iiinova — where your digital self keeps evolving

Reposted by Odysseas Vavourakis

Jeffery Pendleton @jefferypendleton.bsky.social · 13/08/2026

A future does not have to be probable to matter. Our new paper asks how uncertain climate futures become cognitively and institutionally usable for decision-making, bringing together constructive memory, Mental Time Travel, scenario planning and deep uncertainty. www.frontiersin.org/journals/cog...

111

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

Many thanks to my collaborators Henriette Capel, Ben Williams, and Chris Taylor; to our incredible PI Charlotte Deane; and everyone else at the Oxford Protein Informatics Group @opig.stats.ox.ac.uk !

000

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

We look forward to seeing what you do with SAbDab2! Check it out: sabdab2.opig.stats.ox.ac.uk

100

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

We are also releasing antibody and AbAg complex structures processed specifically for AI/ML, alongside ready-made, similarity-based train/test splits. Unlike commonly used date-splits, these should mitigate against test-set contamination with structures similar to those seen in training.

110

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

Currently, published antibody structures are highly sequence-redundant. In SAbDab2, every antibody is given a stable SAbDab2 ID, which attaches to every known structure of that antibody across the entire PDB. This makes it easy to compare different conformations, bound states and more.

100

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

With improvements to our annotation pipeline, SAbDab2 contains more structures than ever before. With this release, we are introducing support for VNARs and a variety of novel antibody formats.

200

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

SAbDab2 collects, annotates, and organises all antibody structures in the PDB. This includes paired- and single-chain antibodies (like VHHs) in various formats, and antibody–antigen complexes. New data is added weekly.

110

Odysseas Vavourakis @odyv.bsky.social · 15/06/2026

Today, we're announcing SAbDab2! In brief: - clean, pre-processed antibody structure data for ML with standardised train/test splits - massive improvements in structure organisation and annotation consistency - support for VNARs and antibody construct annotation - more structures than ever before

173

Reposted by Odysseas Vavourakis

Mohammed AlQuraishi @moalquraishi.bsky.social · 13/03/2026

New OpenFold3 preview out! (OF3p2) It closes the gap to AlphaFold3 for most modalities. Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9

124590

Reposted by Odysseas Vavourakis

Jeffery Pendleton @jefferypendleton.bsky.social · 22/01/2026

I’m excited to share my first peer-reviewed publication, and my first first-author paper, "Time in mind: a multidisciplinary review on temporal perception, cognition, and memory" is now published open access in Frontiers in Cognition! www.frontiersin.org/journals/cog... #psychology #science #time

frontiersin.org

Frontiers | Time in mind: a multidisciplinary review on temporal perception, cognition, and memory

This review examines temporal cognition through the lens of Mental Time Travel (MTT): the subjective experience of recalling past events and using them to co...

141

Odysseas Vavourakis @odyv.bsky.social · 13/10/2025

Thank you for pointing this out. This was due to hitch in our update pipeline; ANARCI seems to number the sequence fine. This entry has now been corrected.

010

Reposted by Odysseas Vavourakis

Fabian Spoendlin @fspoendlin.bsky.social · 20/03/2025

Predicting protein conformational flexibility remains a major challenge in structural biology. While we can now accurately model static protein structures, understanding their dynamics is still difficult, largely due to a lack of suitable training data.

151

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

Huge thanks 🙌 to my fellow members of @opig.stats.ox.ac.uk: - our lead author Alex Greenshields-Watson - my co-authors Fabian Spoendlin and @mcagiada.bsky.social - and our extraordinary P.I. Charlotte Deane! Have questions or thoughts? Let’s discuss! 🧬

010

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

They also give rise to probabilistic metrics (e.g. conformational likelihoods) that could better reflect state occupancies and outperform current metrics as ranking and filtering criteria. Plus, generative models open the door to robust, antigen-conditional de novo design. 🚀 7/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

We also suggest generative approaches (like diffusion or flow matching) can help! Here’s why: • They target conformational distributions directly as the learning objective. • They sample these distributions efficiently. 6/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

We call for: 🧠 More ML-grade unbound data for training predictors, ✅ Better methods to rank/QC structure predictions + estimate uncertainty, 🔄 Improved flexibility/ensemble predictions, 🔬 Carrying multiple conformations into downstream analyses. 5/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

In other words, designing better-targeted, more reliable antibodies demands better handling of multiple conformations! Our paper highlights these challenges, reviews current antibody structure predictors (e.g. AF3, ESM3, ABodyBuilder3), and proposes key directions for progress. 4/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

Worse, this conformational heterogeneity directly affects antibody function! • Entropic contributions influence binding and affinity (ΔG=ΔH–TΔS). • Flexibility impacts many therapeutic traits. • Flexibility could even be exploited—e.g., pH-sensitive antibodies that “switch on” inside tumours! 🧪 3/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

Therapeutic antibodies are manufactured, stored, and administered in their free (unbound) state. So predicting that conformation is crucial! It’s also hard: 1️⃣ Most antibody structures in the PDB are bound forms, leaving little unbound data. 2️⃣ CDR loops are flexible—literal moving targets! 2/

100

Odysseas Vavourakis @odyv.bsky.social · 27/01/2025

It’s an exciting time in protein design! 🧬✨ But much of the therapeutic potential—especially for antibodies—remains untapped. Why? 🤔 Antibodies seem like ideal candidates for design! 💉 Here’s a quick thread summarising our new review paper on the state of antibody structure prediction. 👇 1/

sciencedirect.com

Challenges and compromises: Predicting unbound antibody structures with deep learning

Therapeutic antibodies are manufactured, stored and administered in the free state; this makes understanding the unbound form key to designing and imp…

181