From in silico target prediction to multi-target drug design: current databases, methods and applications

Efficient prediction of anticancer peptides through deep learning

Background

Cancer remains one of the leading causes of mortality globally, with conventional chemotherapy often resulting in severe side effects and limited effectiveness. Recent advancements in bioinformatics and machine learning, particularly deep learning, offer promising new avenues for cancer treatment through the prediction and identification of anticancer peptides.

Objective

This study aimed to develop and evaluate a deep learning model utilizing a two-dimensional convolutional neural network (2D CNN) to enhance the prediction accuracy of anticancer peptides, addressing the complexities and limitations of current prediction methods.

Methods

A diverse dataset of peptide sequences with annotated anticancer activity labels was compiled from various public databases and experimental studies. The sequences were preprocessed and encoded using one-hot encoding and additional physicochemical properties. The 2D CNN model was trained and optimized using this dataset, with performance evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC).

Results

The proposed 2D CNN model achieved superior performance compared to existing methods, with an accuracy of 0.87, precision of 0.85, recall of 0.89, F1-score of 0.87, and an AUC-ROC value of 0.91. These results indicate the model's effectiveness in accurately predicting anticancer peptides and capturing intricate spatial patterns within peptide sequences.

Conclusion

The findings demonstrate the potential of deep learning, specifically 2D CNNs, in advancing the prediction of anticancer peptides. The proposed model significantly improves prediction accuracy, offering a valuable tool for identifying effective peptide candidates for cancer treatment.

Future Work

Further research should focus on expanding the dataset, exploring alternative deep learning architectures, and validating the model's predictions through experimental studies. Efforts should also aim at optimizing computational efficiency and translating these predictions into clinical applications.

Drug repurposing for neurodegenerative diseases

Neurodegenerative diseases (NDDs) are neuronal problems that include the brain and spinal cord and result in loss of sensory and motor dysfunction. Common NDDs include Alzheimer's disease (AD), Parkinson's disease (PD), Huntington's disease (HD), Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS) etc. The occurrence of these diseases increases with age and is one of the challenging problems among elderly people. Though, several scientific research has demonstrated the key pathologies associated with NDDs still the underlying mechanisms and molecular details are not well understood and need to be explored and this poses a lack of effective treatments for NDDs. Several lines of evidence have shown that NDDs have a high prevalence and affect more than a billion individuals globally but still, researchers need to work forward in identifying the best therapeutic target for NDDs. Thus, several researchers are working in the directions to find potential therapeutic targets to alter the disease pathology and treat the diseases. Several steps have been taken to identify the early detection of the disease and drug repurposing for effective treatment of NDDs. Moreover, it is logical that current medications are being evaluated for their efficacy in treating such disorders; therefore, drug repurposing would be an efficient, safe, and cost-effective way in finding out better medication. In the current manuscript we discussed the utilization of drugs that have been repurposed for the treatment of AD, PD, HD, MS, and ALS.

Machine learning in Alzheimer's disease drug discovery and target identification

Alzheimer's disease (AD) stands as a formidable neurodegenerative ailment that poses a substantial threat to the elderly population, with no known curative or disease-slowing drugs in existence. Among the vital and time-consuming stages in the drug discovery process, disease modeling and target identification hold particular significance. Disease modeling allows for a deeper comprehension of disease progression mechanisms and potential therapeutic avenues. On the other hand, target identification serves as the foundational step in drug development, exerting a profound influence on all subsequent phases and ultimately determining the success rate of drug development endeavors. Machine learning (ML) techniques have ushered in transformative breakthroughs in the realm of target discovery. Leveraging the strengths of large dataset analysis, multifaceted data processing, and the exploration of intricate biological mechanisms, ML has become instrumental in the quest for effective AD treatments. In this comprehensive review, we offer an account of how ML methodologies are being deployed in the pursuit of drug discovery for AD. Furthermore, we provide an overview of the utilization of ML in uncovering potential intervention strategies and prospective therapeutic targets for AD. Finally, we discuss the principal challenges and limitations currently faced by these approaches. We also explore the avenues for future research that hold promise in addressing these challenges.

In-vitro Evaluation of Triazine Scaffold for Anticancer Drug Development: A Review

INTRODUCTION

The widespread importance of the synthesis and modification of anticancer agents has given rise to many numbers of medicinal chemistry programs. In this regard, triazine derivatives have attracted attention due to their remarkable activity against a wide range of cancer cells. This evaluation covers work reports to define the anticancer activity, the most active synthesized compound for the target, the SAR and, when described, the probable MOA besides similarly considered to deliver complete and target-pointed data for the development of types of anti-tumour medicines of triazine derivatives. Triazine scaffold for the development of anticancer analogues. Triazine can also relate to numerous beneficial targets, and their analogues have auspicious in-vitro and in-vivo anti-tumour activity. Fused molecules can improve efficacy, and drug resistance and diminish side effects, and numerous hybrid molecules are beneath diverse stages of clinical trials, so hybrid derivatives of triazine may offer valuable therapeutic involvement for the dealing of tumours.

OBJECTIVE

The objective of the recent review was to summarize the recent reports on triazine as well as its analogues with respect to its anticancer therapeutic potential.

