Brennan Abanades

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Our manuscript "T-cell receptor structures and predictive models reveal comparable alpha and beta chain structural diversity despite differing genetic complexity" is now published in @CommsBio:

https://t.co/hWH7esAEGo

[Lewis Chinery @LewisChinery]

Happy to share our recent work on antibody library design, affinity prediction, and optimisation - 'Baselining the Buzz. Trastuzumab-HER2 affinity, and beyond!'

Preprint (inc. SI) - https://t.co/dlNOTfhOxA
Code - https://t.co/WVvOgsR1E4
Data - https://t.co/0AnCl4z1fb

🧵

[Tobias Hegelund Olsen @HegelundOlsen]

Super excited to share our latest preprint! We focus on a central issue with current pretrained LMs for antibody design. Please give the paper a read and reach out if you have any questions! 😊

[AlexGW @ALGW71]

Really happy to share our new study: Investigating the ability of deep learning-based structure prediction to extrapolate and/or enrich the set of antibody CDR canonical forms.

1/N

[AlexGW @ALGW71]

@RolandDunbrack Massive thanks to @brennanaba and Prof Charlotte Deane and the whole OPIG team!

Hope people find this interesting, and feel free to get in touch with any questions.

Looking forward to presenting this work at #AET2023 on Wednesday this week!

11/11

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

The paper describing our Patent and Literature Antibody Database (PLAbDab) is now out at @NAR_Open!

Public database: https://t.co/BuctkY7ZP6
Codebase: https://t.co/X2ziT1mvGi
Paper: https://t.co/EHehuBHDeK

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

AntiFold, our antibody inverse folding model fine-tuned from ESM-IF1, has been accepted at @NeurIPSConf @genbio_workshop (spotlight) and @workshopmlsb! This work was co-led by @magnushoie and @AlissaHummer, who will present it in New Orleans next month.

https://t.co/jwgvPa4R7X

[Alissa Hummer @AlissaHummer]

Structure-based antibody design is such an exciting & fast-paced field! 💥

Amazing how much progress has been made since we published this Current Opinion last year, but many of the challenges we described still remain

[Current Opinion/Research in Structural Biology @COSB_CRSB]

COSB #1 most downloaded article of 2022:
Advances in computational structure-based antibody design
@AlissaHummer @brennanaba
https://t.co/IakQ7HkiWr

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Strong OPIG representation at @ISMB 2023, come and talk to us!

1/4

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Our KA-Search tool for rapid and exhaustive mining through billions of antibody sequences for those with similarities to a query antibody has just been published by @SciReports! Work led by DPhil student @HegelundOlsen.

https://t.co/qwarOjuMJf

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Our recent study comparing the properties of antibody and nanobody binding sites has just been published in Frontiers in Immunology! Work led by DPhil student @GemmaLGordon.

https://t.co/W6ePsUiUNr

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Our latest database (PLAbDab) contains c. 65,000 non-redundant paired sequences & model structures of antibodies reported in the academic literature or patents, representing the largest minable reference set of functionally-characterised antibodies to date.

[Brennan Abanades @brennanaba]

Many thanks to everyone involved in this project!!! @HegelundOlsen , @mijr12 , @BroncioS , @WingKiCatherine , Guy Georges, Alexander Bujotzek, and @OPIGlets

[Brennan Abanades @brennanaba]

Our most recent piece of work "The Patent and Literature Antibody Database (PLAbDab): an evolving reference set of functionally diverse, literature-annotated antibody sequences and structures" has just been released on bioRxiv (https://t.co/JUHJV3PTfb)!!

[Brennan Abanades @brennanaba]

It's free, accessible, and built with the community in mind - you can find PLAbDab on our web server (https://t.co/DrzjvJMfNk) and on GitHub (https://t.co/YCaRazCCha).

[Leo Klarner @leoklarner]

Can we use scientific prior knowledge to make models more robust in low-data, OOD drug discovery?

In our new #ICML2023 paper, we use prior knlg of drug-like chemical space to regularize the function space of neural networks, improving OOD generalization.

https://t.co/AHZbCkmf1B

[Oxford Protein Informatics Group (OPIG) @OPIGlets]

Our most recent immunoinformatics preprint details improvements to our computational epitope binning software (SPACE2): we use the latest antibody 3D modeling technology & benchmark clustering on more precise datasets. Led by @fspoen in collab w/ @Roche

https://t.co/KBZvqIKEGi