BioPhi: A platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning

Abstract

Despite recent advances in transgenic animal models and display technologies, humanization of mouse sequences remains one of the main routes for therapeutic antibody development. Traditionally, humanization is manual, laborious, and requires expert knowledge. Although automation efforts are advancing, existing methods are either demonstrated on a small scale or are entirely proprietary. To predict the immunogenicity risk, the human-likeness of sequences can be evaluated using existing humanness scores, but these lack diversity, granularity or interpretability. Meanwhile, immune repertoire sequencing has generated rich antibody libraries such as the Observed Antibody Space (OAS) that offer augmented diversity not yet exploited for antibody engineering. Here we present BioPhi, an open-source platform featuring novel methods for humanization (Sapiens) and humanness evaluation (OASis). Sapiens is a deep learning humanization method trained on the OAS using language modeling. Based on an in silico humanization benchmark of 177 antibodies, Sapiens produced sequences at scale while achieving results comparable to that of human experts. OASis is a granular, interpretable and diverse humanness score based on 9-mer peptide search in the OAS. OASis separated human and non-human sequences with high accuracy, and correlated with clinical immunogenicity. BioPhi thus offers an antibody design interface with automated methods that capture the richness of natural antibody repertoires to produce therapeutics with desired properties and accelerate antibody discovery campaigns. The BioPhi platform is accessible at https://biophi.dichlab.org and https://github.com/Merck/BioPhi.

Keywords: Antibody humanization; deep learning; deimmunization; human-likeness; humanness; immune repertoires; immunogenicity; machine learning.

Figure 1.

BioPhi integrated pipeline for bulk humanization (Sapiens) and humanness evaluation (OASis).

Figure 2.

Diversity of human antibody germlines compared to human antibody repertoires from OAS.

Figure 3.

OASis provides agranular and interpretable humanness score that is able to separate therapeutic antibodies of different origin.

Figure 4.

Attention within the Sapiens neural network captures long-range dependencies between antibody loops.

Figure 5.

Sapiens achieved abalanced humanness-preservation tradeoff on 25 antibodies with known parental sequences.

Figure 6.

Evaluation of humanization methods on alarge scale using 152 humanized therapeutic antibodies with putative parental sequences.