CONCLUSION

The content of the review would be helpful to update the researchers working towards the synthesis and designing of new molecules for the treatment of various types of cancer disease with the recent molecules that have been produced from the triazine scaffold. Triazine scaffolds based on 1,3,5-triazine considerably boost molecular diversity levels and enable covering chemical space in key medicinal chemistry fields.

A universal programmable Gaussian boson sampler for drug discovery

Gaussian boson sampling (GBS) has the potential to solve complex graph problems, such as clique finding, which is relevant to drug discovery tasks. However, realizing the full benefits of quantum enhancements requires large-scale quantum hardware with universal programmability. Here we have developed a time-bin-encoded GBS photonic quantum processor that is universal, programmable and software-scalable. Our processor features freely adjustable squeezing parameters and can implement arbitrary unitary operations with a programmable interferometer. Leveraging our processor, we successfully executed clique finding on a 32-node graph, achieving approximately twice the success probability compared to classical sampling. As proof of concept, we implemented a versatile quantum drug discovery platform using this GBS processor, enabling molecular docking and RNA-folding prediction tasks. Our work achieves GBS circuitry with its universal and programmable architecture, advancing GBS toward use in real-world applications.

Comprehensive survey of target prediction web servers for Traditional Chinese Medicine

Traditional Chinese medicine (TCM) is characterized by multi-components, multiple targets, and complex mechanisms of action and therefore has significant advantages in treating diseases. However, the clinical application of TCM prescriptions is limited due to the difficulty in elucidating the effective substances and the lack of current scientific evidence on the mechanisms of action. In recent years, the development of network pharmacology based on drug systems research has provided a new approach for understanding the complex systems represented by TCM. The determination of drug targets is the core of TCM network pharmacology research. Over the past years, many web tools for drug targets with various features have been developed to facilitate target prediction, significantly promoting drug discovery. Therefore, this review introduces the widely used web tools for compound-target interaction prediction databases and web resources in TCM pharmacology research, and it compares and analyzes each web tool based on their basic properties, including the underlying theory, algorithms, datasets, and search results. Finally, we present the remaining challenges for the promising future of compound-target interaction prediction in TCM pharmacology research. This work may guide researchers in choosing web tools for target prediction and may also help develop more TCM tools based on these existing resources.

Comprehensive assessment of nine target prediction web services: which should we choose for target fishing?

Identification of potential targets for known bioactive compounds and novel synthetic analogs is of considerable significance. In silico target fishing (TF) has become an alternative strategy because of the expensive and laborious wet-lab experiments, explosive growth of bioactivity data and rapid development of high-throughput technologies. However, these TF methods are based on different algorithms, molecular representations and training datasets, which may lead to different results when predicting the same query molecules. This can be confusing for practitioners in practical applications. Therefore, this study systematically evaluated nine popular ligand-based TF methods based on target and ligand-target pair statistical strategies, which will help practitioners make choices among multiple TF methods. The evaluation results showed that SwissTargetPrediction was the best method to produce the most reliable predictions while enriching more targets. High-recall similarity ensemble approach (SEA) was able to find real targets for more compounds compared with other TF methods. Therefore, SwissTargetPrediction and SEA can be considered as primary selection methods in future studies. In addition, the results showed that k = 5 was the optimal number of experimental candidate targets. Finally, a novel ensemble TF method based on consensus voting is proposed to improve the prediction performance. The precision of the ensemble TF method outperforms the individual TF method, indicating that the ensemble TF method can more effectively identify real targets within a given top-k threshold. The results of this study can be used as a reference to guide practitioners in selecting the most effective methods in computational drug discovery.

Mechanism of action deconvolution of the small-molecule pathological tau aggregation inhibitor Anle138b

BACKGROUND

A key histopathological hallmark of Alzheimer's disease (AD) is the presence of neurofibrillary tangles of aggregated microtubule-associated protein tau in neurons. Anle138b is a small molecule which has previously shown efficacy in mice in reducing tau aggregates and rescuing AD disease phenotypes.

METHODS

In this work, we employed bioinformatics analysis-including pathway enrichment and causal reasoning-of an in vitro tauopathy model. The model consisted of cultured rat cortical neurons either unseeded or seeded with tau aggregates derived from human AD patients, both of which were treated with Anle138b to generate hypotheses for its mode of action. In parallel, we used a collection of human target prediction models to predict direct targets of Anle138b based on its chemical structure.

RESULTS

Combining the different approaches, we found evidence supporting the hypothesis that the action of Anle138b involves several processes which are key to AD progression, including cholesterol homeostasis and neuroinflammation. On the pathway level, we found significantly enriched pathways related to these two processes including those entitled "Superpathway of cholesterol biosynthesis" and "Granulocyte adhesion and diapedesis". With causal reasoning, we inferred differential activity of SREBF1/2 (involved in cholesterol regulation) and mediators of the inflammatory response such as NFKB1 and RELA. Notably, our findings were also observed in Anle138b-treated unseeded neurons, meaning that the inferred processes are independent of tau pathology and thus represent the direct action of the compound in the cellular system. Through structure-based ligand-target prediction, we predicted the intracellular cholesterol carrier NPC1 as well as NF-κB subunits as potential targets of Anle138b, with structurally similar compounds in the model training set known to target the same proteins.

