Profiling Prediction of Kinase Inhibitors: Toward the Virtual Assay

Data-oriented protein kinase drug discovery

The continued growth of data from biological screening and medicinal chemistry provides opportunities for data-driven experimental design and decision making in early-phase drug discovery. Approaches adopted from data science help to integrate internal and public domain data and extract knowledge from historical in-house data. Protein kinase (PK) drug discovery is an exemplary area where large amounts of data are accumulating, providing a valuable knowledge base for discovery projects. Herein, the evolution of PK drug discovery and development of small molecular PK inhibitors (PKIs) is reviewed, highlighting milestone developments in the field and discussing exemplary studies providing a basis for increasing data orientation of PK discovery efforts.

Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors

Conventional machine learning (ML) and deep learning (DL) play a key role in the selectivity prediction of kinase inhibitors. A number of models based on available datasets can be used to predict the kinase profile of compounds, but there is still controversy about the advantages and disadvantages of ML and DL for such tasks. In this study, we constructed a comprehensive benchmark dataset of kinase inhibitors, involving in 141,086 unique compounds and 216,823 well-defined bioassay data points for 354 kinases. We then systematically compared the performance of 12 ML and DL methods on the kinase profiling prediction task. Extensive experimental results reveal that (1) Descriptor-based ML models generally slightly outperform fingerprint-based ML models in terms of predictive performance. RF as an ensemble learning approach displays the overall best predictive performance. (2) Single-task graph-based DL models are generally inferior to conventional descriptor- and fingerprint-based ML models, however, the corresponding multi-task models generally improves the average accuracy of kinase profile prediction. For example, the multi-task FP-GNN model outperforms the conventional descriptor- and fingerprint-based ML models with an average AUC of 0.807. (3) Fusion models based on voting and stacking methods can further improve the performance of the kinase profiling prediction task, specifically, RF::AtomPairs + FP2 + RDKitDes fusion model performs best with the highest average AUC value of 0.825 on the test sets. These findings provide useful information for guiding choices of the ML and DL methods for the kinase profiling prediction tasks. Finally, an online platform called KIPP ( https://kipp.idruglab.cn ) and python software are developed based on the best models to support the kinase profiling prediction, as well as various kinase inhibitor identification tasks including virtual screening, compound repositioning and target fishing.

Pharmacological approaches to understanding protein kinase signaling networks

Protein kinases play vital roles in controlling cell behavior, and an array of kinase inhibitors are used successfully for treatment of disease. Typical drug development pipelines involve biological studies to validate a protein kinase target, followed by the identification of small molecules that effectively inhibit this target in cells, animal models, and patients. However, it is clear that protein kinases operate within complex signaling networks. These networks increase the resilience of signaling pathways, which can render cells relatively insensitive to inhibition of a single kinase, and provide the potential for pathway rewiring, which can result in resistance to therapy. It is therefore vital to understand the properties of kinase signaling networks in health and disease so that we can design effective multi-targeted drugs or combinations of drugs. Here, we outline how pharmacological and chemo-genetic approaches can contribute to such knowledge, despite the known low selectivity of many kinase inhibitors. We discuss how detailed profiling of target engagement by kinase inhibitors can underpin these studies; how chemical probes can be used to uncover kinase-substrate relationships, and how these tools can be used to gain insight into the configuration and function of kinase signaling networks.

KinomeMETA: meta-learning enhanced kinome-wide polypharmacology profiling

Kinase inhibitors are crucial in cancer treatment, but drug resistance and side effects hinder the development of effective drugs. To address these challenges, it is essential to analyze the polypharmacology of kinase inhibitor and identify compound with high selectivity profile. This study presents KinomeMETA, a framework for profiling the activity of small molecule kinase inhibitors across a panel of 661 kinases. By training a meta-learner based on a graph neural network and fine-tuning it to create kinase-specific learners, KinomeMETA outperforms benchmark multi-task models and other kinase profiling models. It provides higher accuracy for understudied kinases with limited known data and broader coverage of kinase types, including important mutant kinases. Case studies on the discovery of new scaffold inhibitors for membrane-associated tyrosine- and threonine-specific cdc2-inhibitory kinase and selective inhibitors for fibroblast growth factor receptors demonstrate the role of KinomeMETA in virtual screening and kinome-wide activity profiling. Overall, KinomeMETA has the potential to accelerate kinase drug discovery by more effectively exploring the kinase polypharmacology landscape.

Artificial intelligence methods in kinase target profiling: Advances and challenges

Kinases have a crucial role in regulating almost the full range of cellular processes, making them essential targets for therapeutic interventions against various diseases. Accurate kinase-profiling prediction is vital for addressing the selectivity/specificity challenges in kinase drug discovery, which is closely related to lead optimization, drug repurposing, and the understanding of potential drug side effects. In this review, we provide an overview of the latest advancements in machine learning (ML)-based and deep learning (DL)-based quantitative structure-activity relationship (QSAR) models for kinase profiling. We highlight current trends in this rapidly evolving field and discuss the existing challenges and future directions regarding experimental data set construction and model architecture design. Our aim is to offer practical insights and guidance for the development and utilization of these approaches.

