Kinase-Kernel Models: Accurate In silico Screening of 4 Million Compounds Across the Entire Human Kinome

On the Choice of Active Site Sequences for Kinase-Ligand Affinity Prediction

Recent work showed that active site rather than full-protein-sequence information improves predictive performance in kinase-ligand binding affinity prediction. To refine the notion of an “active site”, we here propose and compare multiple definitions. We report significant evidence that our novel definition is superior to previous definitions and better models of ATP-noncompetitive inhibitors. Moreover, we leverage the discontiguity of the active site sequence to motivate novel protein-sequence augmentation strategies and find that combining them further improves performance.

KiSSim: Predicting Off-Targets from Structural Similarities in the Kinome

Protein kinases are among the most important drug targets because their dysregulation can cause cancer, inflammatory and degenerative diseases, and many more. Developing selective inhibitors is challenging due to the highly conserved binding sites across the roughly 500 human kinases. Thus, detecting subtle similarities on a structural level can help explain and predict off-targets among the kinase family. Here, we present the kinase-focused, subpocket-enhanced KiSSim fingerprint (Kinase Structural Similarity). The fingerprint builds on the KLIFS pocket definition, composed of 85 residues aligned across all available protein kinase structures, which enables residue-by-residue comparison without a computationally expensive alignment. The residues' physicochemical and spatial properties are encoded within their structural context including key subpockets at the hinge region, the DFG motif, and the front pocket. Since structure was found to contain information complementary to sequence, we used the fingerprint to calculate all-against-all similarities within the structurally covered kinome. We could identify off-targets that are unexpected if solely considering the sequence-based kinome tree grouping; for example, Erlobinib's known kinase off-targets SLK and LOK show high similarities to the key target EGFR (TK group), although belonging to the STE group. KiSSim reflects profiling data better or at least as well as other approaches such as KLIFS pocket sequence identity, KLIFS interaction fingerprints (IFPs), or SiteAlign. To rationalize observed (dis)similarities, the fingerprint values can be visualized in 3D by coloring structures with residue and feature resolution. We believe that the KiSSim fingerprint is a valuable addition to the kinase research toolbox to guide off-target and polypharmacology prediction. The method is distributed as an open-source Python package on GitHub and as a conda package: https://github.com/volkamerlab/kissim.

Active Site Sequence Representations of Human Kinases Outperform Full Sequence Representations for Affinity Prediction and Inhibitor Generation: 3D Effects in a 1D Model

Recent advances in deep learning have enabled the development of large-scale multimodal models for virtual screening and de novo molecular design. The human kinome with its abundant sequence and inhibitor data presents an attractive opportunity to develop proteochemometric models that exploit the size and internal diversity of this family of targets. Here, we challenge a standard practice in sequence-based affinity prediction models: instead of leveraging the full primary structure of proteins, each target is represented by a sequence of 29 discontiguous residues defining the ATP binding site. In kinase-ligand binding affinity prediction, our results show that the reduced active site sequence representation is not only computationally more efficient but consistently yields significantly higher performance than the full primary structure. This trend persists across different models, data sets, and performance metrics and holds true when predicting pIC₅₀ for both unseen ligands and kinases. Our interpretability analysis reveals a potential explanation for the superiority of the active site models: whereas only mild statistical effects about the extraction of three-dimensional (3D) interaction sites take place in the full sequence models, the active site models are equipped with an implicit but strong inductive bias about the 3D structure stemming from the discontiguity of the active sites. Moreover, in direct comparisons, our models perform similarly or better than previous state-of-the-art approaches in affinity prediction. We then investigate a de novo molecular design task and find that the active site provides benefits in the computational efficiency, but otherwise, both kinase representations yield similar optimized affinities (for both SMILES- and SELFIES-based molecular generators). Our work challenges the assumption that the full primary structure is indispensable for modeling human kinases.