CONCLUSIONS

This study has generated feasible hypotheses for the potential mechanism of action of Anle138b, which will enable the development of future molecular interventions aiming to reduce tau pathology in AD patients.

DRDB: A Machine Learning Platform to Predict Chemical-Protein Interactions towards Diabetic Retinopathy

Diabetic retinopathy (DR), a diabetic microangiopathy caused by diabetes, affects approximately 93 million people, worldwide. However, the drugs used to treat DR have limited efficacy and the variety of side effects. This is possibly because the complicated pathogenesis of DR is associated with multiple proteins. In this work, we attempted to identify potential drugs against DR-associated proteins and predict potential targets for drugs using in silico prediction of chemical-protein interactions (CPI) based on multitarget quantitative structure-activity relationship (mt-QSAR) method. Therefore, we developed 128 binary classifiers to predict the CPI for 15 DR targets using random forest (RF), k-nearest neighbours (KNN), support vector machine (SVM), and neural network (NN) algorithms with MACCS, extended connectivity fingerprints (ECFP6) fingerprints, and protein descriptors. In order to facilitate discovery of the novel drugs and target identification using the 128 binary classifiers, a free web server (DRDB) was developed. Compound Danshen Dripping Pills (CDDP), composed of Salvia miltiorrhiza, Panax notoginseng, and borneol, is commonly used in the treatment of cardiovascular diseases. To explore the applicability of DRDB, the potential CPIs of CDDP in treatment of DR were investigated based on DRDB. In vitro experimental validation demonstrated that cryptotanshinone and protocatechuic acid, two key components of CDDP, are capable of targeting ICAM-1 which is one of the key target of DR. We hope that this work can facilitate development of more effective clinical strategies for the treatment of DR.

Biomedical Data and Deep Learning Computational Models for Predicting Compound-Protein Relations

The identification of compound-protein relations (CPRs), which includes compound-protein interactions (CPIs) and compound-protein affinities (CPAs), is critical to drug development. A common method for compound-protein relation identification is the use of in vitro screening experiments. However, the number of compounds and proteins is massive, and in vitro screening experiments are labor-intensive, expensive, and time-consuming with high failure rates. Researchers have developed a computational field called virtual screening (VS) to aid experimental drug development. These methods utilize experimentally validated biological interaction information to generate datasets and use the physicochemical and structural properties of compounds and target proteins as input information to train computational prediction models. At present, deep learning has been widely used in computer vision and natural language processing and has experienced epoch-making progress. At the same time, deep learning has also been used in the field of biomedicine widely, and the prediction of CPRs based on deep learning has developed rapidly and has achieved good results. The purpose of this study is to investigate and discuss the latest applications of deep learning techniques in CPR prediction. First, we describe the datasets and feature engineering (i.e., compound and protein representations and descriptors) commonly used in CPR prediction methods. Then, we review and classify recent deep learning approaches in CPR prediction. Next, a comprehensive comparison is performed to demonstrate the prediction performance of representative methods on classical datasets. Finally, we discuss the current state of the field, including the existing challenges and our proposed future directions. We believe that this investigation will provide sufficient references and insight for researchers to understand and develop new deep learning methods to enhance CPR predictions.

Entrectinib, a new multi-target inhibitor for cancer therapy

Clinical practice shows that when single-target drugs treat multi-factor diseases such as tumors, cardiovascular system and endocrine system diseases, it is often difficult to achieve good therapeutic effects, and even serious adverse reactions may occur. Multi-target drugs can simultaneously regulate multiple links of disease, improve efficacy, reduce adverse reactions, and improve drug resistance. They are ideal drugs for treating complex diseases, and therefore have become the main direction of drug development. At present, some multi-target drugs have been successfully used in many major diseases. Entrectinib is an oral small molecule inhibitor that targets TRK, ROS1, and ALK. It is used to treat locally advanced or metastatic solid tumors with NTRK1/2/3, ROS1 and ALK gene fusion mutations. It can pass through the blood-brain barrier and is the only TRK inhibitor clinically proven to be effective against primary and metastatic brain diseases. In 2019, entrectinib was approved by the FDA to treat adult patients with ROS1-positive metastatic non-small cell lung cancer. Case reports showed that continuous administration of entrectinib was effective and tolerable. In this review, we give a brief introduction to TKK, ROS1 and ALK, and on this basis, we give a detailed and comprehensive introduction to the mechanism of action, pharmacokinetics, pharmacodynamics, clinical efficacy, tolerability and drug interactions of entrectinib.

BACPI: a bi-directional attention neural network for compound-protein interaction and binding affinity prediction

MOTIVATION

The identification of compound-protein interactions (CPIs) is an essential step in the process of drug discovery. The experimental determination of CPIs is known for a large amount of funds and time it consumes. Computational model has therefore become a promising and efficient alternative for predicting novel interactions between compounds and proteins on a large scale. Most supervised machine learning prediction models are approached as a binary classification problem, which aim to predict whether there is an interaction between the compound and the protein or not. However, CPI is not a simple binary on-off relationship, but a continuous value reflects how tightly the compound binds to a particular target protein, also called binding affinity.