Poor Generalization by Current Deep Learning Models for Predicting Binding Affinities of Kinase Inhibitors

The extreme surge of interest over the past decade surrounding the use of neural networks has inspired many groups to deploy them for predicting binding affinities of drug-like molecules to their receptors. A model that can accurately make such predictions has the potential to screen large chemical libraries and help streamline the drug discovery process. However, despite reports of models that accurately predict quantitative inhibition using protein kinase sequences and inhibitors' SMILES strings, it is still unclear whether these models can generalize to previously unseen data. Here, we build a Convolutional Neural Network (CNN) analogous to those previously reported and evaluate the model over four datasets commonly used for inhibitor/kinase predictions. We find that the model performs comparably to those previously reported, provided that the individual data points are randomly split between the training set and the test set. However, model performance is dramatically deteriorated when all data for a given inhibitor is placed together in the same training/testing fold, implying that information leakage underlies the models' performance. Through comparison to simple models in which the SMILES strings are tokenized, or in which test set predictions are simply copied from the closest training set data points, we demonstrate that there is essentially no generalization whatsoever in this model. In other words, the model has not learned anything about molecular interactions, and does not provide any benefit over much simpler and more transparent models. These observations strongly point to the need for richer structure-based encodings, to obtain useful prospective predictions of not-yet-synthesized candidate inhibitors.

Predicting the target landscape of kinase inhibitors using 3D convolutional neural networks

Many therapies in clinical trials are based on single drug-single target relationships. To further extend this concept to multi-target approaches using multi-targeted drugs, we developed a machine learning pipeline to unravel the target landscape of kinase inhibitors. This pipeline, which we call 3D-KINEssence, uses a new type of protein fingerprints (3D FP) based on the structure of kinases generated through a 3D convolutional neural network (3D-CNN). These 3D-CNN kinase fingerprints were matched to molecular Morgan fingerprints to predict the targets of each respective kinase inhibitor based on available bioactivity data. The performance of the pipeline was evaluated on two test sets: a sparse drug-target set where each drug is matched in most cases to a single target and also on a densely-covered drug-target set where each drug is matched to most if not all targets. This latter set is more challenging to train, given its non-exclusive character. Our model's root-mean-square error (RMSE) based on the two datasets was 0.68 and 0.8, respectively. These results indicate that 3D FP can predict the target landscape of kinase inhibitors at around 0.8 log units of bioactivity. Our strategy can be utilized in proteochemometric or chemogenomic workflows by consolidating the target landscape of kinase inhibitors.

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson's correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

CMGN: a conditional molecular generation net to design target-specific molecules with desired properties

The rational design of chemical entities with desired properties for a specific target is a long-standing challenge in drug design. Generative neural networks have emerged as a powerful approach to sample novel molecules with specific properties, termed as inverse drug design. However, generating molecules with biological activity against certain targets and predefined drug properties still remains challenging. Here, we propose a conditional molecular generation net (CMGN), the backbone of which is a bidirectional and autoregressive transformer. CMGN applies large-scale pretraining for molecular understanding and navigates the chemical space for specified targets by fine-tuning with corresponding datasets. Additionally, fragments and properties were trained to recover molecules to learn the structure-properties relationships. Our model crisscrosses the chemical space for specific targets and properties that control fragment-growth processes. Case studies demonstrated the advantages and utility of our model in fragment-to-lead processes and multi-objective lead optimization. The results presented in this paper illustrate that CMGN has the potential to accelerate the drug discovery process.

DeepCancerMap: A versatile deep learning platform for target- and cell-based anticancer drug discovery

Discovering new anticancer drugs has been widely concerned and remains an open challenge. Target- and phenotypic-based experimental screening represent two mainstream anticancer drug discovery methods, which suffer from time-consuming, labor-intensive, and high experimental costs. In this study, we collected 485,900 compounds involving in 3,919,974 bioactivity records against 426 anticancer targets and 346 cancer cell lines from academic literature, as well as 60 tumor cell lines from NCI-60 panel. A total of 832 classification models (426 target- and 406 cell-based predictive models) were then constructed to predict the inhibitory activity of compounds against targets and tumor cell lines using FP-GNN deep learning method. Compared to the classical machine learning and deep learning methods, the FP-GNN models achieve considerable overall predictive performance, with the highest AUC values of 0.91, 0.88, 0.91 for the test sets of targets, academia-sourced and NCI-60 cancer cell lines, respectively. A user-friendly webserver called DeepCancerMap and its local version were developed based on these high-quality models, enabling users to perform anticancer drug discovery-related tasks including large-scale virtual screening, profiling prediction of anticancer agents, target fishing, and drug repositioning. We anticipate this platform to accelerate the discovery of anticancer drugs in the field. DeepCancerMap is freely available at https://deepcancermap.idruglab.cn.

