GitHub - oxpig/ITsFlexible: Prediction of Antibody CDR and protein loop flexibility Prediction of Antibody CDR and protein loop flexibility - oxpig/ITsFlexible

Code: github.com/oxpig/ITsFle...
Paper: www.nature.com/articles/s42...

Thanks to my co-authors Monica Fernández-Quintero, Sai Raghavan, Hannah Turner, Anant Gharpure, Johannes Loeffler, Catherine Wong, Guy Georges, Alexander Bujotzek, Andrew Ward, and Charlotte Deane

2. We developed ITsFlexible, a graph-based deep learning model that predicts the flexibility of CDR3 loops. It surpasses existing methods on crystal structures, generalizes to molecular dynamics, and in three challenging cases is validated by cryo-EM.

In this work, we address this challenge in the context of CDR loops:

1. We present ALL-conformations, a large dataset of 1.2 million loop structures capturing all experimentally observed conformations of CDR3s and related motifs.

Check out our new paper in Nature Machine Intelligence on predicting the structural flexibility of antibody and TCR CDR loops. Although methods like AlphaFold have transformed static structure prediction, capturing conformational dynamics remains a challenge.

GitHub - oxpig/ANARCII: A language model suite for numbering antigen receptor sequences. A language model suite for numbering antigen receptor sequences. - oxpig/ANARCII

We have released the successor to ANARCI - ANARCII - a suite of Seq2Seq language models trained to number antibody (or TCR) sequences!

Read the paper: biorxiv.org/content/10.1...

Play with the webtool: opig.stats.ox.ac.uk/webapps/sabd...

Documentation and codebase: github.com/oxpig/ANARCII

Predicting the conformational flexibility of antibody and T-cell receptor CDRs Many proteins are highly flexible and their ability to adapt their shape can be fundamental to their functional properties. We can now computationally predict a single, static protein structure with h...

Check out the preprint at: www.biorxiv.org/content/10.1...

Thanks to my co-authors Monica Fernández-Quintero, Sai Raghavan, Hannah Turner, Anant Gharpure, Johannes Loeffler, Catherine Wong, Guy Georges, Alexander Bujotzek, Andrew Ward, and Charlotte Deane

2. We introduce ITsFlexible, a tool that predicts CDR3 flexibility with high accuracy evaluated on crystal structure and MD data. Furthermore, we experimentally validate predictions of three challenging case studies using cryo-EM providing fruther evidence for ITsFlexible’s predictive accuracy.

In our latest work, focusing on antibody and TCR CDRs, we take a step towards addressing this challenge:

1. We release ALL-conformations, a large dataset of 1.2 million structures capturing all experimentally observed conformational states of CDR3 loops and related loop motifs.

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.