.5x faster, pip-installable, ipSAE+pDockQ2 scores. Thanks Choonghwan Lee, Marielle Russo, Gyuri Kim 🐍pip install colabfold[alphafold] CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2… 🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"

Milot Mirdita reposted

MDRepo
@mdrepo.bsky.social

mdrepo.org now has its own account (that's me!) Follow the account for updates on content and functionality.

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social

@wheelerlab.org is talking about his effort to build a resource for protein dynamics (PDB for MD). MDRepo is a repository to store simulation data. This is really needed to push the needle in design, function and more. Please help make it successful by sharing your MD data. #ismb2026 🌐 mdrepo.org

Milot Mirdita reposted

Dongwook Kim
@dongwookkim.bsky.social

AI-driven protein structure prediction lets us revisit the question once impossible to tackle at scale: What can we learn from the evolution of protein structures? Our new preprint reviews how to properly assess the quality of structure-based alignments and trees. 🧵1/5 📄 doi.org/10.32942/X2T10D

Milot Mirdita reposted

Dongwook Kim
@dongwookkim.bsky.social

AmpliPhy is now reviewed and published in @bioinfoadv.bsky.social! AmpliPhy improves your gene trees by adding homologs with a single command, based on the observations from a quantitative benchmark design. More details in quoted 🧵 📄 doi.org/10.1093/bioadv/vbag222 💾 github.com/DessimozLab/ampliphy

doi.orgAmpliPhy improves gene trees by adding homologous sequences without affecting alignmentsAbstractMotivation. In phylogenomics, gene tree reconstruction depends on multiple sequence alignment and tree inference, and ongoing work continues to imp
Dongwook Kim@dongwookkim.bsky.social

Can ever-increasing sequence databases improve phylogenetic reconstruction of a gene family? Our new preprint introduces AmpliPhy, a pipeline that automates homolog enrichment to improve gene tree inference, built on a robust phylogenomic benchmark scheme. 🧵1/n 📃 doi.org/10.64898/2026.01.26.701724

doi.orgAmpliPhy improves gene trees by adding homologs without affecting alignmentsIn phylogenomics, gene tree reconstruction depends on multiple sequence alignment (MSA) and tree inference, and ongoing work continues to improve inference quality. Denser taxon sampling has been associated with improved gene tree inference, suggesting that adding homologs could be a practical route to higher accuracy as sequence databases continue to expand. However, adding sequences can influence multiple steps of typical inference pipelines, and little is known on its specific effect on the multiple sequence alignment, tree reconstruction, and rooting steps. We performed a large-scale empirical benchmark to quantify how homolog enrichment affects alignment and phylogenetic inference. Using an enrichment-impoverishment design and a measure of tree accuracy based on taxonomic congruence, we found that enrichment consistently improves tree inference quality, while effects on alignment quality are marginal. We show that this improvement is associated with accurate root placement on enriched trees when sensitive homolog search is accompanied. Notably, much of the benefit can be retained with relatively compact alignments produced by sequence addition. Building on these observations, we provide a tool, AmpliPhy, which efficiently improves phylogenetic reconstruction of protein families through homolog enrichment. The AmpliPhy open-source pipeline software is available at https://github.com/DessimozLab/ampliphy. ### Competing Interest Statement The authors have declared no competing interest. Swiss National Science Foundation, https://ror.org/00yjd3n13, 216623, 10005715

Milot Mirdita reposted

George Bouras
@gbouras13.bsky.social

If you are looking for web-based phage annotation, phage-annotation.org is live. Upload a genome to run Pharokka, Phold and Phynteny sequentially (see our recent protocols paper doi.org/10.1002/cpz1...). If you have feedback, please reach out Thanks to @ardc.edu.au for making this possible!

phage-annotation.orgPhage Annotation Server -- phage genome annotationFree automated phage genome annotation -- pharokka, phold and phynteny in one pipeline.

Milot Mirdita reposted

Spyros Lytras
@spyroslytras.bsky.social

Come work on exciting AI for biology projects in Paris!! 🇫🇷 Details and application below, deadline sept 1st!

Antigen Evolution & Design Lab@antigenevo.bsky.social

🚨 JOB ALERT🚨 We are very excited to be hiring the lab's ✨very first postdoc✨! Work on new AI technologies for decoding antigen protein evolution in a fresh research environment, at the heart of Paris 🇫🇷 Details & link to apply: research.pasteur.fr/en/job/postd... Deadline: Sep 1st

Milot Mirdita reposted

Yo Akiyama
@yoakiyama.bsky.social

Excited to share our now published paper @cp-cell.bsky.social highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to Zhidian Zhang, Olivia Tang, @eunbelivable.bsky.social @milot.bsky.social @martinsteinegger.bsky.social and @sokrypton.org!

cell.comExpanding the scope of protein language modeling to protein-protein interactions with MSA PairformerProtein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein la...

