Sign in

Samuel Sledzieski

@samsl.io
779 followers 256 following 73 posts

Research Fellow @flatironinstitute.org @simonsfoundation.org Formerly @csail.mit.edu @msftresearch.bsky.social @uconn.bsky.social Computational systems x structure biology | he/him | samsl.io | 👨🏼‍💻

PostsRepliesMedia
Reposted by Samuel Sledzieski
pilarcossio.bsky.social @pilarcossio.bsky.social · 30/09/2026
*Job alert*: Postdoc position at the Flatiron Institute to work on biophysical inference and cryo-EM. ❄️ 🔬Applications are welcome! apply.interfolio.com/193799
apply.interfolio.com
Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio
025
Reposted by Samuel Sledzieski
Matt Norlander @norlander.bsky.social · 28/09/2026
One of the most revered and celebrated albums in music history was released on Sept. 28, 1976 — 50 years ago today. Songs in the Key of Life tracks, ranked:
Vinyl copy1. Sir Duke
2. As
3. Contusion
4. Another Star
5. Have a Talk With God
6. I Wish
7. Love’s in Need of Love Today
8. Summer Soft
9. Black Man
10. Pastime Paradise
11. Ordinary Pain
12. Isn’t She Lovely
13. Ngiculela
14. Village Ghetto Land
15. Joy Inside My Tears
16. Knocks Me Off My Feet
17. If It’s Magic
78712
Reposted by Samuel Sledzieski
Rob Patro @robp.bsky.social · 25/09/2026
Ok comp. bio / bioinformatics / genomics friends. Let's talk about @recombconf.bsky.social and, specifically, the way in which the "proceedings" have evolved. This seems like something that we, as a community, should address. RECOMB now has no "published" proceedings in the classic sense.
195
Reposted by Samuel Sledzieski
Martin Pacesa @martinpacesa.bsky.social · 21/09/2026
ʙɪɴᴅᴄʀᴀꜰᴛ2 is out, and we're not waiting for the paper. The full code drops today, free for academic and industry use. We're releasing it early so you can start designing right now, and bring its full power to the current Adaptyv competition. github.com/PacesaLab/Bi...
4292142
Reposted by Samuel Sledzieski
Niema Moshiri @niema.net · 17/09/2026
My department is hiring an Assistant Professor! Come join us at @ucsandiego.bsky.social Computer Science & Engineering! Beautiful city, awesome colleagues, delicious tacos 😄 apol-recruit.ucsd.edu/JPF04649
apol-recruit.ucsd.edu
Assistant Professor - CSE
University of California, San Diego is hiring. Apply now!
11712
Reposted by Samuel Sledzieski
Sukrit Singh @sukritsingh92.bsky.social · 15/09/2026
📣 The Singh Lab opens at Fox Chase Cancer Center in Spring 2027, where I will be starting as an Assistant Professor!📣 Excited to continue studying how protein biophysics shapes drug response. I am hiring across all levels and disciplines! Apply on the "Join" page ( & spread the word!): singhlab.bio
0156
Reposted by Samuel Sledzieski
kate @katewitko.bsky.social · 19/08/2026
[steely dan voice] 8/19
47829
Reposted by Samuel Sledzieski
Niema Moshiri @niema.net · 13/08/2026
Our department is hiring an Adjunct Professor at all ranks! apol-recruit.ucsd.edu/JPF04582
apol-recruit.ucsd.edu
Assistant, Associate or Full Adjunct Professor
University of California, San Diego is hiring. Apply now!
11412
Reposted by Samuel Sledzieski
Max Fürst @maxfus.bsky.social · 11/08/2026
Extraordinary blog post by @moalquraishi.bsky.social moalquraishi.wordpress.com/2026/08/10/a... Starting with the question on whether workaphiles will be dying breed post AGI, it later turns into serious scifi - "The 'easy' solution is to make our brains bigger"
moalquraishi.wordpress.com
A Workaphile’s Apology
Disclaimer: No LLMs were used in the writing of this essay—all em dashes are mine1. Soon after the AlexNet breakthrough burst onto the scene over a decade ago, I became preoccupied with the followi…
033
Reposted by Samuel Sledzieski
Jason Nomburg @jnoms.bsky.social · 22/07/2026
Ad forthcoming, but I am hiring for a postdoc or staff scientist to advance related investigations of the virus-host conflict. This position is ~80-100% computational, but with opportunities for experimental work if desired. If interested, shoot me an email with your CV! Reposts appreciated! 15/15
046
Reposted by Samuel Sledzieski
Nicholas Grossman @nicholasgrossman.bsky.social · 18/07/2026
The US built the greatest talent magnet ever, attracting the smart, skilled, and striving. They’d come to study, then stay and build things here, or leave with positive impressions and fruitful connections. Helped make the US wealthy and powerful. Then America chose to throw it away. And for what?