RESULTS

In this study, we propose an end-to-end neural network model, called BACPI, to predict CPI and binding affinity. We employ graph attention network and convolutional neural network (CNN) to learn the representations of compounds and proteins and develop a bi-directional attention neural network model to integrate the representations. To evaluate the performance of BACPI, we use three CPI datasets and four binding affinity datasets in our experiments. The results show that, when predicting CPIs, BACPI significantly outperforms other available machine learning methods on both balanced and unbalanced datasets. This suggests that the end-to-end neural network model that predicts CPIs directly from low-level representations is more robust than traditional machine learning-based methods. And when predicting binding affinities, BACPI achieves higher performance on large datasets compared to other state-of-the-art deep learning methods. This comparison result suggests that the proposed method with bi-directional attention neural network can capture the important regions of compounds and proteins for binding affinity prediction.

AVAILABILITY AND IMPLEMENTATION

Data and source codes are available at https://github.com/CSUBioGroup/BACPI.

CK1 Is a Druggable Regulator of Microtubule Dynamics and Microtubule-Associated Processes

Protein kinases of the Casein Kinase 1 family play a vital role in the regulation of numerous cellular processes. Apart from functions associated with regulation of proliferation, differentiation, or apoptosis, localization of several Casein Kinase 1 isoforms to the centrosome and microtubule asters also implicates regulatory functions in microtubule dynamic processes. Being localized to the spindle apparatus during mitosis Casein Kinase 1 directly modulates microtubule dynamics by phosphorylation of tubulin isoforms. Additionally, site-specific phosphorylation of microtubule-associated proteins can be related to the maintenance of genomic stability but also microtubule stabilization/destabilization, e.g., by hyper-phosphorylation of microtubule-associated protein 1A and RITA1. Consequently, approaches interfering with Casein Kinase 1-mediated microtubule-specific functions might be exploited as therapeutic strategies for the treatment of cancer. Currently pursued strategies include the development of Casein Kinase 1 isoform-specific small molecule inhibitors and therapeutically useful peptides specifically inhibiting kinase-substrate interactions.

Validation strategies for target prediction methods

Computational methods for target prediction, based on molecular similarity and network-based approaches, machine learning, docking and others, have evolved as valuable and powerful tools to aid the challenging task of mode of action identification for bioactive small molecules such as drugs and drug-like compounds. Critical to discerning the scope and limitations of a target prediction method is understanding how its performance was evaluated and reported. Ideally, large-scale prospective experiments are conducted to validate the performance of a model; however, this expensive and time-consuming endeavor is often not feasible. Therefore, to estimate the predictive power of a method, statistical validation based on retrospective knowledge is commonly used. There are multiple statistical validation techniques that vary in rigor. In this review we discuss the validation strategies employed, highlighting the usefulness and constraints of the validation schemes and metrics that are employed to measure and describe performance. We address the limitations of measuring only generalized performance, given that the underlying bioactivity and structural data are biased towards certain small-molecule scaffolds and target families, and suggest additional aspects of performance to consider in order to produce more detailed and realistic estimates of predictive power. Finally, we describe the validation strategies that were employed by some of the most thoroughly validated and accessible target prediction methods.

Recent Progress on Tubulin Inhibitors with Dual Targeting Capabilities for Cancer Therapy

Microtubules play a crucial role in multiple cellular functions including mitosis, cell signaling, and organelle trafficking, which makes the microtubule an important target for cancer therapy. Despite the great successes of microtubule-targeting agents in the clinic, the development of drug resistance and dose-limiting toxicity restrict their clinical efficacy. In recent years, multitarget therapy has been considered an effective strategy to achieve higher therapeutic efficacy, in particular dual-target drugs. In terms of the synergetic effect of tubulin and other antitumor agents such as receptor tyrosine kinases inhibitors, histone deacetylases inhibitors, DNA-damaging agents, and topoisomerase inhibitors in combination therapy, designing dual-target tubulin inhibitors is regarded as a promising approach to overcome these limitations and improve therapeutic efficacy. In this Perspective, we discussed rational target combinations, design strategies, structure-activity relationships, and future directions of dual-target tubulin inhibitors.

Discovery of New Potent anti-MERS CoV Fusion Inhibitors

Middle East respiratory syndrome coronavirus (MERS-CoV), capable of zoonotic transmission, has been associated with emerging viral pneumonia in humans. In this study, a set of highly potent peptides were designed to prevent MERS-CoV fusion through competition with heptad repeat domain 2 (HR2) at its HR1 binding site. We designed eleven peptides with stronger estimated HR1 binding affinities than the wild-type peptide to prevent viral fusion with the cell membrane. Eight peptides showed strong inhibition of spike-mediated MERS-CoV cell-cell fusion with IC50 values in the nanomolar range (0.25–2.3 µM). Peptides #4–6 inhibited 95–98.3% of MERS-CoV plaque formation. Notably, peptide four showed strong inhibition of MERS-CoV plaques formation with EC50 = 0.302 µM. All peptides demonstrated safe profiles without cytotoxicity up to a concentration of 10 μM, and this cellular safety, combined with their anti-MERS-CoV antiviral activity, indicate all peptides can be regarded as potential promising antiviral agents.

