Artificial intelligence to guide precision anticancer therapy with multitargeted kinase inhibitors.

BACKGROUND: Vast amounts of rapidly accumulating biological data related to cancer and a remarkable progress in the field of artificial intelligence (AI) have paved the way for precision oncology. Our recent contribution to this area of research is CancerOmicsNet, an AI-based system to predict the therapeutic effects of multitargeted kinase inhibitors across various cancers. This approach was previously demonstrated to outperform other deep learning methods, graph kernel models, molecular docking, and drug binding pocket matching. METHODS: CancerOmicsNet integrates multiple heterogeneous data by utilizing a deep graph learning model with sophisticated attention propagation mechanisms to extract highly predictive features from cancer-specific networks. The AI-based system was devised to provide more accurate and robust predictions than data-driven therapeutic discovery using gene signature reversion. RESULTS: Selected CancerOmicsNet predictions obtained for "unseen" data are positively validated against the biomedical literature and by live-cell time course inhibition assays performed against breast, pancreatic, and prostate cancer cell lines. Encouragingly, six molecules exhibited dose-dependent antiproliferative activities, with pan-CDK inhibitor JNJ-7706621 and Src inhibitor PP1 being the most potent against the pancreatic cancer cell line Panc 04.03. CONCLUSIONS: CancerOmicsNet is a promising AI-based platform to help guide the development of new approaches in precision oncology involving a variety of tumor types and therapeutics.

Binding site matching in rational drug design: algorithms and applications.

Interactions between proteins and small molecules are critical for biological functions. These interactions often occur in small cavities within protein structures, known as ligand-binding pockets. Understanding the physicochemical qualities of binding pockets is essential to improve not only our basic knowledge of biological systems, but also drug development procedures. In order to quantify similarities among pockets in terms of their geometries and chemical properties, either bound ligands can be compared to one another or binding sites can be matched directly. Both perspectives routinely take advantage of computational methods including various techniques to represent and compare small molecules as well as local protein structures. In this review, we survey 12 tools widely used to match pockets. These methods are divided into five categories based on the algorithm implemented to construct binding-site alignments. In addition to the comprehensive analysis of their algorithms, test sets and the performance of each method are described. We also discuss general pharmacological applications of computational pocket matching in drug repurposing, polypharmacology and side effects. Reflecting on the importance of these techniques in drug discovery, in the end, we elaborate on the development of more accurate meta-predictors, the incorporation of protein flexibility and the integration of powerful artificial intelligence technologies such as deep learning.

BionoiNet: ligand-binding site classification with off-the-shelf deep neural network.

MOTIVATION: Fast and accurate classification of ligand-binding sites in proteins with respect to the class of binding molecules is invaluable not only to the automatic functional annotation of large datasets of protein structures but also to projects in protein evolution, protein engineering and drug development. Deep learning techniques, which have already been successfully applied to address challenging problems across various fields, are inherently suitable to classify ligand-binding pockets. Our goal is to demonstrate that off-the-shelf deep learning models can be employed with minimum development effort to recognize nucleotide- and heme-binding sites with a comparable accuracy to highly specialized, voxel-based methods. RESULTS: We developed BionoiNet, a new deep learning-based framework implementing a popular ResNet model for image classification. BionoiNet first transforms the molecular structures of ligand-binding sites to 2D Voronoi diagrams, which are then used as the input to a pretrained convolutional neural network classifier. The ResNet model generalizes well to unseen data achieving the accuracy of 85.6% for nucleotide- and 91.3% for heme-binding pockets. BionoiNet also computes significance scores of pocket atoms, called BionoiScores, to provide meaningful insights into their interactions with ligand molecules. BionoiNet is a lightweight alternative to computationally expensive 3D architectures. AVAILABILITY AND IMPLEMENTATION: BionoiNet is implemented in Python with the source code freely available at: https://github.com/CSBG-LSU/BionoiNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network.

