Sign in

Oxford Protein Informatics Group (OPIG)

@opig.stats.ox.ac.uk
164 followers 30 following 73 posts

Research group led by Charlotte Deane, based in the Department of Statistics at the University of Oxford. opig.stats.ox.ac.uk

PostsRepliesMedia
Reposted by Oxford Protein Informatics Group (OPIG)
Benjie McMaster @benjamin-mcmaster.bsky.social · 20/07/2026
I am pleased to share our work “Characterising AlphaFold 3’s ability to predict T cell antigen specificity” (www.biorxiv.org/content/10.6...)!
biorxiv.org
Characterising AlphaFold 3’s ability to predict T cell antigen specificity
T cells are a key part of the adaptive immune system. Using their surface-bound T cell antigen receptors (TCRs), these cells scan peptides and other antigens presented to them by major histocompatibil...
131
Reposted by Oxford Protein Informatics Group (OPIG)
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
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 10/06/2026
Following an unexpectedly long outage of our website and web apps yesterday, our services are returning to normal. Please email us at opig@stats.ox.ac.uk if you still find any issues. We apologise for the disruption.
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 09/06/2026
Following some routine maintenance to our web servers, we are experiencing some delays in bringing OPIG's web services back up. We apologise for this and will post an update here when we have resolved the issue
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/04/2026
Please be aware that OPIG's web apps will be down for maintenance from 09:00 UTC on Tuesday 28th April 2026 and unavailable for a period of approximately one hour. Apologies for any inconvenience and for the short notice of this downtime.
000
Reposted by Oxford Protein Informatics Group (OPIG)
Department of Statistics @oxfordstatistics.bsky.social · 11/02/2026
What would you tell your younger self? For International Day of Women and Girls in Science, Professor Charlotte Deane shares her advice: worry a little bit less, and just go and do what you really enjoy doing. #IDWGS
051
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 20/01/2026
We are excited that Charlotte Deane will be speaking at NextGen Biomed 2026! NextGen Biomed runs from 24-25 March 2026 at the QEII Centre, London, UK. Pharma and biotech R&D leaders will come together to explore the future of biologics and immunotherapy hubs.la/Q03-WVg40 #NGB2026 #OGNextGenBiomed
020
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 19/01/2026
We're offering the following projects: Project 1 - "Machine Learning and AI for SARS-CoV-2 Mpro Inhibitor Discovery" with @garrettmm.bsky.social Project 2 - "Understanding the Effects of Data Quantity and Label Noise on Machine Learning Models in Drug Discovery" with @fergusimrie.bsky.social
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 19/01/2026
We are delighted to once again support the UNIQ+ programme and offer two projects in OPIG this summer! UNIQ+ is a paid summer research internship and is open to UK undergraduates from under-represented and disadvantaged backgrounds 📆 Applications close 18 Feb 👉 Apply: www.ox.ac.uk/admissions/g...
ox.ac.uk
UNIQplus | University of Oxford
UNIQplus is aimed at talented undergraduates from under-represented groups, who would find continuing into postgraduate study a challenge for reasons other than their academic ability. This section
110
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 07/01/2026
We're also happy to share that "Inferring residue level hydrogen deuterium exchange with ReX" by Oliver Crook, Charlotte Deane, and co-authors Nathan Gittens & Chun-wa Chung from GSK, was published in Communications Chemistry in the tail end of 2025. www.nature.com/articles/s42...
nature.com
Inferring residue level hydrogen deuterium exchange with ReX - Communications Chemistry
Hydrogen-Deuterium Exchange Mass-Spectrometry (HDX-MS) is a powerful method to study protein conformational dynamics, but peptide-level measurements obscure residue-level detail. The authors present R...
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 06/01/2026
Next, we are happy to announce that our pandemic preparedness orthopoxvirus antibody database “Pox-AbDab” has now been published in Frontiers in Immunology. First data update to come later in January! Paper: doi.org/10.3389/fimm... Database: opig.stats.ox.ac.uk/webapps/poxa...
doi.org
Frontiers | Pox-AbDab: the orthopoxvirus antibody database
In August 2024, the World Health Organization declared the mpox orthopoxvirus to be a Public Health Emergency of International Concern for the second time in...