Discovery of 7-O-1, 2, 3-triazole hesperetin derivatives as multi-target-directed ligands against Alzheimer's disease

The development of multi-target-directed ligands (MTDLs) may improve complex central nervous system diseases such as Alzheimer's disease (AD). Here, a series of 7-O-1, 2, 3-triazole hesperetin derivatives was evaluated for their inhibition of cholinesterase, anti-neuroinflammatory, and neuroprotective activity. Among the hesperetin derivatives, compound a8 (7-O-((1-(3-chlorobenzyl)-1H-1,2,3-triazol-4-yl)methyl)hesperetin) possessed excellent anti-butyrylcholinesterase activity (IC50 = 3.08 ± 0.29 μM) and exhibited good anti-neuroinflammatory activity (IC50 = 2.91 ± 0.47 μM) against NO production through remarkably blocking the NF-κB signaling pathway and inhibiting the phosphorylation of P65. In addition, a8 showed a remarkable neuroprotective effect and lacked neurotoxicity up to 50 μM concentration. Furthermore, possessing significant self-mediated Aβ1-42 aggregation inhibitory activity, chelated biometals and reduced ROS production were found in compound a8. In the bi-directional transport assay, a8 exhibited a blood-brain barrier penetrating ability. In this study, the Morris water maze task showed that compound a8 significantly improved the learning and memory impairment of the scopolamine-induced AD mice model. Results highlighted the potential of compound a8 to be a potential MTDL for the development of anti-AD agents.

Fine-tuning of a generative neural network for designing multi-target compounds

Exploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

Systematic review on role of structure based drug design (SBDD) in the identification of anti-viral leads against SARS-Cov-2

The outbreak of existing public health distress is threatening the entire world with emergence and rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The novel coronavirus disease 2019 (COVID-19) is mild in most people. However, in some elderly people with co-morbid conditions, it may progress to pneumonia, acute respiratory distress syndrome (ARDS) and multi organ dysfunction leading to death. COVID-19 has caused global panic in the healthcare sector and has become one of the biggest threats to the global economy. Drug discovery researchers are expected to contribute rapidly than ever before. The complete genome sequence of coronavirus had been reported barely a month after the identification of first patient. Potential drug targets to combat and treat the coronavirus infection have also been explored. The iterative structure-based drug design (SBDD) approach could significantly contribute towards the discovery of new drug like molecules for the treatment of COVID-19. The existing antivirals and experiences gained from SARS and MERS outbreaks may pave way for identification of potential drug molecules using the approach. SBDD has gained momentum as the essential tool for faster and costeffective lead discovery of antivirals in the past. The discovery of FDA approved human immunodeficiency virus type 1 (HIV-1) inhibitors represent the foremost success of SBDD. This systematic review provides an overview of the novel coronavirus, its pathology of replication, role of structure based drug design, available drug targets and recent advances in in-silico drug discovery for the prevention of COVID-19. SARSCoV- 2 main protease, RNA dependent RNA polymerase (RdRp) and spike (S) protein are the potential targets, which are currently explored for the drug development.

Resources and computational strategies to advance small molecule SARS-CoV-2 discovery: Lessons from the pandemic and preparing for future health crises

There is an urgent need to identify new therapies that prevent SARS-CoV-2 infection and improve the outcome of COVID-19 patients. This pandemic has thus spurred intensive research in most scientific areas and in a short period of time, several vaccines have been developed. But, while the race to find vaccines for COVID-19 has dominated the headlines, other types of therapeutic agents are being developed. In this mini-review, we report several databases and online tools that could assist the discovery of anti-SARS-CoV-2 small chemical compounds and peptides. We then give examples of studies that combined in silico and in vitro screening, either for drug repositioning purposes or to search for novel bioactive compounds. Finally, we question the overall lack of discussion and plan observed in academic research in many countries during this crisis and suggest that there is room for improvement.

Cluster Analysis of Medicinal Plants and Targets Based on Multipartite Network

Network-based methods for the analysis of drug-target interactions have gained attention and rely on the paradigm that a single drug can act on multiple targets rather than a single target. In this study, we have presented a novel approach to analyze the interactions between the chemicals in the medicinal plants and multiple targets based on the complex multipartite network of the medicinal plants, multi-chemicals, and multiple targets. The multipartite network was constructed via the conjunction of two relationships: chemicals in plants and the biological actions of those chemicals on the targets. In doing so, we introduced an index of the efficacy of chemicals in a plant on a protein target of interest, called target potency score (TPS). We showed that the analysis can identify specific chemical profiles from each group of plants, which can then be employed for discovering new alternative therapeutic agents. Furthermore, specific clusters of plants and chemicals acting on specific targets were retrieved using TPS that suggested potential drug candidates with high probability of clinical success. We expect that this approach may open a way to predict the biological functions of multi-chemicals and multi-plants on the targets of interest and enable repositioning of the plants and chemicals.