Comprehensive characterization of ligand-binding sites is invaluable to infer molecular functions of hypothetical proteins, trace evolutionary relationships between proteins, engineer enzymes to achieve a desired substrate specificity, and develop drugs with improved selectivity profiles. These research efforts pose significant challenges owing to the fact that similar pockets are commonly observed across different folds, leading to the high degree of promiscuity of ligand-protein interactions at the system-level. On that account, novel algorithms to accurately classify binding sites are needed. Deep learning is attracting a significant attention due to its successful applications in a wide range of disciplines. In this communication, we present DeepDrug3D, a new approach to characterize and classify binding pockets in proteins with deep learning. It employs a state-of-the-art convolutional neural network in which biomolecular structures are represented as voxels assigned interaction energy-based attributes. The current implementation of DeepDrug3D, trained to detect and classify nucleotide- and heme-binding sites, not only achieves a high accuracy of 95%, but also has the ability to generalize to unseen data as demonstrated for steroid-binding proteins and peptidase enzymes. Interestingly, the analysis of strongly discriminative regions of binding pockets reveals that this high classification accuracy arises from learning the patterns of specific molecular interactions, such as hydrogen bonds, aromatic and hydrophobic contacts. DeepDrug3D is available as an open-source program at https://github.com/pulimeng/DeepDrug3D with the accompanying TOUGH-C1 benchmarking dataset accessible from https://osf.io/enz69/.

Elucidating the druggability of the human proteome with eFindSite.

Identifying the viability of protein targets is one of the preliminary steps of drug discovery. Determining the ability of a protein to bind drugs in order to modulate its function, termed the druggability, requires a non-trivial amount of time and resources. Inability to properly measure druggability has accounted for a significant portion of failures in drug discovery. This problem is only further exacerbated by the large sample space of proteins involved in human diseases. With these barriers, the druggability space within the human proteome remains unexplored and has made it difficult to develop drugs for numerous diseases. Hence, we present a new feature developed in eFindSite that employs supervised machine learning to predict the druggability of a given protein. Benchmarking calculations against the Non-Redundant data set of Druggable and Less Druggable binding sites demonstrate that an AUC for druggability prediction with eFindSite is as high as 0.88. With eFindSite, we elucidated the human druggability space to be 10,191 proteins. Considering the disease space from the Open Targets Platform and excluding already known targets from the predicted data set reveal 2731 potentially novel therapeutic targets. eFindSite is freely available as a stand-alone software at https://github.com/michal-brylinski/efindsite .

Comparative assessment of strategies to identify similar ligand-binding pockets in proteins.

BACKGROUND: Detecting similar ligand-binding sites in globally unrelated proteins has a wide range of applications in modern drug discovery, including drug repurposing, the prediction of side effects, and drug-target interactions. Although a number of techniques to compare binding pockets have been developed, this problem still poses significant challenges. RESULTS: We evaluate the performance of three algorithms to calculate similarities between ligand-binding sites, APoc, SiteEngine, and G-LoSA. Our assessment considers not only the capabilities to identify similar pockets and to construct accurate local alignments, but also the dependence of these alignments on the sequence order. We point out certain drawbacks of previously compiled datasets, such as the inclusion of structurally similar proteins, leading to an overestimated performance. To address these issues, a rigorous procedure to prepare unbiased, high-quality benchmarking sets is proposed. Further, we conduct a comparative assessment of techniques directly aligning binding pockets to indirect strategies employing structure-based virtual screening with AutoDock Vina and rDock. CONCLUSIONS: Thorough benchmarks reveal that G-LoSA offers a fairly robust overall performance, whereas the accuracy of APoc and SiteEngine is satisfactory only against easy datasets. Moreover, combining various algorithms into a meta-predictor improves the performance of existing methods to detect similar binding sites in unrelated proteins by 5-10%. All data reported in this paper are freely available at https://osf.io/6ngbs/ .

Cysteines and N-Glycosylation Sites Conserved among All Alphaherpesviruses Regulate Membrane Fusion in Herpes Simplex Virus 1 Infection.

