banner
delalamo.xyz
Diego del Alamo
@delalamo.xyz
3.2K followers 2K following 1.8K posts
Computational protein engineering & synthetic biochemistry Opinions my own https://linktr.ee/ddelalamo
linktr.ee
Posts Media Videos Starter Packs
Pinned
delalamo.xyz
Diego del Alamo @delalamo.xyz · May 15
"Adapting ProteinMPNN for antibody design without retraining"

Our several-years-old fix to ProteinMPNN's tendency to make weird antibody CDR sequences is finally preprinted
Adapting ProteinMPNN for antibody design without retraining
The neural network ProteinMPNN designs protein sequences capable of folding into predefined tertiary structures and quaternary assemblies. It has become widely used due to its high success rates when ...
www.biorxiv.org
1 14 47
delalamo.xyz
Diego del Alamo @delalamo.xyz · 1d
The entire J-gene of PDB 7czv (3.3 Å, shown in salmon) seems to have fallen victim to a register/misassignment error, with the C-terminal valines (right) and tryptophan (center-left) on the wrong side of the beta sheet compared to where they would be expected to be
6
delalamo.xyz
Diego del Alamo @delalamo.xyz · 3d
The worst offender I've found so far is PDB 5OMM chain C on Sabdab, which has many unassigned residues despite being 1.7 Å resolution. For example its C-terminal VTVSS starts at IMGT pos 115 instead of pos 124. Probably AbNum/ANARCI struggling w/ the gaps

opig.stats.ox.ac.uk/webapps/sabd...
delalamo.xyz
Diego del Alamo @delalamo.xyz · 3d
I've put together a tool to renumber antibody structures using only main chain atomic coords. No sequence info is used at all. In the process I found a few numbering mistakes in Sabdab/PDB, which is numbered by sequence & thus sensitive to gaps/register errors (deleted prev post due to bugs)
GitHub - delalamo/SAbR: Structure-based antibody renumbering
Structure-based antibody renumbering. Contribute to delalamo/SAbR development by creating an account on GitHub.
github.com
1 2 12
delalamo.xyz
Diego del Alamo @delalamo.xyz · 8d
I flirted with doing something like this a year or two ago - prepending a mAb-specific structure prediction NN to the AF2 template input for mAb design by hallucination - but was stopped by the fact that every Bio/ML NN is in PyTorch except AF2 which is written in freaking JAX
aixbiobot.bsky.social
AI x Bio Discovery @aixbiobot.bsky.social · 9d
mBER: Controllable de novo antibody design with million-scale experimental screening [new]
Ab design via seq/struct conditioning designs VHHs. Million-scale screens show success.
mBER: Controllable de novo antibody design with million-scale experimental screening Figure 1 Figure 2 Figure 3
1 1 8
delalamo.xyz
Diego del Alamo @delalamo.xyz · 8d
One mo'
mBER: Controllable de novo antibody design with million-scale experimental screening
Recent machine learning approaches have achieved high success rates in designing protein binders that demonstrate in vitro binding to their targets. While open models for unconstrained "minibinder" de...
www.biorxiv.org
2
Reposted by Diego del Alamo
nboyd.bsky.social
Nick Boyd @nboyd.bsky.social · 11d
It's a very cool result but IMO there are caveats. Inference is (mostly) slower. There is existing work on faster models (e.g. MiniFold or protenix mini), and also existing work on ensemble prediction. I doubt this works without training on AFDB, which bakes in inductive bias from triangle layers
1 1 10
delalamo.xyz
Diego del Alamo @delalamo.xyz · 12d
Oh interesting, what’s the TLDR for where these mutations are located? Will read later
1 1
delalamo.xyz
Diego del Alamo @delalamo.xyz · 13d
Still boggles my mind that we can leave frameworks as-is and only edit CDRs and still reliably get nM binders. Complete opposite of what I would have expected given how hard it is to graft CDRs from one FW to another (such as humanizing mouse mAbs). First RFantibody and now this
arcinstitute.org
Arc Institute @arcinstitute.org · 14d
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.
1 3 11
Reposted by Diego del Alamo
franknoe.bsky.social
Frank Noe @franknoe.bsky.social · 14d
Postdoc position available in the BioEmu team at @msftresearch.bsky.social AI for Science - Berlin DE or Cambridge UK. Looking for candidates with backgrounds in #MachineLearning #AI Biophysics or Bioinformatics

jobs.careers.microsoft.com/global/en/jo...
9 13
delalamo.xyz
Diego del Alamo @delalamo.xyz · 14d
Apple now has a protein folding NN?...