Comparison of Chemical Structure and Cell Morphology Information for Multitask Bioactivity Predictions

The understanding of the mechanism-of-action (MoA) of compounds and the prediction of potential drug targets play an important role in small-molecule drug discovery. The aim of this work was to compare chemical and cell morphology information for bioactivity prediction. The comparison was performed using bioactivity data from the ExCAPE database, image data (in the form of CellProfiler features) from the Cell Painting data set (the largest publicly available data set of cell images with ∼30,000 compound perturbations), and extended connectivity fingerprints (ECFPs) using the multitask Bayesian matrix factorization (BMF) approach Macau. We found that the BMF Macau and random forest (RF) performance were overall similar when ECFPs were used as compound descriptors. However, BMF Macau outperformed RF in 159 out of 224 targets (71%) when image data were used as compound information. Using BMF Macau, 100 (corresponding to about 45%) and 90 (about 40%) of the 224 targets were predicted with high predictive performance (AUC > 0.8) with ECFP data and image data as side information, respectively. There were targets better predicted by image data as side information, such as β-catenin, and others better predicted by fingerprint-based side information, such as proteins belonging to the G-protein-Coupled Receptor 1 family, which could be rationalized from the underlying data distributions in each descriptor domain. In conclusion, both cell morphology changes and chemical structure information contain information about compound bioactivity, which is also partially complementary, and can hence contribute to in silico MoA analysis.

Drug Repurposing: An Emerging Tool for Drug Reuse, Recycling and Discovery

Drug repositioning or repurposing is a revolutionary breakthrough in drug development that focuses on rediscovering new uses for old therapeutic agents. Drug repositioning can be defined more precisely as the process of exploring new indications for an already approved drug while drug repurposing includes overall re-development approaches grounded in the identical chemical structure of the active drug moiety as in the original product. The repositioning approach accelerates the drug development process, curtails the cost and risk inherent to drug development. The strategy focuses on the polypharmacology of drugs to unlocks novel opportunities for logically designing more efficient therapeutic agents for unmet medical disorders. Drug repositioning also expresses certain regulatory challenges that hamper its further utilization. The review outlines the eminent role of drug repositioning in new drug discovery, methods to predict the molecular targets of a drug molecule, advantages that the strategy offers to the pharmaceutical industries, explaining how the industrial collaborations with academics can assist in the discovering more repositioning opportunities. The focus of the review is to highlight the latest applications of drug repositioning in various disorders. The review also includes a comparison of old and new therapeutic uses of repurposed drugs, assessing their novel mechanisms of action and pharmacological effects in the management of various disorders. Various restrictions and challenges that repurposed drugs come across during their development and regulatory phases are also highlighted.

Target shortage and less explored multiple targeting: hurdles in the development of novel antifungals but overcome/addressed effectively through structural bioinformatics

Billions of people are affected by fungal infection worldwide, which is a major cause of morbidity and mortality in humans. Regardless of development in the field of antifungal therapeutics over the last three decades, multidrug resistance and limited efficacy of available antifungal drugs are very prominent and still a great hurdle in the patient treatment. The current antifungal pipeline is dry, which is needed to be strengthened. Although several strategies have been implemented over time to discover novel promising antifungal leads, but very little emphasis has been given to address the gap of fungal target identification. Undeniably, the need for identifying novel cellular fungal targets is as vital as discovering novel antifungal leads and a structural bioinformatics approach could be an effective strategy in this regard. To address the issue, we have performed in silico screening to identify a few potent multiple targeting ligands and their respective antifungal targets. Thus, we offer a perspective on the phenomena of 'target shortage' and least explored 'multiple targeting' being the most underrated challenges in antifungal drug discovery. 'Structural bioinformatics' could be an effective approach in the recognition of new/innovative antifungal target and identification/development of novel antifungal lead molecule aiming multiple molecular targets of the fungal pathogen.

Systems Biology Approaches for Therapeutics Development Against COVID-19

Understanding the systems biology approaches for promoting the development of new therapeutic drugs is attaining importance nowadays. The threat of COVID-19 outbreak needs to be vanished for global welfare, and every section of research is focusing on it. There is an opportunity for finding new, quick, and accurate tools for developing treatment options, including the vaccine against COVID-19. The review at this moment covers various aspects of pathogenesis and host factors for exploring the virus target and developing suitable therapeutic solutions through systems biology tools. Furthermore, this review also covers the extensive details of multiomics tools i.e., transcriptomics, proteomics, genomics, lipidomics, immunomics, and in silico computational modeling aiming towards the study of host-virus interactions in search of therapeutic targets against the COVID-19.

Eficacia y seguridad de la medicina tradicional china en COVID-19: una revisión exploratoria

Introducción

Ante la ausencia de una vacuna o tratamiento específico para controlar la actual pandemia, es necesario seguir investigando potenciales agentes terapéuticos contra la COVID-19. La medicina tradicional china (MTC) se ha usado en el tratamiento de pacientes con SARS (síndrome respiratorio agudo grave) y MERS (síndrome respiratorio de Oriente Medio), y podría tener un rol en la prevención, tratamiento o rehabilitación de pacientes con COVID-19.

Objetivo

Describir el estado actual de la literatura científica publicada hasta el 17 de mayo de 2020, sobre la eficacia y seguridad de la MTC en pacientes con COVID-19.

