Journal
MABS
Volume 14, Issue 1, Pages -Publisher
TAYLOR & FRANCIS INC
DOI: 10.1080/19420862.2022.2069075
Keywords
Antibody repertoires; deep learning; machine learning; deep sequencing; convolutional neural networks; generative adversarial networks
Categories
Ask authors/readers for more resources
This study utilized deep learning methods to investigate antibody sequences, encoding antibody images and training neural network models for classification, and further generating synthetic antibodies using generative adversarial network models. The results demonstrate that deep learning methods can offer insights into antibody engineering, optimization, and discovery by mining and learning patterns in antibody sequences.
The antibody drug field has continually sought improvements to methods for candidate discovery and engineering. Historically, most such methods have been laboratory-based, but informatics methods have recently started to make an impact. Deep learning, a subfield of machine learning, is rapidly gaining prominence in the biomedical research. Recent advances in microfluidics technologies and next-generation sequencing have not only revolutionized therapeutic antibody discovery, but also contributed to a vast amount of antibody repertoire sequencing data, providing opportunities for deep learning-based applications. Previously, we used microfluidics, yeast display, and deep sequencing to generate a panel of binder and non-binder antibody sequences to the cancer immunotherapy targets PD-1 and CTLA-4. Here we encoded the antibody light and heavy chain complementarity-determining regions (CDR3s) into antibody images, then built and trained convolutional neural network models to classify binders and non-binders. To improve model interpretability, we performed in silico mutagenesis to identify CDR3 residues that were important for binder classification. We further built generative deep learning models using generative adversarial network models to produce synthetic antibodies against PD-1 and CTLA-4. Our models generated variable length CDR3 sequences that resemble real sequences. Overall, our study demonstrates that deep learning methods can be leveraged to mine and learn patterns in antibody sequences, offering insights into antibody engineering, optimization, and discovery.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available