Neurotropism is a defining characteristic of alphaherpesvirus pathogenicity. Glycoprotein K (gK) is a conserved virion glycoprotein of all alphaherpesviruses that is not found in other herpesvirus subfamilies. The extracellular amino terminus of gK has been shown to be important to the ability of the prototypic alphaherpesvirus herpes simplex virus 1 (HSV-1) to enter neurons via axonal termini. Here, we determined the role of the two conserved N-linked glycosylation (N48 and N58) sites of gK in virus-induced cell fusion and replication. We found that N-linked glycosylation is important to the regulation of HSV-1-induced membrane fusion since mutating N58 to alanine (N58A) caused extensive virus-induced cell fusion. Due to the known contributions of N-linked glycosylation to protein processing and correct disulfide bond formation, we investigated whether the conserved extracellular cysteine residues within the amino terminus of gK contributed to the regulation of HSV-1-induced membrane fusion. We found that mutation of C37 and C114 residues led to a gK-null phenotype characterized by very small plaque formation and drastic reduction in infectious virus production, while mutation of C82 and C243 caused extensive virus-induced cell fusion. Comparison of N-linked glycosylation and cysteine mutant replication kinetics identified disparate effects on infectious virion egress from infected cells. Specifically, cysteine mutations caused defects in the accumulation of infectious virus in both the cellular and supernatant fractions, while glycosylation site mutants did not adversely affect virion egress from infected cells. These results demonstrate a critical role for the N glycosylation sites and cysteines for the structure and function of the amino terminus of gK.IMPORTANCE We have previously identified important entry and neurotropic determinants in the amino terminus of HSV-1 glycoprotein K (gK). Alphaherpesvirus-mediated membrane fusion is a complex and highly regulated process that is not clearly understood. gK and UL20, which are highly conserved across all alphaherpesviruses, play important roles in the regulation of HSV-1 fusion in the context of infection. A greater understanding of mechanisms governing alphaherpesvirus membrane fusion is expected to inform the rational design of therapeutic and prevention strategies to combat herpesviral infection and pathogenesis. This work adds to the growing reports regarding the importance of gK to alphaherpesvirus pathogenesis and details important structural features of gK that are involved in gK-mediated regulation of virus-induced membrane fusion.

Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks.

BACKGROUND: Deciphering complete networks of interactions between proteins is the key to comprehend cellular regulatory mechanisms. A significant effort has been devoted to expanding the coverage of the proteome-wide interaction space at molecular level. Although a growing body of research shows that protein docking can, in principle, be used to predict biologically relevant interactions, the accuracy of the across-proteome identification of interacting partners and the selection of near-native complex structures still need to be improved. RESULTS: In this study, we developed a new method to discover and model protein interactions employing an exhaustive all-to-all docking strategy. This approach integrates molecular modeling, structural bioinformatics, machine learning, and functional annotation filters in order to provide interaction data for the bottom-up assembly of protein interaction networks. Encouragingly, the success rates for dimer modeling is 57.5 and 48.7% when experimental and computer-generated monomer structures are employed, respectively. Further, our protocol correctly identifies 81% of protein-protein interactions at the expense of only 19% false positive rate. As a proof of concept, 61,913 protein-protein interactions were confidently predicted and modeled for the proteome of E. coli. Finally, we validated our method against the human immune disease pathway. CONCLUSIONS: Protein docking supported by evolutionary restraints and machine learning can be used to reliably identify and model biologically relevant protein assemblies at the proteome scale. Moreover, the accuracy of the identification of protein-protein interactions is improved by considering only those protein pairs co-localized in the same cellular compartment and involved in the same biological process. The modeling protocol described in this communication can be applied to detect protein-protein interactions in other organisms and pathways as well as to construct dimer structures and estimate the confidence of protein interactions experimentally identified with high-throughput techniques.

Herpes Simplex Virus 1 UL37 Protein Tyrosine Residues Conserved among All Alphaherpesviruses Are Required for Interactions with Glycoprotein K, Cytoplasmic Virion Envelopment, and Infectious Virus Production.

