Abstract
MotivationThe precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a model that relates antibody sequence to desired properties.ResultsHere, we present Ens-Grad, a machine learning method that can design complementarity determining regions of human Immunoglobulin G antibodies with target affinities that are superior to candidates derived from phage display panning experiments. We also demonstrate that machine learning can improve target specificity by the modular composition of models from different experimental campaigns, enabling a new integrative approach to improving target specificity. Our results suggest a new path for the discovery of therapeutic molecules by demonstrating that predictive and differentiable models of antibody binding can be learned from high-throughput experimental data without the need for target structural data.Availability and implementationSequencing data of the phage panning experiment are deposited at NIH’s Sequence Read Archive (SRA) under the accession number SRP158510. We make our code available at https://github.com/gifford-lab/antibody-2019.Supplementary information Supplementary data are available at Bioinformatics online.
Highlights
The identification of human antibodies and receptors with high affinity and specificity to human disease-associated targets is a key challenge in producing effective human therapeutics
We define enrichment as the log10 of the round-to-round ratio of sequence frequencies and Round 2 (R2)-to-Round 3 (R3) enrichment was used for training as it had a higher signal-to-noise ratio
We have found that machine learning-based methods are an effective way to both model and optimize antibody complementaritydetermining region sequences based upon experimental training data
Summary
The identification of human antibodies and receptors with high affinity and specificity to human disease-associated targets is a key challenge in producing effective human therapeutics. At present antibody sequences are discovered in vivo using animal immunization or by in vitro affinity selection of candidates from large synthetic libraries of antibody sequences (Breitling et al, 1991; McCafferty et al, 1990; O’Brien and Aitken, 2004; Scott and Barbas, 2001; Smith, 1985) These methods both have the advantage that they do not require the structure of a target to be known for antibodies to be discovered. Other approaches seek to optimize antibody properties primarily focused on predicting the structural conformation of the CDR-H3 loop, which to date remains a difficult unsolved challenge (Kuroda et al, 2012; Reczko et al, 1995) Many such approaches are based on calculations of binding free energies, where the multitude of possible expressions have been found to be of highly variable quality for predicting actual affinities in experiments (Kunik and Ofran, 2013; Moal et al, 2011).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