Establishment of extensive artificial intelligence models for kinase inhibitor prediction: Identification of novel PDGFRB inhibitors

Identifying hit compounds is an important step in drug development. Unfortunately, this process continues to be a challenging task. Several machine learning models have been generated to aid in simplifying and improving the prediction of candidate compounds. Models tuned for predicting kinase inhibitors have been established. However, an effective model can be limited by the size of the chosen training dataset. In this study, we tested several machine learning models to predict potential kinase inhibitors. A dataset was curated from a number of publicly available repositories. This resulted in a comprehensive dataset covering more than half of the human kinome. More than 2,000 kinase models were established using different model approaches. The performances of the models were compared, and the Keras-MLP model was determined to be the best performing model. The model was then used to screen a chemical library for potential inhibitors targeting platelet-derived growth factor receptor-β (PDGFRB). Several PDGFRB candidates were selected, and in vitro assays confirmed four compounds with PDGFRB inhibitory activity and IC₅₀ values in the nanomolar range. These results show the effectiveness of machine learning models trained on the reported dataset. This report would aid in the establishment of machine learning models as well as in the discovery of novel kinase inhibitors.

Development of machine learning models based on molecular fingerprints for selection of small molecule inhibitors against JAK2 protein

Janus kinase 2 (JAK2) is emerging as a potential therapeutic target for many inflammatory diseases such as myeloproliferative disorders (MPD), cancer and rheumatoid arthritis (RA). In this study, we have collected experimental data of JAK2 protein containing 6021 unique inhibitors. We then characterized them based on Morgan (ECFP6) fingerprints followed by clustering into training and test set based on their molecular scaffolds. These data were used to build the classification models with various supervised machine learning (ML) algorithms that could prioritize novel inhibitors for future drug development against JAK2 protein. The best model built by Random Forest (RF) and Morgan fingerprints achieved the G-mean value of 0.84 on the external test set. As an application of our classification model, virtual screening was performed against Drugbank molecules in order to identify the potential inhibitors based on the confidence score by RF model. Nine potential molecules were identified, which were further subject to molecular docking studies to evaluate the virtual screening results of the best RF model. This proposed method can prove useful for developing novel target-specific JAK2 inhibitors.

Papyrus: a large-scale curated dataset aimed at bioactivity predictions

With the ongoing rapid growth of publicly available ligand-protein bioactivity data, there is a trove of valuable data that can be used to train a plethora of machine-learning algorithms. However, not all data is equal in terms of size and quality and a significant portion of researchers' time is needed to adapt the data to their needs. On top of that, finding the right data for a research question can often be a challenge on its own. To meet these challenges, we have constructed the Papyrus dataset. Papyrus is comprised of around 60 million data points. This dataset contains multiple large publicly available datasets such as ChEMBL and ExCAPE-DB combined with several smaller datasets containing high-quality data. The aggregated data has been standardised and normalised in a manner that is suitable for machine learning. We show how data can be filtered in a variety of ways and also perform some examples of quantitative structure-activity relationship analyses and proteochemometric modelling. Our ambition is that this pruned data collection constitutes a benchmark set that can be used for constructing predictive models, while also providing an accessible data source for research.

Redesigning plant specialized metabolism with supervised machine learning using publicly available reactome data

The immense structural diversity of products and intermediates of plant specialized metabolism (specialized metabolites) makes them rich sources of therapeutic medicine, nutrients, and other useful materials. With the rapid accumulation of reactome data that can be accessible on biological and chemical databases, along with recent advances in machine learning, this review sets out to outline how supervised machine learning can be used to design new compounds and pathways by exploiting the wealth of said data. We will first examine the various sources from which reactome data can be obtained, followed by explaining the different machine learning encoding methods for reactome data. We then discuss current supervised machine learning developments that can be employed in various aspects to help redesign plant specialized metabolism.

Kinome-wide polypharmacology profiling of small molecules by multi-task graph isomorphism network approach

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

The use of machine learning modeling, virtual screening, molecular docking, and molecular dynamics simulations to identify potential VEGFR2 kinase inhibitors

Targeting the signaling pathway of the Vascular endothelial growth factor receptor-2 is a promising approach that has drawn attention in the quest to develop novel anti-cancer drugs and cardiovascular disease treatments. We construct a screening pipeline using machine learning classification integrated with similarity checks of approved drugs to find new inhibitors. The statistical metrics reveal that the random forest approach has slightly better performance. By further similarity screening against several approved drugs, two candidates are selected. Analysis of absorption, distribution, metabolism, excretion, and toxicity, along with molecular docking and dynamics are performed for the two candidates with regorafenib as a reference. The binding energies of molecule1, molecule2, and regorafenib are - 89.1, - 95.3, and - 87.4 (kJ/mol), respectively which suggest candidate compounds have strong binding to the target. Meanwhile, the median lethal dose and maximum tolerated dose for regorafenib, molecule1, and molecule2 are predicted to be 800, 1600, and 393 mg/kg, and 0.257, 0.527, and 0.428 log mg/kg/day, respectively. Also, the inhibitory activity of these compounds is predicted to be 7.23 and 7.31, which is comparable with the activity of pazopanib and sorafenib drugs. In light of these findings, the two compounds could be further investigated as potential candidates for anti-angiogenesis therapy.

