Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained On Docked Poses

10.26434/chemrxiv.13637756.v1 ◽

2021 ◽

Author(s):

Fergus Boyles ◽

Charlotte M Deane ◽

Garrett Morris

Keyword(s):

Machine Learning ◽

Ligand Binding ◽

Crystal Structures ◽

Binding Affinity ◽

Scoring Function ◽

Scoring Functions ◽

Data Set ◽

Core Sets ◽

Strong Performance

Machine learning scoring functions for protein-ligand binding affinity have been found to consistently outperform classical scoring functions when trained and tested on crystal structures of bound protein-ligand complexes. However, it is less clear how these methods perform when applied to docked poses of complexes. We explore how the use of docked, rather than crystallographic, poses for both training and testing affects the performance of machine learning scoring functions. Using the PDBbind Core Sets as benchmarks, we show that the performance of a structure-based machine learning scoring function trained and tested on docked poses is lower than that of the same scoring function trained and tested on crystallographic poses. We construct a hybrid scoring function by combining both structure-based and ligand-based features, and show that its ability to predict binding affinity using docked poses is comparable to that of purely structure-based scoring functions trained and tested on crystal poses. Despite strong performance on docked poses of the PDBbind Core Sets, we find that our hybrid scoring function fails to generalise to anew data set, demonstrating the need for improved scoring functions and additional validation benchmarks. Code and data to reproduce our results are available from https://github.com/oxpig/learning-from-docked-poses.

Download Full-text

The Impact of CrystallographicData for the Development of Machine Learning Models to Predict Protein-Ligand Binding Affinity

Current Medicinal Chemistry ◽

10.2174/0929867328666210210121320 ◽

2021 ◽

Vol 28 ◽

Author(s):

Martina Veit-Acosta ◽

Walter Filgueira de Azevedo Junior

Keyword(s):

Machine Learning ◽

Experimental Data ◽

Ligand Binding ◽

Crystal Structures ◽

Binding Affinity ◽

Thermodynamic Data ◽

Ligand Docking ◽

Scoring Functions ◽

Learning Models ◽

Machine Learning Models

Background: One of the main challenges in the early stages of drug discovery is the computational assessment of protein-ligand binding affinity. Machine learning techniques can contribute to predicting this type of interaction. We may apply these techniques following two approaches. First, using the experimental structures for which affinity data is available. Second, using protein-ligand docking simulations. Objective: In this review, we describe recently published machine learning models based on crystal structures for which binding affinity and thermodynamic data are available. Method: We used experimental structures available at the protein data bank and binding affinity and thermodynamic data accessed at BindingDB, Binding MOAD, and PDBbind. We reviewed machine learning models to predict binding created using open source programs such as SAnDReS and Taba. Results: Analysis of machine learning models trained against datasets composed of crystal structure complexes indicated the high predictive performance of these models compared with classical scoring functions. Conclusion: The rapid increase in the number of crystal structures of protein-ligand complexes created a favorable scenario for developing machine learning models to predict binding affinity. These models rely on experimental data from two sources, the structural and the affinity data. The combination of experimental data generates computational models that outperform classical scoring functions.

Download Full-text

Random Forest Refinement of Pairwise Potentials for Protein-ligand Decoy Detection

10.26434/chemrxiv.8047820.v1 ◽

2019 ◽

Cited By ~ 1

Author(s):

Jun Pei ◽

Zheng Zheng ◽

Hyunji Kim ◽

Lin Song ◽

Sarah Walworth ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Probability Function ◽

Pair Potential ◽

Scoring Function ◽

Stable Structure ◽

Scoring Functions ◽

Atom Pair ◽

Data Set ◽

Atom Pairs

An accurate scoring function is expected to correctly select the most stable structure from a set of pose candidates. One can hypothesize that a scoring function’s ability to identify the most stable structure might be improved by emphasizing the most relevant atom pairwise interactions. However, it is hard to evaluate the relevant importance for each atom pair using traditional means. With the introduction of machine learning methods, it has become possible to determine the relative importance for each atom pair present in a scoring function. In this work, we use the Random Forest (RF) method to refine a pair potential developed by our laboratory (GARF6) by identifying relevant atom pairs that optimize the performance of the potential on our given task. Our goal is to construct a machine learning (ML) model that can accurately differentiate the native ligand binding pose from candidate poses using a potential refined by RF optimization. We successfully constructed RF models on an unbalanced data set with the ‘comparison’ concept and, the resultant RF models were tested on CASF-2013.5 In a comparison of the performance of our RF models against 29 scoring functions, we found our models outperformed the other scoring functions in predicting the native pose. In addition, we used two artificial designed potential models to address the importance of the GARF potential in the RF models: (1) a scrambled probability function set, which was obtained by mixing up atom pairs and probability functions in GARF, and (2) a uniform probability function set, which share the same peak positions with GARF but have fixed peak heights. The results of accuracy comparison from RF models based on the scrambled, uniform, and original GARF potential clearly showed that the peak positions in the GARF potential are important while the well depths are not.

