The knowledge of potentially druggable binding sites on proteins is an important preliminary step towards the discovery of novel drugs. The computational prediction of such areas can be boosted by following the recent major advances in the deep learning field and by exploiting the increasing availability of proper data. In this paper, a novel computational method for the prediction of potential binding sites is proposed, called DeepSurf. DeepSurf combines a surface-based representation, where a number of 3D voxelized grids are placed on the protein's surface, with state-of-the-art deep learning architectures. After being trained on the large database of scPDB, DeepSurf demonstrates superior results on three diverse testing datasets, by surpassing all its main deep learning-based competitors, while attaining competitive performance to a set of traditional non-data-driven approaches.
Most widely used ligand docking methods assume a rigid protein structure. This leads to problems when the structure of the target protein deforms upon ligand binding. In particular, the ligand's true binding pose is often scored very unfavorably due to apparent clashes between ligand and protein atoms, which lead to extremely high values of the calculated van der Waals energy term. Traditionally, this problem has been addressed by explicitly searching for receptor conformations to account for the flexibility of the receptor in ligand binding. Here we present a deep learning model trained to ta…
Shenzhen University（深圳大学）；Tencent AI Lab（腾讯人工智能实验室）
Binding affinity prediction of three-dimensional (3D) protein ligand complexes is critical for drug repositioning and virtual drug screening. Existing approaches transform a 3D protein-ligand complex to a two-dimensional (2D) graph, and then use graph neural networks (GNNs) to predict its binding affinity. However, the node and edge features of the 2D graph are extracted based on invariant local coordinate systems of the 3D complex. As a result, the method can not fully learn the global information of the complex, such as, the physical symmetry and the topological information of bonds. To addr…
The effective representation of proteins is a crucial task that directly affects the performance of many bioinformatics problems. Related proteins usually bind to similar ligands. Chemical characteristics of ligands are known to capture the functional and mechanistic properties of proteins suggesting that a ligand based approach can be utilized in protein representation. In this study, we propose SMILESVec, a SMILES-based method to represent ligands and a novel method to compute similarity of proteins by describing them based on their ligands. The proteins are defined utilizing the word-embedd…
University of Pittsburgh（匹兹堡大学）；The College of New Jersey（新泽西学院）
Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding and structural data enables the use of deep machine learning techniques for protein-ligand scoring. We describe convolutional neural network (CNN) scoring functions that take as input a comprehensive 3D representation of a protein-ligand interaction. A CNN scoring function automati…
Xiangya International Academy of Translational Medicine, Central South University（中南大学湘雅国际转化医学研究院）；Hunan Engineering Research Center of Combinatorial Biosynthesis and Natural Product Drug Discover（湖南省组合生物合成与天然产物药物发现工程研究中心）；National Engineering Research Center of Combinatorial Biosynthesis for Drug Discovery（国家组合生物合成与新药发现工程研究中心）
Motivation: Protein-ligand affinity prediction is an important part of structure-based drug design. It includes molecular docking and affinity prediction. Although molecular dynamics can predict affinity with high accuracy at present, it is not suitable for large-scale virtual screening. The existing affinity prediction and evaluation functions based on deep learning mostly rely on experimentally-determined conformations. Results: We build a predictive model of protein-ligand affinity through the ResNet neural network with added attention mechanism. The resulting ResAtom-Score model achieves P…
Protein-ligand scoring is an important step in a structure-based drug design pipeline. Selecting a correct binding pose and predicting the binding affinity of a protein-ligand complex enables effective virtual screening. Machine learning techniques can make use of the increasing amounts of structural data that are becoming publicly available. Convolutional neural network (CNN) scoring functions in particular have shown promise in pose selection and affinity prediction for protein-ligand complexes. Neural networks are known for being difficult to interpret. Understanding the decisions of a part…
Prediction of protein-ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the effects of changes in protein dynamics induced by the binding ligand. However, the relationship between protein dynamics and binding affinity remains unclear. Here, we propose a novel method that represents protein behavioral change upon ligand binding with a simple feature that can be used to predict protein-ligand affinity. From unbiased molecular simulation data, an unsupervis…
Many biologically important ligands of proteins are large, flexible, and often charged molecules that bind to extended regions on the protein surface. It is infeasible or expensive to locate such ligands on proteins with standard methods such as docking or molecular dynamics (MD) simulation. The alternative approach proposed here is the scanning of a spatial and angular grid around the protein with smaller fragments of the large ligand. Energy values for complete grids can be computed efficiently with a well-known Fast Fourier Transform accelerated algorithm and a physically meaningful interac…
