banner
samsl.io
Samuel Sledzieski
@samsl.io
730 followers 220 following 53 posts
Research Fellow @flatironinstitute.org @simonsfoundation.org Formerly @csail.mit.edu @msftresearch.bsky.social @uconn.bsky.social Computational systems x structure biology | he/him | https://samsl.io | 👨🏼‍💻
samsl.io
Posts Media Videos Starter Packs
Pinned
samsl.io
Samuel Sledzieski @samsl.io · Jun 23
New preprint 🚨--protein language models + MD training ➡️ allosteric networks!

@sonyahanson.bsky.social and I are developing RocketSHP 🚀 for rapid genome-scale inference of local+correlated fluctuations + structure token distributions!

📄: www.biorxiv.org/content/10.1...
💻: github.com/flatironinst...
www.biorxiv.org
1 6 9
Reposted by Samuel Sledzieski
lindorfflarsen.bsky.social
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 6d
Integrative modelling of biomolecular dynamics

Time-dependent and -resolved experiments combined with computation provide a view on molecular dynamics beyond that available from static, ensemble-averaged experiments

Review w @dariagusew.bsky.social & Carl G Henning Hansen
doi.org/10.48550/arX...
Figure 1 from the review. Caption: Comparison of a schematic example showing static, time-dependent, and time-resolved experiments illustrated by a protein folding process. (a) A static experiment measuring the observable O$_{\text{exp}}$ is shown, which can be modelled as a distribution of simulated values, O$_{\text{calc}}$, representing a conformational ensemble of folded and unfolded states. (b) Shows a time-dependent experiment, where the equilibrium dynamics of reversible folding gives rise to measured transition times $\tau_1$ and $\tau_2$. These can be modelled as equilibrium dynamics, illustrated by a free energy (FE) surface along a chosen degree of freedom (D.O.F.) (c) A time-resolved experiment probes a non-equilibrium process, where the system begins at $t_{0}$ in the folded state. During the observation time $t$ the protein unfolds until $t_{\text{max}}$. At each time point, a distinct ensemble average, O$_{\text{exp}}$, can be observed, reflecting the proteins changing structure. This evolution can be modelled as distributions of O$_{\text{calc}}$ at each time point. These are shown together with a FE surface.
11 35
Reposted by Samuel Sledzieski
rodger.bsky.social
Rodger Sherman @rodger.bsky.social · 7d
These are the quarterbacks since 2010 who complete passes at roughly the rate Microsoft Excel’s AI mode accurately edits spreadsheets
Jake Locker Davis Webb Tom Savage Rex Grossman Garrett Gilbert Kellen Clemens Mark Sanchez Logan Woodside Zach Wilson David Blough Derek Anderson Johnny Manziel
41 200 630
Reposted by Samuel Sledzieski
pilarcossio.bsky.social
pilarcossio.bsky.social @pilarcossio.bsky.social · 19d
*Job Alert*: postdoc positions available @flatironinstitute.org in Computational Mathematics: apply.interfolio.com/173401
Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio
apply.interfolio.com
4 2
Reposted by Samuel Sledzieski
ekimb.bsky.social
Barış Ekim @ekimb.bsky.social · 22d
Happy (a^2, b^2, c^2)!

www.npr.org/2025/09/16/n...
On 9/16/25, celebrate a date of mathematical beauty
Pythagorean Triple Square Day, as one man affectionately calls 9/16/25, is a day like no other this century.
www.npr.org
2 8
Reposted by Samuel Sledzieski
davidaknowles.bsky.social
David A Knowles @davidaknowles.bsky.social · 28d
YouTube link for MLCB2025 is up! Starting in 30 min. www.youtube.com/live/19I7xTh...
Machine Learning in Computational Biology 2025
YouTube video by Machine Learning in Computational Biology
www.youtube.com
1 5 19
samsl.io
Samuel Sledzieski @samsl.io · 28d
I’ll be at MLCB today and tomorrow, and talking about our latest work on modeling protein dynamics 🚀 tomorrow afternoon!
pkoo562.bsky.social
Peter Koo @pkoo562.bsky.social · 28d
2025 Machine Learning in Computational Biology (#MLCB) meeting starts TODAY (9/10) at 9:30a (EST) at the NY Genome Center in NYC!

We have a great lineup of keynotes, contributed talks, and posters today and tomorrow

Schedule: mlcb.org/schedule

Join for free via livestream: m.youtube.com/@mlcbconf
MLCB - Schedule
The in-person component will be held at the New York Genome Center, 101 6th Ave, New York, NY 10013. All times below are Eastern Time.
mlcb.org
1 1
Reposted by Samuel Sledzieski
pkoo562.bsky.social
Peter Koo @pkoo562.bsky.social · 28d
2025 Machine Learning in Computational Biology (#MLCB) meeting starts TODAY (9/10) at 9:30a (EST) at the NY Genome Center in NYC!

We have a great lineup of keynotes, contributed talks, and posters today and tomorrow

Schedule: mlcb.org/schedule

Join for free via livestream: m.youtube.com/@mlcbconf
MLCB - Schedule
The in-person component will be held at the New York Genome Center, 101 6th Ave, New York, NY 10013. All times below are Eastern Time.
mlcb.org
1 7 13
Reposted by Samuel Sledzieski
bergerlab.bsky.social
Bonnie Berger Lab @bergerlab.bsky.social · Sep 3
Excited to share our recent work: Sparse autoencoders uncover biologically interpretable features in protein language model representations now in PNAS. Thread below 🧵
1 2 7
Reposted by Samuel Sledzieski
diffuseproject.bsky.social
Diffuse Project @diffuseproject.bsky.social · Aug 12
Announcing the Diffuse Project! We're unlocking protein dynamics through diffuse X-ray scattering - the overlooked signal that could revolutionize how we understand protein motion. seemay.substack.com/p/from-syste...
From systems operators to systems architects
Going up a level from data generation to think about the data systems we design and embed
seemay.substack.com
1 6 9
Reposted by Samuel Sledzieski
iscb.bsky.social
ISCB News @iscb.bsky.social · Aug 13
The results of the ISCB Leadership vote are in! 

