Nick Boyd
@nboyd.bsky.social
optimization, inverse problems, also proteins. ml at escalante. formerly: atomicai, xgenomes, broad, berkeley.
vibe translated ligand/protein/soluble-mpnn from PyTorch to JAX. not sure if this works, but it was pretty fun and took 45 minutes of my time. Claude Code is going to make my virtuous no-torch lifestyle a lot easier... github.com/nboyd/jigand...
GitHub - nboyd/jigandmpnn: Fully vibe-coded translation of ligand/soluble/etc+proteinMPNN to JAX/eqx
Fully vibe-coded translation of ligand/soluble/etc+proteinMPNN to JAX/eqx - nboyd/jigandmpnn
github.com
January 13, 2026 at 2:58 PM
vibe translated ligand/protein/soluble-mpnn from PyTorch to JAX. not sure if this works, but it was pretty fun and took 45 minutes of my time. Claude Code is going to make my virtuous no-torch lifestyle a lot easier... github.com/nboyd/jigand...
Loved this post from A-Alpha: aalphabio.substack.com/p/building-a.... If anything I think the IPSAE (or any other post-hoc metric) picture is even worse than they show: after optimization the fraction of false positives would (probably) be even higher than in this dataset
Building antibodies blindfolded: the paradox of de novo design
By Natasha Murakowska and Joseph Harman
aalphabio.substack.com
January 9, 2026 at 10:46 PM
Loved this post from A-Alpha: aalphabio.substack.com/p/building-a.... If anything I think the IPSAE (or any other post-hoc metric) picture is even worse than they show: after optimization the fraction of false positives would (probably) be even higher than in this dataset
finally wrote up some notes on the adaptyv competition: blog.escalante.bio/180-lines-of....
~180 lines of code to win the in silico portion of the Adaptyv Nipah binding competition
Here's the script we used to get 1st place in the in silico portion of the Adaptyv Nipah competition:
import modal
def download_boltz2():
from mosaic.models.boltz2 import Boltz2
Boltz2()
...
blog.escalante.bio
January 8, 2026 at 3:50 PM
finally wrote up some notes on the adaptyv competition: blog.escalante.bio/180-lines-of....
PXdesign finally open-sourced with a permissive license. Hopefully it will get more attention now, imo one of the best current binder design methods github.com/bytedance/PX...
GitHub - bytedance/PXDesign: Official repository of PXDesign
Official repository of PXDesign. Contribute to bytedance/PXDesign development by creating an account on GitHub.
github.com
December 18, 2025 at 3:37 AM
PXdesign finally open-sourced with a permissive license. Hopefully it will get more attention now, imo one of the best current binder design methods github.com/bytedance/PX...
Phage (or maybe cDNA or something more exotic?) display as a service is an interesting offering: www.diffuse.bio/ramax-fast-s.... Turnaround time is impressively short.
RamaX: Fast, Selective, Sensitive Screening Platform
www.diffuse.bio
December 16, 2025 at 6:43 PM
Phage (or maybe cDNA or something more exotic?) display as a service is an interesting offering: www.diffuse.bio/ramax-fast-s.... Turnaround time is impressively short.
oh, this is nice: x.com/proteinbase/.... only a few lines of code…
December 3, 2025 at 7:26 PM
oh, this is nice: x.com/proteinbase/.... only a few lines of code…
Vote for @martinpacesa.bsky.social ‘s designs in the adaptyv nipah virus competition: proteinbase.com/collections/.... because they’ll actually bind
Submission 1
This is a submission to the Nipah Binder Competition competition.
proteinbase.com
December 3, 2025 at 1:51 AM
Vote for @martinpacesa.bsky.social ‘s designs in the adaptyv nipah virus competition: proteinbase.com/collections/.... because they’ll actually bind
always amazes me that you can take code written on an A10, change a single line and get power utilization like this in JAX
November 14, 2025 at 4:52 PM
always amazes me that you can take code written on an A10, change a single line and get power utilization like this in JAX
hack to get more diverse binders out of BoltzGen: sample an unconditional monomer, then sample a binder with secondary structure conditioning to match the monomer. this solves the long-standing open problem of generating 76 AA binders that aren't ubiquitin.
November 4, 2025 at 3:15 PM
hack to get more diverse binders out of BoltzGen: sample an unconditional monomer, then sample a binder with secondary structure conditioning to match the monomer. this solves the long-standing open problem of generating 76 AA binders that aren't ubiquitin.