Assessing the information content of structural and protein-ligand interaction representations for the classification of kinase inhibitor binding modes via machine learning and active learning

For kinase inhibitors, X-ray crystallography has revealed different types of binding modes. Currently, more than 2000 kinase inhibitors with known binding modes are available, which makes it possible to derive and test machine learning models for the prediction of inhibitors with different binding modes. We have addressed this prediction task to evaluate and compare the information content of distinct molecular representations including protein–ligand interaction fingerprints (IFPs) and compound structure-based structural fingerprints (i.e., atom environment/fragment fingerprints). IFPs were designed to capture binding mode-specific interaction patterns at different resolution levels. Accurate predictions of kinase inhibitor binding modes were achieved with random forests using both representations. The performance of IFPs was consistently superior to atom environment fingerprints, albeit only by less than 10%. An active learning strategy applying information entropy-based selection of training instances was applied as a diagnostic approach to assess the relative information content of distinct representations. IFPs were found to capture more binding mode-relevant information than atom environment fingerprints, leading to highly predictive models even when training instances were randomly selected. By contrast, for atom environment fingerprints, the derivation of accurate models via active learning depended on entropy-based selection of informative training compounds. Notably, higher information content of IFPs confirmed by active learning only resulted in small improvements in global prediction accuracy compared to models derived using atom environment fingerprints. For practical applications, prediction of binding modes of new kinase inhibitors on the basis of chemical structure is highly attractive.

Rational Use of Heterogeneous Data in Quantitative Structure-Activity Relationship (QSAR) Modeling of Cyclooxygenase/Lipoxygenase Inhibitors

Numerous studies have been published in recent years with acceptable quantitative structure-activity relationship (QSAR) modeling based on heterogeneous data. In many cases, the training sets for QSAR modeling were constructed from compounds tested by different biological assays, contradicting the opinion that QSAR modeling should be based on the data measured by a single protocol. We attempted to develop approaches that help to determine how heterogeneous data should be used for the creation of QSAR models on the basis of different sets of compounds tested by different experimental methods for the same target and the same endpoint. To this end, more than 100 QSAR models for the IC50 values of ligands interacting with cyclooxygenase 1,2 (COX) and seed lipoxygenase (LOX), obtained from ChEMBL database were created using the GUSAR software. The QSAR models were tested on the external set, including 26 new thiazolidinone derivatives, which were experimentally tested for COX-1,2/LOX inhibition. The IC50 values of the derivatives varied from 89 μM to 26 μM for LOX, from 200 μM to 0.018 μM for COX-1, and from 210 μM to 1 μM for COX-2. This study showed that the accuracy of the models is dependent on the distribution of IC50 values of low activity compounds in the training sets. In the most cases, QSAR models created based on the combined training sets had advantages in comparison with QSAR models, based on a single publication. We introduced a new method of combination of quantitative data from different experimental studies based on the data of reference compounds, which was called "scaling".

The Future of Computational Chemogenomics

Following the elucidation of the human genome, chemogenomics emerged in the beginning of the twenty-first century as an interdisciplinary research field with the aim to accelerate target and drug discovery by making best usage of the genomic data and the data linkable to it. What started as a systematization approach within protein target families now encompasses all types of chemical compounds and gene products. A key objective of chemogenomics is the establishment, extension, analysis, and prediction of a comprehensive SAR matrix which by application will enable further systematization in drug discovery. Herein we outline future perspectives of chemogenomics including the extension to new molecular modalities, or the potential extension beyond the pharma to the agro and nutrition sectors, and the importance for environmental protection. The focus is on computational sciences with potential applications for compound library design, virtual screening, hit assessment, analysis of phenotypic screens, lead finding and optimization, and systems biology-based prediction of toxicology and translational research.

Protocols for the Design of Kinase-focused Compound Libraries

Protocols for the design of kinase-focused compound libraries are presented. Kinase-focused compound libraries can be differentiated based on the design goal. Depending on whether the library should be a discovery library specific for one particular kinase, a general discovery library for multiple distinct kinase projects, or even phenotypic screening, there exists today a variety of in silico methods to design candidate compound libraries. We address the following scenarios: 1) Datamining of SAR databases and kinase focused vendor catalogues; 2) Predictions and virtual screening; 3) Structure-based design of combinatorial kinase inhibitors; 4) Design of covalent kinase inhibitors; 5) Design of macrocyclic kinase inhibitors; and 6) Design of allosteric kinase inhibitors and activators.

Dual or multi-targeting inhibitors: The next generation anticancer agents

Dual-targeting/Multi-targeting of oncoproteins by a single drug molecule represents an efficient, logical and alternative approach to drug combinations. An increasing interest in this approach is indicated by a steady upsurge in the number of articles on targeting dual/multi proteins published in the last 5 years. Combining different inhibitors that destiny specific single target is the standard treatment for cancer. A new generation of dual or multi-targeting drugs is emerging, where a single chemical entity can act on multiple molecular targets. Dual/Multi-targeting agents are beneficial for solving limited efficiencies, poor safety and resistant profiles of an individual target. Designing dual/multi-target inhibitors with predefined biological profiles present a challenge. The latest advances in bioinformatic tools and the availability of detailed structural information of target proteins have shown a way of discovering multi-targeting molecules. This neoteric artifice that amalgamates the molecular docking of small molecules with protein-based common pharmacophore to design multi-targeting inhibitors is gaining great importance in anticancer drug discovery. Current review focus on the discoveries of dual targeting agents in cancer therapy using rational, computational, proteomic, bioinformatics and polypharmacological approach that enables the discovery and rational design of effective and safe multi-target anticancer agents.