20746331580
Samuel Sledzieski @samsl.io · 15/07/2026
I'm giving a poster on MIMIC at #ISMB2026 today (C-211)! Drop by and chat with me about multimodal modeling for DNA, RNA, and protein biology. Inference code + checkpoints + sample data are all now available on GitHub/HuggingFace. github.com/PolymathicAI...
github.com
GitHub - PolymathicAI/MIMIC: A Generative Multimodal Model for Biomolecules
A Generative Multimodal Model for Biomolecules. Contribute to PolymathicAI/MIMIC development by creating an account on GitHub.
013
Reposted by Samuel Sledzieski
Magnus Bauer @kinasekid.bsky.social · 14/07/2026
Can we program a kinase like a switch? Inspired by natural autoinhibitory complexes, we designed miniproteins against active- and inactive-like conformations of Focal Adhesion Kinase. Depending on the targeted state, the resulting binders either activated or inhibited the kinase.
12513
Reposted by Samuel Sledzieski
Yun S. Song @yun-s-song.bsky.social · 06/07/2026
I am thrilled to share that UC Berkeley and UCSF have launched a joint initiative in Computational Biomedicine! cdss.berkeley.edu/news/uc-berk... We will soon be recruiting new faculty and postdoctoral fellows. Please repost to help spread the word.
cdss.berkeley.edu
UC Berkeley and UCSF Launch Computational Biomedicine Initiative
UC Berkeley and UCSF have launched a joint program called the Bakar Computational Biomedicine Initiative to develop the frontier of AI and biomedicine, tremendously accelerating advances in clinical c...
36127
Reposted by Samuel Sledzieski
Wandering Scientist @wandsci.bsky.social · 30/05/2026
My go to example of this sort of thing is the study of weird thermophilic bacteria gave us PCR, upon which so much of modern biological research and its many applications (including drug discovery!) depend
1106
Reposted by Samuel Sledzieski
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 30/05/2026
Everything you wanted to know about the protein chemistry behind how amino-acid changes affect the cellular abundance of proteins from @tkschulze.bsky.social Effects of residue substitutions on the cellular abundance of proteins doi.org/10.7554/eLif...
27021
Reposted by Samuel Sledzieski
EMBL-EBI @ebi.embl.org · 28/05/2026
We told you it wouldn’t be a long wait. 👀 Even more predicted protein structures have been added to the #AlphaFold Database. This time, the database has expanded to include heterodimers – protein complexes made up of two different proteins. alphafold.ebi.ac.uk
12915
Samuel Sledzieski @samsl.io · 28/04/2026
The preprint is live right now, and we’re currently preparing the code and data for public, open-source release. More details in the blog post as well! 🌐 polymathic-ai.org/blog/mimic/ 📄 arxiv.org/abs/2604.24506 💻 github.com/PolymathicAI...
polymathic-ai.org
Polymathic
020
Samuel Sledzieski @samsl.io · 28/04/2026
Thanks also to our generous funders and institutions for supporting this work @polymathicai.bsky.social @flatironinstitute.org @simonsfoundation.org @nyudatascience.bsky.social @princeton.edu @schmidtsciences.bsky.social !
110
Samuel Sledzieski @samsl.io · 28/04/2026
...,Claudia Skok Gibbs, @albertobietti.bsky.social , Geraud Krawezik, @vkmulligan.bsky.social, @pilarcossio.bsky.social @sonyahanson.bsky.social, Alisha Jones, Olga Troyanskaya, and Shirley Ho.
110
Samuel Sledzieski @samsl.io · 28/04/2026
This work was a huge collaboration and was only possible thanks to our amazing team: Siavash Golkar (lead), Irina Espejo Morales, Jake Kovalic, @minhuanli.bsky.social, Ksenia Sokolova,...