Milot Mirdita reposted

Travis Wheeler
@wheelerlab.org

Thanks for the advert, @martinsteinegger.bsky.social. If you're reading this and you're sitting on a pile of molecular dynamics simulations, please consider contributing them to MDRepo. This is the path to AI for dynamics (And if you're wondering: yes, there was only 1 person in the audience! 🤥)

Martin Steinegger 🇺🇦@martinsteinegger.bsky.social

@wheelerlab.org is talking about his effort to build a resource for protein dynamics (PDB for MD). MDRepo is a repository to store simulation data. This is really needed to push the needle in design, function and more. Please help make it successful by sharing your MD data. #ismb2026 🌐 mdrepo.org

Milot Mirdita reposted

hbkgenomics.bsky.social
@hbkgenomics.bsky.social

Does your designed active site already exist in nature? Is an uncharacterized protein hiding a catalytic site or a pocket? Folddisco answers both, searching millions of structures for a 3D motif in seconds. @natbiotech.nature.com 🧬 📄 www.nature.com/articles/s41... 🧵1/7👇

nature.comStructural motif search across the protein universe with Folddisco - Nature BiotechnologyFolddisco enables protein structural motif search in million scale databases.

Milot Mirdita reposted

Sebastian Deorowicz
@sdeorowicz.bsky.social

10 years after the first FAMSA paper, its successor is now published in Nat Biotech! We believe that FAMSA2 can enable analyses of large protein collections that were previously unattainable. Thank you, Andrzej and Cedric, for great collaboration www.nature.com/articles/s41...

nature.comFast and accurate multiple-protein-sequence alignment at scale with FAMSA2 - Nature BiotechnologyFAMSA2 accurately aligns millions of protein sequences at high speed.

Milot Mirdita reposted

George Bouras
@gbouras13.bsky.social

Whenever I presented Phold, I was frequently asked "can you do the same beyond phages?" We ( @oschwengers.bsky.social @linsalrob.bsky.social @binomicalabs.org et al) finally did it with Baktfold github.com/gbouras13/ba... www.biorxiv.org/content/10.6...

github.comGitHub - gbouras13/baktfold: Rapid & standardized genome annotation using protein structural informationRapid & standardized genome annotation using protein structural information - gbouras13/baktfold

Milot Mirdita reposted

Nabil-Fareed Alikhan
@happykhan.mstdn.science.ap.brid.gy

Replying to @happykhan.mstdn.science.ap.brid.gy

the web application is available at : https://brigx.genomicx.org/ I would be interested to hear feedback regarding bugs or any unexpected behaviour, any suggestions for the user interface, or any features you feel would be useful .

brigx.genomicx.orgBRIGX - Browser-Based Ring Image GeneratorCircular comparative genome visualization tool running entirely in your browser

Milot Mirdita reposted

Debora Marks
@deboramarks.bsky.social

Meet evedesign: open-source AI, accessible protein design ✅Combine models for multiobjective optimization ✅Integrate experimental data ✅ Run on your own infrastructure 📄Paper: www.biorxiv.org/content/10.6... 💻Code: github.com/evedesignbio 🌐Webserver: evedesign.bio Collaborate: hello@evedesign.bio

deboramarkslab.substack.comevedesign: accessible biosequence design with a unified frameworkUnified protein design for computational researchers and experimentalists

Milot Mirdita reposted

EMBL-EBI
@ebi.embl.org

You asked, we listened. Millions of AI-predicted protein complex structures are now available in the #AlphaFold Database. This spans homodimers from 20 of the most studied species, including humans, as well as the World Health Organization’s priority pathogens list. www.ebi.ac.uk/about/news/t...

Milot Mirdita reposted

Wei Shen 沈 伟
@shenwei356.bsky.social

Can't wait to release a 10-year-old birthday version for SeqKit! - 10 years - 2 papers, 3500 citations - 20 contributors - 40 subcommands - 880 commits - 500 issues - 685.5K Bioconda total downloads Thank you all, dear contributors and users! I'll keep maintaining it. github.com/shenwei356/s...

github.comRelease SeqKit v2.13.0 (10-year-old birthday version) · shenwei356/seqkitChangelog SeqKit is 10 years old! SeqKit v2.13.0 - 2026-02-28 seqkit: add support for reading and writing LZ4 compression format. new command: seqkit sample2: improved seqkit sample by @stahiga....

Milot Mirdita reposted

Fabian Theis
@fabiantheis.bsky.social

At the 132nd Internat. Titisee Conference on Biology 2.0: The AI Revolution in Biology & Medicine From sequence→function models 🧬 to protein & generative structure models 🧪 to AI of cell states & perturbations 🧫 Great science, great friends, beautiful lake. Thanks @BIFonds!

Milot Mirdita reposted

Steven Salzberg
@stevensalzberg.bsky.social

Our new review on genome annotation just appeared in @naturerevgenet.bsky.social, with a particular focus on the human genome, with Hayden Ji and Mihaela Pertea: rdcu.be/e4mI1

rdcu.beAnnotating genomes at increased scale and resolutionNature Reviews Genetics - In this Review, Ji et al. overview how rapidly advancing experimental and computational methods are enabling improved and automated annotation of gene structure and...

Milot Mirdita reposted

Patrick Bryant
@patrickbryant1.bsky.social

Introducing The Structural History of Eukarya (SHE): The first proteome-scale phylogeny constructed entirely from 3D structure. We computed 300 trillion alignments across 1,542 species to map the tree of life. 🧵👇 (1/5)