Profile-QSAR 2.0: Kinase Virtual Screening Accuracy Comparable to Four-Concentration IC50s for Realistically Novel Compounds

While conventional random forest regression (RFR) virtual screening models appear to have excellent accuracy on random held-out test sets, they prove lacking in actual practice. Analysis of 18 historical virtual screens showed that random test sets are far more similar to their training sets than are the compounds project teams actually order. A new, cluster-based "realistic" training/test set split, which mirrors the chemical novelty of real-life virtual screens, recapitulates the poor predictive power of RFR models in real projects. The original Profile-QSAR (pQSAR) method greatly broadened the domain of applicability over conventional models by using as independent variables a profile of activity predictions from all historical assays in a large protein family. However, the accuracy still fell short of experiment on realistic test sets. The improved "pQSAR 2.0" method replaces probabilities of activity from naïve Bayes categorical models at several thresholds with predicted IC₅₀s from RFR models. Unexpectedly, the high accuracy also requires removing the RFR model for the actual assay of interest from the independent variable profile. With these improvements, pQSAR 2.0 activity predictions are now statistically comparable to medium-throughput four-concentration IC₅₀ measurements even on the realistic test set. Beyond the yes/no activity predictions from a typical high-throughput screen (HTS) or conventional virtual screen, these semiquantitative IC₅₀ predictions allow for predicted potency, ligand efficiency, lipophilic efficiency, and selectivity against antitargets, greatly facilitating hitlist triaging and enabling virtual screening panels such as toxicity panels and overall promiscuity predictions.

KinMap: a web-based tool for interactive navigation through human kinome data

Background

Annotations of the phylogenetic tree of the human kinome is an intuitive way to visualize compound profiling data, structural features of kinases or functional relationships within this important class of proteins. The increasing volume and complexity of kinase-related data underlines the need for a tool that enables complex queries pertaining to kinase disease involvement and potential therapeutic uses of kinase inhibitors.

Results

Here, we present KinMap, a user-friendly online tool that facilitates the interactive navigation through kinase knowledge by linking biochemical, structural, and disease association data to the human kinome tree. To this end, preprocessed data from freely-available sources, such as ChEMBL, the Protein Data Bank, and the Center for Therapeutic Target Validation platform are integrated into KinMap and can easily be complemented by proprietary data. The value of KinMap will be exemplarily demonstrated for uncovering new therapeutic indications of known kinase inhibitors and for prioritizing kinases for drug development efforts.

Conclusion

KinMap represents a new generation of kinome tree viewers which facilitates interactive exploration of the human kinome. KinMap enables generation of high-quality annotated images of the human kinome tree as well as exchange of kinome-related data in scientific communications. Furthermore, KinMap supports multiple input and output formats and recognizes alternative kinase names and links them to a unified naming scheme, which makes it a useful tool across different disciplines and applications. A web-service of KinMap is freely available at http://www.kinhub.org/kinmap/.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1433-7) contains supplementary material, which is available to authorized users.

Prediction of Protein Kinase-Ligand Interactions through 2.5D Kinochemometrics

So far, 518 protein kinases have been identified in the human genome. They share a common mechanism of protein phosphorylation and are involved in many critical biological processes of eukaryotic cells. Deregulation of the kinase phosphorylation function induces severe illnesses such as cancer, diabetes, or inflammatory diseases. Many actors in the pharmaceutical domain have made significant efforts to design potent and selective protein kinase inhibitors as new potential drugs. Because the ATP binding site is highly conserved in the protein kinase family, the design of selective inhibitors remains a challenge and has negatively impacted the progression of drug candidates to late-stage clinical development. The work presented here adopts a 2.5D kinochemometrics (KCM) approach, derived from proteochemometrics (PCM), in which protein kinases are depicted by a novel 3D descriptor and the ligands by 2D fingerprints. We demonstrate in two examples that the protein descriptor successfully classified protein kinases based on their group membership and their Asp-Phe-Gly (DFG) conformation. We also compared the performance of our models with those obtained from a full 2D KCM model and QSAR models. In both cases, the internal validation of the models demonstrated good capabilities to distinguish "active" from "inactive" protein kinase-ligand pairs. However, the external validation performed on two independent data sets showed that the two statistical models tended to overestimate the number of "inactive" pairs.