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 05/01/2026
A happy new year from all at OPIG! We start the year with an article in Expert Opinion on Drug Discovery by Charlotte Deane and co-founders at DaltonTx. Here, they share a vision of integrating computation into drug discovery for maximum added value & efficiency www.tandfonline.com/doi/full/10....
tandfonline.com
From algorithms to systems: integrating computation into drug discovery
Despite remarkable advances in computational methods, pre-clinical drug discovery continues to grapple with rising timelines and costs. Software, data, and automation are more powerful than ever, a...
010
Reposted by Oxford Protein Informatics Group (OPIG)
Nele Quast @nele-q.bsky.social · 17/12/2025
I'm really pleased that our collaboration with Shira Sagie, Tomer Babu and Yardena Samuels has been published in Cell Reports Medicine. This has been a really fun and productive collaboration as well as an incredible learning process. www.cell.com/cell-reports...
cell.com
Lymphodepleting chemotherapy potentiates neoantigen-directed T cell therapy by enhancing antigen presentation
Sagie et al. identify a KRAS.G12V-specific TCR and show that lymphodepleting chemotherapy enhances antigen presentation via immunoproteasome activation and HLA-I upregulation. Together, these changes ...
111
Reposted by Oxford Protein Informatics Group (OPIG)
Matteo Cagiada @mcagiada.bsky.social · 12/11/2025
My first full contribution from my time in @opig.stats.ox.ac.uk is now out! Together with @fspoendlin.bsky.social (and with contributions from King Ifashe), we created FlAbDab and FTCRDab: two large-scale, open molecular dynamics datasets to study flexibility in immune receptors.
1156
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 03/11/2025
We highlight key advances and remaining challenges in this emerging structure-aware paradigm, and discuss how integrating protein information can enable AI to design molecules with stronger binding potential and real-world drug-like properties. Check out the paper: pubs.rsc.org/en/content/a...
pubs.rsc.org
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 03/11/2025
We cover the evolution from early shape-based strategies to modern co-folding models, detailing how different representations of protein pockets (voxel and graph) can encode structural information (shape, interactions, all-atom detail) and guide molecular generation.
110
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 03/11/2025
Excited to share our new review on deep learning for structure-based drug design! 🎉 pubs.rsc.org/en/content/a... Authors: @lucyvost.bsky.social*, Yael Ziv*, Charlotte Deane
120
Reposted by Oxford Protein Informatics Group (OPIG)
Nele Quast @nele-q.bsky.social · 31/10/2025
STCRpy, an easy-to-use python package for T-cell receptor structures has just been published in Bioinformatics! Big thanks to @mraybould.bsky.social and Charlotte Deane for their support, and to @opig.stats.ox.ac.uk for being an amazing collaborative group! Paper: doi.org/10.1093/bioi...
doi.org
STCRpy: a software suite for T-cell receptor structure parsing, interaction profiling, and machine learning dataset preparation
AbstractSummary. Computational methods to guide early-stage TCR drug discovery and TCR repertoire informatics currently under-utilize solved and predicted
021
Reposted by Oxford Protein Informatics Group (OPIG)
Nele Quast @nele-q.bsky.social · 29/10/2025
We won the Boltz Hackathon Challenge improving computational efficiency! Big thanks to Boltz team and @merckgroup.bsky.social for the event and very proud of our prototype Boltz Flow Matching model. Huge thanks to Niklas Abraham and Aaron Schöne for being excellent collaborators! ms.spr.ly/6043tBeAL
merckgroup.com
011
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 29/10/2025
Recently, Prof. Charlotte Deane participated in a discussion about AI as part of the Bradford Science Festival. Read some of her (and the other participants') thoughts here: blog.scienceandmediamuseum.org.uk/how-britain-...
blog.scienceandmediamuseum.org.uk
How Britain can harness the AI revolution - National Science and Media Museum blog
Roger Highfield, Science Director, reports on an AI discussion at the Bradford Science Festival.
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 24/10/2025
Great work by DPhil student Kate Fieseler. Thanks also to co-authors Max Winokan, Joseph Morrone, Charlotte Deane, Frank von Delft, and Warren Thompson
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 24/10/2025
Syndirella proposes congeneric series you can actually make (multi-step, digitized routes) and explores the pocket more broadly. Additionally, by buying reactants (not products), it allows you to test far more designs for the same budget
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 24/10/2025
📜 New preprint! Syndirella is a pipeline for proposing synthesis-directed elaborations for fragment-inspired designs with explicit routes and poses! Preprint: chemrxiv.org/engage/chemr... Code: github.com/oxpig/syndir...
chemrxiv.org
Syndirella: Synthesis-directed fragment elaboration enables extensive binding site exploration beyond catalog compounds
Fragment screens provide an information-rich starting point for designing derivative compounds that recapitulate key protein-ligand interactions in structure-based drug discovery. Maximizing the compo...
