Predicting protein-ligand interactions based on bow-pharmacological space and Bayesian additive regression trees

Exploring Scoring Function Space: Developing Computational Models for Drug Discovery

BACKGROUND

The idea of scoring function space established a systems-level approach to address the development of models to predict the affinity of drug molecules by those interested in drug discovery.

OBJECTIVE

Our goal here is to review the concept of scoring function space and how to explore it to develop machine learning models to address protein-ligand binding affinity.

METHODS

We searched the articles available in PubMed related to the scoring function space. We also utilized crystallographic structures found in the protein data bank (PDB) to represent the protein space.

RESULTS

The application of systems-level approaches to address receptor-drug interactions allows us to have a holistic view of the process of drug discovery. The scoring function space adds flexibility to the process since it makes it possible to see drug discovery as a relationship involving mathematical spaces.

CONCLUSION

The application of the concept of scoring function space has provided us with an integrated view of drug discovery methods. This concept is useful during drug discovery, where we see the process as a computational search of the scoring function space to find an adequate model to predict receptor-drug binding affinity.

Prediction of protein-ligand binding affinity with deep learning

The prediction of binding affinities between target proteins and small molecule drugs is essential for speeding up the drug research and design process. To attain precise and effective affinity prediction, computer-aided methods are employed in the drug discovery pipeline. In the last decade, a variety of computational methods has been developed, with deep learning being the most commonly used approach. We have gathered several deep learning methods and classified them into convolutional neural networks (CNNs), graph neural networks (GNNs), and Transformers for analysis and discussion. Initially, we conducted an analysis of the different deep learning methods, focusing on their feature construction and model architecture. We discussed the advantages and disadvantages of each model. Subsequently, we conducted experiments using four deep learning methods on the PDBbind v.2016 core set. We evaluated their prediction capabilities in various affinity intervals and statistically and visually analyzed the samples of correct and incorrect predictions for each model. Through visual analysis, we attempted to combine the strengths of the four models to improve the Root Mean Square Error (RMSE) of predicted affinities by 1.6% (reducing the absolute value to 1.101) and the Pearson Correlation Coefficient (R) by 2.9% (increasing the absolute value to 0.894) compared to the current state-of-the-art method. Lastly, we discussed the challenges faced by current deep learning methods in affinity prediction and proposed potential solutions to address these issues.

Screening Power of End-Point Free-Energy Calculations in Cucurbituril Host-Guest Systems

End-point free-energy methods as an indispensable component in virtual screening are commonly recognized as a tool with a certain level of screening power in pharmaceutical research. While a huge number of records could be found for end-point applications in protein-ligand, protein-protein, and protein-DNA complexes from academic and industrial reports, up to now, there is no large-scale benchmark in host-guest complexes supporting the screening power of end-point free-energy techniques. A good benchmark requires a data set of sufficient coverage of pharmaceutically relevant chemical space, a long-time sampling length supporting the trajectory approximation of the ensemble average, and a sufficient sample size of receptor-acceptor pairs to stabilize the performance statistics. In this work, selecting a popular family of macrocyclic hosts named cucurbiturils, we construct a large data set containing 154 host-guest pairs, perform extensive end-point sampling of several hundred nanosecond lengths for each system, and extract the free-energy estimates with a variety of end-point free-energy techniques, including the advanced three-trajectory dielectric-constant-variable regime proposed in our recent work. The best-performing end-point protocol employs GAFF2 for solute descriptions, the three-trajectory end-point sampling regime, and the MM/GBSA Hamiltonian in free-energy extraction, achieving a high ranking metrics of Kendall τ > 0.6, a Pearlman predictive index of ∼0.8, and a high scoring power of Pearson r > 0.8. The current project as the first large-scale systematic benchmark of end-point methods in host-guest complexes in academic publications provides solid evidence of the applicability of end-point techniques and direct guidance of computational setups in practical host-guest systems.