The herpes simplex virus 1 (HSV-1) UL37 protein functions in virion envelopment at trans-Golgi membranes, as well as in retrograde and anterograde transport of virion capsids. Recently, we reported that UL37 interacts with glycoprotein K (gK) and its interacting partner protein UL20 (N. Jambunathan, D. Chouljenko, P. Desai, A. S. Charles, R. Subramanian, V. N. Chouljenko, and K. G. Kousoulas, J Virol 88:5927-5935, 2014, http://dx.doi.org/10.1128/JVI.00278-14), facilitating cytoplasmic virion envelopment. Alignment of UL37 homologs encoded by alphaherpesviruses revealed the presence of highly conserved residues in the central portion of the UL37 protein. A cadre of nine UL37 site-specific mutations were produced and tested for their ability to inhibit virion envelopment and infectious virus production. Complementation analysis revealed that replacement of tyrosines 474 and 480 with alanine failed to complement the UL37-null virus, while all other mutated UL37 genes complemented the virus efficiently. The recombinant virus DC474-480 constructed with tyrosines 474, 476, 477, and 480 mutated to alanine residues produced a gK-null-like phenotype characterized by the production of very small plaques and accumulation of capsids in the cytoplasm of infected cells. Recombinant viruses having either tyrosine 476 or 477 replaced with alanine produced a wild-type phenotype. Immunoprecipitation assays revealed that replacement of all four tyrosines with alanines substantially reduced the ability of gK to interact with UL37. Alignment of HSV UL37 with the human cytomegalovirus and Epstein-Barr virus UL37 homologs revealed that Y480 was conserved only for alphaherpesviruses. Collectively, these results suggest that the UL37 conserved tyrosine 480 residue plays a crucial role in interactions with gK to facilitate cytoplasmic virion envelopment and infectious virus production. IMPORTANCE: The HSV-1 UL37 protein is conserved among all herpesviruses, functions in both retrograde and anterograde transport of virion capsids, and plays critical roles in cytoplasmic virion envelopment by interacting with gK. We show here that UL37 tyrosine residues conserved among all alphaherpesviruses serve critical roles in cytoplasmic virion envelopment and interactions with gK.

Predicting protein interface residues using easily accessible on-line resources.

It has been more than a decade since the completion of the Human Genome Project that provided us with a complete list of human proteins. The next obvious task is to figure out how various parts interact with each other. On that account, we review 10 methods for protein interface prediction, which are freely available as web servers. In addition, we comparatively evaluate their performance on a common data set comprising different quality target structures. We find that using experimental structures and high-quality homology models, structure-based methods outperform those using only protein sequences, with global template-based approaches providing the best performance. For moderate-quality models, sequence-based methods often perform better than those structure-based techniques that rely on fine atomic details. We note that post-processing protocols implemented in several methods quantitatively improve the results only for experimental structures, suggesting that these procedures should be tuned up for computer-generated models. Finally, we anticipate that advanced meta-prediction protocols are likely to enhance interface residue prediction. Notwithstanding further improvements, easily accessible web servers already provide the scientific community with convenient resources for the identification of protein-protein interaction sites.

PDID: database of molecular-level putative protein-drug interactions in the structural human proteome.

MOTIVATION: Many drugs interact with numerous proteins besides their intended therapeutic targets and a substantial portion of these interactions is yet to be elucidated. Protein-Drug Interaction Database (PDID) addresses incompleteness of these data by providing access to putative protein-drug interactions that cover the entire structural human proteome. RESULTS: PDID covers 9652 structures from 3746 proteins and houses 16 800 putative interactions generated from close to 1.1 million accurate, all-atom structure-based predictions for several dozens of popular drugs. The predictions were generated with three modern methods: ILbind, SMAP and eFindSite. They are accompanied by propensity scores that quantify likelihood of interactions and coordinates of the putative location of the binding drugs in the corresponding protein structures. PDID complements the current databases that focus on the curated interactions and the BioDrugScreen database that relies on docking to find putative interactions. Moreover, we also include experimentally curated interactions which are linked to their sources: DrugBank, BindingDB and Protein Data Bank. Our database can be used to facilitate studies related to polypharmacology of drugs including repurposing and explaining side effects of drugs. AVAILABILITY AND IMPLEMENTATION: PDID database is freely available at http://biomine.ece.ualberta.ca/PDID/.