130
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 13/10/2025
Please be aware that OPIG's website and web apps will be down for maintenance from 09:30 UTC on Tuesday 14th October 2025, and will be unavailable for approximately one hour. Apologies for any inconvenience and for the short notice of this downtime.
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 09/10/2025
AIR Street Capital's "State of AI" 2025 Report references Nicholas Runcie, Charlotte Deane, and Fergus Imrie's work on Assessing the Chemical Intelligence of Large Language Models. Read the whole report here: stateof.ai And our preprint here: lnkd.in/gbuNXR93
stateof.ai
State of AI Report 2025
The State of AI Report analyses the most interesting developments in AI. Read and download here.
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 17/09/2025
If this sounds interesting, we’d love to hear from you (email deane@stats.ox.ac.uk or imrie@stats.ox.ac.uk)! Positions available to start immediately.
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 17/09/2025
Postdocs will contribute to: - Developing and applying AI/ML methods for small molecule design and selection - Running blind community challenges - Assessing the value of large-scale structural biology datasets
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 17/09/2025
🚨 We’re hiring! The OPIG group is looking for multiple postdocs to join OpenBind, an open science initiative generating foundational structural biology data to power the next era of AI/ML for drug discovery. opig.stats.ox.ac.uk openbind.uk
openbind.uk
OpenBind
122
Reposted by Oxford Protein Informatics Group (OPIG)
Agents of Tech @agentsoftech.bsky.social · 04/09/2025
New episode of Agents of Tech!🚨“AI is going to completely change the way we ask questions" We were thrilled to be joined at ISMB/ECCB by Prof. Charlotte Deane to discuss the changing role of AI in science and why humans will always be essential #ai #podcast @iscb.bsky.social
022
Reposted by Oxford Protein Informatics Group (OPIG)
Agents of Tech @agentsoftech.bsky.social · 08/09/2025
AI can’t work without data. OpenBind could spark the next revolution in AI drug discovery, building the datasets we need to predict how small molecules bind to proteins. Full episode out now! #AI #OpenBind #AlphaFold #Biotech #ArtificialIntelligence
031
Reposted by Oxford Protein Informatics Group (OPIG)
Agents of Tech @agentsoftech.bsky.social · 09/09/2025
“We are the third best country in the world at AI… that’s incredible. Start there.” Live from ISMB/ECCB, Professor Charlotte Deane reflects on the 'AI race' - is it really about competition? And does the UK have a true strategic advantage? @iscb.bsky.social #podcast #ai #academicsky #research
022
Reposted by Oxford Protein Informatics Group (OPIG)
Nature Computational Science @natcomputsci.nature.com · 25/08/2025
🚨Our August issue is now live and includes research on antibody-antigen binding, molecular screening for zeolite synthesis, psychological experiments with LLMs, and much more! www.nature.com/natcomputsci...
Yellow and orange antibody binding to purple and blue membrane proteins
052
Reposted by Oxford Protein Informatics Group (OPIG)
Alissa Hummer @alissahummer.com · 26/08/2025
Our paper on generalizable antibody-antigen binding affinity prediction has been featured on the cover of the August Issue of @natcomputsci.nature.com! 📔🎉
1101
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/08/2025
Our first pandemic preparedness database, Pox-AbDab, is now available! We present sequence, structural & functional data on antibodies and nanobodies that bind/neutralise orthopoxviruses: DB: opig.stats.ox.ac.uk/webapps/poxa... Preprint: doi.org/10.1101/2025... Work led by Henriette Capel
opig.stats.ox.ac.uk
Pox-AbDab
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/08/2025
Congratulations to the authors: Henriette Capel, Isaac Ellmen, Chris Murray, Giulia Mignone, Megan Black, Brendan Clarke, Conor Breen, Sean Tierney, Patrick Dougan, Richard Buick, Alex Greenshields-Watson, and Charlotte Deane, for their contributions and support on the project.
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/08/2025
See more in the Paper: www.biorxiv.org/content/10.1... GitHub: github.com/oxpig/LICHEN Web tool: opig.stats.ox.ac.uk/webapps/lich...
