Aviv Spinner
@AvivSpinner
Followers
995
Following
5K
Media
37
Statuses
835
Protein Eng ML Research Fellow @Align_Bio Previously PhD w/ @deboramarks, ML Researcher @Flagship_PI, investor @pillar_vc & scientist @scribetx. 🧬🧑💻 🏳️⚧️
they/them
Joined June 2012
1/5 Biological data is noisy, redundant, and ever-growing. 🗣️ In our new paper (first paper of my post doc!! ⚡️), we track model performance across 14 years of UniRef100 snapshots to ask: how does pLM performance scale with training data?
1
24
107
"When efforts to break the status quo fail, we all lose a little. If we actually want to improve how science is organized, funded, and translated, we certainly can’t ridicule those trying. I want more people trying."
We’ve been heads down @ArcadiaScience for a bit but the @arenabioworks news this week caused me to dump thoughts. hard things are hard; don’t be such a fucking hater. Reflections on parallels w our own institutional experiment here
0
0
2
protein design is not solved. it is hard with no end in sight. but the pursuit is meaningful, credible, and will bear incredible fruit along the path
11
17
252
Extended deadline, manuscript and GitHub repo! Really excited for this end stage of the competition. We have about 220 registrations and have gotten a lot of great feedback from the community. It'll be cool to see which models come out of this!
We have 3 important updates to share regarding the antibody developability competition: 1.⏳ We're extending its final submission deadline to Monday, Nov 17 AOE (Anywhere on Earth) to align with the end of the 10-day AI x Bio Evolved25 Hackathon. (1/4)
0
1
1
I'll be presenting in the Bio session and also helping run the Math session! Come and listen to some awesome talks!!
Our first symposium is this weekend! Check out these three public flash talk events where nonbinary researchers from across scientific disciplines will present their work.
0
0
2
We're thrilled to announce SeqHub, an AI-enabled platform for biological sequence analysis. SeqHub brings together sequence search, genome annotation, and data sharing in one place. I dreamed of a single place where I could learn everything about my sequences. Today, a much more
13
106
530
YES +10000 GINA!!!!!
im excited for a world where we don’t need to computationally screen 10ks of designs for µM binders. nearly every pipeline now depends on this; depending on who you talk to, we are either missing better models, better discriminators, or both
1
1
5
Very happy to see this work come to life :D
Announcing our new protein design server https://t.co/uu4co1sHhq: • End-to-end protein design for everyone! • Analyze your generated library interactively and on 3D structures • Export codon-optimized DNA sequences for experimental testing. Developed in collaboration
0
0
1
an absolute shame. @harvard cutting PhD admissions "The Organismic and Evolutionary Biology department will shrink its class size by roughly 75 percent to three new Ph.D. students [...] Molecular and Cellular Biology will reduce its figure to four new students, and Chemistry and
thecrimson.com
Harvard FAS Cuts Ph.D. Seats By More Than Half Across Next Two Admissions Cycles | News | The Harvard Crimson
46
136
927
Happy to announce a new preprint from my former academic lab, where we use PACE to evolve halogenase enzymes! Congrats to Andre Pulschen and @justinbrbooth who led the study! A 🧵:
Continuous evolution of a halogenase enzyme with improved solubility and activity for sustainable bioproduction https://t.co/1myNQduYUv
#biorxiv_biochem
2
7
17
📣 Check out our Antibody Developability Competition announcement with @huggingface here: https://t.co/GihrUiien5, with up to $60k in prizes! 📷 Submissions close November 1st, 2025.
1
10
41
🧬 We’re hiring a Technical Project Manager I/II to keep GROQ-seq experiments on track and DNA design pipelines running smoothly. 📍 Remote | 🕒 Full-time ⏳ Apply by Sept 15 👉 https://t.co/pUmYJTWWzr
#AlignHiring #BiotechJobs
0
1
2
Antibody competition!! Love this - so many antibody prediction models exist and v curious to see the results 🥁
Announcing our FIRST AI competition: Antibody Developability Prediction Ginkgo Datapoints and @huggingface are teaming up to create the first open benchmark for AI-driven antibody developability modeling, with up to $60k in prizes.
0
1
7
very amped to see more of these competitions coming up!!
Super excited about this competition! Use your own developability predictors or build your own on our public dataset of 250 antibodies. We're hoping to benchmark the current state-of-the-art hydrophobicity/thermostability/etc models out there 🏆 (1/2)
0
1
4
all registered teams get freeeeeee ESM inference !
📣 Evolutionary Scale is supporting the 2025 Protein Engineering Tournament! Teams get sponsored ESM inference through @EvoscaleAI's API (Forge), bringing frontier protein AI models into the competition. Level playing field, real experiments, open results. Register now 👇
0
2
11
🚨New paper 🚨 Can protein language models help us fight viral outbreaks? Not yet. Here’s why 🧵👇 1/12
1
37
155
Happy to announce that PepMLM is now published in Nature Biotechnology @NatureBiotech after 2.5 years (in the pre-RFDiffusion era 🥲) A brief recap: We simply concatenate the target protein sequence with the peptide binder sequence, mask the whole binder region, and fine-tune
8
30
148
PepMLM is out in @NatureBiotech! 🎭Want a short binder for any target? Just input its sequence + desired binder length → PepMLM unmasks it. Simple? No way? The results speak for themselves. 👇 📜: https://t.co/RRZwQe82tu 💻: https://t.co/8l3nSNEtHo 🤗: https://t.co/9aSfxzZZTo
6
59
287
Why PETase for our tournament? In 2024, the world made about 30 million tonnes of PET plastic, most from fossil fuels. PETase can degrade PET, but isn’t ready for industrial-scale waste. The challenge: design an improved variant that can change that. Register by Oct 17 👇
1
13
27
Sea squirt!!
Most importantly, first in our new series of organismal spotlight shorts (open source illustrations coming soon!). Sea squirts!
0
0
0
I’ve thoroughly enjoyed reading two (VERY!) recent papers that model protein sequences by retrieving evolutionary information (dynamically) at inference time, and there's a lot to unpack! [1] https://t.co/NWzDzvYALu [2] https://t.co/H4tWxZwScl (1/n)
2
28
188