A Proteometric Analysis of Human Kinome: Insight into Discriminant Conformation-dependent Residues

Because of the success of imatinib, the first type-II kinase inhibitor approved by the FDA in 2001, sustained efforts have been made by the pharmaceutical industry to discover novel compounds stabilizing the inactive conformation of protein kinases. On the seven type-II inhibitors having reached the market, four were released in 2012, suggesting an acceleration of the research of such a class of compounds. Still, they represent less than a third of the protein kinase inhibitors available to patients today. The identification of key residues involved in the binding of this type of ligands in the kinase active site might ease the design of potent and selective type-II inhibitors. In order to identify those discriminant residues, we have developed a proteometric approach combining residue descriptors of protein kinase sequences and biological activities of various type-II kinase inhibitors. We applied Partial Least Squares (PLS) regression to identify 29 key residues that influence the binding of four type-II inhibitors to most proteins of the kinome. The gatekeeper residue was found to be the most relevant, confirming an essential role in ligand binding as well as in protein kinase conformational changes. Using the newly developed proteometric model, we predicted the propensity of each protein kinase to be inhibited by type-II ligands. The model was further validated using an external data set of protein/ligand activity pairs. Other residues present in the kinase domain, and more specifically in the binding site, have been highlighted by this approach, but their role in biological mechanisms is still unknown.

Assessing protein kinase target similarity: Comparing sequence, structure, and cheminformatics approaches

In just over two decades, structure based protein kinase inhibitor discovery has grown from trial and error approaches, using individual target structures, to structure and data driven approaches that may aim to optimize inhibition properties across several targets. This is increasingly enabled by the growing availability of potent compounds and kinome-wide binding data. Assessing the prospects for adapting known compounds to new therapeutic uses is thus a key priority for current drug discovery efforts. Tools that can successfully link the diverse information regarding target sequence, structure, and ligand binding properties now accompany a transformation of protein kinase inhibitor research, away from single, block-buster drug models, and toward "personalized medicine" with niche applications and highly specialized research groups. Major hurdles for the transformation to data driven drug discovery include mismatches in data types, and disparities of methods and molecules used; at the core remains the problem that ligand binding energies cannot be predicted precisely from individual structures. However, there is a growing body of experimental data for increasingly successful focussing of efforts: focussed chemical libraries, drug repurposing, polypharmacological design, to name a few. Protein kinase target similarity is easily quantified by sequence, and its relevance to ligand design includes broad classification by key binding sites, evaluation of resistance mutations, and the use of surrogate proteins. Although structural evaluation offers more information, the flexibility of protein kinases, and differences between the crystal and physiological environments may make the use of crystal structures misleading when structures are considered individually. Cheminformatics may enable the "calibration" of sequence and crystal structure information, with statistical methods able to identify key correlates to activity but also here, "the devil is in the details." Examples from specific repurposing and polypharmacology applications illustrate these points. This article is part of a Special Issue entitled: Inhibitors of Protein Kinases.

Perspective on computational and structural aspects of kinase discovery from IPK2014

Recent advances in understanding the activity and selectivity of kinase inhibitors and their relationships to protein structure are presented. Conformational selection in kinases is studied from empirical, data-driven and simulation approaches. Ligand binding and its affinity are, in many cases, determined by the predetermined active and inactive conformation of kinases. Binding affinity and selectivity predictions highlight the current state of the art and advances in computational chemistry as it applies to kinase inhibitor discovery. Kinome wide inhibitor profiling and cell panel profiling lead to a better understanding of selectivity and allow for target validation and patient tailoring hypotheses. This article is part of a Special Issue entitled: Inhibitors of Protein Kinases.

SAR156497, an exquisitely selective inhibitor of aurora kinases

The Aurora family of serine/threonine kinases is essential for mitosis. Their crucial role in cell cycle regulation and aberrant expression in a broad range of malignancies have been demonstrated and have prompted intensive search for small molecule Aurora inhibitors. Indeed, over 10 of them have reached the clinic as potential anticancer therapies. We report herein the discovery and optimization of a novel series of tricyclic molecules that has led to SAR156497, an exquisitely selective Aurora A, B, and C inhibitor with in vitro and in vivo efficacy. We also provide insights into its mode of binding to its target proteins, which could explain its selectivity.