Target-specific compound selectivity for multi-target drug discovery and repurposing

Most drug molecules modulate multiple target proteins, leading either to therapeutic effects or unwanted side effects. Such target promiscuity partly contributes to high attrition rates and leads to wasted costs and time in the current drug discovery process, and makes the assessment of compound selectivity an important factor in drug development and repurposing efforts. Traditionally, selectivity of a compound is characterized in terms of its target activity profile (wide or narrow), which can be quantified using various statistical and information theoretic metrics. Even though the existing selectivity metrics are widely used for characterizing the overall selectivity of a compound, they fall short in quantifying how selective the compound is against a particular target protein (e.g., disease target of interest). We therefore extended the concept of compound selectivity towards target-specific selectivity, defined as the potency of a compound to bind to the particular protein in comparison to the other potential targets. We decompose the target-specific selectivity into two components: 1) the compound’s potency against the target of interest (absolute potency), and 2) the compound’s potency against the other targets (relative potency). The maximally selective compound-target pairs are then identified as a solution of a bi-objective optimization problem that simultaneously optimizes these two potency metrics. In computational experiments carried out using large-scale kinase inhibitor dataset, which represents a wide range of polypharmacological activities, we show how the optimization-based selectivity scoring offers a systematic approach to finding both potent and selective compounds against given kinase targets. Compared to the existing selectivity metrics, we show how the target-specific selectivity provides additional insights into the target selectivity and promiscuity of multi-targeting kinase inhibitors. Even though the selectivity score is shown to be relatively robust against both missing bioactivity values and the dataset size, we further developed a permutation-based procedure to calculate empirical p-values to assess the statistical significance of the observed selectivity of a compound-target pair in the given bioactivity dataset. We present several case studies that show how the target-specific selectivity can distinguish between highly selective and broadly-active kinase inhibitors, hence facilitating the discovery or repurposing of multi-targeting drugs.

Improving the Prediction of Potential Kinase Inhibitors with Feature Learning on Multisource Knowledge

PURPOSE

The identification of potential kinase inhibitors plays a key role in drug discovery for treating human diseases. Currently, most existing computational methods only extract limited features such as sequence information from kinases and inhibitors. To further enhance the identification of kinase inhibitors, more features need to be leveraged. Hence, it is appealing to develop effective methods to aggregate feature information from multisource knowledge for predicting potential kinase inhibitors. In this paper, we propose a novel computational framework called FLMTS to improve the performance of kinase inhibitor prediction by aggregating multisource knowledge.

METHOD

FLMTS uses a random walk with restart (RWR) to combine multiscale information in a heterogeneous network. We used the combined information as features of compounds and kinases and input them into random forest (RF) to predict unknown compound-kinase interactions.

RESULTS

Experimental results reveal that FLMTS obtains significant improvement over existing state-of-the-art methods. Case studies demonstrated the reliability of FLMTS, and pathway enrichment analysis demonstrated that FLMTS could also accurately predict signaling pathways in disease treatment.

CONCLUSION

In conclusion, our computational framework of FLMTS for improving the prediction of potential kinase inhibitors successfully aggregates feature information from multisource knowledge, yielding better prediction performance than existing state-of-the-art methods.

Profiling prediction of nuclear receptor modulators with multi-task deep learning methods: toward the virtual screening

Nuclear receptors (NRs) are ligand-activated transcription factors, which constitute one of the most important targets for drug discovery. Current computational strategies mainly focus on a single target, and the transfer of learned knowledge among NRs was not considered yet. Herein we proposed a novel computational framework named NR-Profiler for prediction of potential NR modulators with high affinity and specificity. First, we built a comprehensive NR data set including 42 684 interactions to connect 42 NRs and 31 033 compounds. Then, we used multi-task deep neural network and multi-task graph convolutional neural network architectures to construct multi-task multi-classification models. To improve the predictive capability and robustness, we built a consensus model with an area under the receiver operating characteristic curve (AUC) = 0.883. Compared with conventional machine learning and structure-based approaches, the consensus model showed better performance in external validation. Using this consensus model, we demonstrated the practical value of NR-Profiler in virtual screening for NRs. In addition, we designed a selectivity score to quantitatively measure the specificity of NR modulators. Finally, we developed a freely available standalone software for users to make profiling predictions for their compounds of interest. In summary, our NR-Profiler provides a useful tool for NR-profiling prediction and is expected to facilitate NR-based drug discovery.

