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 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.