Oxford Protein Informatics Group (OPIG)
@OPIGlets
Followers
2K
Following
179
Media
45
Statuses
525
Research group led by Charlotte Deane, based in the Department of Statistics at the University of Oxford.
Oxford, England
Joined November 2018
RT @AlissaHummer: Our work exploring the ability of and requirements for ML to predict the effects of mutations on antibody–antigen binding….
0
6
0
RT @NatComputSci: Out now! @AlissaHummer, @OPIGlets and colleagues present Graphinity, a method to predict change in antibody-antigen bindi….
www.nature.com
Nature Computational Science - Predicting the effects of mutations on antibody–antigen binding is a key challenge in therapeutic antibody development. Orders of magnitude more data will be...
0
6
0
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: More details here:
www.univ.ox.ac.uk
Professor Charlotte Deane MBE (1993, Chemistry) is a Professor in the Department of Statistics at the University of Oxford and the...
0
0
6
🚨 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. Apologies for any inconvenience.
1
0
3
RT @JCIM_JCTC: MolSnapper: Conditioning Diffusion for Structure-Based Drug Design #DrugDesign .@YaeliZiv @fergus_im….
pubs.acs.org
Generative models have emerged as potentially powerful methods for molecular design, yet challenges persist in generating molecules that effectively bind to the intended target. The ability to...
0
18
0
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.
0
1
10
RT @NicholasRuncie: 🚀 LLMs can now do chemistry! Our new preprint shows that state-of-the-art reasoning models can now perform advanced che….
0
12
0
RT @NeleQuast: Do you wish working with T-cell receptor structures was easier?.Us too!. STCRpy, our software suite for TCR structure parsin….
github.com
Contribute to npqst/STCRpy development by creating an account on GitHub.
0
2
0
Interviews are anticipated to be held 11th-13th June 2025. We proudly hold a Race Equality Charter Bronze Award and a departmental Athena SWAN Silver Award. We particularly welcome applications from candidates who remain underrepresented in positions of this type at Oxford.
0
0
0
We're hiring a Research Software Engineer to join OPIG and @OxfordStats!. This is a permanent role to support the group's world-leading open source tools. Grade 8 salary band £48k-£57k pa. Apply by 4th June 2025, noon UK time. Further details here:
1
2
3
MolSnapper has now been published in @JCIM_JCTC!. MolSnapper integrates expert knowledge into diffusion models for structure-based drug design using a conditioning approach. Congratulations @YaeliZiv, @fergus_imrie, Brian Marsden, and Charlotte Deane.
pubs.acs.org
Generative models have emerged as potentially powerful methods for molecular design, yet challenges persist in generating molecules that effectively bind to the intended target. The ability to...
0
9
40
RT @mijr12: Was an honour for our collaboration with Sarosh Irani's group to be recognised with the PNAS Cozzarelli Prize #immunoinformatic….
0
1
0
RT @fergus_imrie: 3-year postdoc opportunity as part of the Novo Nordisk - Oxford Fellowship programme! . Develop machine learning approach….
0
10
0
Work led by Alex Greenshields-Watson and Parth Agarwal, and initially began by Sarah Robinson. Many contributions from @HenrietteCapel, @GemmaLGordon, Fabian Spoendlin, Yushi Li, @BroncioS, Fergus Boyles, and Benjamin Williams. Project supervised by Charlotte Deane.
0
0
0
We will continue to update and develop the software so if you have feedback or suggestions don't hesitate to contact us.
1
0
0
For details on the model development, examples of how ANARCII can generalise to unseen sequence types such as VNARs, and how we used conditioning and fine-tuning to customise the numbering, please read the paper:
lnkd.in
This link will take you to a page that’s not on LinkedIn
1
0
0
We sought to find a balance between accuracy, generalisation, and inference speed - a combination of constraints that could not be solved by throwing larger models at the problem.
1
0
0
We wanted to build a tool that did not rely on traditional alignment algorithms or constructing HMMs from germline reference sets. Moving away from standard (and highly successful) approaches was a challenge that required us to work around intrinsic limitations of language models.
1
0
0
We have released the successor to ANARCI - ANARCII - a suite of Seq2Seq language models trained to number antibody (or TCR) sequences!. Read the paper: Play with the webtool: Documentation and codebase:
github.com
A language model suite for numbering antigen receptor sequences. - oxpig/ANARCII
1
6
27