110
Samuel Sledzieski @samsl.io · 28/04/2026
There are still exciting frontiers to explore. Data integration in biology requires working carefully with domain experts, but by providing a framework to integrate diverse modalities, MIMIC represents a step toward one generative model across molecular biology.
100
Samuel Sledzieski @samsl.io · 28/04/2026
MIMIC also treats experimental context as a first-class modality. Given assay + cellular context in natural language, it predicts condition-specific RNA reactivity better than sequence-only baselines, improving downstream RNA structure modeling.
Three-panel comparison of RNA 2D structure prediction. Top (orange): RNA sequence alone fed to ViennaRNA yields a branched 2D structure with F1 = 0.404. Middle (gray): RNA sequence plus experimental chemical reactivity data fed to ViennaRNA yields the reference structure. Bottom (blue): RNA sequence plus MIMIC-predicted reactivity fed to ViennaRNA yields a structure with F1 = 0.987, closely matching the experimental reference.
110
Samuel Sledzieski @samsl.io · 28/04/2026
Protein design makes the multimodal advantage clear. Backbone geometry and surface chemistry provide different, complementary constraints on protein function. Conditioning on both, MIMIC generates diverse, high-confidence sequences with strong in silico binding support.
Left: three strip plots showing TM-score vs. WT (median 0.89), MaSIF surface similarity vs. WT (median 0.91), and AF3 cofolding iPTM (median 0.81) for 37 MIMIC-designed PD-L1 sequences. Right: PyMOL-style structural visualization overlaying a MIMIC-designed protein (blue) on the PD-L1 binding partner (gray), with the interface region highlighted in red.
100
Samuel Sledzieski @samsl.io · 28/04/2026
Multimodal conditioning also improves design. MIMIC doesn't just predict aberrant splicing, it can design around it. For a pathogenic mutation, it proposes corrective edits that suppress cryptic exon inclusion while keeping the disease-causing mutation fixed.
Left panel: schematic of the MIMIC RNA design pipeline, showing a mutated RNA sequence conditioned on wild-type splice pattern and wild-type phylogenetic conservation scores to produce a designed sequence. Right panel: four stacked line plots showing PhyloP scores, MIMIC phyloP VEP scores (C>T splice-altering vs. C>A non-splice-altering), and SpliceAI acceptor and donor probabilities (unconditioned vs. PhyloP-conditioned) across positions relative to the HBB IVS-II-654 C>T pathogenic mutation, illustrating that conditioning on conservation suppresses the cryptic splice site.
110
Samuel Sledzieski @samsl.io · 28/04/2026
Another example is splicing. MIMIC does something most splice models can't: isoform-aware splice prediction. By conditioning on transcript boundaries, it can recover the full transcript-specific splice structure, not just score donor/acceptor sites in isolation.
Left: four horizontal bar charts showing AUPR for gene-level and transcript-level splice site prediction (coding and non-coding) comparing MIMIC, AlphaGenome, SpliceAI, and NT3. MIMIC (dark blue) leads all comparisons; a light blue bar shows MIMIC with TSS+TES conditioning. Right: line plot of splice site probability versus transcript position for SPRY1, comparing ground truth, unconditioned MIMIC prediction, and conditioned MIMIC prediction, with donor and acceptor site calls marked. After TSS+TES conditioning, false positive predictions decrease.
100
Samuel Sledzieski @samsl.io · 28/04/2026
What does this training paradigm buy you? MIMIC learns representations that are SOTA across both RNA and protein downstream benchmarks, and multimodal conditioning consistently improves sequence reconstruction in both nucleic-acid and amino-acid settings.
Two dot-plot benchmark comparisons. Left (PFMBench): MIMIC (dark blue) versus ~13 protein language model baselines (gray) across 11 tasks spanning function, structure, interaction, and developability. MIMIC leads or is competitive on most tasks. Bottom bar chart shows win rates of each baseline against MIMIC; all are below 50%. Right (mRNABench): Same format for 7 RNA/multimodal tasks. MIMIC leads on most; Evo2 and Orthrus show the highest win rates but remain below 50%.
100
Samuel Sledzieski @samsl.io · 28/04/2026
Biological data is complex, and training MIMIC required a new substrate. We built LORE: an aligned multimodal dataset connecting nucleic acid, protein, evolutionary, structural, regulatory, and experimental/context signals within shared biomolecular states.