Exploring kinase family inhibitors and their moiety preferences using deep SHapley additive exPlanations

Background

While it has been known that human protein kinases mediate most signal transductions in cells and their dysfunction can result in inflammatory diseases and cancers, it remains a challenge to find effective kinase inhibitor as drugs for these diseases. One major challenge is the compensatory upregulation of related kinases following some critical kinase inhibition. To circumvent the compensatory effect, it is desirable to have inhibitors that inhibit all the kinases belonging to the same family, instead of targeting only a few kinases. However, finding inhibitors that target a whole kinase family is laborious and time consuming in wet lab.

Results

In this paper, we present a computational approach taking advantage of interpretable deep learning models to address this challenge. Specifically, we firstly collected 9,037 inhibitor bioassay results (with 3991 active and 5046 inactive pairs) for eight kinase families (including EGFR, Jak, GSK, CLK, PIM, PKD, Akt and PKG) from the ChEMBL25 Database and the Metz Kinase Profiling Data. We generated 238 binary moiety features for each inhibitor, and used the features as input to train eight deep neural networks (DNN) models to predict whether an inhibitor is active for each kinase family. We then employed the SHapley Additive exPlanations (SHAP) to analyze the importance of each moiety feature in each classification model, identifying moieties that are in the common kinase hinge sites across the eight kinase families, as well as moieties that are specific to some kinase families. We finally validated these identified moieties using experimental crystal structures to reveal their functional importance in kinase inhibition.

Conclusion

With the SHAP methodology, we identified two common moieties for eight kinase families, 9 EGFR-specific moieties, and 6 Akt-specific moieties, that bear functional importance in kinase inhibition. Our result suggests that SHAP has the potential to help finding effective pan-kinase family inhibitors.

Discovery of moiety preference by Shapley value in protein kinase family using random forest models

Background

Human protein kinases play important roles in cancers, are highly co-regulated by kinase families rather than a single kinase, and complementarily regulate signaling pathways. Even though there are > 100,000 protein kinase inhibitors, only 67 kinase drugs are currently approved by the Food and Drug Administration (FDA).

Results

In this study, we used “merged moiety-based interpretable features (MMIFs),” which merged four moiety-based compound features, including Checkmol fingerprint, PubChem fingerprint, rings in drugs, and in-house moieties as the input features for building random forest (RF) models. By using > 200,000 bioactivity test data, we classified inhibitors as kinase family inhibitors or non-inhibitors in the machine learning. The results showed that our RF models achieved good accuracy (> 0.8) for the 10 kinase families. In addition, we found kinase common and specific moieties across families using the Shapley Additive exPlanations (SHAP) approach. We also verified our results using protein kinase complex structures containing important interactions of the hinges, DFGs, or P-loops in the ATP pocket of active sites.

Conclusions

In summary, we not only constructed highly accurate prediction models for predicting inhibitors of kinase families but also discovered common and specific inhibitor moieties between different kinase families, providing new opportunities for designing protein kinase inhibitors.

Transfer inhibitory potency prediction to binary classification: A model only needs a small training set

One of the most laborious for drug discovery is to select compounds from a library for experimental evaluation. Hence, we propose a machine learning model only needs to be trained on a small dataset to predict the inhibition constant (Ki) and half maximal inhibitory concentration (IC50) for a compound. We transfer the prediction task to a simpler binary classification task based on a naive but effective idea that we only need the related rank of a compound to determine whether to take it for further examination. To achieve this, we design a data augmentation strategy to effectively leverage the relationship between the compounds in the training set. After that, we formulate a new reward function for deep reinforcement learning to balance the feature selection and the accuracy. We employ a particle swarm optimized support vector machine for the binary classification task. Finally, a soft voting mechanism is introduced to solve the contradiction from the binary classification. Sufficient experiments show that our model achieves high and reliable accuracy, and is capable of ranking compounds based on a selected set of molecular descriptors. The current results show that our model provides a potential ligand-based in silico approach for prioritizing chemicals for experimental studies.

Generalized vec trick for fast learning of pairwise kernel models

Pairwise learning corresponds to the supervised learning setting where the goal is to make predictions for pairs of objects. Prominent applications include predicting drug-target or protein-protein interactions, or customer-product preferences. In this work, we present a comprehensive review of pairwise kernels, that have been proposed for incorporating prior knowledge about the relationship between the objects. Specifically, we consider the standard, symmetric and anti-symmetric Kronecker product kernels, metric-learning, Cartesian, ranking, as well as linear, polynomial and Gaussian kernels. Recently, a $$O(nm+nq)$$ O ( n m + n q ) time generalized vec trick algorithm, where $$n$$ n , $$m$$ m , and $$q$$ q denote the number of pairs, drugs and targets, was introduced for training kernel methods with the Kronecker product kernel. This was a significant improvement over previous $$O(n^2)$$ O ( n 2 ) training methods, since in most real-world applications $$m,q<< n$$ m , q < < n . In this work we show how all the reviewed kernels can be expressed as sums of Kronecker products, allowing the use of generalized vec trick for speeding up their computation. In the experiments, we demonstrate how the introduced approach allows scaling pairwise kernels to much larger data sets than previously feasible, and provide an extensive comparison of the kernels on a number of biological interaction prediction tasks.