Break Down in Order To Build Up: Decomposing Small Molecules for Fragment-Based Drug Design with eMolFrag.

Constructing high-quality libraries of molecular building blocks is essential for successful fragment-based drug discovery. In this communication, we describe eMolFrag, a new open-source software to decompose organic compounds into nonredundant fragments retaining molecular connectivity information. Given a collection of molecules, eMolFrag generates a set of unique fragments comprising larger moieties, bricks, and smaller linkers connecting bricks. These building blocks can subsequently be used to construct virtual screening libraries for targeted drug discovery. The robustness and computational performance of eMolFrag is assessed against the Directory of Useful Decoys, Enhanced database conducted in serial and parallel modes with up to 16 computing cores. Further, the application of eMolFrag in de novo drug design is illustrated using the adenosine receptor. eMolFrag is implemented in Python, and it is available as stand-alone software and a web server at www.brylinski.org/emolfrag and https://github.com/liutairan/eMolFrag .

Template-based identification of protein-protein interfaces using eFindSitePPI.

Protein-protein interactions orchestrate virtually all cellular processes, therefore, their exhaustive exploration is essential for the comprehensive understanding of cellular networks. A reliable identification of interfacial residues is vital not only to infer the function of individual proteins and their assembly into biological complexes, but also to elucidate the molecular and physicochemical basis of interactions between proteins. With the exponential growth of protein sequence data, computational approaches for detecting protein interface sites have drawn an increased interest. In this communication, we discuss the major features of eFindSite(PPI), a recently developed template-based method for interface residue prediction available at http://brylinski.cct.lsu.edu/efindsiteppi. We describe the requirements and installation procedures for the stand-alone version, and explain the content and format of output data. Furthermore, the functionality of the eFindSite(PPI) web application that is designed to provide a simple and convenient access for the scientific community is presented with illustrative examples. Finally, we discuss common problems encountered in predicting protein interfaces and set forth directions for the future development of eFindSite(PPI).

Use of protein cross-linking and radiolytic footprinting to elucidate PsbP and PsbQ interactions within higher plant Photosystem II.

Protein cross-linking and radiolytic footprinting coupled with high-resolution mass spectrometry were used to examine the structure of PsbP and PsbQ when they are bound to Photosystem II. In its bound state, the N-terminal 15-amino-acid residue domain of PsbP, which is unresolved in current crystal structures, interacts with domains in the C terminus of the protein. These interactions may serve to stabilize the structure of the N terminus and may facilitate PsbP binding and function. These interactions place strong structural constraints on the organization of PsbP when associated with the Photosystem II complex. Additionally, amino acid residues in the structurally unresolved loop 3A domain of PsbP ((90)K-(107)V), (93)Y and (96)K, are in close proximity (≤ 11.4 Å) to the N-terminal (1)E residue of PsbQ. These findings are the first, to our knowledge, to identify a putative region of interaction between these two components. Cross-linked domains within PsbQ were also identified, indicating that two PsbQ molecules can interact in higher plants in a manner similar to that observed by Liu et al. [(2014) Proc Natl Acad Sci 111(12):4638-4643] in cyanobacterial Photosystem II. This interaction is consistent with either intra-Photosystem II dimer or inter-Photosystem II dimer models in higher plants. Finally, OH(•) produced by synchrotron radiolysis of water was used to oxidatively modify surface residues on PsbP and PsbQ. Domains on the surface of both protein subunits were resistant to modification, indicating that they were shielded from water and appear to define buried regions that are in contact with other Photosystem II components.

Use of Protein Cross-Linking and Radiolytic Labeling To Elucidate the Structure of PsbO within Higher-Plant Photosystem II.