AmorProt: Amino Acid Molecular Fingerprints Repurposing-Based Protein Fingerprint

As protein therapeutics play an important role in almost all medical fields, numerous studies have been conducted on proteins using artificial intelligence. Artificial intelligence has enabled data-driven predictions without the need for expensive experiments. Nevertheless, unlike the various molecular fingerprint algorithms that have been developed, protein fingerprint algorithms have rarely been studied. In this study, we proposed the amino acid molecular fingerprints repurposing-based protein (AmorProt) fingerprint, a protein sequence representation method that effectively uses the molecular fingerprints corresponding to 20 amino acids. Subsequently, the performances of the tree-based machine learning and artificial neural network models were compared using (1) amyloid classification and (2) isoelectric point regression. Finally, the applicability and advantages of the developed platform were demonstrated through a case study and the following experiments: (3) comparison of dataset dependence with feature-based methods, (4) feature importance analysis, and (5) protein space analysis. Consequently, the significantly improved model performance and data-set-independent versatility of the AmorProt fingerprint were verified. The results revealed that the current protein representation method can be applied to various fields related to proteins, such as predicting their fundamental properties or interaction with ligands.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

In Vitro and In Silico Studies for the Identification of Potent Metabolites of Some High-Altitude Medicinal Plants from Nepal Inhibiting SARS-CoV-2 Spike Protein

Despite ongoing vaccination programs against COVID-19 around the world, cases of infection are still rising with new variants. This infers that an effective antiviral drug against COVID-19 is crucial along with vaccinations to decrease cases. A potential target of such antivirals could be the membrane components of the causative pathogen, SARS-CoV-2, for instance spike (S) protein. In our research, we have deployed in vitro screening of crude extracts of seven ethnomedicinal plants against the spike receptor-binding domain (S1-RBD) of SARS-CoV-2 using an enzyme-linked immunosorbent assay (ELISA). Following encouraging in vitro results for Tinospora cordifolia, in silico studies were conducted for the 14 reported antiviral secondary metabolites isolated from T. cordifolia-a species widely cultivated and used as an antiviral drug in the Himalayan country of Nepal-using Genetic Optimization for Ligand Docking (GOLD), Molecular Operating Environment (MOE), and BIOVIA Discovery Studio. The molecular docking and binding energy study revealed that cordifolioside-A had a higher binding affinity and was the most effective in binding to the competitive site of the spike protein. Molecular dynamics (MD) simulation studies using GROMACS 5.4.1 further assayed the interaction between the potent compound and binding sites of the spike protein. It revealed that cordifolioside-A demonstrated better binding affinity and stability, and resulted in a conformational change in S1-RBD, hence hindering the activities of the protein. In addition, ADMET analysis of the secondary metabolites from T. cordifolia revealed promising pharmacokinetic properties. Our study thus recommends that certain secondary metabolites of T. cordifolia are possible medicinal candidates against SARS-CoV-2.

In silico prediction suggests inhibitory effect of halogenated boroxine on human catalase and carbonic anhydrase

Background

This research work included bioinformatics modeling of the dipotassium-trioxohydroxytetrafluorotriborate-halogenated boroxine molecule, as well as simulation and prediction of structural interactions between the halogenated boroxine molecule, human carbonic anhydrase, and human catalase structures. Using computational methods, we tried to confirm the inhibitory effect of halogenated boroxine on the active sites of these previously mentioned enzymes. The three-dimensional crystal structures of human catalase (PDB ID: 1DGB) and human carbonic anhydrase (PDB ID: 6FE2) were retrieved from RCSB Protein Data Bank and the protein preparation was performed using AutoDock Tools. ACD/ChemSketch and ChemDoodle were used for creating the three-dimensional structure of halogenated boroxine. Molecular docking was performed using AutoDock Vina, while the results were visualized using PyMOL.

Results

Results obtained in this research are showing evidence that there are interactions between the halogenated boroxine molecule and both previously mentioned proteins (human carbonic anhydrase and human catalase) in their active sites, which led us to the conclusion that the inhibitory function of halogenated boroxine has been confirmed.

Conclusion

These findings could be an important step in determining the exact mechanisms of inhibitory activity and will hopefully serve in further research purposes of complex pharmacogenomics studies.

Metabolization and sequestration of plant specialized metabolites in insect herbivores: Current and emerging approaches

Herbivorous insects encounter diverse plant specialized metabolites (PSMs) in their diet, that have deterrent, anti-nutritional, or toxic properties. Understanding how they cope with PSMs is crucial to understand their biology, population dynamics, and evolution. This review summarizes current and emerging cutting-edge methods that can be used to characterize the metabolic fate of PSMs, from ingestion to excretion or sequestration. It further emphasizes a workflow that enables not only to study PSM metabolism at different scales, but also to tackle and validate the genetic and biochemical mechanisms involved in PSM resistance by herbivores. This review thus aims at facilitating research on PSM-mediated plant-herbivore interactions.