Diagram titled "LORE: Multi-modal and multi-source data alignment." Left: a table mapping transcript IDs to UniProt IDs with checkmarks and X marks indicating data availability across modalities (PhyloP, RNA chemical probing, splice pattern, backbone structure). Right: expanded view of a single entry (ENST000012345 / P04637) showing linked RNA and protein data including sequence, PhyloP conservation track, splice pattern diagram, and AlphaFold structure.
132
Samuel Sledzieski @samsl.io · 28/04/2026
MIMIC is built so any subset of modalities can be observed, and any subset can be generated Sequence → prediction is only one case You can also go the other way: use structure, splicing, or assay context to constrain the sequences compatible with a biological state.
Schematic of MIMIC's split-track input encoding and encoder-decoder architecture. Left panel shows two input tracks: nucleic acid (DNA sequence + conservation scores summed per token) and protein (amino acid residues + backbone structure summed per token), plus cellular context and gene taxonomy tokens. Right panel shows selected tokens fed into an encoder, producing a multimodal embedding passed to a decoder that outputs predictions.
111
Samuel Sledzieski @samsl.io · 28/04/2026
Introducing MIMIC: a new foundation model trained natively across DNA, RNA and proteins. MIMIC is multimodal and generative: it can use structure, regulation, evolution, and experimental context to infer missing biology or design new sequences. 🧵⬇️
1209
Reposted by Samuel Sledzieski
Miro Astore @miroastore.bsky.social · 24/04/2026
We just preprinted one of my favorite studies @FlatironInst . I was lucky to be part of an amazing team studying the effects of rapid cooling to preserve samples in cryoEM. Read on to learn about the limits of cryoEM for biophysics and how to overcome them www.biorxiv.org/content/10.6...
15322
Samuel Sledzieski @samsl.io · 02/04/2026
Our review on ML for modeling conformational ensembles is out now in Current Opinion in Structural Biology (w/ @sonyahanson.bsky.social)! It's been exciting to follow all the progress in this field recently, and I'm equally excited to see where it goes! www.sciencedirect.com/science/arti...
sciencedirect.com
The landscape of machine learning approaches for modeling protein conformational ensembles
The conformational ensemble of a protein and its corresponding probabilities and dynamics are crucial determinants of its function, but are difficult …
0124
Reposted by Samuel Sledzieski
Matt Norlander @norlander.bsky.social · 30/03/2026
ONE OF THE BIGGEST SHOTS AND CRAZIEST MOMENTS IN CBB HISTORY
726351
Reposted by Samuel Sledzieski
cryoEM papers @cryoempapers.bsky.social · 20/03/2026
StrucTTY: An Interactive, Terminal-Native Protein Structure Viewer www.biorxiv.org/content/10.64898/2026.03.17.712308v1 #cryoEM
054
Reposted by Samuel Sledzieski
Michael Baym @baym.lol · 17/03/2026
Annual reminder: if you’ve been accepted to multiple graduate programs and are still deciding, please let the ones you’re definitely not going to know as soon as possible! -Someone who got into his PhD off the waitlist the day after the deadline
519881
Reposted by Samuel Sledzieski
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 17/03/2026
AlphaFold database has entered the era of complexes. Together with NVIDIA, DeepMind and EBI, we use ColabFold, OpenFold and MMseqs2-GPU to predict ~31 million complexes (homo & hetro-dimers) resulting in 1.8 million high-quality predictions 📄 research.nvidia.com/labs/dbr/ass... 🌐 alphafold.ebi.ac.uk
8263110
Reposted by Samuel Sledzieski
EMBL-EBI @ebi.embl.org · 16/03/2026
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...
816087
Samuel Sledzieski @samsl.io · 11/03/2026
Had a lot of fun working on this with Darius, Christian, and Rohit. We address the problem of unpredictable scaling behavior for PLMs -- with a simple 2-line drop-in replacement for ESM2, you no longer need to worry that a smaller model might end up performing better! 🧵⬇️
000
Reposted by Samuel Sledzieski
Pedro Beltrao @pedrobeltrao.bsky.social · 04/03/2026
We have started a project trying to predic the interactions/structures of all yeast protein pairs using an AlphaFold pooling approach. We are making the current dataset open and we welcome collaborations. www.evocellnet.com/2026/03/mapp...
evocellnet.com
Mapping the yeast atructural interactome with AlphaFold3: an open call for collaboration
We are excited to announce the early-stage release of our S. cerevisiae  structural interactome mapping project. Using AlphaFold3 (AF3), w...