S2DV: converting SMILES to a drug vector for predicting the activity of anti-HBV small molecules

In the past few decades, chronic hepatitis B caused by hepatitis B virus (HBV) has been one of the most serious diseases to human health. The development of innovative systems is essential for preventing the complex pathogenesis of hepatitis B and reducing side effects caused by drugs. HBV inhibitory drugs have been developed through various compounds, and they are often limited by routine experimental screening and delay drug development. More recently, virtual screening of compounds has gradually been used in drug research with strong computational capability and is further applied in anti-HBV drug screening, thus facilitating a reliable drug screening process. However, the lack of structural information in traditional compound analysis is an important hurdle for unsatisfactory efficiency in drug screening. Here, a natural language processing technique was adopted to analyze compound simplified molecular input line entry system strings. By using the targeted optimized word2vec model for pretraining, we can accurately represent the relationship between the compound and its substructure. The machine learning model based on training results can effectively predict the inhibitory effect of compounds on HBV and liver toxicity. The reliability of the model is verified by the results of wet-lab experiments. In addition, a tool has been published to predict potential compounds. Hence, this article provides a new perspective on the prediction of compound properties for anti-HBV drugs that can help improve hepatitis B diagnosis and further develop human health in the future.

Deep Learning and Computational Chemistry

Within the context of the latest resurgence in the application of artificial intelligence approaches, deep learning has undergone a renaissance over recent years. These methods have been applied to a number of problems in computational chemistry. Compared to other machine learning approaches, the practical performance advantages of deep neural networks are often unclear. However, deep learning does appear to offer a number of other advantages such as the facile incorporation of multitask learning and the enhancement of generative modeling. The high complexity of contemporary network architectures represents a potentially significant barrier to their future adoption due to the costs of training such models and challenges in interpreting their predictions. When combined with the relative paucity of very large datasets, it is interesting to reflect on whether deep learning is likely to have the kind of transformational impact on computational chemistry that it is commonly held to have had in other domains such as image recognition.

Evolution of kinase polypharmacology across HSP90 drug discovery

Most small molecules interact with several target proteins but this polypharmacology is seldom comprehensively investigated or explicitly exploited during drug discovery. Here, we use computational and experimental methods to identify and systematically characterize the kinase cross-pharmacology of representative HSP90 inhibitors. We demonstrate that the resorcinol clinical candidates ganetespib and, to a lesser extent, luminespib, display unique off-target kinase pharmacology as compared with other HSP90 inhibitors. We also demonstrate that polypharmacology evolved during the optimization to discover luminespib and that the hit, leads, and clinical candidate all have different polypharmacological profiles. We therefore recommend the computational and experimental characterization of polypharmacology earlier in drug discovery projects to unlock new multi-target drug design opportunities.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

Facing small and biased data dilemma in drug discovery with enhanced federated learning approaches

Artificial intelligence (AI) models usually require large amounts of high-quality training data, which is in striking contrast to the situation of small and biased data faced by current drug discovery pipelines. The concept of federated learning has been proposed to utilize distributed data from different sources without leaking sensitive information of the data. This emerging decentralized machine learning paradigm is expected to dramatically improve the success rate of AI-powered drug discovery. Here, we simulated the federated learning process with different property and activity datasets from different sources, among which overlapping molecules with high or low biases exist in the recorded values. Beyond the benefit of gaining more data, we also demonstrated that federated training has a regularization effect superior to centralized training on the pooled datasets with high biases. Moreover, different network architectures for clients and aggregation algorithms for coordinators have been compared on the performance of federated learning, where personalized federated learning shows promising results. Our work demonstrates the applicability of federated learning in predicting drug-related properties and highlights its promising role in addressing the small and biased data dilemma in drug discovery.

Recent advances in drug repurposing using machine learning

Drug repurposing aims to find new uses for already existing and approved drugs. We now provide a brief overview of recent developments in drug repurposing using machine learning alongside other computational approaches for comparison. We also highlight several applications for cancer using kinase inhibitors, Alzheimer's disease as well as COVID-19.

Elucidating direct kinase targets of compound Danshen dropping pills employing archived data and prediction models

Research on direct targets of traditional Chinese medicine (TCM) is the key to study the mechanism and material basis of it, but there is still no effective methods at present. We took Compound Danshen dropping pills (CDDP) as a study case to establish a strategy to identify significant direct targets of TCM. As a result, thirty potential active kinase targets of CDDP were identified. Nine of them had potential dose-dependent effects. In addition, the direct inhibitory effect of CDDP on three kinases, AURKB, MET and PIM1 were observed both on biochemical level and cellular level, which could not only shed light on the mechanisms of action involved in CDDP, but also suggesting the potency of drug repositioning of CDDP. Our results indicated that the research strategy including both in silico models and experimental validation that we built, were relatively efficient and reliable for direct targets identification for TCM prescription, which will help elucidating the mechanisms of TCM and promoting the modernization of TCM.