A machine learning model for classifying G-protein-coupled receptors as agonists or antagonists

Background

G-protein coupled receptors (GPCRs) sense and transmit extracellular signals into the intracellular machinery by regulating G proteins. GPCR malfunctions are associated with a variety of signaling-related diseases, including cancer and diabetes; at least a third of the marketed drugs target GPCRs. Thus, characterization of their signaling and regulatory mechanisms is crucial for the development of effective drugs.

Results

In this study, we developed a machine learning model to identify GPCR agonists and antagonists. We designed two-step prediction models: the first model identified the ligands binding to GPCRs and the second model classified the ligands as agonists or antagonists. Using 990 selected subset features from 5270 molecular descriptors calculated from 4590 ligands deposited in two drug databases, our model classified non-ligands, agonists, and antagonists of GPCRs, and achieved an area under the ROC curve (AUC) of 0.795, sensitivity of 0.716, specificity of 0.744, and accuracy of 0.733. In addition, we verified that 70% (44 out of 63) of FDA-approved GPCR-targeting drugs were correctly classified into their respective groups.

Conclusions

Studies of ligand–GPCR interaction recognition are important for the characterization of drug action mechanisms. Our GPCR–ligand interaction prediction model can be employed in the pharmaceutical sciences for the efficient virtual screening of putative GPCR-binding agonists and antagonists.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04877-7.

Pathogenomic in silico approach identifies NSP-A and Fe-IIISBP as possible drug targets in Neisseria Meningitidis MC58 and development of pharmacophores as novel therapeutic candidates

Meningitis creates a life-threatening clinical crisis. Moreover, the administered antibiotics result into multi-drug resistance, thereby necessitating development of alternative therapeutic strategies. This study aimed at identifying novel-drug targets in Neisseria meningitidis and therapeutic molecules which can be exploited for the treatment of meningitis. Novel targets were identified by applying a pathogenomic approach involving protein data-set mining, subtractive channel analysis and subsequent qualitative analysis comprising of in silico pharmacokinetics, molecular docking and pharmacophore generation. Pathogenomic studies revealed Neisserial Surface Protein A (NSP-A) and Iron-III-Substrate Binding Protein (Fe-IIISBP) as potential targets. Two pharmacophore models comprising of 2-(biaryl) carbapenems, efavirenz, praziquantel and pyrimethamine for NSP-A and 2-(biaryl) carbapenems, trimipramine and pyrimethamine for Fe-IIISBP, showed successful docking, followed drug-likeness criteria and generated pharmacophore model with a score of 8.08 and 8.818, respectively, which had further been docked to the target stably. Thus, our study identifies NSP-A and Fe-IIISBP as novel targets in Neisseria meningitidis for which 2-(biaryl) carbapenems, efavirenz, praziquantel, trimipramine and pyrimethamine may be employed for effective treatment of meningitis.

Hesperidin abrogates bisphenol A endocrine disruption through binding with fibroblast growth factor 21 (FGF-21), α-amylase and α-glucosidase: an in silico molecular study

Background

Fibroblast growth factor 21 (FGF-21), alpha-amylase, and alpha-glucosidase are key proteins implicated in metabolic dysregulations. Bisphenol A (BPA) is an environmental toxicant known to cause endocrine dysregulations. Hesperidin from citrus is an emerging flavonoid for metabolic diseases management. Through computational approach, we investigated the potentials of hesperidin in abrogating BPA interference in metabolism. The 3D crystal structure of the proteins (FGF-21, α-amylase, and α-glucosidase) and the ligands (BPA and hesperidin) were retrieved from the PDB and PubChem database respectively. Using Autodock plugin Pyrx, molecular docking of the ligands and individual proteins were performed to ascertain their binding affinities and their potentials to compete for the same binding site. Validation of the docking study was considered as the ability of the ligands to bind at the same site of each proteins. The docking poses were visualized using UCSF Chimera and Discovery Studio 2020, respectively to reveal each of the protein-ligands interactions within the binding pockets. Using SwissAdme and AdmeSar servers, we further investigated hesperidin’s ADMET profile. Hesperidin used was purchased commercially.