Playing around with a JAX translation of @gcorso.bsky.social et al's BoltzGen (github.com/escalante-bi...). Super fun model! Has anyone tried skipping the inverse folding step for binder design? I'm wondering how well the all-atom designs do on their own...
GitHub - escalante-bio/joltzgen: JAX translation of BoltzGen
JAX translation of BoltzGen. Contribute to escalante-bio/joltzgen development by creating an account on GitHub.
github.com
October 31, 2025 at 9:37 PM
Playing around with a JAX translation of @gcorso.bsky.social et al's BoltzGen (github.com/escalante-bi...). Super fun model! Has anyone tried skipping the inverse folding step for binder design? I'm wondering how well the all-atom designs do on their own...
This paper is incredible; IMO large-scale, unbiased data is our best chance to get beyond the relatively small set of sequences that AlphaFold loves
Our latest work seeks to answer a longstanding question: why is discovering new protein binders seemingly unpredictable – and can we better quantify and understand the de novo binder discover process? 1/12
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Mapping the diverse topologies of protein-protein interaction fitness landscapes
De novo binder discovery is unpredictable and inefficient due to a lack of quantitative understanding of protein-protein interaction (PPI) sequence-function landscapes. Here, we use our PANCS-Binder t...
www.biorxiv.org
October 17, 2025 at 7:24 PM
This paper is incredible; IMO large-scale, unbiased data is our best chance to get beyond the relatively small set of sequences that AlphaFold loves
proteinbase.com from @adaptyv.bio looks amazing - hundreds of open-source binding affinity measurements. It’s hard to overstate the value of high-quality, uniform affinity data for training and evaluating filtering and ranking methods
Proteinbase
The home of protein design data
proteinbase.com
October 3, 2025 at 11:19 PM
proteinbase.com from @adaptyv.bio looks amazing - hundreds of open-source binding affinity measurements. It’s hard to overstate the value of high-quality, uniform affinity data for training and evaluating filtering and ranking methods
Another great post on binder design from @btnaughton.bsky.social !
New blogpost on the latest in AI antibody design.
Including some code to easily run Germinal and IgGM on modal!
blog.booleanbiotech.com/ai-antibody-...
Including some code to easily run Germinal and IgGM on modal!
blog.booleanbiotech.com/ai-antibody-...
Boolean Biotech
blog.booleanbiotech.com
September 29, 2025 at 1:16 AM
Another great post on binder design from @btnaughton.bsky.social !
Great nanobody design paper from @brianhie.bsky.social and @synbiogaolab.bsky.social ! Amazing what combining a few public models can do
In another preprint from the @brianhie.bsky.social Lab and @synbiogaolab.bsky.social, they introduce Germinal, a generative AI system for de novo antibody design.
Germinal produces functional nanobodies in just dozens of tests, making custom antibody design more accessible than ever before.
Germinal produces functional nanobodies in just dozens of tests, making custom antibody design more accessible than ever before.
September 24, 2025 at 3:54 PM
Great nanobody design paper from @brianhie.bsky.social and @synbiogaolab.bsky.social ! Amazing what combining a few public models can do
Reposted by Nick Boyd
Today we're dropping the "beta" tag from Adaptyv, launching our new website and announcing our $8M seed round.
When we started Adaptyv a few years ago, our core belief was: AI models for biology are only as good as the lab data they're trained on and the hypotheses they can test in the real world.
When we started Adaptyv a few years ago, our core belief was: AI models for biology are only as good as the lab data they're trained on and the hypotheses they can test in the real world.
September 18, 2025 at 5:40 PM
Today we're dropping the "beta" tag from Adaptyv, launching our new website and announcing our $8M seed round.
When we started Adaptyv a few years ago, our core belief was: AI models for biology are only as good as the lab data they're trained on and the hypotheses they can test in the real world.
When we started Adaptyv a few years ago, our core belief was: AI models for biology are only as good as the lab data they're trained on and the hypotheses they can test in the real world.
Reposted by Nick Boyd
Looks interesting (particularly for in silico affinity maturation) & code available on github: github.com/TencentAI4S/...
September 16, 2025 at 9:59 PM
Looks interesting (particularly for in silico affinity maturation) & code available on github: github.com/TencentAI4S/...
