Abstract
Antibodies are a popular and powerful class of therapeutic due to their ability to exhibit high affinity and specificity to target proteins. However, the majority of antibody therapeutics are not genetically human, with initial therapeutic designs typically obtained from animal models. Humanization of these precursors is essential to reduce immunogenic risks when administered to humans.Here, we present Humatch, a computational tool designed to offer experimental-like joint humanization of heavy and light chains in seconds. Humatch consists of three lightweight Convolutional Neural Networks (CNNs) trained to identify human heavy V-genes, light V-genes, and well-paired antibody sequences with near-perfect accuracy. We show that these CNNs, alongside germline similarity, can be used for fast humanization that aligns well with known experimental data. Throughout the humanization process, a sequence is guided toward a specific target gene and away from others via multiclass CNN outputs and gene-specific germline data. This guidance ensures final humanized designs do not sit 'between' genes, a trait that is not naturally observed. Humatch's optimization toward specific genes and good VH/VL pairing increases the chances that final designs will be stable and express well and reduces the chances of immunogenic epitopes forming between the two chains. Humatch's training data and source code are provided open-source.