69853
Reposted by Samuel Sledzieski
Andre Cornman @ancornman1.bsky.social · 03/03/2026
Predicting protein-protein interactions (PPIs) at proteome scale can take months with co-folding models due to the massive all-vs-all comparisons required. We are excited to announce FlashPPI, a contrastive learning framework that predicts proteome wide physical interfaces in minutes. 1/🧵
16727
Reposted by Samuel Sledzieski
Mayor Zohran Kwame Mamdani @mayor.nyc.gov · 28/02/2026
Additionally, I want to speak directly to Iranian New Yorkers: you are part of the fabric of this city — you are our neighbors, small business owners, students, artists, workers, and community leaders. You will be safe here.
5099241412
Reposted by Samuel Sledzieski
Sonya @sonyahanson.bsky.social · 22/02/2026
A great start to the Biophysical Society Annual Meeting in San Francisco! Check out the various projects being presented on work from Flatiron Institute people! #bps2026
0114
Reposted by Samuel Sledzieski
Patrick Bryant @patrickbryant1.bsky.social · 07/02/2026
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)
28439
Samuel Sledzieski @samsl.io · 03/02/2026
Looking forward to speaking to @jhucompsci.bsky.social and JHU Biomedical Engineering this Thursday!
051
Reposted by Samuel Sledzieski
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 30/01/2026
FoldMason is out now in @science.org. It generates accurate multiple structure alignments for thousands of protein structures in seconds. Great work by Cameron L. M. Gilchrist and @milot.bsky.social. 📄 www.science.org/doi/10.1126/... 🌐 search.foldseek.com/foldmason 💾 github.com/steineggerla...
science.org
Multiple protein structure alignment at scale with FoldMason
Protein structure is conserved beyond sequence, making multiple structural alignment (MSTA) essential for analyzing distantly related proteins. Computational prediction methods have vastly extended ou...
4302147
Reposted by Samuel Sledzieski
Sam Thielmonster @samthielman.com · 22/01/2026
I just thought everyone should see this
Dr Kareem Carr
man: i wish to publish
@kareem_carr
Jan 21
reviewer 2: your paper is no good
man: i'll do anything to improve
reviewer 2: it's simple. you must read the work of the great scientist Pagliarini
man: *bursts into tears* but i am Pagliarini
Andre Pagliarini
@apagliar
Jan 21
a first: in rejecting an article I submitted to a journal, reviewer 2 noted I failed to engage the work of one Andre Pagliarini
Jan 21, 2026 • 3:47 PM UTC
43252945988
Reposted by Samuel Sledzieski
Milot Mirdita @milot.bsky.social · 20/01/2026
My time in @martinsteinegger.bsky.social's group is ending, but I’m staying in Korea to build a lab at Sungkyunkwan University School of Medicine. If you or someone you know is interested in molecular machine learning and open-source bioinformatics, please reach out. I am hiring! mirdita.org
mirdita.org
Mirdita Lab - Laboratory for Computational Biology & Molecular Machine Learning
Mirdita Lab builds scalable bioinformatics methods.
710756
Reposted by Samuel Sledzieski
Minhuan Li @minhuanli.bsky.social · 02/01/2026
Check our new preprint smoothing rugged Cryo-EM landscapes: shorturl.at/gYs9U We tackle practical hurdles of Optimal Transport (OT) loss—differentiability, cost & noise sensitivity—make it a feasible inference workhorse. W/ G. Woollard, D. Herreros, @pilarcossio.bsky.social, K. Dao Duc 🧵👇 (1/9)
1148
Samuel Sledzieski @samsl.io · 07/01/2026
🌿 MINT is out now in Nature Communications! 📄: www.nature.com/articles/s41... 💻: github.com/VarunUllanat...
nature.com
Learning the language of protein-protein interactions - Nature Communications
Protein language models capture single proteins but struggle with interactions. Here, authors present MINT, trained on large PPI datasets, which outperforms existing PLMs in predicting binding, mutati...
021
Reposted by Samuel Sledzieski
Rodger Sherman @rodger.bsky.social · 19/12/2025
Terrifying headline if you don’t realize they are sports teams.
Rockets owners expand talks to buy, move Sun
129139432799