iiinova — where your digital self keeps evolving

Please email me with CV and cover letter if you're interested. Protein sequencing project is a comp + exp role. Cryptic pocket project is a comp role (maybe some exp if you are keen on it). Could start asap!

010

I'm also looking to hire a postdoc as the computational lead to train new deep-learning models for predicting cryptic druggable pockets in human proteins using proprietary data. Lots of resources to train new models from scratch and finetune existing ones!

I'm looking to hire a postdoc to lead the charge developing new peptide binders to enable in situ single-molecule protein sequencing. Collab with Ed Boyden's group at MIT. Funded by Keck Fdn. Would be transformative tech, maybe as big as DNA sequencing!

Roberto Chica Lab @chicalab.bsky.social · 06/10/2026

I have postdoc positions available to lead two new exciting projects! One is on in situ protein sequencing (collab with Ed Boyden at MIT) and the other is on modeling cryptic pockets for drug discovery (collab with Scripps and MGH). Reach out if interested! Details below

245

Reposted by Nick Polizzi

In our latest preprint, we introduce Multistate Enzyme Design, a computational framework that simultaneously optimizes enzyme sequences across multiple transition states while preserving the conformational flexibility needed to access them. www.biorxiv.org/content/10.6...

biorxiv.org

Multistate Enzyme Design Enables Efficient and Stereoselective Multistep Catalysis

Enzymes catalyze multistep reactions by stabilizing successive transition states within well organized, yet dynamic active sites. However, computational enzyme design typically targets a single transi...

154

Reposted by Nick Polizzi

Magnus Kjærgaard @proteinmagnus.bsky.social · 30/09/2026

How does the extreme thermostability of de novo designed proteins arise? We aimed to answer this question by combined chemical and thermal denaturation of de novo designed minibinders in a paper out now in Protein Science (@proteinsociety.bsky.social): dx.doi.org/10.1002/pro....

1164

Nick Polizzi @nickpolizzi.bsky.social · 30/09/2026

Happening this evening at dfci!

001

Nick Polizzi @nickpolizzi.bsky.social · 29/09/2026

Like something out of "Star Trek: The Next Generation", Jody used protein design as a protein "phase inverter" to convert K-Ras(G12C) into something that biology doesn't interact with 🫥. The resulting LUCI-tag is a fast, orthogonal SLP that can be multiplexed with Halo- and SNAP-tags!

100

Nick Polizzi @nickpolizzi.bsky.social · 29/09/2026

Do you use self-labeling proteins (SLPs) like HaloTag and SNAP-tag? Then check out Jody's new preprint to learn about LUCI-tag! Jody built LUCI-tag starting from K-Ras(G12C), using protein design to erase K-Ras from biology 🤯!

120

Reposted by Nick Polizzi

Ben de Bivort @debivort.bsky.social · 22/09/2026

Hello friends, the Harvard Life Science departments have banded together to hire a new colleague working at the intersection of Life Sciences and AI. Could be primarily an experimentalist, or could be primarily a compute/theorist. academicpositions.harvard.edu/postings/16773

academicpositions.harvard.edu

Tenure-Track Professor in Life Science and AI

The Life Sciences Departments in Harvard Faculty of Arts and Sciences seek to recruit a tenure-track professor whose research is at the interface of AI and life sciences, from methodological developme...

34254

Reposted by Nick Polizzi

Derek Lowe @dereklowe.bsky.social · 18/09/2026

A new intracellular system that binds to and recognizes glutathione adducts is uncovered during a screen for glutathione degraders. What’s its function and what other proteins participate?

science.org

Not The Glue They Thought It Was

0214

Nick Polizzi @nickpolizzi.bsky.social · 15/09/2026

Might add a protease character. Obvious finishing move

120

Reposted by Nick Polizzi

Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 13/09/2026

Fold Spacer lets you fly through protein structures (Weekend project #2). It’s my first game: I originally set out to build a racer with structures as the tracks, but was a little too crazy. So it became this instead. You can upload your own structures. 🌐 martin-steinegger.github.io/Fold-Spacer/

215759

Nick Polizzi @nickpolizzi.bsky.social · 11/09/2026

Congrats on the awesome paper!!

Alan Brown @alanbrownhms.bsky.social · 10/09/2026

Reposted by Nick Polizzi

Millions of beating cilia keep airways clean. At the base of each is the transition zone (TZ), a gate that controls which proteins enter and leave. In our paper out today in Science, we used cryo-FIB-ET to image the TZ inside human airway cells www.science.org/doi/10.1126/...

science.org

In situ structure of the human ciliary transition zone links linker defects to primary ciliary dyskinesia

The ciliary transition zone (TZ) regulates ciliary proteome composition, yet its molecular architecture, protein content, and contribution to motile ciliopathies remain poorly defined. We applied in situ cryo-electron tomography and subtomogram averaging ...