Results

Hesperidin and BPA competitively bound to the same site on each protein. Interestingly, hesperidin had greater binding affinities (Kcal/mol) − 5.80, − 9.60, and − 9.60 than BPA (Kcal/mol) − 4.40, − 7.20, − 7.10 for FGF-21, α-amylase, and α-glucosidase respectively. Visualizations of the binding poses showed that hesperidin interacted with stronger bonds than BPA within the proteins’ pockets. Although hesperidin violated Lipinski rule of five, this however can be optimized through structural modifications.

Conclusions

Hesperidin may be an emerging natural product with promising therapeutic potentials against metabolic and endocrine derangement.

Toward the Identification of Natural Antiviral Drug Candidates against Merkel Cell Polyomavirus: Computational Drug Design Approaches

Merkel cell carcinoma (MCC) is a rare form of aggressive skin cancer mainly caused by Merkel cell polyomavirus (MCPyV). Most MCC tumors express MCPyV large T (LT) antigens and play an important role in the growth-promoting activities of oncoproteins. Truncated LT promotes tumorigenicity as well as host cell proliferation by activating the viral replication machinery, and inhibition of this protein in humans drastically lowers cellular growth linked to the corresponding cancer. Our study was designed with the aim of identifying small molecular-like natural antiviral candidates that are able to inhibit the proliferation of malignant tumors, especially those that are aggressive, by blocking the activity of viral LT protein. To identify potential compounds against the target protein, a computational drug design including molecular docking, ADME (absorption, distribution, metabolism, and excretion), toxicity, molecular dynamics (MD) simulation, and molecular mechanics generalized Born surface area (MM-GBSA) approaches were applied in this study. Initially, a total of 2190 phytochemicals isolated from 104 medicinal plants were screened using the molecular docking simulation method, resulting in the identification of the top five compounds having the highest binding energy, ranging between −6.5 and −7.6 kcal/mol. The effectiveness and safety of the selected compounds were evaluated based on ADME and toxicity features. A 250 ns MD simulation confirmed the stability of the selected compounds bind to the active site (AS) of the target protein. Additionally, MM-GBSA analysis was used to determine the high values of binding free energy (ΔG bind) of the compounds binding to the target protein. The five compounds identified by computational approaches, Paulownin (CID: 3084131), Actaealactone (CID: 11537736), Epigallocatechin 3-O-cinnamate (CID: 21629801), Cirsilineol (CID: 162464), and Lycoricidine (CID: 73065), can be used in therapy as lead compounds to combat MCPyV-related cancer. However, further wet laboratory investigations are required to evaluate the activity of the drugs against the virus.

Oncological drug discovery: AI meets structure-based computational research

The integration of machine learning and structure-based methods has proven valuable in the past as a way to prioritize targets and compounds in early drug discovery. In oncological research, these methods can be highly beneficial in addressing the diversity of neoplastic diseases portrayed by the different hallmarks of cancer. Here, we review six use case scenarios for integrated computational methods, namely driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis. We address the heterogeneity of integration approaches and individual methods, while acknowledging their current limitations and highlighting their potential to bring drugs for personalized oncological therapies to the market faster.

Complex machine learning model needs complex testing: Examining predictability of molecular binding affinity by a graph neural network

Drug discovery pipelines typically involve high-throughput screening of large amounts of compounds in a search of potential drugs candidates. As a chemical space of small organic molecules is huge, a "navigation" over it urges for fast and lightweight computational methods, thus promoting machine-learning approaches for processing huge pools of candidates. In this contribution, we present a graph-based deep neural network for prediction of protein-drug binding affinity and assess its predictive power under thorough testing conditions. Within the suggested approach, both protein and drug molecules are represented as graphs and passed to separate graph sub-networks, then concatenated and regressed towards a binding affinity. The neural network is trained on two binding affinity datasets-PDBbind and data imported from RCSB Protein Data Bank. In order to explore the generalization capabilities of the model we go beyond traditional random or leave-cluster-out techniques and demonstrate the need for more elaborate model performance assessment - six different strategies for test/train data partitioning (random, time- and property-arranged, protein- and ligand-clustered) with a k-fold cross-validation are engaged. Finally, we discuss the model performance in terms of a set of metrics for different split strategies and fold arrangement. Our code is available at https://github.com/SoftServeInc/affinity-by-GNN.

A review on machine learning approaches and trends in drug discovery

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs. This review article focuses on how these new methodologies are being used in recent years of research. Analyzing the state of the art in this field will give us an idea of where cheminformatics will be developed in the short term, the limitations it presents and the positive results it has achieved. This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.

