Although DNA is often bent in vivo, it is unclear how DNA-bending forces modulate DNA-protein binding affinity. Here, we report how a range of DNA-bending forces modulates the binding of the Integration Host Factor (IHF) protein to various DNAs. Using solution fluorimetry and electrophoretic mobility shift assays, we measured the affinity of IHF for DNAs with different bending forces and sequence mutations. Bending force was adjusted by varying the fraction of double-stranded DNA in a circular substrate, or by changing the overall size of the circle (1). DNA constructs contained a pair of Forster Resonance Energy Transfer dyes that served as probes for affinity assays, and read out bending forces measured by optical force sensors (2). Small bending forces significantly increased binding affinity; this effect saturated beyond ~3 pN. Surprisingly, when DNA sequences that bound IHF only weakly were mechanically bent by circularization, they bound IHF more tightly than the linear "high-affinity" binding sequence. These findings demonstrate that small bending forces can greatly augment binding at sites that deviate from a protein's consensus binding sequence. Since cellular DNA is subject to mechanical deformation and condensation, affinities of architectural proteins determined in vitro using short linear DNAs may not reflect in vivo affinities.
Advanced mathematics, such as multiscale weighted colored graph and element specific persistent homology, and machine learning including deep neural networks were integrated to construct mathematical deep learning models for pose and binding affinity prediction and ranking in the last two D3R grand challenges in computer-aided drug design and discovery. D3R Grand Challenge 2 (GC2) focused on the pose prediction and binding affinity ranking and free energy prediction for Farnesoid X receptor ligands. Our models obtained the top place in absolute free energy prediction for free energy Set 1 in S…
Assay-Aware BindingDB: Curating Experimental Context for Binding Affinity Prediction
The University of Texas Health Science Center at Houston（休斯顿德克萨斯大学健康科学中心）；Texas A&M University（德克萨斯农工大学）；The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；Mayo Clinic（梅奥诊所）
Although algebraic graph theory based models have been widely applied in physical modeling and molecular studies, they are typically incompetent in the analysis and prediction of biomolecular properties when compared with other quantitative approaches. There is a need to explore the capability and limitation of algebraic graph theory for molecular and biomolecular modeling, analysis, and prediction. In this work, we propose novel algebraic graph learning (AGL) models that encode high-dimensional physical and biological information into intrinsically low-dimensional representations. The propose…
Molecular surface representations have been advertised as a great tool to study protein structure and functions, including protein-ligand binding affinity modeling. However, the conventional surface-area-based methods fail to deliver a competitive performance on the energy scoring tasks. The main reason is the lack of crucial physical and chemical interactions encoded in the molecular surface generations. We present novel molecular surface representations embedded in different scales of the element interactive manifolds featuring the dramatically dimensional reduction and accurately physical a…
Superoxide dismutase-1 (SOD1) is a ubiquitous, Cu and Zn binding, free radical defense enzyme whose misfolding and aggregation play a potential key role in amyotrophic lateral sclerosis, an invariably fatal neurodegenerative disease. Over 150 mutations in SOD1 have been identified with a familial form of the disease, but it is presently not clear what unifying features, if any, these mutants share to make them pathogenic. Here, we develop several new computational assays for probing the thermo-mechanical properties of both ALS-associated and rationally-designed SOD1 variants. Allosteric intera…
Affinity maturation produces antibodies that bind antigens with high specificity by accumulating mutations in the antibody sequence. Mapping out the antibody-antigen affinity landscape can give us insight into the accessible paths during this rapid evolutionary process. By developing a carefully controlled null model for noninteracting mutations, we characterized epistasis in affinity measurements of a large library of antibody variants obtained by Tite-Seq, a recently introduced Deep Mutational Scan method yielding physical values of the binding constant. We show that representing affinity as…
The major histocompatibility complex (MHC) molecules, which bind peptides for presentation on the cell surface, play an important role in cell-mediated immunity. In light of developing databases and technologies over the years, significant progress has been made in research on peptide binding affinity calculation. Several in techniques have been developed to predict peptide binding to MHC class I. Most of the research on MHC Class I due to its nature brings better performance and more. Considering the use of different methods and different technologies, and the approach of similar methods on d…
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tsinghua University（清华大学）
Modeling the effects of mutations on the binding affinity plays a crucial role in protein engineering and drug design. In this study, we develop a novel deep learning based framework, named GraphPPI, to predict the binding affinity changes upon mutations based on the features provided by a graph neural network (GNN). In particular, GraphPPI first employs a well-designed pre-training scheme to enforce the GNN to capture the features that are predictive of the effects of mutations on binding affinity in an unsupervised manner and then integrates these graphical features with gradient-boosting tr…
How molecular motors like Kinesin regulates the affinity to the rail protein in the process of ATP hydrolysis remains to be uncovered. To understand the regulation mechanism, we investigate the structural fluctuation of KIF1A in different nucleotide states that are realized in the ATP hydrolysis process by molecular dynamics simulations of Go-like model. We found that "alpha4 helix", which is a part of the microtubule (MT) binding site, changes its fluctuation systematically according to the nucleotide states. In particular, the frequency of large fluctuations of alpha4 strongly correlates wit…
