Projects/CASF: Comparative assessment of scoring functions

Problem 53

• Title: CASF: Comparative assessment of scoring functions for protein-ligand docking problem
• Problem: We have to create a scoring model^ which predicts will the couple protein and ligand be a complex.
• Data: The project code contain two parts. The first one is ProbalilisticMetricSpaces, the second on in a notebook, by request.
• References:
  1. Convex-PL: a novel knowledge-based potential for protein-ligand interactions deduced from structural databases using convex optimization by Maria Kadukova and Sergei Grudinin, 2017[1]
  2. Predicting Binding Poses and Affinities in the CSAR 2013–2014 Docking Exercises Using the Knowledge-Based Convex-PL Potential by Sergei Grudinin et al, 2016[2]
  3. Comparative Assessment of Scoring Functions: The CASF-2016 Update by Minyi Su et al., 2018[3]
  4. Docking rigid macrocycles using Convex-PL, AutoDock Vina, and RDKit in the D3R Grand Challenge 4 Maria Kadukova et al., 2020[4]
• Basic solution: The solution is a linear combination, it is described in this paper, and draft.
• Method: We propose a novel approach to reconstruct distribution of bonding angles and solve the scoring problem as a problem of metric classification.
• Authors: Sergei Grudinin, Maria Kadukova, and Vadim Strijov

Current goals

1. To run the basic code with slight model variations and repeat the computational experiment
2. To combine the probability distributions with the basic code
3. To develop the model and beat the tests