Lightnews — Scholar-powered news

Reposted by Mohammed AlQuraishi

Yehlin Cho @yehlincho.bsky.social · 3d

Thrilled to announce our new preprint, “Protein Hunter: Exploiting Structure Hallucination within Diffusion for Protein Design,” in collaboration with @Griffin, @GBhardwaj8 and @sokrypton.org

🧬Code and notebooks will be released by the end of this week.
🎧Golden- Kpop Demon Hunters

2 13 46

Mohammed AlQuraishi @moalquraishi.bsky.social · 16d

Why not use OpenFold (: ?

4

Mohammed AlQuraishi @moalquraishi.bsky.social · 16d

We're looking for a scientific program manager to help manage complex team projects in biomolecular modeling and machine learning that span academia and industry. If you're interested please apply here!

opportunities.columbia.edu/cw/en-us/job...

Scientific Program Manager - Columbia University Medical Center, New York, United States

Job Type: Officer of Administration Bargaining Unit: Regular/Temporary: Regular End Date if Temporary: Hours Per Week: 35 Standard Work Schedule: Building: Salary Range: $120,000-$170,000 The salary ...

opportunities.columbia.edu

4

Reposted by Mohammed AlQuraishi

Julia Rogers @juliarurogers.bsky.social · Sep 10

First time at #MLCB! I'll be speaking tomorrow about my development of an ML predictor of domain–peptide interaction affinity to model proteome-scale signaling networks. It'll be livestreamed too.

Peter Koo @pkoo562.bsky.social · Sep 10

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

2 14

Mohammed AlQuraishi @moalquraishi.bsky.social · Sep 2

Virtual seminar on ROCKET and inference-time optimization of AlphaFold predictions using experimental data. Alisia gives fantastic talks!

Alisia Fadini @alisiafadini.bsky.social · Sep 2

We'll cover our latest work on low resolution applications, a run-through of our codebase, and tutorials of how to run ROCKET on your own data. Join if you're interested!! 🚀

SBGrid Consortium @sbgrid.bsky.social · Sep 2

Our monthly software webinars will resume in October with @alisiafadini.bsky.social and @minhuanli.bsky.social covering AlphaFold as a Prior: Guiding Protein Structure Prediction Using Experimental Data with ROCKET.

Tuesday, October 14, 2025 at 12:00pm ET
Register here: buff.ly/uLlQGVr

#SBGrid

6

Reposted by Mohammed AlQuraishi

Alisia Fadini @alisiafadini.bsky.social · Sep 2

We'll cover our latest work on low resolution applications, a run-through of our codebase, and tutorials of how to run ROCKET on your own data. Join if you're interested!! 🚀

SBGrid Consortium @sbgrid.bsky.social · Sep 2

Our monthly software webinars will resume in October with @alisiafadini.bsky.social and @minhuanli.bsky.social covering AlphaFold as a Prior: Guiding Protein Structure Prediction Using Experimental Data with ROCKET.

Tuesday, October 14, 2025 at 12:00pm ET
Register here: buff.ly/uLlQGVr

#SBGrid

Webinars

The SBGrid Consortium is an innovative global research computing group operated out of Harvard Medical School. SBGrid provides the global structural biology community with support for research…

buff.ly

3 9

Reposted by Mohammed AlQuraishi

Nate Corley @ncorley.bsky.social · Aug 15

(1/7)
Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3)

[https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)

Accelerating Biomolecular Modeling with AtomWorks and RF3

Deep learning methods trained on protein structure databases have revolutionized biomolecular structure prediction, but developing and training new models remains a considerable challenge. To facilita...

www.biorxiv.org

2 28 66

Reposted by Mohammed AlQuraishi

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 Mohammed AlQuraishi

Tal Korem @tkorem.bsky.social · Aug 7

We are hiring a postdoc - come work with us (www.koremlab.science) at the intersection of #microbiome, data science, and women's health!
Message or email me if interested. 🖥️ 🧬

Korem Lab - Microbiome Systems Biology @ Columbia | New York, USA

We apply systems biology approaches to decipher the metabolic interactions between the microbiome and its human host in diverse clinical settings, aiming towards personalized microbiome-based therapeu...

www.koremlab.science

10 13

Reposted by Mohammed AlQuraishi

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Jul 25

In 1965, Margaret Dayhoff published the Atlas of Protein Sequence and Structure, which collated the 65 proteins whose amino acid sequences were then known.

Inspired by that Atlas, today we are releasing the Dayhoff Atlas of protein sequence data and protein language models.

3 28 66

Mohammed AlQuraishi @moalquraishi.bsky.social · Jul 22

The more proteins are added, the more there is a "ladder" of possible alternatives, and thus the less likely that a false positive interface ("minimally viable") will be picked as other potential interfaces will outcompete it. 2/2

1 13

Mohammed AlQuraishi @moalquraishi.bsky.social · Jul 22

I think there is. If AF always gives the most favorable conformation, irrespective of how shallow the energy well is, then when only two proteins are present it gives a sort of minimally viable interface. When a 3rd protein is added, it must pick the preferred interface among 3 possible dimers. 1/2

2 1 13

Mohammed AlQuraishi @moalquraishi.bsky.social · Jul 9

To say this is well-deserved would be the understatement of the century. Julia’s research vision is so clear-eyed, brilliant, and dare I say blindingly creative it gives me imposter syndrome (-:

Julia Rogers @juliarurogers.bsky.social · Jul 8

I am incredibly grateful to so many people for their guidance and support along the way! Especially @moalquraishi.bsky.social who gave a statistical mechanician + molecular biophysicist an opportunity to become a ML’er + system biologist, and encouragement to pursue my own research vision!