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 …
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 …
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…
Accurately determining a change in protein binding affinity upon mutations is important for the discovery and design of novel therapeutics and to assist mutagenesis studies. Determination of change in binding affinity upon mutations requires sophisticated, expensive, and time-consuming wet-lab experiments that can be aided with computational methods. Most of the computational prediction techniques require protein structures that limit their applicability to protein complexes with known structures. In this work, we explore the sequence-based prediction of change in protein binding affinity upon…
Transcription factors (TFs) are regulatory proteins that bind DNA in promoter regions of the genome and either promote or repress gene expression. Here we predict analytically that enhanced homo-oligonucleotide sequence correlations, such as poly(dA:dT) and poly(dC:dG) tracts, statistically enhance non-specific TF-DNA binding affinity. This prediction is generic and qualitatively independent of microscopic parameters of the model. We show that non-specific TF binding affinity is universally controlled by the strength and symmetry of DNA sequence correlations. We perform correlation analysis of…
Preliminary epidemiologic, phylogenetic and clinical findings suggest that several novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants have increased transmissibility and decreased efficacy of several existing vaccines. Four mutations in the receptor-binding domain (RBD) of the spike protein that are reported to contribute to increased transmission. Understanding physical mechanism responsible for the affinity enhancement between the SARS-CoV-2 variants and ACE2 is the "urgent challenge" for developing blockers, vaccines and therapeutic antibodies against the coronaviru…
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…
Huazhong Agricultural University（华中农业大学）；College of Informatics, Huazhong Agricultural University（华中农业大学信息学院）
The identification of drug-target binding affinity (DTA) has attracted increasing attention in the drug discovery process due to the more specific interpretation than binary interaction prediction. Recently, numerous deep learning-based computational methods have been proposed to predict the binding affinities between drugs and targets benefiting from their satisfactory performance. However, the previous works mainly focus on encoding biological features and chemical structures of drugs and targets, with a lack of exploiting the essential topological information from the drug-target affinity n…
The first step in drug discovery is finding drug molecule moieties with medicinal activity against specific targets. Therefore, it is crucial to investigate the interaction between drug-target proteins and small chemical molecules. However, traditional experimental methods for discovering potential small drug molecules are labor-intensive and time-consuming. There is currently a lot of interest in building computational models to screen small drug molecules using drug molecule-related databases. In this paper, we propose a method for predicting drug-target binding affinity using deep learning …
Despite the central role that antibodies play in the adaptive immune system and in biotechnology, much remains unknown about the quantitative relationship between an antibody's amino acid sequence and its antigen binding affinity. Here we describe a new experimental approach, called Tite-Seq, that is capable of measuring binding titration curves and corresponding affinities for thousands of variant antibodies in parallel. The measurement of titration curves eliminates the confounding effects of antibody expression and stability that arise in standard deep mutational scanning assays. We demonst…
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…
Interactions between a protein and a ligand are often accompanied by a redistribution of the population of thermally accessible conformations. This dynamic response of the protein's functional energy landscape enables a protein to modulate binding affinities and control binding sensitivity to ligand concentration. In this paper, we investigate the structural origins of binding affinity and allosteric cooperativity of binding two calcium ions to each domain of calmodulin (CaM) through simulations of a simple coarse-grained model. In this model, the protein's conformational transitions between o…
We propose a specialized string kernel for small bio-molecules, peptides and pseudo-sequences of binding interfaces. The kernel incorporates physico-chemical properties of amino acids and elegantly generalize eight kernels, such as the Oligo, the Weighted Degree, the Blended Spectrum, and the Radial Basis Function. We provide a low complexity dynamic programming algorithm for the exact computation of the kernel and a linear time algorithm for it's approximation. Combined with kernel ridge regression and SupCK, a novel binding pocket kernel, the proposed kernel yields biologically relevant and …
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…
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…
Computational drug discovery provides an efficient tool helping large scale lead molecules screening. One of the major tasks of lead discovery is identifying molecules with promising binding affinities towards a target, a protein in general. The accuracies of current scoring functions which are used to predict the binding affinity are not satisfactory enough. Thus, machine learning (ML) or deep learning (DL) based methods have been developed recently to improve the scoring functions. In this study, a deep convolutional neural network (CNN) model (called OnionNet) is introduced and the features…