Compound Structure-Independent Activity Prediction in High-Dimensional Target Space

Profiling of compound libraries against arrays of targets has become an important approach in pharmaceutical research. The prediction of multi-target compound activities also represents an attractive task for machine learning with potential for drug discovery applications. Herein, we have explored activity prediction in high-dimensional target space. Different types of models were derived to predict multi-target activities. The models included naïve Bayesian (NB) and support vector machine (SVM) classifiers based upon compound structure information and NB models derived on the basis of activity profiles, without considering compound structure. Because the latter approach can be applied to incomplete training data and principally depends on the feature independence assumption, SVM modeling was not applicable in this case. Furthermore, iterative hybrid NB models making use of both activity profiles and compound structure information were built. In high-dimensional target space, NB models utilizing activity profile data were found to yield more accurate activity predictions than structure-based NB and SVM models or hybrid models. An in-depth analysis of activity profile-based models revealed the presence of correlation effects across different targets and rationalized prediction accuracy. Taken together, the results indicate that activity profile information can be effectively used to predict the activity of test compounds against novel targets.

Discovery of novel drugs for promising targets

BACKGROUND

Once a promising drug target is identified, the steps to actually discover and optimize a drug are diverse and challenging.

OBJECTIVE

The goal of this study was to provide a road map to navigate drug discovery.

METHODS

Review general steps for drug discovery and provide illustrating references.

RESULTS

A number of approaches are available to enhance and accelerate target identification and validation. Consideration of a variety of potential mechanisms of action of potential drugs can guide discovery efforts. The hit to lead stage may involve techniques such as high-throughput screening, fragment-based screening, and structure-based design, with informatics playing an ever-increasing role. Biologically relevant screening models are discussed, including cell lines, 3-dimensional culture, and in vivo screening. The process of enabling human studies for an investigational drug is also discussed.

CONCLUSIONS

Drug discovery is a complex process that has significantly evolved in recent years.

Predictive in silico off-target profiling in drug discovery

Drug action can be rationalized as interaction of a molecule with proteins in a regulatory network of targets from a specific biological system. Both drug and side effects are often governed by interaction of the drug molecule with many, often unrelated, targets. Accordingly, arrays of protein–ligand interaction data from numerous in vitro profiling assays today provide growing evidence of polypharmacological drug interactions, even for marketed drugs. In vitro off-target profiling has therefore become an important tool in early drug discovery to learn about potential off-target liabilities, which are sometimes beneficial, but more often safety relevant. The rapidly developing field of in silico profiling approaches is complementing in vitro profiling. These approaches capitalize from large amounts of biochemical data from multiple sources to be exploited for optimizing undesirable side effects in pharmaceutical research. Therefore, current in silico profiling models are nowadays perceived as valuable tools in drug discovery, and promise a platform to support optimally informed decisions.

Are phylogenetic trees suitable for chemogenomics analyses of bioactivity data sets: the importance of shared active compounds and choosing a suitable data embedding method, as exemplified on Kinases

Background

‘Phylogenetic trees’ are commonly used for the analysis of chemogenomics datasets and to relate protein targets to each other, based on the (shared) bioactivities of their ligands. However, no real assessment as to the suitability of this representation has been performed yet in this area. We aimed to address this shortcoming in the current work, as exemplified by a kinase data set, given the importance of kinases in many diseases as well as the availability of large-scale datasets for analysis. In this work, we analyzed a dataset comprising 157 compounds, which have been tested at concentrations of 1 μM and 10 μM against a panel of 225 human protein kinases in full-matrix experiments, aiming to explain kinase promiscuity and selectivity against inhibitors. Compounds were described by chemical features, which were used to represent kinases (i.e. each kinase had an active set of features and an inactive set).

Results

Using this representation, a bioactivity-based classification was made of the kinome, which partially resembles previous sequence-based classifications, where particularly kinases from the TK, CDK, CLK and AGC branches cluster together. However, we were also able to show that in approximately 57% of cases, on average 6 kinase inhibitors exhibit activity against kinases which are located at a large distance in the sequence-based classification (at a relative distance of 0.6 – 0.8 on a scale from 0 to 1), but are correctly located closer to each other in our bioactivity-based tree (distance 0 – 0.4). Despite this improvement on sequence-based classification, also the bioactivity-based classification needed further attention: for approximately 80% of all analyzed kinases, kinases classified as neighbors according to the bioactivity-based classification also show high SAR similarity (i.e. a high fraction of shared active compounds and therefore, interaction with similar inhibitors). However, in the remaining ~20% of cases a clear relationship between kinase bioactivity profile similarity and shared active compounds could not be established, which is in agreement with previously published atypical SAR (such as for LCK, FGFR1, AKT2, DAPK1, TGFR1, MK12 and AKT1).