Download Full-text

RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features

10.26434/chemrxiv.12636704.v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Stefan Holderbach ◽

Lukas Adam ◽

Bhyravabhotla Jayaram ◽

Rebecca Wade ◽

Goutam Mukherjee

Keyword(s):

Machine Learning ◽

Ligand Binding ◽

Protein Binding ◽

Binding Affinity ◽

Binding Free Energy ◽

Rapid Screening ◽

Scoring Functions ◽

Energy Prediction ◽

Molecular Features ◽

Physicochemical Descriptors

The virtual screening of large numbers of compounds against target protein binding sites has become an integral component of drug discovery workflows. This screening is often done by computationally docking ligands into a protein binding site of interest, but this has the drawback that a large number of poses must be evaluated to obtain accurate estimates of protein-ligand binding affinity. We here introduce a fast prefiltering method for ligand prioritization that is based on a set of machine learning models and uses simple pose-invariant physicochemical descriptors of the ligands and the protein binding pocket. Our method, Rapid Screening with Physicochemical Descriptors + machine learning (RASPD+), is trained on PDBbind data and achieves a regression performance better than for the original RASPD method and comparable to traditional scoring functions on a range of different test sets without the need for generating ligand poses. Additionally, we use RASPD+ to identify molecular features important for binding affinity and assess the ability of RASPD+ to enrich active molecules from decoys.

Download Full-text

OnionNet-2: A Convolutional Neural Network Model for Predicting Protein-Ligand Binding Affinity Based on Residue-Atom Contacting Shells

Frontiers in Chemistry ◽

10.3389/fchem.2021.753002 ◽

2021 ◽

Vol 9 ◽

Author(s):

Zechen Wang ◽

Liangzhen Zheng ◽

Yang Liu ◽

Yuanyuan Qu ◽

Yong-Qiang Li ◽

...

Keyword(s):

Neural Network ◽

Ligand Binding ◽

Convolutional Neural Network ◽

Binding Affinity ◽

Binding Free Energy ◽

Computational Cost ◽

Scoring Function ◽

Quality Data ◽

Great Success ◽

Data Set

One key task in virtual screening is to accurately predict the binding affinity (△G) of protein-ligand complexes. Recently, deep learning (DL) has significantly increased the predicting accuracy of scoring functions due to the extraordinary ability of DL to extract useful features from raw data. Nevertheless, more efforts still need to be paid in many aspects, for the aim of increasing prediction accuracy and decreasing computational cost. In this study, we proposed a simple scoring function (called OnionNet-2) based on convolutional neural network to predict △G. The protein-ligand interactions are characterized by the number of contacts between protein residues and ligand atoms in multiple distance shells. Compared to published models, the efficacy of OnionNet-2 is demonstrated to be the best for two widely used datasets CASF-2016 and CASF-2013 benchmarks. The OnionNet-2 model was further verified by non-experimental decoy structures from docking program and the CSAR NRC-HiQ data set (a high-quality data set provided by CSAR), which showed great success. Thus, our study provides a simple but efficient scoring function for predicting protein-ligand binding free energy.

Download Full-text

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

PeerJ ◽

10.7717/peerj.7362 ◽

2019 ◽

Vol 7 ◽

pp. e7362 ◽

Cited By ~ 13

Author(s):

Haiping Zhang ◽

Linbu Liao ◽

Konda Mani Saravanan ◽

Peng Yin ◽

Yanjie Wei

Keyword(s):

Deep Learning ◽

Ligand Binding ◽

Binding Affinity ◽

Mean Squared Error ◽

Scoring Function ◽

Binding Mode ◽

Scoring Functions ◽

Autodock Vina ◽

Cellular Functions ◽

Ligand Complex

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.

Download Full-text

RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features

10.26434/chemrxiv.12636704 ◽

2020 ◽

Author(s):

Stefan Holderbach ◽

Lukas Adam ◽

Bhyravabhotla Jayaram ◽

Rebecca Wade ◽

Goutam Mukherjee

Keyword(s):

Machine Learning ◽

Ligand Binding ◽

Protein Binding ◽

Binding Affinity ◽

Binding Free Energy ◽

Rapid Screening ◽

Scoring Functions ◽

Energy Prediction ◽

Molecular Features ◽

Physicochemical Descriptors

The virtual screening of large numbers of compounds against target protein binding sites has become an integral component of drug discovery workflows. This screening is often done by computationally docking ligands into a protein binding site of interest, but this has the drawback that a large number of poses must be evaluated to obtain accurate estimates of protein-ligand binding affinity. We here introduce a fast prefiltering method for ligand prioritization that is based on a set of machine learning models and uses simple pose-invariant physicochemical descriptors of the ligands and the protein binding pocket. Our method, Rapid Screening with Physicochemical Descriptors + machine learning (RASPD+), is trained on PDBbind data and achieves a regression performance better than for the original RASPD method and comparable to traditional scoring functions on a range of different test sets without the need for generating ligand poses. Additionally, we use RASPD+ to identify molecular features important for binding affinity and assess the ability of RASPD+ to enrich active molecules from decoys.