Material y métodos

Revisión sistemática exploratoria que incluyó PubMed, Embase, Scopus y 18 bases de datos de la Plataforma de Registros Internacionales de Ensayos Clínicos de la Organización Mundial de la Salud. Se incluyeron publicaciones empíricas y teóricas en inglés y español.

Resultados

Se incluyeron 35 documentos y 93 registros de ensayos clínicos (n = 128); 46 ensayos clínicos evalúan decocciones, cápsulas, gránulos, inyecciones y soluciones orales a base de agentes herbarios. Los documentos son revisiones narrativas (n = 9), cartas al editor (n = 6), revisiones sistemáticas (n = 4), estudios in silico (n = 4), editoriales (n = 3), comentarios (n = 2), serie de casos (n = 2), recomendaciones de práctica clínica (n = 2), guías de práctica clínica (n = 1), estudios in vitro (n = 1) y artículo de opinión (n = 1).

Conclusiones

Solo 2 estudios de series de casos en las que se emplean fórmulas a base de agentes herbarios reportaron beneficios en pacientes con neumonía leve y grave por SARS-CoV-2. Hay 78 ensayos controlados aleatorizados en curso que pronto arrojarán evidencia sobre la eficacia y seguridad de la MTC en pacientes con COVID-19.

Computational/in silico methods in drug target and lead prediction

Drug-like compounds are most of the time denied approval and use owing to the unexpected clinical side effects and cross-reactivity observed during clinical trials. These unexpected outcomes resulting in significant increase in attrition rate centralizes on the selected drug targets. These targets may be disease candidate proteins or genes, biological pathways, disease-associated microRNAs, disease-related biomarkers, abnormal molecular phenotypes, crucial nodes of biological network or molecular functions. This is generally linked to several factors, including incomplete knowledge on the drug targets and unpredicted pharmacokinetic expressions upon target interaction or off-target effects. A method used to identify targets, especially for polygenic diseases, is essential and constitutes a major bottleneck in drug development with the fundamental stage being the identification and validation of drug targets of interest for further downstream processes. Thus, various computational methods have been developed to complement experimental approaches in drug discovery. Here, we present an overview of various computational methods and tools applied in predicting or validating drug targets and drug-like molecules. We provide an overview on their advantages and compare these methods to identify effective methods which likely lead to optimal results. We also explore major sources of drug failure considering the challenges and opportunities involved. This review might guide researchers on selecting the most efficient approach or technique during the computational drug discovery process.

Multi-targeted drug design strategies for the treatment of schizophrenia

INTRODUCTION

Schizophrenia is a complex psychiatric disease (or a conglomeration of disorders) manifesting with positive, negative and cognitive symptoms. The pathophysiology of schizophrenia is not completely known; however, it involves many neurotransmitters and their receptors. In order to treat schizophrenia, drugs need to be multi-target drugs. Indeed, the action of second and third generation antipsychotics involves interactions with many receptors, belonging mainly to aminergic GPCRs.

AREAS COVERED

In this review, the authors summarize current concepts of schizophrenia with the emphasis on the modern dopaminergic, serotoninergic, and glutamatergic hypotheses. Next, they discuss treatments of the disease, stressing multi-target antipsychotics. They cover different aspects of design of multi-target ligands, including the application of molecular modeling approaches for the design and benefits and limitations of multifunctional compounds. Finally, they present successful case studies of multi-target drug design against schizophrenia.

EXPERT OPINION

Treatment of schizophrenia requires the application of multi-target drugs. While designing single target drugs is relatively easy, designing multifunctional compounds is a challenge due to the necessity to balance the affinity to many targets, while avoiding promiscuity and the problems with drug-likeness. Multi-target drugs bring many benefits: better efficiency, fewer adverse effects, and drug-drug interactions and better patient compliance to drug regime.

Artificial Neural Networks in Computer-Aided Drug Design: An Overview of Recent Advances

Computer-aided drug design (CADD) is the framework in which the huge amount of data accumulated by high-throughput experimental methods used in drug design is quantitatively studied. Its objectives include pattern recognition, biomarker identification and/or classification, etc. In order to achieve these objectives, machine learning algorithms and especially artificial neural networks (ANNs) have been used over ADMET factor testing and QSAR modeling evaluation. This paper provides an overview of the current trends in CADD-applied ANNs, since their use was re-boosted over a decade ago.

Targeting shikimate pathway: In silico analysis of phosphoenolpyruvate derivatives as inhibitors of EPSP synthase and DAHP synthase

The shikimate pathway consists of seven enzymatic steps involved in the conversion of erythrose-4-phosphate and phosphoenolpyruvate to chorismate and also responsible to the production of aromatic amino acids, such as phenylalanine, tyrosine, and tryptophan which are essential to the bacterial metabolism. The 3-deoxy-D-arabino-heptulosonate-7-phosphate synthase (DAHPS) and 5-enolpyruvylshikimate 3-phosphate synthase (EPSPS) catalyze important steps in the shikimate pathway using as substrate the phosphoenolpyruvate (PEP). Due to the importance of PEP in shikimate pathway, its structure has been investigated to develop new bioinspired competitive inhibitors against DAHPS and EPSPS. In the present study, we perform a literature survey of 28 PEP derivatives, then we analyzed the selectivity and affinity of these compounds against the EPSPS and DAHPS structures using consensual molecular docking, pharmacophore prediction, molecular dynamics (MD) simulations, and binding free energy calculations. Here, we propose consistent binding modes of the selected ligands and indicate that their structures show interesting pharmacophoric properties related to multi-targets inhibitors for both enzymes. Our computational results are supported by previous experimental findings related to the interactions of PEP derivatives with DAHPS and EPSPS structures.