We have used protein cross-linking with the zero-length cross-linker 1-ethyl-3-(3-dimethylaminopropyl) carbodiimide, and radiolytic footprinting coupled with high-resolution tandem mass spectrometry, to examine the structure of higher-plant PsbO when it is bound to Photosystem II. Twenty intramolecular cross-linked residue pairs were identified. On the basis of this cross-linking data, spinach PsbO was modeled using the Thermosynechococcus vulcanus PsbO structure as a template, with the cross-linking distance constraints incorporated using the MODELLER program. Our model of higher-plant PsbO identifies several differences between the spinach and cyanobacterial proteins. The N-terminal region is particularly interesting, as this region has been suggested to be important for oxygen evolution and for the specific binding of PsbO to Photosystem II. Additionally, using radiolytic mapping, we have identified regions on spinach PsbO that are shielded from the bulk solvent. These domains may represent regions on PsbO that interact with other components, as yet unidentified, of the photosystem.

Deletion of a Predicted ß-Sheet Domain within the Amino Terminus of Herpes Simplex Virus Glycoprotein K Conserved among Alphaherpesviruses Prevents Virus Entry into Neuronal Axons.

UNLABELLED: We have shown previously that herpes simplex virus 1 (HSV-1) lacking expression of the entire glycoprotein K (gK) or expressing gK with a 38-amino-acid deletion (gKΔ31-68 mutation) failed to infect ganglionic neurons after ocular infection of mice. We constructed a new model for the predicted three-dimensional structure of gK, revealing that the gKΔ31-68 mutation spans a well-defined ß-sheet structure within the amino terminus of gK, which is conserved among alphaherpesviruses. The HSV-1(McKrae) gKΔ31-68 virus was tested for the ability to enter into ganglionic neuronal axons in cell culture of explanted rat ganglia using a novel virus entry proximity ligation assay (VEPLA). In this assay, cell surface-bound virions were detected by the colocalization of gD and its cognate receptor nectin-1 on infected neuronal surfaces. Capsids that have entered into the cytoplasm were detected by the colocalization of the virion tegument protein UL37, with dynein required for loading of virion capsids onto microtubules for retrograde transport to the nucleus. HSV-1(McKrae) gKΔ31-68 attached to cell surfaces of Vero cells and ganglionic axons in cell culture as efficiently as wild-type HSV-1(McKrae). However, unlike the wild-type virus, the mutant virus failed to enter into the axoplasm of ganglionic neurons. This work suggests that the amino terminus of gK is a critical determinant for entry into neuronal axons and may serve similar conserved functions for other alphaherpesviruses. IMPORTANCE: Alphaherpesviruses, unlike beta- and gammaherpesviruses, have the unique ability to infect and establish latency in neurons. Glycoprotein K (gK) and the membrane protein UL20 are conserved among all alphaherpesviruses. We show here that a predicted ß-sheet domain, which is conserved among alphaherpesviruses, functions in HSV-1 entry into neuronal axons, suggesting that it may serve similar functions for other herpesviruses. These results are in agreement with our previous observations that deletion of this gK domain prevents the virus from successfully infecting ganglionic neurons after ocular infection of mice.

GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field.

Molecular docking is an important component of computer-aided drug discovery. In this communication, we describe GeauxDock, a new docking approach that builds on the ideas of ligand homology modeling. GeauxDock features a descriptor-based scoring function integrating evolutionary constraints with physics-based energy terms, a mixed-resolution molecular representation of protein-ligand complexes, and an efficient Monte Carlo sampling protocol. To drive docking simulations toward experimental conformations, the scoring function was carefully optimized to produce a correlation between the total pseudoenergy and the native-likeness of binding poses. Indeed, benchmarking calculations demonstrate that GeauxDock has a strong capacity to identify near-native conformations across docking trajectories with the area under receiver operating characteristics of 0.85. By excluding closely related templates, we show that GeauxDock maintains its accuracy at lower levels of homology through the increased contribution from physics-based energy terms compensating for weak evolutionary constraints. GeauxDock is available at http://www.institute.loni.org/lasigma/package/dock/.

Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning.