Terms for the ISCB President-Elect and ISCB Vice President will start on January 21, 2026.
1 2 10
Reposted by Samuel Sledzieski
drglam.bsky.social
Dr Sian Gramates @drglam.bsky.social · Aug 11
I just got the notice that all the FlyBase people at Harvard, including me, will be laid off on October 12. I'm devastated.
65 220 380
Reposted by Samuel Sledzieski
vkmulligan.bsky.social
Vikram K. Mulligan @vkmulligan.bsky.social · Jul 14
We have a new preprint out on the Masala software suite, a free and open-source platform for easy biomolecular modelling methods development. www.biorxiv.org/content/10.1...
The open-source Masala software suite: Facilitating rapid methods development for synthetic heteropolymer design
Although canonical protein design has benefited from machine learning methods trained on databases of protein sequences and structures, synthetic heteropolymer design still relies heavily on physics-b...
www.biorxiv.org
3 8
Reposted by Samuel Sledzieski
yoakiyama.bsky.social
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 Samuel Sledzieski
ksdrew.bsky.social
Kevin Drew @ksdrew.bsky.social · Jul 29
We are excited to share our preprint describing DirectContacts2! Here we develop a machine learning model to discriminate between direct and indirect protein interactions. We use our model to construct a highly accurate wiring diagram of the human cell.

www.biorxiv.org/content/10.1...
DirectContacts2: A network of direct physical protein interactions derived from high-throughput mass spectrometry experiments
Cellular function is driven by the activity proteins in stable complexes. Protein complex assembly depends on the direct physical association of component proteins. Advances in macromolecular structur...
www.biorxiv.org
2 14 45
Reposted by Samuel Sledzieski
workshopmlsb.bsky.social
MLSB (in San Diego + Copenhagen) @workshopmlsb.bsky.social · Jul 28
Stay tuned for details on the 6th edition of MLSB, officially happening this December in downtown San Diego, CA!
ginaelnesr.bsky.social
Gina El Nesr @ginaelnesr.bsky.social · Jul 28
The MLSB workshop will be in San Diego, CA (co-located with NeurIPS) this year for its 6th edition in December 🧬🔬

Stay tuned @workshopmlsb.bsky.social as we share details about the stellar lineup of speakers, the official call for papers, and other announcements!🌟
7 15
Reposted by Samuel Sledzieski
miroastore.bsky.social
Miro Astore @miroastore.bsky.social · Jul 23
That's a wrap! The results of the first #cryoEM heterogeneity challenge are up on biorxiv!
biorxiv.org/content/10.110
biorxiv.org
3 22 45
Reposted by Samuel Sledzieski
dr-alphalyrae.bsky.social
Vega Shah @dr-alphalyrae.bsky.social · Jul 23
Everyone working in a STEM field should read this - ‘writing is thinking’
www.nature.com/articles/s44...
4 39 120
Reposted by Samuel Sledzieski
flatironinstitute.org
Flatiron Institute @flatironinstitute.org · Jul 21
#FlatironCCB scientists Natalie Sauerwald, Olga Troyanskaya and colleagues leveraged @sparkforautism.bsky.social data to reveal four distinct groups that link autism-related traits with underlying genetics. Read more: www.simonsfoundation.org/2025/07/09/n... #science #biology #autismresearch
New Study Reveals Subclasses of Autism by Linking Traits to Genetics
New Study Reveals Subclasses of Autism by Linking Traits to Genetics on Simons Foundation
www.simonsfoundation.org
2 2
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
We hope this update will significantly expand the types of researchers + compute systems that can use D-SCRIPT! Manuscript with benchmarks + implementation details coming hopefully soon, and thanks again so much to Daniel for his hard work pushing this out!
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
Along with a bunch of other quality-of-life updates (including a mode specifically designed for host x pathogen/symbiont interactions! 🦠), v0.3.0 will power the sorts of comparative genomics and network analyses that we imagined when we first designed D-SCRIPT.
1 1
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
BMPI makes D-SCRIPT fully parallel in both embedding loading and inference, and can distribute inference to an arbitrary number of available GPUs. At the same time, the blocked inference procedure means that memory usage can be decreased arbitrarily low (with a small trade-off in speed).
1
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
In v0.3.0, we solve *both* of these issues, enabling efficient inference on both personal computers and multi-GPU HPC systems. The secret? Our new Blocked Multi-GPU Parallel Inference (BMPI) procedure, led by Daniel Schaffer (github.com/schafferde).
1
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
This ends up being extremely wasteful, since D-SCRIPT still made predictions in serial on a single GPU; inference was not possible on personal systems, but much of the compute capacity of these large machines was sitting unused. Whole-genome all-by-all prediction could still take upwards of a week!
1
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
Despite this, one of the most common user issues we heard about was that pre-loading embeddings achieved speed by trading off massive memory usage, restricting D-SCRIPT inference at whole-genome scale only to large HPC-like machines.
1
samsl.io
Samuel Sledzieski @samsl.io · Jul 22
We designed D-SCRIPT to be extremely high-throughput, and the most common use case we've seen is whole-proteome all-by-all prediction (this use case is at the core of our recent 🎼philharmonic work!)
1