1 10

Reposted by Mohammed AlQuraishi

Julia Rogers @juliarurogers.bsky.social · Jul 8

I am beyond excited and honored to receive a BWF CASI! This amazing program will support my transition from postdoc to faculty as I continue to develop new modeling frameworks for elucidating and programming cellular behaviors.

Burroughs Wellcome Fund @bwfund.bsky.social · Jul 8

BWF is pleased to announce the 2025 recipients of its Career Awards at the Scientific Interface (CASI). buff.ly/WDswUnt #bwfcasi

buff.ly

6 4 37

Reposted by Mohammed AlQuraishi

Pedro Beltrao @pedrobeltrao.bsky.social · May 2

Our work on deriving protein-protein (functional) associations across different human tissues from proteomics data is now published. There is quite a lot in this paper, so I will just touch on a few highlights:
www.nature.com/articles/s41...

A tissue-specific atlas of protein–protein associations enables prioritization of candidate disease genes - Nature Biotechnology

Protein–protein interactions specific to 11 individual tissues are presented in a comprehensive resource.

www.nature.com

3 51 140

Reposted by Mohammed AlQuraishi

Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · Apr 27

AFESM: a metagenomic guide through the protein structure universe! We clustered 821M structures (AFDB&ESMatlas) into 5.12M groups; revealing biome-specific groups, only 1 new fold even after AlphaFold2 re-prediction & many novel domain combos. 🧵
🌐 afesm.foldseek.com
📄 www.biorxiv.org/content/10.1...

4 71 140

Reposted by Mohammed AlQuraishi

Tim Stearns @stearnslab.bsky.social · Apr 11

Join us at Columbia on April 22 for the latest round of Postdoc Night Science NYC!

Itai Yanai @itaiyanai.bsky.social · Apr 11

New York City postdocs: What do you do when hitting a contradiction? Night science loves this first glimpse of a new concept! Our next 'Postdoc Night Science NYC’ session is April 22 @ Columbia. docs.google.com/forms/d/1v_b... @stearnslab.bsky.social @kelseymonson.bsky.social @sophiekorn.bsky.social

1 5

Reposted by Mohammed AlQuraishi

Hannah Wayment-Steele @hkws.bsky.social · Mar 20

Protein dynamics was the first research to enchant me >10yrs ago, but I left in PhD bc I couldn't find big experimental data to evaluate models.

Today w @ginaelnesr.bsky.social, I'm thrilled to share the big dynamics data I've been dreaming of, and the mdl we trained w them: Dyna-1.
📝: rb.gy/de5axp

2 25 84

Reposted by Mohammed AlQuraishi

Keystone Symposia @keystonesymposia.bsky.social · Feb 26

Join Elizabeth Kellogg at our Machine Learning meeting. Submit your poster abstract by Feb. 27 for a chance to present alongside pioneers in microscopy, cryoEM, live cell imaging, and ultra-resolution technologies!

#KSMLStructure #ML #AI @moalquraishi.bsky.social @possuhuanglab.bsky.social

KSQA: Dr. Elizabeth Kellogg (Machine Learning)

YouTube video by KeystoneSymposia

youtu.be

2 5

Mohammed AlQuraishi @moalquraishi.bsky.social · Feb 24

Thanks to the leadership & generosity of @randyjread.bsky.social and @hekstralab.bsky.social, this has been an amazingly rewarding collaboration. I learned a lot about crystallography and got to think about satisfying technical problems. It was a project I kept coming back to for the sheer joy of it

2

Mohammed AlQuraishi @moalquraishi.bsky.social · Feb 24

I highlight these two aspects because it is only due to the technical virtuosity of @alisiafadini.bsky.social and @minhuanli.bsky.social that this exceedingly challenging problem was finally overcome.

1 1 2

Mohammed AlQuraishi @moalquraishi.bsky.social · Feb 24

Second, while "SGD in MSA space" is🔥and debuted in journals.plos.org/ploscompbiol..., it took delicate meta-optimization (multiphases, disjoint learning rates, resolution bins) to go from minor structural tweaks (2 months) to large-scale rearrangements (year+) that truly leverage e.g., cryoET.

1 2

Mohammed AlQuraishi @moalquraishi.bsky.social · Feb 24

See @alisiafadini.bsky.social's thread for main results--here I want to highlight two aspects of🚀. First, integrating complex data modalities like xtallography requires faithful modeling of experimental observables--non-trivial to get right--e.g., the log-likelihood-gain on intensity LLGI used by 🚀.

1

Mohammed AlQuraishi @moalquraishi.bsky.social · Feb 24

Injecting arbitrary experimental data into AlphaFold has been a missing feature. With high-throughput crystallography yielding 1000s of structures/year (@covid_moonshot) & cryoET making 😍 but low-res in situ models, it's also become a necessary one for scaling up structural biology. Hence ROCKET👇!

Alisia Fadini @alisiafadini.bsky.social · Feb 24

Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. @minhuanli.bsky.social and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.

2 10 40

Reposted by Mohammed AlQuraishi

Randy Read 🇨🇦🇬🇧 @randyjread.bsky.social · Feb 22

Watch out for an upcoming bluetorial/tweetorial on this work from the amazing @alisiafadini.bsky.social!

www.biorxiv.org/content/10.1...

AlphaFold as a Prior: Experimental Structure Determination Conditioned on a Pretrained Neural Network

Advances in machine learning have transformed structural biology, enabling swift and accurate prediction of protein structure from sequence. However, challenges persist in capturing sidechain packing,...

www.biorxiv.org

2 14 32