We have developed an analytical, ligand-specific and scalable algorithm that detects a "signature" of the 3D binding site of a given ligand in a protein 3D structure. The said signature is a 3D motif in the form of an irregular tetrahedron whose vertices represent the backbone or side-chain centroids of the amino acid residues at the binding site that physically interact with the bound ligand atoms. The motif is determined from a set of solved training structures, all of which bind the ligand. Just as alignment of linear amino acid sequences enables one to determine consensus sequences in prot…
Understanding and accurately predicting protein-ligand binding affinity are essential in the drug design and discovery process. At present, machine learning-based methodologies are gaining popularity as a means of predicting binding affinity due to their efficiency and accuracy, as well as the increasing availability of structural and binding affinity data for protein-ligand complexes. In biomolecular studies, graph theory has been widely applied since graphs can be used to model molecules or molecular complexes in a natural manner. In the present work, we upgrade the graph-based learners for …
Expanding the scope of graph-based, deep-learning models to noncovalent protein-ligand interactions has earned increasing attention in structure-based drug design. Modeling the protein-ligand interactions with graph neural networks (GNNs) has experienced difficulties in the conversion of protein-ligand complex structures into the graph representation and left questions regarding whether the trained models properly learn the appropriate noncovalent interactions. Here, we proposed a GNN architecture, denoted as InteractionNet, which learns two separated molecular graphs, being covalent and nonco…
A pharmacophore consists of the parts of the structure of the ligand that are sufficient to express the biological and pharmacological effects of the ligand. It is usually a substructure of the entire structure of the ligand. Small organic molecules called ligands or metabolites in the cell form complexes with biomolecules (usually proteins) to serve different purposes. The sites at which the ligands bind are known as ligand binding sites, which are essentially "pockets" which have complementary shapes and patterns of charge distribution with the ligands. Sometimes a pocket is induced by the l…
Protein-ligand binding is essential to almost all life processes. The understanding of protein-ligand interactions is fundamentally important to rational drug design and protein design. Based on large scale data sets, we show that protein rigidity strengthening or flexibility reduction is a pivoting mechanism in protein-ligand binding. Our approach based solely on rigidity is able to unveil a surprisingly long range contribution of four residue layers to protein-ligand binding, which has a ramification for drug and protein design. Additionally, the present work reveals that among various pairw…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
Protein-ligand complex structures have been utilised to design benchmark machine learning methods that perform important tasks related to drug design such as receptor binding site detection, small molecule docking and binding affinity prediction. However, these methods are usually trained on only ligand bound (or holo) conformations of the protein and therefore are not guaranteed to perform well when the protein structure is in its native unbound conformation (or apo), which is usually the conformation available for a newly identified receptor. A primary reason for this is that the local struc…
There is great interest to develop artificial intelligence-based protein-ligand affinity models due to their immense applications in drug discovery. In this paper, PointNet and PointTransformer, two pointwise multi-layer perceptrons have been applied for protein-ligand affinity prediction for the first time. Three-dimensional point clouds could be rapidly generated from the data sets in PDBbind-2016, which contain 3 772 and 11 327 individual point clouds derived from the refined or/and general sets, respectively. These point clouds were used to train PointNet or PointTransformer, resulting in …
Institute of Biochemistry and Biophysics, Polish Academy of Sciences（波兰科学院生物化学与生物物理研究所）；University of Warsaw（华沙大学）
In recent years machine learning (ML) took bio- and cheminformatics fields by storm, providing new solutions for a vast repertoire of problems related to protein sequence, structure, and interactions analysis. ML techniques, deep neural networks especially, were proven more effective than classical models for tasks like predicting binding affinity for molecular complex. In this work we investigated the earlier stage of drug discovery process - finding druggable pockets on protein surface, that can be later used to design active molecules. For this purpose we developed a 3D fully convolutional …
Renmin University of China（中国人民大学）；DP Technology（深势科技）
The prediction of protein-ligand binding affinity is of great significance for discovering lead compounds in drug research. Facing this challenging task, most existing prediction methods rely on the topological and/or spatial structure of molecules and the local interactions while ignoring the multi-level inter-molecular interactions between proteins and ligands, which often lead to sub-optimal performance. To solve this issue, we propose a novel global-local interaction (GLI) framework to predict protein-ligand binding affinity. In particular, our GLI framework considers the inter-molecular i…
Binding of a ligand on a protein changes the flexibility of certain parts of the protein, which directly affects its function. These changes are not the same at each point, some parts become more flexible and some others become stiffer. Here, an equation is derived that gives the stiffness map for proteins. The model is based on correlations of fluctuations of pairs of points that need to be evaluated by molecular dynamics simulations. The model is also cast in terms of the Gaussian Network Model and changes of stiffness upon dimerization of AKT1 are evaluated as an example.