Ensembling machine learning models to boost molecular affinity prediction

This study unites six popular machine learning approaches to enhance the prediction of a molecular binding affinity between receptors (large protein molecules) and ligands (small organic molecules). Here we examine a scheme where affinity of ligands is predicted against a single receptor - human thrombin, thus, the models consider ligand features only. However, the suggested approach can be repurposed for other receptors. The methods include Support Vector Machine, Random Forest, CatBoost, feed-forward neural network, graph neural network, and Bidirectional Encoder Representations from Transformers. The first five methods use input features based on physico-chemical properties of molecules, while the last one is based on textual molecular representations. All approaches do not rely on atomic spatial coordinates, avoiding a potential bias from known structures, and are capable of generalizing for compounds with unknown conformations. Within each of the methods, we have trained two models that solve classification and regression tasks. Then, all models are grouped into a pipeline of two subsequent ensembles. The first ensemble aggregates six classification models which vote whether a ligand binds to a receptor or not. If a ligand is classified as active (i.e., binds), the second ensemble predicts its binding affinity in terms of the inhibition constant K_i.

Deep Learning-Based Ligand Design Using Shared Latent Implicit Fingerprints from Collaborative Filtering

In their previous work, Srinivas et al. [ J. Cheminf. 2018, 10, 56] have shown that implicit fingerprints capture ligands and proteins in a shared latent space, typically for the purposes of virtual screening with collaborative filtering models applied on known bioactivity data. In this work, we extend these implicit fingerprints/descriptors using deep learning techniques to translate latent descriptors into discrete representations of molecules (SMILES), without explicitly optimizing for chemical properties. This allows the design of new compounds based upon the latent representation of nearby proteins, thereby encoding druglike properties including binding affinities to known proteins. The implicit descriptor method does not require any fingerprint similarity search, which makes the method free of any bias arising from the empirical nature of the fingerprint models [Srinivas, R.; J. Cheminf. 2018, 10, 56]. We evaluate the properties of the potentially novel drugs generated by our approach using physical properties of druglike molecules and chemical complexity. Additionally, we analyze the reliability of the biological activity of the new compounds generated using this method by employing models of protein-ligand interaction, which assists in assessing the potential binding affinity of the designed compounds. We find that the generated compounds exhibit properties of chemically feasible compounds and are predicted to be excellent binders to known proteins. Furthermore, we also analyze the diversity of compounds created using the Tanimoto distance and conclude that there is a wide diversity in the generated compounds.

A review on compound-protein interaction prediction methods: Data, format, representation and model

There has recently been a rapid progress in computational methods for determining protein targets of small molecule drugs, which will be termed as compound protein interaction (CPI). In this review, we comprehensively review topics related to computational prediction of CPI. Data for CPI has been accumulated and curated significantly both in quantity and quality. Computational methods have become powerful ever to analyze such complex the data. Thus, recent successes in the improved quality of CPI prediction are due to use of both sophisticated computational techniques and higher quality information in the databases. The goal of this article is to provide reviews of topics related to CPI, such as data, format, representation, to computational models, so that researchers can take full advantages of these resources to develop novel prediction methods. Chemical compounds and protein data from various resources were discussed in terms of data formats and encoding schemes. For the CPI methods, we grouped prediction methods into five categories from traditional machine learning techniques to state-of-the-art deep learning techniques. In closing, we discussed emerging machine learning topics to help both experimental and computational scientists leverage the current knowledge and strategies to develop more powerful and accurate CPI prediction methods.

BOW-GBDT: A GBDT Classifier Combining With Artificial Neural Network for Identifying GPCR-Drug Interaction Based on Wordbook Learning From Sequences

Background: As a class of membrane protein receptors, G protein-coupled receptors (GPCRs) are very important for cells to complete normal life function and have been proven to be a major drug target for widespread clinical application. Hence, it is of great significance to find GPCR targets that interact with drugs in the process of drug development. However, identifying the interaction of the GPCR–drug pairs by experimental methods is very expensive and time-consuming on a large scale. As more and more database about GPCR–drug pairs are opened, it is viable to develop machine learning models to accurately predict whether there is an interaction existing in a GPCR–drug pair.

