MILCDock: Machine Learning Enhanced Consensus Docking for Virtual Screening in Drug Discovery

Abstract

Molecular docking tools are regularly used to computationally identify new molecules in virtual screening for drug discovery. However, docking tools suffer from inaccurate scoring functions with widely varying performance on different proteins. To enable more accurate ranking of active over inactive ligands in virtual screening, we created a machine learning consensus docking tool, MILCDock, that uses predictions from five traditional molecular docking tools to predict the probability a ligand binds to a protein. MILCDock was trained and tested on data from both the DUD-E and LIT-PCBA docking datasets and shows improved performance over traditional molecular docking tools and other consensus docking methods on the DUD-E dataset. LIT-PCBA targets proved to be difficult for all methods tested. We also find that DUD-E data, although biased, can be effective in training machine learning tools if care is taken to avoid DUD-E's biases during training.

Ligand binding affinity prediction with fusion of graph neural networks and 3D structure-based complex graph

“…Accurate prediction of protein-ligand binding affinity remains one of the grand challenges of computational chemistry and biology. [1][2][3] With the ever increasing amount of high-resolution experimentally determined protein-ligand structures, 4 the binding affinity prediction methods have switched from physicsbased [5][6][7][8][9][10][11] to empirical scoring functions [12][13][14][15] and knowledgebased, 16,17 and in the last decade to machine learning [18][19][20][21][22][23][24][25][26][27] and deep learning based methods. [28][29][30][31][32][33][34][35][36][37][38] Especially, deep learning is an end-to-end method that is ideally suited to find hidden nonlinear relationships 39 between 3D protein-ligand complex structures and binding affinity.…”

Keeping pace with the explosive growth of chemical libraries with structure‐based virtual screening

“…However, as the library size increases, so does the number of potential artifacts, 24 calling for the development of novel automated ways to limit human intervention. One of the proposed strategies is to select molecules that showed consensus results across multiple docking programs with the aim to counterbalance overestimations of individual scoring functions 24,26,108,109 . For example, a consensus strategy adopted in our recent DD screen of a multi‐billion library composed of REAL Space and ZINC15 against the nontrivial Mpro target allowed to achieve significantly high hit rates, especially when paired with expert hit selection 41 .…”

“…One of the proposed strategies is to select molecules that showed consensus results across multiple docking programs with the aim to counterbalance overestimations of individual scoring functions. 24,26,108,109 For example, a consensus strategy adopted in our recent DD screen of a multi-billion library composed of REAL Space and ZINC15 against the nontrivial Mpro target allowed to achieve significantly high hit rates, especially when paired with expert hit selection. 41 Lyu et al proposed to select candidates for experimental validation also from lower scoring bins because they observed that artifact molecules may be heavily concentrated at the top of the docking rank.…”

ESSENCE-Dock: A Consensus-Based Approach to Enhance Virtual Screening Enrichment in Drug Discovery

“…A brief overview of this has been provided in a review of molecular docking written by Torres et al 11 Some of the most recent consensus docking publications include DockECR 17 and MILCDock. 18 Palacio-Rodri ́guez et al described an exponential consensus ranking (ECR) method that uses an exponential distribution for each individual rank of every docking method. 19 Their method is implemented in such a way that compounds which score very well in a single method can still be ranked highly even though they score worse in the other docking methods.…”

“…A brief overview of this has been provided in a review of molecular docking written by Torres et al . Some of the most recent consensus docking publications include DockECR and MILCDock . Palacio-Rodríguez et al.…”