top of page

Binder-non Binder Discrimination of Therapeutic Antibodies

Our Classifier module has a 95% success ratio predicting if an antibody binds a specific epitope for 310 different antigens.

Binder-non Binder Discrimination of Therapeutic Antibodies

After antibody lead generation with conventional methods like screening with phage display, selected candidates bind different epitopes of the target. However, often antibodies that bind a certain epitope of interest are required. With AI, we can select antibodies that bind a specified epitope within days, significantly lowering the number of candidates for further cost-intensive characterization.

Our test included 310 different Antibody-Antigen pairs, where 60 of them where approved therapeutic antibodies and 250 were non-therapeutic antibodies. We add to each antibody additional 9 variants that differ from the original one to emulate drug discovery screening conditions.

As a result, our AI solution can accurately distinguish antibodies that bind a specified epitope from ones that don’t. The predicted probabilities for binders are strongly skewed towards 1.0 with mean predicted probability of 95%. The predicted probabilities for binding of the non-binders are strongly skewed towards 0.0 with mean predicted probability of 18%.

bottom of page