Methods: In this paper, the proposed model aims to improve the accuracy of predicting the interactions of GPCR–drug pairs. For GPCRs, the work extracts protein sequence features based on a novel bag-of-words (BOW) model improved with weighted Silhouette Coefficient and has been confirmed that it can extract more pattern information and limit the dimension of feature. For drug molecules, discrete wavelet transform (DWT) is used to extract features from the original molecular fingerprints. Subsequently, the above-mentioned two types of features are contacted, and SMOTE algorithm is selected to balance the training dataset. Then, artificial neural network is used to extract features further. Finally, a gradient boosting decision tree (GBDT) model is trained with the selected features. In this paper, the proposed model is named as BOW-GBDT.

Results: D92M and Check390 are selected for testing BOW-GBDT. D92M is used for a cross-validation dataset which contains 635 interactive GPCR–drug pairs and 1,225 non-interactive pairs. Check390 is used for an independent test dataset which consists of 130 interactive GPCR–drug pairs and 260 non-interactive GPCR–drug pairs, and each element in Check390 cannot be found in D92M. According to the results, the proposed model has a better performance in generation ability compared with the existing machine learning models.

Conclusion: The proposed predictor improves the accuracy of the interactions of GPCR–drug pairs. In order to facilitate more researchers to use the BOW-GBDT, the predictor has been settled into a brand-new server, which is available at http://www.jci-bioinfo.cn/bowgbdt.

SSnet: A Deep Learning Approach for Protein-Ligand Interaction Prediction

Computational prediction of Protein-Ligand Interaction (PLI) is an important step in the modern drug discovery pipeline as it mitigates the cost, time, and resources required to screen novel therapeutics. Deep Neural Networks (DNN) have recently shown excellent performance in PLI prediction. However, the performance is highly dependent on protein and ligand features utilized for the DNN model. Moreover, in current models, the deciphering of how protein features determine the underlying principles that govern PLI is not trivial. In this work, we developed a DNN framework named SSnet that utilizes secondary structure information of proteins extracted as the curvature and torsion of the protein backbone to predict PLI. We demonstrate the performance of SSnet by comparing against a variety of currently popular machine and non-Machine Learning (ML) models using various metrics. We visualize the intermediate layers of SSnet to show a potential latent space for proteins, in particular to extract structural elements in a protein that the model finds influential for ligand binding, which is one of the key features of SSnet. We observed in our study that SSnet learns information about locations in a protein where a ligand can bind, including binding sites, allosteric sites and cryptic sites, regardless of the conformation used. We further observed that SSnet is not biased to any specific molecular interaction and extracts the protein fold information critical for PLI prediction. Our work forms an important gateway to the general exploration of secondary structure-based Deep Learning (DL), which is not just confined to protein-ligand interactions, and as such will have a large impact on protein research, while being readily accessible for de novo drug designers as a standalone package.

Bringing Structural Implications and Deep Learning-Based Drug Identification for KRAS Mutants

Colorectal cancer is considered one of the leading causes of death that is linked with the Kirsten Rat Sarcoma (KRAS) harboring codons 13 and 61 mutations. The objective for this study is to search for clinically important codon 61 mutations and analyze how they affect the protein structural dynamics. Additionally, a deep-learning approach is used to carry out a similarity search for potential compounds that might have a comparatively better affinity. Public databases like The Cancer Genome Atlas and Genomic Data Commons were accessed for obtaining the data regarding mutations that are associated with colon cancer. Multiple analysis such as genomic alteration landscape, survival analysis, and systems biology-based kinetic simulations were carried out to predict dynamic changes for the selected mutations. Additionally, a molecular dynamics simulation of 100 ns for all the seven shortlisted codon 61 mutations have been conducted, which revealed noticeable deviations. Finally, the deep learning-based predicted compounds were docked with the KRAS 3D conformer, showing better affinity and good docking scores as compared to the already existing drugs. Taking together the outcomes of systems biology and molecular dynamics, it is observed that the reported mutations in the SII region are highly detrimental as they have an immense impact on the protein sensitive sites' native conformation and overall stability. The drugs reported in this study show increased performance and are encouraged to be used for further evaluation regarding the situation that ascends as a result of KRAS mutations.

Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning

The accurate predicting of physical properties and bioactivity of drug molecules in deep learning depends on how molecules are represented. Many types of molecular descriptors have been developed for quantitative structure-activity/property relationships quantitative structure-activity relationships (QSPR). However, each molecular descriptor is optimized for a specific application with encoding preference. Considering that standalone featurization methods may only cover parts of information of the chemical molecules, we proposed to build the conjoint fingerprint by combining two supplementary fingerprints. The impact of conjoint fingerprint and each standalone fingerprint on predicting performance was systematically evaluated in predicting the logarithm of the partition coefficient (logP) and binding affinity of protein-ligand by using machine learning/deep learning (ML/DL) methods, including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), long short-term memory network (LSTM), and deep neural network (DNN). The results demonstrated that the conjoint fingerprint yielded improved predictive performance, even outperforming the consensus model using two standalone fingerprints among four out of five examined methods. Given that the conjoint fingerprint scheme shows easy extensibility and high applicability, we expect that the proposed conjoint scheme would create new opportunities for continuously improving predictive performance of deep learning by harnessing the complementarity of various types of fingerprints.

Development of simultaneous interaction prediction approach (SiPA) for the expansion of interaction network of traditional Chinese medicine

Background

Due to the lack of enough interaction data among compositions, targets and diseases, it is difficult to construct a complete network of Traditional Chinese Medicine (TCM) that comprehensively reflects active compositions and their synergistic network in terms of specific diseases. Therefore, mapping of the full spectrum of interaction between compounds and their targets is of central importance when we use network pharmacology approach to explore the therapeutic potential of the TCM.

Methods

To address this challenge, we developed a large-scale simultaneous interaction prediction approach (SiPA) integrated one interaction network based simple inference model (SIM), focusing on ‘logical relevance’ between compounds, proteins or diseases, and another compound-target correlation space based interaction prediction model (CTCS-IPM) that was built on the basis of the canonical correlation analysis (CCA) to estimate the position of compounds (or targets) in compound-protein correlated space. Then SiPA was applied to discover reliable multiple interactions for interaction network expansion of a TCM, compound Salvia miltiorrhiza. By means of network analysis, potential active compounds and their related network synergy underlying cardiovascular diseases were evaluated between expanded and original interaction networks. Part of new interactions were validated with existing experimental evidence and molecular docking.

Results

As evaluated with known test dataset, the established combination approach was proved to make highly accurate prediction, showing a well prediction performance for the SIM and a high recall rate of 85.2% for the CTCS-IPM. Then 710 pairs of new compound-target interactions, 24 pairs of new compound-cardiovascular disease interactions and 294 pairs of new cardiovascular disease-protein interactions were predicted for compound Salvia miltiorrhiza. Results of network analysis suggested the network expansion could dramatically improve the completeness and effectiveness of the network. Validation results of literature and molecular docking manifested that inferred interactions had good reliability.

Conclusions

We provided a practical and efficient way for large-scale inference of multiple interactions of TCM ingredients, which was not limited by the lack of negative samples, sample size and target 3D structures. SiPA could help researchers more accurately prioritize the effective compounds and more completely explore network synergy of TCM for treating specific diseases, indicating a potential way for effectively identifying candidate compound (or target) in drug discovery.

Identifying GPCR-drug interaction based on wordbook learning from sequences

BACKGROUND

G protein-coupled receptors (GPCRs) mediate a variety of important physiological functions, are closely related to many diseases, and constitute the most important target family of modern drugs. Therefore, the research of GPCR analysis and GPCR ligand screening is the hotspot of new drug development. Accurately identifying the GPCR-drug interaction is one of the key steps for designing GPCR-targeted drugs. However, it is prohibitively expensive to experimentally ascertain the interaction of GPCR-drug pairs on a large scale. Therefore, it is of great significance to predict the interaction of GPCR-drug pairs directly from the molecular sequences. With the accumulation of known GPCR-drug interaction data, it is feasible to develop sequence-based machine learning models for query GPCR-drug pairs.

RESULTS

In this paper, a new sequence-based method is proposed to identify GPCR-drug interactions. For GPCRs, we use a novel bag-of-words (BoW) model to extract sequence features, which can extract more pattern information from low-order to high-order and limit the feature space dimension. For drug molecules, we use discrete Fourier transform (DFT) to extract higher-order pattern information from the original molecular fingerprints. The feature vectors of two kinds of molecules are concatenated and input into a simple prediction engine distance-weighted K-nearest-neighbor (DWKNN). This basic method is easy to be enhanced through ensemble learning. Through testing on recently constructed GPCR-drug interaction datasets, it is found that the proposed methods are better than the existing sequence-based machine learning methods in generalization ability, even an unconventional method in which the prediction performance was further improved by post-processing procedure (PPP).