Download Full-text

Computational Prediction of Binding Affinity for CDK2-ligand Complexes. A Protein Target for Cancer Drug Discovery

Current Medicinal Chemistry ◽

10.2174/0929867328666210806105810 ◽

2021 ◽

Vol 28 ◽

Author(s):

Martina Veit-Acosta ◽

Walter Filgueira de Azevedo Junior

Keyword(s):

Machine Learning ◽

Ligand Binding ◽

Binding Affinity ◽

Physical Modeling ◽

Predictive Performance ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Scoring Functions ◽

Protein Target ◽

Learning Techniques

Background: CDK2 participates in the control of eukaryotic cell-cycle progression. Due to the great interest in CDK2 for drug development and the relative easiness in crystallizing this enzyme, we have over 400 structural studies focused on this protein target. This structural data is the basis for the development of computational models to estimate CDK2-ligand binding affinity. Objective: This work focuses on the recent developments in the application of supervised machine learning modeling to develop scoring functions to predict the binding affinity of CDK2. Method: We employed the structures available at the protein data bank and the ligand information accessed from the BindingDB, Binding MOAD, and PDBbind to evaluate the predictive performance of machine learning techniques combined with physical modeling used to calculate binding affinity. We compared this hybrid methodology with classical scoring functions available in docking programs. Results: Our comparative analysis of previously published models indicated that a model created using a combination of a mass-spring system and cross-validated Elastic Net to predict the binding affinity of CDK2-inhibitor complexes outperformed classical scoring functions available in AutoDock4 and AutoDock Vina. Conclusion: All studies reviewed here suggest that targeted machine learning models are superior to classical scoring functions to calculate binding affinities. Specifically for CDK2, we see that the combination of physical modeling with supervised machine learning techniques exhibits improved predictive performance to calculate the protein-ligand binding affinity. These results find theoretical support in the application of the concept of scoring function space.

Download Full-text

A Comparative Assessment of Predictive Accuracies of Conventional and Machine Learning Scoring Functions for Protein-Ligand Binding Affinity Prediction

IEEE/ACM Transactions on Computational Biology and Bioinformatics ◽

10.1109/tcbb.2014.2351824 ◽

2015 ◽

Vol 12 (2) ◽

pp. 335-347 ◽

Cited By ~ 22

Author(s):

Hossam M. Ashtawy ◽

Nihar R. Mahapatra

Keyword(s):

Machine Learning ◽

Ligand Binding ◽

Binding Affinity ◽

Comparative Assessment ◽

Scoring Functions ◽

Binding Affinity Prediction ◽

Affinity Prediction

Download Full-text

DLSCORE: A Deep Learning Model for Predicting Protein-Ligand Binding Affinities

10.26434/chemrxiv.6159143 ◽

2018 ◽

Cited By ~ 1

Author(s):

Mahmudulla Hassan ◽

Daniel Castaneda Mogollon ◽

Olac Fuentes ◽

suman sirimulla

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Ligand Binding ◽

Scoring Function ◽

Learning Approaches ◽

Scoring Functions ◽

Binding Affinities ◽

Discovery Research ◽

Drug Discovery Research ◽

Fully Connected

In recent years, the cheminformatics community has seen an increased success with machine learning-based scoring functions for estimating binding affinities and pose predictions. The prediction of protein-ligand binding affinities is crucial for drug discovery research. Many physics-based scoring functions have been developed over the years. Lately, machine learning approaches are proven to boost the performance of traditional scoring functions. In this study, a novel deep learning based scoring function (DLSCORE) was developed and trained on the refined PDBBind v.2016 dataset using 348 BINding ANAlyzer (BINANA) descriptors. The neural networks of the DLSCORE model have different number of fully connected hidden layers. Our model, an ensemble of 10 networks, yielded a Pearson R2 of 0.82, a Spearman Rho R2 of 0.90, Kendall Tau R2 of 0.74, an RMSE of 1.15 kcal=mol, and an MAE of 0.86 kcal=mol for our test set. This software is available on Github at https://github.com/sirimullalab/dlscore.git

Download Full-text