Artificial intelligence in drug discovery: recent advances and future perspectives

Introduction: Artificial intelligence (AI) has inspired computer-aided drug discovery. The widespread adoption of machine learning, in particular deep learning, in multiple scientific disciplines, and the advances in computing hardware and software, among other factors, continue to fuel this development. Much of the initial skepticism regarding applications of AI in pharmaceutical discovery has started to vanish, consequently benefitting medicinal chemistry.Areas covered: The current status of AI in chemoinformatics is reviewed. The topics discussed herein include quantitative structure-activity/property relationship and structure-based modeling, de novo molecular design, and chemical synthesis prediction. Advantages and limitations of current deep learning applications are highlighted, together with a perspective on next-generation AI for drug discovery.Expert opinion: Deep learning-based approaches have only begun to address some fundamental problems in drug discovery. Certain methodological advances, such as message-passing models, spatial-symmetry-preserving networks, hybrid de novo design, and other innovative machine learning paradigms, will likely become commonplace and help address some of the most challenging questions. Open data sharing and model development will play a central role in the advancement of drug discovery with AI.

Identifying Novel Drug Targets by iDTPnd: A Case Study of Kinase Inhibitors

Current FDA-approved kinase inhibitors cause diverse adverse effects, some of which are due to the mechanism-independent effects of these drugs. Identifying these mechanism-independent interactions could improve drug safety and support drug repurposing. Here, we develop iDTPnd (integrated Drug Target Predictor with negative dataset), a computational approach for large-scale discovery of novel targets for known drugs. For a given drug, we construct a positive structural signature as well as a negative structural signature that captures the weakly conserved structural features of drug-binding sites. To facilitate assessment of unintended targets, iDTPnd also provides a docking-based interaction score and its statistical significance. We confirm the interactions of sorafenib, imatinib, dasatinib, sunitinib, and pazopanib with their known targets at a sensitivity of 52% and a specificity of 55%. We also validate 10 predicted novel targets by using in vitro experiments. Our results suggest that proteins other than kinases, such as nuclear receptors, cytochrome P450, and MHC class I molecules, can also be physiologically relevant targets of kinase inhibitors. Our method is general and broadly applicable for the identification of protein–small molecule interactions, when sufficient drug–target 3D data are available. The code for constructing the structural signatures is available at https://sfb.kaust.edu.sa/Documents/iDTP.zip.

Image-based profiling for drug discovery: due for a machine-learning upgrade?

Image-based profiling is a maturing strategy by which the rich information present in biological images is reduced to a multidimensional profile, a collection of extracted image-based features. These profiles can be mined for relevant patterns, revealing unexpected biological activity that is useful for many steps in the drug discovery process. Such applications include identifying disease-associated screenable phenotypes, understanding disease mechanisms and predicting a drug's activity, toxicity or mechanism of action. Several of these applications have been recently validated and have moved into production mode within academia and the pharmaceutical industry. Some of these have yielded disappointing results in practice but are now of renewed interest due to improved machine-learning strategies that better leverage image-based information. Although challenges remain, novel computational technologies such as deep learning and single-cell methods that better capture the biological information in images hold promise for accelerating drug discovery.

IDDkin: Network-based influence deep diffusion model for enhancing prediction of kinase inhibitors

MOTIVATION

Protein kinases have been the focus of drug discovery research for many years because they play a causal role in many human diseases. Understanding the binding profile of kinase inhibitors is a prerequisite for drug discovery, and traditional methods of predicting kinase inhibitors are time-consuming and inefficient. Calculation-based predictive methods provide a relatively low-cost and high-efficiency approach to the rapid development and effective understanding of the binding profile of kinase inhibitors. Particularly, the continuous improvement of network pharmacology methods provides unprecedented opportunities for drug discovery, network-based computational methods could be employed to aggregate the effective information from heterogeneous sources, which have become a new way for predicting the binding profile of kinase inhibitors.

RESULTS

In this study, we proposed a network-based influence deep diffusion model, named IDDkin, for enhancing the prediction of kinase inhibitors. IDDkin uses deep graph convolutional networks, graph attention networks and adaptive weighting methods to diffuse the effective information of heterogeneous networks. The updated kinase and compound representations are used to predict potential compound-kinase pairs. The experimental results show that the performance of IDDkin is superior to the comparison methods, including the state-of-the art kinase inhibitor prediction method and the classic model widely used in relationship prediction. In experiments conducted to verify its generalizability and in case studies, the IDDkin model also shows excellent performance. All of these results demonstrate the powerful predictive ability of the IDDkin model in the field of kinase inhibitors.

AVAILABILITY AND IMPLEMENTATION

Source code and data can be downloaded from https://github.com/ CS-BIO/IDDkin.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Convolutional architectures for virtual screening

Background

A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy.

Results

A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% in high precision discrimination).