CONCLUSIONS

The proposed methods are effective for GPCR-drug interaction prediction, and may also be potential methods for other target-drug interaction prediction, or protein-protein interaction prediction. In addition, the new proposed feature extraction method for GPCR sequences is the modified version of the traditional BoW model and may be useful to solve problems of protein classification or attribute prediction. The source code of the proposed methods is freely available for academic research at https://github.com/wp3751/GPCR-Drug-Interaction.

Intrinsically disordered protein domains in flavivirus infection

Intrinsically disordered protein regions are at the core of biological processes and involved in key protein-ligand interactions. The Flavivirus proteins, of viruses of great biomedical importance such as Zika and dengue viruses, exemplify this. Several proteins of these viruses have disordered regions that are of the utmost importance for biological activity. Disordered proteins can adopt several conformations, each able to interact with and/or bind to different ligands. In fact, such interactions can help stabilize a particular fold. Moreover, by being promiscuous in the number of target molecules they can bind to, these protein regions increase the number of functions that their small proteome (10 proteins) can achieve. A folding energy waterfall better describes the protein folding landscape of these proteins. A disordered protein can be thought as rolling down the folding energy cascade, in order "to fall, fold and function". This is the case of many viral protein regions, as seen in the flaviviruses proteome. Given their small size, flaviviruses are a good model system for understanding the role of intrinsically disordered protein regions in viral function. Finally, studying these viruses disordered protein regions will certainly contribute to the development of therapeutic approaches against such promising (yet challenging) targets.

Designing nanoparticle release systems for drug-vitamin cancer co-therapy with multiplicative perturbation-theory machine learning (PTML) models

Nano-systems for cancer co-therapy including vitamins or vitamin derivatives have showed adequate results to continue with further research studies to better understand them. However, the number of different combinations of drugs, vitamins, nanoparticle types, coating agents, synthesis conditions, and system types (nanocapsules, micelles, etc.) to be tested is very large generating a high cost in experimentations. In this context, there are reports of large datasets of preclinical assays of compounds (like in the ChEMBL database) and increasing but yet limited reports of experimental measurements of nano-systems per se. On the other hand, Machine Learning is gaining momentum in Nanotechnology and Pharmaceutical Sciences as a tool for rational design of new drugs and drug-release nano-systems. In this work, we propose to combine Perturbation Theory principles and Machine Learning to develop a PTML model for rational selection of the components of cancer co-therapy drug-vitamin release nano-systems (DVRNs). In doing so, we apply information fusion techniques with 2 data sets: (1) a large ChEMBL dataset of >36 000 preclinical assays of vitamin derivatives and a new dataset of >1000 outcomes of DVRNs, collected herein from the literature for the first time. The ChEMBL dataset used covers a considerable number of assay conditions (cjvit) each one with multiple levels. These conditions included >504 biological activity parameters (c0vit), >340 types of proteins (c1vit), >650 types of cells (c2vit), >120 assay organisms (c3vit), >60 assay strains (c4vit). Regarding the DVRNs, there are 25 different types of nano-systems (njn), with up to 16 conditions (cjn) including also different levels such as 8 biological activity parameters (c0n), 9 raw nanomaterials (c4n), 15 assay cells (c11n), etc. In the first stage, we used Moving Average operators to quantify the perturbations (deviations) in all input variables with respect to the conditions. After that, we used multiplicative PT operators to carry out data fusion, and dimension reduction, and Linear Discriminant Analysis (LDA) to seek the PTML model. The best PTML model found showed values of specificity, sensitivity, and accuracy in the range of 83-88% in training and external validation series for >130 000 cases (DVRNs vs. ChEMBL data pairs) formed after data fusion. To the best of our knowledge, this is the first general purpose model for the rational design of DVRNs for cancer co-therapy.

Machine learning for target discovery in drug development

The discovery of macromolecular targets for bioactive agents is currently a bottleneck for the informed design of chemical probes and drug leads. Typically, activity profiling against genetically manipulated cell lines or chemical proteomics is pursued to shed light on their biology and deconvolute drug-target networks. By taking advantage of the ever-growing wealth of publicly available bioactivity data, learning algorithms now provide an attractive means to generate statistically motivated research hypotheses and thereby prioritize biochemical screens. Here, we highlight recent successes in machine intelligence for target identification and discuss challenges and opportunities for drug discovery.