Towards a Greener AlphaFold2 Protocol for Antibody–Antigen Modeling: Insights From CAPRI Round 55

Abstract

In the 55th round of CAPRI, we used enhanced AlphaFold2 (AF2) sampling and data‐driven docking. Our AF2 protocol relies on Wallner's massive sampling approach, which combines different AF2 versions and sampling parameters to produce thousands of models per target. For T231 (an antibody‐peptide complex) and T232 (PP2A:TIPRL complex), we employed a 50‐fold reduced MinnieFold sampling and a custom ranking approach, leading to a top‐ranking medium prediction in both cases. For T233 and T234 (two antibody bound MHC I complexes), we followed data‐driven docking, which did not lead to an acceptable model. Our post‐CAPRI55 analysis showed that if we had used our MinnieFold approach on T233 and T234, we could have submitted a medium‐quality model for T233 as well. In the scoring challenge, we utilized the scoring function of FoldX, which was effective in selecting acceptable models for T231 and medium‐quality models for T232. Our success, especially in predicting and ranking a medium‐quality model for T231 and potentially for T233, underscores the feasibility of green and accurate enhanced AF2 sampling in antibody complex prediction.