The identification of protein-protein interactions is vital for understanding protein function, elucidating interaction mechanisms, and for practical applications in drug discovery. With the exponentially growing protein sequence data, fully automated computational methods that predict interactions between proteins are becoming essential components of system-level function inference. A thorough analysis of protein complex structures demonstrated that binding site locations as well as the interfacial geometry are highly conserved across evolutionarily related proteins. Because the conformational space of protein-protein interactions is highly covered by experimental structures, sensitive protein threading techniques can be used to identify suitable templates for the accurate prediction of interfacial residues. Toward this goal, we developed eFindSite(PPI) , an algorithm that uses the three-dimensional structure of a target protein, evolutionarily remotely related templates and machine learning techniques to predict binding residues. Using crystal structures, the average sensitivity (specificity) of eFindSite(PPI) in interfacial residue prediction is 0.46 (0.92). For weakly homologous protein models, these values only slightly decrease to 0.40-0.43 (0.91-0.92) demonstrating that eFindSite(PPI) performs well not only using experimental data but also tolerates structural imperfections in computer-generated structures. In addition, eFindSite(PPI) detects specific molecular interactions at the interface; for instance, it correctly predicts approximately one half of hydrogen bonds and aromatic interactions, as well as one third of salt bridges and hydrophobic contacts. Comparative benchmarks against several dimer datasets show that eFindSite(PPI) outperforms other methods for protein-binding residue prediction. It also features a carefully tuned confidence estimation system, which is particularly useful in large-scale applications using raw genomic data. eFindSite(PPI) is freely available to the academic community at http://www.brylinski.org/efindsiteppi.

Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures.

BACKGROUND: Protein-protein interactions (PPIs) mediate the vast majority of biological processes, therefore, significant efforts have been directed to investigate PPIs to fully comprehend cellular functions. Predicting complex structures is critical to reveal molecular mechanisms by which proteins operate. Despite recent advances in the development of new methods to model macromolecular assemblies, most current methodologies are designed to work with experimentally determined protein structures. However, because only computer-generated models are available for a large number of proteins in a given genome, computational tools should tolerate structural inaccuracies in order to perform the genome-wide modeling of PPIs. RESULTS: To address this problem, we developed eRank(PPI), an algorithm for the identification of near-native conformations generated by protein docking using experimental structures as well as protein models. The scoring function implemented in eRank(PPI) employs multiple features including interface probability estimates calculated by eFindSite(PPI) and a novel contact-based symmetry score. In comparative benchmarks using representative datasets of homo- and hetero-complexes, we show that eRank(PPI) consistently outperforms state-of-the-art algorithms improving the success rate by ~10 %. CONCLUSIONS: eRank(PPI) was designed to bridge the gap between the volume of sequence data, the evidence of binary interactions, and the atomic details of pharmacologically relevant protein complexes. Tolerating structure imperfections in computer-generated models opens up a possibility to conduct the exhaustive structure-based reconstruction of PPI networks across proteomes. The methods and datasets used in this study are available at www.brylinski.org/erankppi.

eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models.

Detecting similarities between ligand binding sites in the absence of global homology between target proteins has been recognized as one of the critical components of modern drug discovery. Local binding site alignments can be constructed using sequence order-independent techniques, however, to achieve a high accuracy, many current algorithms for binding site comparison require high-quality experimental protein structures, preferably in the bound conformational state. This, in turn, complicates proteome scale applications, where only various quality structure models are available for the majority of gene products. To improve the state-of-the-art, we developed eMatchSite, a new method for constructing sequence order-independent alignments of ligand binding sites in protein models. Large-scale benchmarking calculations using adenine-binding pockets in crystal structures demonstrate that eMatchSite generates accurate alignments for almost three times more protein pairs than SOIPPA. More importantly, eMatchSite offers a high tolerance to structural distortions in ligand binding regions in protein models. For example, the percentage of correctly aligned pairs of adenine-binding sites in weakly homologous protein models is only 4-9% lower than those aligned using crystal structures. This represents a significant improvement over other algorithms, e.g. the performance of eMatchSite in recognizing similar binding sites is 6% and 13% higher than that of SiteEngine using high- and moderate-quality protein models, respectively. Constructing biologically correct alignments using predicted ligand binding sites in protein models opens up the possibility to investigate drug-protein interaction networks for complete proteomes with prospective systems-level applications in polypharmacology and rational drug repositioning. eMatchSite is freely available to the academic community as a web-server and a stand-alone software distribution at http://www.brylinski.org/ematchsite.