DeepBindRG: a deep learning based method for estimating effective protein–ligand affinity

Abstract

Proteins interact with small molecules to modulate several important cellular functions. Many acute diseases were cured by small molecule binding in the active site of protein either by inhibition or activation. Currently, there are several docking programs to estimate the binding position and the binding orientation of protein–ligand complex. Many scoring functions were developed to estimate the binding strength and predict the effective protein–ligand binding. While the accuracy of current scoring function is limited by several aspects, the solvent effect, entropy effect, and multibody effect are largely ignored in traditional machine learning methods. In this paper, we proposed a new deep neural network-based model named DeepBindRG to predict the binding affinity of protein–ligand complex, which learns all the effects, binding mode, and specificity implicitly by learning protein–ligand interface contact information from a large protein–ligand dataset. During the initial data processing step, the critical interface information was preserved to make sure the input is suitable for the proposed deep learning model. While validating our model on three independent datasets, DeepBindRG achieves root mean squared error (RMSE) value of pKa (−logKd or −logKi) about 1.6–1.8 and R value around 0.5–0.6, which is better than the autodock vina whose RMSE value is about 2.2–2.4 and R value is 0.42–0.57. We also explored the detailed reasons for the performance of DeepBindRG, especially for several failed cases by vina. Furthermore, DeepBindRG performed better for four challenging datasets from DUD.E database with no experimental protein–ligand complexes. The better performance of DeepBindRG than autodock vina in predicting protein–ligand binding affinity indicates that deep learning approach can greatly help with the drug discovery process. We also compare the performance of DeepBindRG with a 4D based deep learning method “pafnucy”, the advantage and limitation of both methods have provided clues for improving the deep learning based protein–ligand prediction model in the future.

Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds

“…The development of deep learning scoring functions has been already attempted, but results have shown various degrees of success which could be due to a lack of appropriate datasets. [32,33] Likely, as the very nature of docking is approximate, the improvements are likely to come from better approximation of physical-chemical processes, including solvation, enthalpic and entropic factors, rather than from a better training base and procedures. [34,35] Thus, our method represents not just feasible, but also practical options for utilizing deep learning in virtual screening.…”

FDA-approved Pralatrexate identified by virtual drug screening inhibits SARS-CoV-2 replication in vitro

“…To perform the drug screening process e ciently and accurately is still a challenge for computer-aided drug design. Though a recent deep learning-based approaches has demonstrated its potential to be e cient/accurate by learning from a su cient amount of training data, problems such as over tting, and the discrepancy between training data and real-world data remain [20]. The proposed deep learning and molecular simulation based drug screening method was able to select 4 FDA-approved drug candidates targeting RdRp from 1906 drugs, and 2 out of 4 (Pralatrexate and Azithromycin) can effectively inhibit SARS-CoV-2 replication in vitro with EC 50 values of 0.008µM and 9.453 µM.…”

“…The DeepBindBC is a ResNet model trained over the PDBbind database. In DeepBindBC, the protein-ligand interaction interface information will be converted into gure-like metric, similar to DeepBindRG [20]. By incorporating the cross-docking (docking proteins and ligands from different experimental complexes) conformation as negative training data, DeepBindBC is highly possible to distinguish non-binders.…”

Deep learning model can predict water binding sites on the surface of proteins using limited-resolution data

“…In this study, we attempted to go a step further and capture the landscape of water interaction with the protein surface, at the resolution of individual water molecules.Convolutional neural networks have been repeatedly shown to excel in solving the tasks of image recognition [18][19][20][21], speech recognition [22][23][24][25] and even genetic or protein sequence analysis [26][27][28][29][30][31][32][33]. In the field of computational chemistry, they have been applied to predict ligand binding affinities [34][35][36][37] as well as to identify binding pockets within protein structures [38]. These successes have been attributed to their ability of hierarchically learning attributes indicative of each target class.With sufficiently large training datasets, increasingly more complex problems can be solved using ever deeper network architectures.…”