Ligand diffusion through proteins is a fundamental process governing biological signaling and enzymatic catalysis. The complex topology of protein tunnels results in difficulties with computing ligand escape pathways by standard molecular dynamics (MD) simulations. Here, two novel methods for searching of ligand exit pathways and cavity exploration are proposed: memory random acceleration MD (mRAMD), and memetic algorithms (MA). In mRAMD, finding exit pathways is based on a non-Markovian biasing that is introduced to optimize the unbinding force. In MA, hybrid learning protocols are exploited …
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Predicting accurate protein-ligand binding affinity is important in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the deep convolutional and graph neural network based approaches, the model performance depends on the input data representation and suffers from distinct limitations. It is natural to combine complementary features and their inference from the individual models for better predictions. We present fusion models to benefit from different f…
Institute of Biochemistry and Biophysics, Polish Academy of Sciences（波兰科学院生物化学与生物物理研究所）；University of Warsaw（华沙大学）
Structure based ligand discovery is one of the most successful approaches for augmenting the drug discovery process. Currently, there is a notable shift towards machine learning (ML) methodologies to aid such procedures. Deep learning has recently gained considerable attention as it allows the model to "learn" to extract features that are relevant for the task at hand. We have developed a novel deep neural network estimating the binding affinity of ligand-receptor complexes. The complex is represented with a 3D grid, and the model utilizes a 3D convolution to produce a feature map of this repr…
We describe two complementary methods to quantify the degree of burial of ligand and/or ligand binding site (LBS) in a protein-ligand complex, namely, the "cutting plane" (CP) and the "tangent sphere" (TS) methods. To construct the CP and TS, two centroids are required: the protein molecular centroid (global centroid, GC), and the LBS centroid (local centroid, LC). The CP is defined as the plane passing through the LBS centroid (LC) and normal to the line passing through the LC and the protein molecular centroid (GC). The "anterior side" of the CP is the side not containing the GC (which the "…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；Peking University（北京大学）；University of Washington（华盛顿大学）；Georgia Institute of Technology（佐治亚理工学院）；Helixon Research（Helixon研究院）
A disease that caused by dengue virus (DENV) has become the major health problem of the world. Nowadays, no effective treatment is available to overcome the disease due to the level of dengue virus pathogeneses. A novel treatment method such as antiviral drug is highly necessary for coping with the dengue disease. Envelope protein is one of the non-structural proteins of DENV, which engaged in the viral fusion process. The fusion process is mediated by the conformational change in the protein structure from dimer to trimer state. The previous research showed the existing cavity on the dimer st…
Protein-ligand binding is a fundamental biological process that is paramount to many other biological processes, such as signal transduction, metabolic pathways, enzyme construction, cell secretion, gene expression, etc. Accurate prediction of protein-ligand binding affinities is vital to rational drug design and the understanding of protein-ligand binding and binding induced function. Existing binding affinity prediction methods are inundated with geometric detail and involve excessively high dimensions, which undermines their predictive power for massive binding data. Topology provides an ul…
We have developed a web server that implements two complementary methods to quantify the depth of ligand binding site (LBS) in protein-ligand complexes: the "secant plane" (SP) and "tangent sphere" (TS) methods. The protein molecular centroid (global centroid, GC), and the LBS centroid (local centroid, LC) are first determined. The SP is the plane passing through the LC and normal to the line passing through the LC and the GC. The "exterior side" of the SP is the side opposite GC. The TS is the sphere with center at GC and tangent to the SP at LC. The percentage of protein atoms inside the TS …
Protein-ligand interactions are one of the fundamental types of molecular interactions in living systems. Ligands are small molecules that interact with protein molecules at specific regions on their surfaces called binding sites. Tasks such as assessment of protein functional similarity and detection of side effects of drugs need identification of similar binding sites of disparate proteins across diverse pathways. Machine learning methods for similarity assessment require feature descriptors of binding sites. Traditional methods based on hand engineered motifs and atomic configurations are n…
The cornerstone of computational drug design is the calculation of binding affinity between two biological counterparts, especially a chemical compound, i.e., a ligand, and a protein. Predicting the strength of protein-ligand binding with reasonable accuracy is critical for drug discovery. In this paper, we propose a data-driven framework named DeepAtom to accurately predict the protein-ligand binding affinity. With 3D Convolutional Neural Network (3D-CNN) architecture, DeepAtom could automatically extract binding related atomic interaction patterns from the voxelized complex structure. Compar…
Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）；Beijing StoneWise Technology Co Ltd（北京思睿科技有限公司）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
One-step Structure Prediction and Screening for Protein-Ligand Complexes using Multi-Task Geometric Deep Learning
Medical School of Nanjing University（南京大学医学院）；National Institute of Healthcare Data Science, Nanjing University（南京大学国家健康数据科学研究院）；School of Life Sciences, Nanjing University（南京大学生命科学学院）