Conclusion

The proposed architecture outperforms state-of-the-art ML approaches, and some interesting insights on molecular fingerprints are devised.

KinomeX: a web application for predicting kinome-wide polypharmacology effect of small molecules

MOTIVATION

The large-scale kinome-wide virtual profiling for small molecules is a daunting task by experimental and traditional in silico drug design approaches. Recent advances in deep learning algorithms have brought about new opportunities in promoting this process.

RESULTS

KinomeX is an online platform to predict kinome-wide polypharmacology effect of small molecules based solely on their chemical structures. The prediction is made by a multi-task deep neural network model trained with over 140 000 bioactivity data points for 391 kinases. Extensive computational and experimental validations have been performed. Overall, KinomeX enables users to create a comprehensive kinome interaction network for designing novel chemical modulators, and is of practical value on exploring the previously less studied or untargeted kinases.

AVAILABILITY AND IMPLEMENTATION

KinomeX is available at: https://kinome.dddc.ac.cn.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping

An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (~ 0.65 and ~ 0.70 for similarity searching depending on data sets, and ~ 0.85 for classification) and EF5 (~ 4.67 and ~ 5.82 for similarity searching depending on data sets, and ~ 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of ~ 0.57 and ~ 0.66, and EF5 of ~ 4.09 and ~ 6.41, depending on data sets, classification AUC of ~ 0.87, and EF5 of ~ 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds.

KinaMetrix: a web resource to investigate kinase conformations and inhibitor space

Protein kinases are among the most explored protein drug targets. Visualization of kinase conformations is critical for understanding structure–function relationship in this family and for developing chemically unique, conformation-specific small molecule drugs. We have developed Kinformation, a random forest classifier that annotates the conformation of over 3500 protein kinase structures in the Protein Data Bank. Kinformation was trained on structural descriptors derived from functionally important motifs to automatically categorize kinases into five major conformations with pharmacological relevance. Here we present KinaMetrix (http://KinaMetrix.com), a web resource enabling researchers to investigate the protein kinase conformational space as well as a subset of kinase inhibitors that exhibit conformational specificity. KinaMetrix allows users to classify uploaded kinase structures, as well as to derive structural descriptors of protein kinases. Uploaded structures can then be compared to atomic structures of other kinases, enabling users to identify kinases that occupy a similar conformational space to their uploaded structure. Finally, KinaMetrix also serves as a repository for both small molecule substructures that are significantly associated with each conformation type, and for homology models of kinases in inactive conformations. We expect KinaMetrix to serve as a resource for researchers studying kinase structural biology or developing conformation-specific kinase inhibitors.

In silico Methods for Design of Kinase Inhibitors as Anticancer Drugs

Rational drug design implies usage of molecular modeling techniques such as pharmacophore modeling, molecular dynamics, virtual screening, and molecular docking to explain the activity of biomolecules, define molecular determinants for interaction with the drug target, and design more efficient drug candidates. Kinases play an essential role in cell function and therefore are extensively studied targets in drug design and discovery. Kinase inhibitors are clinically very important and widely used antineoplastic drugs. In this review, computational methods used in rational drug design of kinase inhibitors are discussed and compared, considering some representative case studies.

Machine Learning Models for Accurate Prediction of Kinase Inhibitors with Different Binding Modes

Noncovalent inhibitors of protein kinases have different modes of action. They bind to the active or inactive form of kinases, compete with ATP, stabilize inactive kinase conformations, or act through allosteric sites. Accordingly, kinase inhibitors have been classified on the basis of different binding modes. For medicinal chemistry, it would be very useful to derive mechanistic hypotheses for newly discovered inhibitors. Therefore, we have applied different machine learning approaches to generate models for predicting different classes of kinase inhibitors including types I, I¹/₂, and II as well as allosteric inhibitors. These models were built on the basis of compounds with binding modes confirmed by X-ray crystallography and yielded unexpectedly accurate and stable predictions without the need for deep learning. The results indicate that the new machine learning models have considerable potential for practical applications. Therefore, our data sets and models are made freely available.

Deep Learning Enhancing Kinome-Wide Polypharmacology Profiling: Model Construction and Experiment Validation

The kinome-wide virtual profiling of small molecules with high-dimensional structure-activity data is a challenging task in drug discovery. Here, we present a virtual profiling model against a panel of 391 kinases based on large-scale bioactivity data and the multitask deep neural network algorithm. The obtained model yields excellent internal prediction capability with an auROC of 0.90 and consistently outperforms conventional single-task models on external tests, especially for kinases with insufficient activity data. Moreover, more rigorous experimental validations including 1410 kinase-compound pairs showed a high-quality average auROC of 0.75 and confirmed many novel predicted "off-target" activities. Given the verified generalizability, the model was further applied to various scenarios for depicting the kinome-wide selectivity and the association with certain diseases. Overall, the computational model enables us to create a comprehensive kinome interaction network for designing novel chemical modulators or drug repositioning and is of practical value for exploring previously less studied kinases.