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/08/2025
LICHEN outputs are customisable and tuneable to experimental needs or desired content, enabling a collaborative light sequence design by leveraging computational capabilities alongside experimental expertise.
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/08/2025
Our preprint, LICHEN: Light-chain Immunoglobulin sequence generation Conditioned on the Heavy chain and Experimental Needs, is now on bioRxiv. LICHEN is a machine learning tool to generate an appropriate light sequence for a given heavy sequence. www.biorxiv.org/content/10.1...
biorxiv.org
LICHEN: Light-chain Immunoglobulin sequence generation Conditioned on the Heavy chain and Experimental Needs
In developing therapeutic antibodies, the heavy chain is often prioritised due to its higher variability and its central role in antigen binding. An appropriate pairing of the light sequence is howeve...
120
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 11/08/2025
🛠️ Web apps are back! We completed our scheduled maintenance this morning. If you notice any issues, please let us know at opig<~at~>stats.ox.ac.uk!
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 05/08/2025
🛠️ Scheduled maintenance Please be aware that OPIG's website, including our web apps, will be down for routine maintenance at 10:00 UTC on Monday 11th August 2025 for a period of approximately one hour. Apologies for any inconvenience.
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/07/2025
Project led by Isaac Ellmen together with @cschneider.bsky.social‬, @mraybould.bsky.social‬, and Charlotte Deane
000
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/07/2025
Compared to structural tokenization, Transformers imbued with coordinates maintain a better understanding of global contacts but may struggle with fine-grained reasoning We hope that this will help others in rationally designing Transformer-based protein structure models
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/07/2025
We investigate how models like AlphaFold3 and ESM2 learn to reason about structural data using standard inner-product attention. We show Transformers can learn a 3D analog of linear positional encoding to attend to nearby tokens in space.
100
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 28/07/2025
Our paper "Transformers trained on proteins can learn to attend to Euclidean distance" is now published in @tmlrorg.bsky.social @tmlr-pub.bsky.social openreview.net/forum?id=mU5...
openreview.net
Transformers trained on proteins can learn to attend to Euclidean...
While conventional Transformers generally operate on sequence data, they can be used in conjunction with structure models, typically SE(3)-invariant or equivariant graph neural networks (GNNs), for...
110
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 25/07/2025
Earlier this week at ISMB, Prof. Charlotte Deane spoke to @websedgetv.bsky.social for @iscb.bsky.social Spotlight TV. Check out what she had to say about AI, biological datasets, drug discovery, and so much more youtu.be/PyZbeoLsLuQ?... www.instagram.com/p/DMaQVr8tEF...
youtu.be
Building Reliable AI Systems for Bioinformatics
YouTube video by WebsEdge Science
040
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 02/07/2025
Professor Charlotte Deane is speaking this Thursday, 3rd July at her former college (Univ) as part of a session on Creativity and AI. Online and in-person tickets available (free for students) Profile: www.univ.ox.ac.uk/news/profile... More details here: www.univ.ox.ac.uk/event/univ-s...
univ.ox.ac.uk
Profile: Charlotte Deane - University College Oxford (Univ) Univ Oxford
Professor Charlotte Deane MBE (1993, Chemistry) is a Professor in the Department of Statistics at the University of Oxford and the...
010
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 16/06/2025
Thank you to all our users for your patience. The advertised routine maintenance is now complete. Please report any ongoing issues to opig@stats.ox.ac.uk
000
Reposted by Oxford Protein Informatics Group (OPIG)
haroldgrosjean.bsky.social @haroldgrosjean.bsky.social · 28/05/2025
🚨New preprint We extract structure–activity relationships (xSAR) directly from HT crystallography of crude reaction mixtures ⚡No hit resynthesis = faster DMTA 📄 doi.org/10.26434/che... @oxfordbiochemistry.bsky.social @diamondlightsource.bsky.social @opig.stats.ox.ac.uk @philbiggin.bsky.social #FBDD
041
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 13/06/2025
🚨 Website maintenance Please be aware that OPIG's website, including our web apps, will be down for routine maintenance at 08:30 UTC on Monday 16th June 2025 for a period of about two hours. We apologise for any inconvenience.
110
Oxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/05/2025
Come and find OPIG at #PEGSummit today (Thursday) C089: LICHEN: Light-Chain Immunoglobulin Sequence Generation Conditioned on the Heavy Chain and Experimental Needs - Henriette Capel C090: Predicting the Developability of Nanobodies to Improve Therapeutic Design - Gemma Gordon
030