Conclusions

In this work we were hence able to show that (1) targets (here kinases) with few shared activities are difficult to establish neighborhood relationships for, and (2) phylogenetic tree representations make implicit assumptions (i.e. that neighboring kinases exhibit similar interaction profiles with inhibitors) that are not always suitable for analyses of bioactivity space. While both points have been implicitly alluded to before, this is to the information of the authors the first study that explores both points on a comprehensive basis. Excluding kinases with few shared activities improved the situation greatly (the percentage of kinases for which no neighborhood relationship could be established dropped from 20% to only 4%). We can conclude that all of the above findings need to be taken into account when performing chemogenomics analyses, also for other target classes.

De novo design of protein kinase inhibitors by in silico identification of hinge region-binding fragments

Protein kinases constitute an attractive family of enzyme targets with high relevance to cell and disease biology. Small molecule inhibitors are powerful tools to dissect and elucidate the function of kinases in chemical biology research and to serve as potential starting points for drug discovery. However, the discovery and development of novel inhibitors remains challenging. Here, we describe a structure-based de novo design approach that generates novel, hinge-binding fragments that are synthetically feasible and can be elaborated to small molecule libraries. Starting from commercially available compounds, core fragments were extracted, filtered for pharmacophoric properties compatible with hinge-region binding, and docked into a panel of protein kinases. Fragments with a high consensus score were subsequently short-listed for synthesis. Application of this strategy led to a number of core fragments with no previously reported activity against kinases. Small libraries around the core fragments were synthesized, and representative compounds were tested against a large panel of protein kinases and subjected to co-crystallization experiments. Each of the tested compounds was active against at least one kinase, but not all kinases in the panel were inhibited. A number of compounds showed high ligand efficiencies for therapeutically relevant kinases; among them were MAPKAP-K3, SRPK1, SGK1, TAK1, and GCK for which only few inhibitors are reported in the literature.

Cheminformatics aspects of high throughput screening: from robots to models: symposium summary

The "Cheminformatics aspects of high throughput screening (HTS): from robots to models" symposium was part of the computers in chemistry technical program at the American Chemical Society National Meeting in Denver, Colorado during the fall of 2011. This symposium brought together researchers from high throughput screening centers and molecular modelers from academia and industry to discuss the integration of currently available high throughput screening data and assays with computational analysis. The topics discussed at this symposium covered the data-infrastructure at various academic, hospital, and National Institutes of Health-funded high throughput screening centers, the cheminformatics and molecular modeling methods used in real world examples to guide screening and hit-finding, and how academic and non-profit organizations can benefit from current high throughput screening cheminformatics resources. Specifically, this article also covers the remarks and discussions in the open panel discussion of the symposium and summarizes the following talks on "Accurate Kinase virtual screening: biochemical, cellular and selectivity", "Selective, privileged and promiscuous chemical patterns in high-throughput screening" and "Visualizing and exploring relationships among HTS hits using network graphs".

Prediction of chemical-protein interactions: multitarget-QSAR versus computational chemogenomic methods

Elucidation of chemical-protein interactions (CPI) is the basis of target identification and drug discovery. It is time-consuming and costly to determine CPI experimentally, and computational methods will facilitate the determination of CPI. In this study, two methods, multitarget quantitative structure-activity relationship (mt-QSAR) and computational chemogenomics, were developed for CPI prediction. Two comprehensive data sets were collected from the ChEMBL database for method assessment. One data set consisted of 81 689 CPI pairs among 50 924 compounds and 136 G-protein coupled receptors (GPCRs), while the other one contained 43 965 CPI pairs among 23 376 compounds and 176 kinases. The range of the area under the receiver operating characteristic curve (AUC) for the test sets was 0.95 to 1.0 and 0.82 to 1.0 for 100 GPCR mt-QSAR models and 100 kinase mt-QSAR models, respectively. The AUC of 5-fold cross validation were about 0.92 for both 176 kinases and 136 GPCRs using the chemogenomic method. However, the performance of the chemogenomic method was worse than that of mt-QSAR for the external validation set. Further analysis revealed that there was a high false positive rate for the external validation set when using the chemogenomic method. In addition, we developed a web server named CPI-Predictor, , which is available for free. The methods and tool have potential applications in network pharmacology and drug repositioning.