arxiv.org/pdf/2509.18480
7 19
delalamo.xyz
Diego del Alamo @delalamo.xyz · 14d
How to request your swiss criminal record:
1. Fill out a form online
2. Pay a processing fee, also online
3. Print form and put it in an envelope and MAIL it
4. Receive criminal record by email
1 2
delalamo.xyz
Diego del Alamo @delalamo.xyz · 18d
It’s a bit goofy. I think RosettaFold2 is also still in peer review and RosettaFold3 is out?
1
delalamo.xyz
Diego del Alamo @delalamo.xyz · 18d
The only thing more compelling than this preprint's science are the names of some of its authors
alexis-verger.cpesr.fr
Alexis Verger 🧬🧫🧪 @alexis-verger.cpesr.fr · 19d
De novo design of All-atom biomolecular interactions with RFdiffusion3 www.biorxiv.org/content/10.1...
De novo Design of All-atom Biomolecular Interactions with RFdiffusion3
Deep learning has accelerated protein design, but most existing methods are restricted to generating protein backbone coordinates and often neglect interactions with other biomolecules. We present RFd...
www.biorxiv.org
2
delalamo.xyz
Diego del Alamo @delalamo.xyz · 18d
This upcoming week is my last week at GSK. I’m going to move on to greener pastures but first a few weeks off to … close on a house! Go for some bike rides! Paint 40k models! Etc.!
12
Reposted by Diego del Alamo
delalamo.xyz
Diego del Alamo @delalamo.xyz · 19d
Yep. Reminds me of the bar plot error bars that were just capital Ts
1 1 6
delalamo.xyz
Diego del Alamo @delalamo.xyz · 19d
Yep. Reminds me of the bar plot error bars that were just capital Ts
1 1 6
delalamo.xyz
Diego del Alamo @delalamo.xyz · 19d
Protein language models can predict epistasis (non-additivity of multiple point mutations) if predictions are nonlinearly transformed first www.biorxiv.org/content/10.1...
2 15
delalamo.xyz
Diego del Alamo @delalamo.xyz · 19d
I posted this on the other site and will repost here: something is fishy with Fig 2F results on inverse folding performance (left). Variance is way too low. Compare that to my results preprinted earlier this year (right). Definitely causing me to scrutinize other results in this paper more closely
1 8
delalamo.xyz
Diego del Alamo @delalamo.xyz · 19d
Does anyone know of an NN-based drop-in replacement for protein side chain repacking (e.g., Rosetta repack/SCWRL)? Ideally something lightweight
2 1
Reposted by Diego del Alamo
lindorfflarsen.bsky.social
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 21d
New review on computational design of intrinsically disordered proteins 🖥️🍝 by @giuliotesei.bsky.social @fpesce.bsky.social & 👴

doi.org/10.48550/arX...
Figure 3 from the paper with the caption: "Role of machine learning in de novo design of IDRs. (A) Machine-learning models can be trained on diverse data sources, from molecular dynamics simulations to annotations of cellular localization and protein structures from the Protein Data Bank. (B) Often implemented as neural networks using sequence-encoded features as input, these models can initially be trained on a limited region of sequence space as surrogate models. Through active learning, additional simulations are performed during the design campaign to generate new data, and the surrogate model is retrained on the expanded dataset to progressively improve its accuracy. (C) Machine-learning models have been developed to predict biophysical observables, biological annotations, and protein structures. When combined, machine-learning models can be used to identify a set of sequences that strike a trade-off between multiple design objectives, defining a Pareto front."
16 48
delalamo.xyz
Diego del Alamo @delalamo.xyz · 25d
This was a great read! If it were up to me, this specific part of rule #4 would be expanded into a full Opinion piece, because proteins for structural characterization are definitely not sampled IID from uniprot/wherever
2 1 6
Reposted by Diego del Alamo
stephanieaw.bsky.social
Stephanie Wankowicz @stephanieaw.bsky.social · 27d
Structural bioinformatics is incredibly powerful on its own or when paired with theory or experiment. One of the PDB's superpowers isn’t from one structure, but comparing many to uncover folds, binding sites, and subtle conformational shifts. chemrxiv.org/engage/chemr...
10 Rules for a Structural Bioinformatic Analysis
The Protein Data Bank (PDB) is one of the richest open‑source repositories in biology, housing over 277,000 macromolecular structural models alongside much of the experimental data that underpins thes...
chemrxiv.org
1 15 54
delalamo.xyz
Diego del Alamo @delalamo.xyz · 26d
Time to test their claim that diffusion is competitive with hallucination in generating realistic backbones of huge (>800 AA) proteins...
2 11
Reposted by Diego del Alamo
anthonygitter.bsky.social
Anthony Gitter @anthonygitter.bsky.social · 26d
The journal version of "Biophysics-based protein language models for protein engineering" with @philromero.bsky.social is live! Mutational Effect Transfer Learning (METL) is a protein language model trained on biophysical simulations that we use for protein engineering. 1/

doi.org/10.1038/s415...
Biophysics-based protein language models for protein engineering - Nature Methods
Mutational effect transfer learning (METL) is a protein language model framework that unites machine learning and biophysical modeling. Transformer-based neural networks are pretrained on biophysical ...
doi.org
1 2 13
delalamo.xyz
Diego del Alamo @delalamo.xyz · 27d
Can anyone familiar with the economics of this situation explain how UK salaries can be 1/3 of US salaries, yet the UK is still described as being more unfriendly for R&D than the US, even when the quality of the work being done is largely the same?
financialtimes.com
Financial Times @financialtimes.com · 28d
Merck scraps £1bn London drug research centre in blow to UK growth on.ft.com/3I1IBWR
Merck scraps £1bn London drug research centre in blow to UK growth
US company says Britain ‘is not internationally competitive’ as it lays off 125 staff
on.ft.com
3