Abstract
Docking calculations can accelerate drug discovery by predicting the bound poses of ligands for a targeted protein. However, it is not clear which docking methods work best. Furthermore, predicting poses requires steps outside the docking algorithm itself, such as preparation of the protein and ligand, and it is not known which components are most in need of improvement. The Continuous Evaluation of Ligand Protein Predictions (CELPP) is a blinded prediction challenge designed to address these issues. Participants create a workflow to predict protein-ligand binding poses, which is then tasked with predicting 10–100 new protein-ligand crystal structures each week. CELPP evaluates the accuracy of each workflow's predictions and posts the scores online. The results can be used to identify the strengths and weaknesses of current approaches, help map docking problems to the algorithms most likely to overcome them, and illuminate areas of unmet need in structure-guided drug design.
[Display omitted]
•The CELPP challenge evaluates protein-ligand pose prediction workflows•Participants are tasked with predicting dozens of complexes each week•We invite additional researchers to participate in CELPP
Docking calculations can accelerate drug discovery by predicting the bound poses of ligands for a targeted protein. However, it is not clear which docking methods work best. The Continuous Evaluation of Ligand Protein Predictions (CELPP) is a weekly public challenge designed to address this question.