Recently tested some de-novo minibinders against two targets (thanks Adaptyv!) designed using our open-source design library, `mosaic`; our best method got hit rates of 7/10 and 8/10 and affinities as low as single-digit nanomolar. Wrote up some thoughts here: blog.escalante.bio/minibinder-d...
September 2, 2025 at 2:39 PM
Recently tested some de-novo minibinders against two targets (thanks Adaptyv!) designed using our open-source design library, `mosaic`; our best method got hit rates of 7/10 and 8/10 and affinities as low as single-digit nanomolar. Wrote up some thoughts here: blog.escalante.bio/minibinder-d...
Reposted by Nick Boyd
Have no fear if you weren't in the packed audience this week for @martinpacesa.bsky.social's awesome seminar, because you can check out the recording 👇
youtu.be/qQihl6If9vU
youtu.be/qQihl6If9vU
BindCraft: one-shot design of functional protein binders
YouTube video by Boston Protein Design and Modeling Club
youtu.be
August 15, 2025 at 8:56 PM
Have no fear if you weren't in the packed audience this week for @martinpacesa.bsky.social's awesome seminar, because you can check out the recording 👇
youtu.be/qQihl6If9vU
youtu.be/qQihl6If9vU
Reposted by Nick Boyd
✨Cradle is hiring protein+ML researchers!✨
We operate ML for lab-in-the-loop lead optimization across all industries (pharma, synbio, ...), modalities (antibodies, enzymes, ...), properties (binding, activity, ...)
We're a scaleup and already relied upon by 4 of the top 20 big pharma.
Apply here!
We operate ML for lab-in-the-loop lead optimization across all industries (pharma, synbio, ...), modalities (antibodies, enzymes, ...), properties (binding, activity, ...)
We're a scaleup and already relied upon by 4 of the top 20 big pharma.
Apply here!
Machine Learning Researcher in Protein Design (f/m/*)
Join a scaleup researching and operating ML-guided lead optimization of proteins. This means developing a combination of protein language models, and multi-property prediction and generation.
jobs.ashbyhq.com
June 18, 2025 at 1:55 PM
✨Cradle is hiring protein+ML researchers!✨
We operate ML for lab-in-the-loop lead optimization across all industries (pharma, synbio, ...), modalities (antibodies, enzymes, ...), properties (binding, activity, ...)
We're a scaleup and already relied upon by 4 of the top 20 big pharma.
Apply here!
We operate ML for lab-in-the-loop lead optimization across all industries (pharma, synbio, ...), modalities (antibodies, enzymes, ...), properties (binding, activity, ...)
We're a scaleup and already relied upon by 4 of the top 20 big pharma.
Apply here!
We added Boltz-2 to our protein design package! Under the hood this relies on a JAX translation, which, thanks to @jeremywohlwend.bsky.social and @gcorso.bsky.social ’s clean code, was fairly easy to write. We’ve been getting great results -- and we have yet to explore the most exciting new features
June 12, 2025 at 8:52 PM
We added Boltz-2 to our protein design package! Under the hood this relies on a JAX translation, which, thanks to @jeremywohlwend.bsky.social and @gcorso.bsky.social ’s clean code, was fairly easy to write. We’ve been getting great results -- and we have yet to explore the most exciting new features
Designed my (the?) first minibinder using @gcorso.bsky.social 's new Boltz-2 model. Excited to explore how templates and increased MSA dropout impact binder design. This is work in progress but will be open sourced as usual
June 9, 2025 at 6:01 PM
Designed my (the?) first minibinder using @gcorso.bsky.social 's new Boltz-2 model. Excited to explore how templates and increased MSA dropout impact binder design. This is work in progress but will be open sourced as usual
Want to try ESMC but don't want to switch from #JAX to pytorch?
Here’s a super barebones translation to @patrickkidger.bsky.social's excellent equinox: github.com/escalante-bi...
Here’s a super barebones translation to @patrickkidger.bsky.social's excellent equinox: github.com/escalante-bi...
GitHub - escalante-bio/esmj: jax translation of esmc
jax translation of esmc. Contribute to escalante-bio/esmj development by creating an account on GitHub.
github.com
May 8, 2025 at 7:53 PM
Want to try ESMC but don't want to switch from #JAX to pytorch?
Here’s a super barebones translation to @patrickkidger.bsky.social's excellent equinox: github.com/escalante-bi...
Here’s a super barebones translation to @patrickkidger.bsky.social's excellent equinox: github.com/escalante-bi...