Humatch is an antibody humanisation tool designed to offer experimental-like sequence humanisation in seconds.
- Humatch uses a set of convolutional neural networks trained to detect human heavy V-genes, light V-genes, and well-paired sequences to classify sequences and suggest mutations that will make sequences appear more human.
- CDR residues are excluded from the humanisation process, reducing the likelihood of humanisation affecting the binding properties of the antibody.
- Heavy and light chains are humanised concurrently, ensuring that the humanised heavy and light chain are likely to pair well.
The paper describing Humatch and its results can be found here:
Lewis Chinery, Jeliazko R. Jeliazkov, and Charlotte M. Deane. Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains., MAbs (2024).
If you are interested in analyising unpaired heavy/light chains, please take a look at our other humanisation tool, Hu-mAb