Instituto de Ciencias Matemáticas (ICMAT)（数学科学研究所（ICMAT））；Universidad Autónoma de Madrid（马德里自治大学）；Universidad Politécnica de Madrid（马德里理工大学）；Ingenii Inc.（Ingenii公司）
One of the main challenges in drug discovery is to find molecules that bind specifically and strongly to their target protein while having minimal binding to other proteins. By predicting binding affinity, it is possible to identify the most promising candidates from a large pool of potential compounds, reducing the number of compounds that need to be tested experimentally. Recently, deep learning methods have shown superior performance than traditional computational methods for making accurate predictions on large datasets. However, the complexity and time-consuming nature of these methods ha…
SARS-CoV-2 is a global challenge due to its ability to spread much faster than SARS-CoV, which was attributed to the mutations in the receptor binding domain (RBD). These mutations enhanced the electrostatic interactions. Recently, a new strain was reported in the UK that includes a mutation (N501Y) in the RBD, that possibly increases the infection rate. Using Molecular Dynamics simulations (MD) and Monte Carlo (MC) sampling, we showed that the N501 mutation enhances the electrostatic interactions due to the formation of a strong hydrogen bond between SARS-CoV-2-T500 and ACE2-D355 near the mut…
ZeroFold: Protein-RNA Binding Affinity Predictions from Pre-Structural Embeddings
Centre for Misfolding Diseases, Yusuf Hamied Department of Chemistry, University of Cambridge（错误折叠疾病中心，尤斯夫·哈米埃德化学系，剑桥大学）；Medicinal Chemistry, Research and Early Development, Respiratory and Immunology, BioPharmaceuticals R&D, AstraZeneca（药物化学，研发与早期开发，呼吸与免疫学，生物制药研发，阿斯利康）
Zhejiang University School of Medicine（浙江大学医学院）；First Affiliated Hospital, Zhejiang University School of Medicine（浙江大学医学院附属第一医院）；Liangzhu Laboratory（良渚实验室）；Zhejiang University（浙江大学）；Nantong University（南通大学）；Hunan First Normal University（湖南第一师范学院）
Due to the lack of a method to efficiently represent the multimodal information of a protein, including its structure and sequence information, predicting compound-protein binding affinity (CPA) still suffers from low accuracy when applying machine learning methods. To overcome this limitation, in a novel end-to-end architecture (named FeatNN), we develop a coevolutionary strategy to jointly represent the structure and sequence features of proteins and ultimately optimize the mathematical models for predicting CPA. Furthermore, from the perspective of data-driven approach, we proposed a ration…
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…
Heterochromatin protein 1 (HP1) participates in establishing and maintaining heterochromatin via its histone modification dependent chromatin interactions. In recent papers HP1 binding to nucleosomal arrays was measured in vitro and interpreted in terms of nearest-neighbor cooperative binding. This mode of chromatin interactions could lead to spreading of HP1 along the nucleosome chain. Here, we reanalyzed previous data by representing the nucleosome chain as a one-dimensional binding lattice, and show how the experimental HP1 binding isotherms can be explained by a simpler model without coope…
The adhesion of cells is mediated by receptors and ligands anchored in apposing membranes. A central question is how to characterize the binding affinity of these membrane-anchored molecules. For soluble molecules, the binding affinity is typically quantified by the binding equilibrium constant K3D in the linear relation [RL] = K3D [R][L] between the volume concentration [RL] of bound complexes and the volume concentrations [R] and [L] of unbound molecules. For membrane-anchored molecules, it is often assumed by analogy that the area concentration of bound complexes [RL] is proportional to the…
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infectivity is a major concern in coronavirus disease 2019 (COVID-19) prevention and economic reopening. However, rigorous determination of SARS-COV-2 infectivity is essentially impossible owing to its continuous evolution with over 13752 single nucleotide polymorphisms (SNP) variants in six different subtypes. We develop an advanced machine learning algorithm based on the algebraic topology to quantitatively evaluate the binding affinity changes of SARS-CoV-2 spike glycoprotein (S protein) and host angiotensin-converting enzyme 2 (A…
Persistent local Laplacian prediction of protein-ligand binding affinities
Mathematical Science Research Center, Chongqing University of Technology（重庆理工大学数学科学研究中心）；Department of Mathematics and Statistics, University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校数学与统计系）
In response to pathogens, the adaptive immune system generates specific antibodies that bind and neutralize foreign antigens. Understanding the composition of an individual's immune repertoire can provide insights into this process and reveal potential therapeutic antibodies. In this work, we explore the application of antibody-specific language models to aid understanding of immune repertoires. We introduce AntiBERTy, a language model trained on 558M natural antibody sequences. We find that within repertoires, our model clusters antibodies into trajectories resembling affinity maturation. Imp…
AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
Structural Molecular Biology, Division of Biosciences, University College London（伦敦大学学院生物结构分子生物学系）；Institute of Computational Life Sciences, Zürich University of Applied Sciences (ZHAW)（苏黎世应用科学大学计算生命科学研究所）；Biomedical Informatics and Data Science, Yale School of Medicine（耶鲁医学院生物医学信息学与数据科学）；Centre for Artificial Intelligence, University College London（伦敦大学学院人工智能中心）
The infectivity of SARS-CoV-2 depends on the binding affinity of the receptor-binding domain (RBD) of the spike protein with the angiotensin converting enzyme 2 (ACE2) receptor. The calculated RBD-ACE2 binding energies indicate that the difference in transmission efficiency of SARS-CoV-2 variants cannot be fully explained by electrostatic interactions, hydrogen-bond interactions, van der Waals interactions, internal energy, and nonpolar solvation energies. Here, we demonstrate that low-entropy regions of hydration shells around proteins drive hydrophobic attraction between shape-matched low-en…