211945

Reposted by Nick Polizzi

Boston Protein Design and Modeling Club @bpdmc.org · 02/09/2026

Come join us on Wednesday, September 9th 2026 at 7pm EDT in Room 181, Building 68, @mit.edu to see Natasha Murakowska! "Quantitative Affinity Data at Scale: Addressing the Data Bottleneck in AI-Enabled Protein Design"

011

Reposted by Nick Polizzi

Rosetta Commons @rosettacommons.bsky.social · 18/08/2026

🧬 Want to stay updated on protein science? Check out the @bpdmc.org monthly presentation series! Recent topics: • Computational antibody design • Energy-based models & structure • De novo small-molecule induced changes Learn more, watch past presentations, and join the community at bpdmc.org.

054

Reposted by Nick Polizzi

Boston Protein Design and Modeling Club @bpdmc.org · 14/08/2026

If you weren't able to make it out for Jeffrey Chang's marvelous seminar this week, you can check out the recording 👇 youtu.be/q3Xn2-TIZEo

youtu.be

De novo design of small-molecule-induced conformational change

YouTube video by Boston Protein Design and Modeling Club

051

Reposted by Nick Polizzi

Ruth Huttenhain @rhuttenhain.bsky.social · 13/08/2026

My lab at Stanford University School of Medicine is recruiting! We are looking for a postdoc at the interface of quantitative proteomics, structural biology and G protein-coupled receptor (GPCR) biology: postdocs.stanford.edu/prospective/...

postdocs.stanford.edu

Open Postdoctoral position, faculty mentor Ruth Huttenhain | Office of Postdoctoral Affairs

03831

Reposted by Nick Polizzi

Paola Laurino @paolalaurino.bsky.social · 13/08/2026

We're seeking a motivated postdoc candidate to join us at the Okinawa Institute of Science and Technology to work on the structural and functional characterisation of plant enzymes that break down polysaccharides, exploring sequence space to understand the emergence of enzyme function using AI tools

122

Nick Polizzi @nickpolizzi.bsky.social · 13/08/2026

Not sure how difficult but would be interesting to try. Just need someone ambitious like you! Happy to supply the pizza in return for good ideas ;) Hopefully will see you next meeting!

010

Reposted by Nick Polizzi

Boston Protein Design and Modeling Club @bpdmc.org · 05/08/2026

Next week, Jeffrey Chang from @nickpolizzi.bsky.social's lab will present cutting-edge work from a pre-print that just came out today! Wednesday, August 12th 2026, 7pm EDT in Room 6055, Longwood Center, @danafarber.bsky.social "De novo design of small-molecule-induced conformational change"

biorxiv.org

De novo design of small-molecule-induced conformational change

Many biological proteins function by changing shape upon small-molecule binding. Here, we present a general strategy for designing de novo proteins that undergo small-molecule-induced conformational c...

141

Perhaps obvious at this point, but Jeffrey is a super star! He was able to drive the whole project to completion, and with incredible care and precision to boot. Perhaps a level of rigor to be expected (and indeed commended) from a graduate student in the Harvard Physics Dept!

130

We're rather excited by the approach. It turns static binders into dynamic responders, endowing them with binding "super powers". It lets binders communicate with us and potentially other molecular machinery down the road. So cool! Can't wait to see what we and others do with this technology!

210

He wasn't done there. He wanted to see a snapshot of his proteins at work, so he solved some crystal structures of his lidded designs with exatecan bound. As predicted, no way in, no way out. But there the drug is, sitting there at 100% occupancy. So the lid's gotta move.

comparison of structures of original exatecan binder EPIC and a new lidded binder, d6.4, which encases the drug entirely.

100

He turned a lidded binder into a de novo FRET sensor of exatecan, directly coupling binding to function! The sensor even worked in biological matrices like human serum 🤯

FRET spectra of lidded design fused to fluorescent proteins in various conditions with different amounts of exatecan

100

The designs worked spectacularly. Of 24 tested, 10 showed ligand-induced lid closure. Some showed ultrahigh affinity in the pM regime, with very slow off-rates (up to months)! Jeffrey could rationally tune the on-rate via mutation or lid truncation.

equilibrium and kinetic experiments showing the lids can be tuned to be more open in absence of drug, which correlates with faster binding kinetics

100

The lid (purple) completely encloses the drug (blue). There's no way in and no way out when the lid is closed. So the lid has to open to allow drug entry/egress. Jeffrey came up with a nifty algorithm using a new method called QBITS, AF3, and LASErMPNN to design metastable lids that open w/o ligand.

The original de novo protein bound exatecan inside a rigid bundle that looks the same w/ or w/o the drug. But exatecan presented a tiny, polar epitope on the protein surface that Jeffrey took advantage of. He designed a lid to interact with this portion, coupling lid closure to binding.

100

Proteins like streptavidin, Abl kinase, and GPCRs use a lid-like loop to enclose a ligand. We thought this kind of induced-fit mechanism might also produce ultratight de novo binders, breaking the "nanomolar" affinity limit. Jeffrey set out to design this de novo, starting from a static drug binder.

lid domains that close behind a ligand after it binds