Hancornia speciosa serum fraction latex stimulates the angiogenesis and extracellular matrix remodeling processes

The Hancornia speciosa latex reveals angiogenic, osteogenic, and anti-inflammatory properties, which present its potential for developing of wound healing drugs; however, the latex compounds responsible for angiogenesis remain unknown. One strategy to screen these active compounds is evaluation of latex fractions. This study aimed to obtain different fractions of latex and evaluate its angiogenic activity separately using the chick chorioallantoic membrane (CAM) assay. The serum (SE) fraction was responsible for angiogenesis, which was subject to biochemical characterization and computational simulations in order to understand the contribution of H. speciosa latex in wound healing process. Our results revealed weak antioxidant potential and absence of antimicrobial activity in the SE fraction. Phytochemical analysis identified chlorogenic acids (CGA) as the main compound of SE fraction. CGA bioactivity predictions identify different molecules associated with extracellular matrix (ECM) remodeling, such as metalloproteinases, which also are overexpressed in our CAM assay experiment. Docking simulations revealed the interactions between CGA and matrix metalloproteinase 2. In conclusion, SE latex fraction stimulates angiogenesis and may influence ECM remodeling. These properties may contribute to the wound healing process, and also confirm the widespread use of this plant.

QSAR-derived affinity fingerprints (part 2): modeling performance for potency prediction

Affinity fingerprints report the activity of small molecules across a set of assays, and thus permit to gather information about the bioactivities of structurally dissimilar compounds, where models based on chemical structure alone are often limited, and model complex biological endpoints, such as human toxicity and in vitro cancer cell line sensitivity. Here, we propose to model in vitro compound activity using computationally predicted bioactivity profiles as compound descriptors. To this aim, we apply and validate a framework for the calculation of QSAR-derived affinity fingerprints (QAFFP) using a set of 1360 QSAR models generated using K_i, K_d, IC₅₀ and EC₅₀ data from ChEMBL database. QAFFP thus represent a method to encode and relate compounds on the basis of their similarity in bioactivity space. To benchmark the predictive power of QAFFP we assembled IC₅₀ data from ChEMBL database for 18 diverse cancer cell lines widely used in preclinical drug discovery, and 25 diverse protein target data sets. This study complements part 1 where the performance of QAFFP in similarity searching, scaffold hopping, and bioactivity classification is evaluated. Despite being inherently noisy, we show that using QAFFP as descriptors leads to errors in prediction on the test set in the ~ 0.65-0.95 pIC₅₀ units range, which are comparable to the estimated uncertainty of bioactivity data in ChEMBL (0.76-1.00 pIC₅₀ units). We find that the predictive power of QAFFP is slightly worse than that of Morgan2 fingerprints and 1D and 2D physicochemical descriptors, with an effect size in the 0.02-0.08 pIC₅₀ units range. Including QSAR models with low predictive power in the generation of QAFFP does not lead to improved predictive power. Given that the QSAR models we used to compute the QAFFP were selected on the basis of data availability alone, we anticipate better modeling results for QAFFP generated using more diverse and biologically meaningful targets. Data sets and Python code are publicly available at https://github.com/isidroc/QAFFP_regression .

Prospects of multitarget drug designing strategies by linking molecular docking and molecular dynamics to explore the protein-ligand recognition process

The designing of drugs that can simultaneously affect different protein targets is one novel and promising way to treat complex diseases. Multitarget drugs act on multiple protein receptors each implicated in the same disease state, and may be considered to be more beneficial than conventional drug therapies. For example, these drugs can have improved therapeutic potency due to synergistic effects on multiple targets, as well as improved safety and resistance profiles due to the combined regulation of potential primary therapeutic targets and compensatory elements and lower dosage typically required. This review analyzes in-silico methods that facilitate multitarget drug design that facilitate the discovery and development of novel therapeutic agents. Here presented is a summary of the progress in structure-based drug discovery techniques that study the process of molecular recognition of targets and ligands, moving from static molecular docking to improved molecular dynamics approaches in multitarget drug design, and the advantages and limitations of each.

Industry-scale application and evaluation of deep learning for drug target prediction

Artificial intelligence (AI) is undergoing a revolution thanks to the breakthroughs of machine learning algorithms in computer vision, speech recognition, natural language processing and generative modelling. Recent works on publicly available pharmaceutical data showed that AI methods are highly promising for Drug Target prediction. However, the quality of public data might be different than that of industry data due to different labs reporting measurements, different measurement techniques, fewer samples and less diverse and specialized assays. As part of a European funded project (ExCAPE), that brought together expertise from pharmaceutical industry, machine learning, and high-performance computing, we investigated how well machine learning models obtained from public data can be transferred to internal pharmaceutical industry data. Our results show that machine learning models trained on public data can indeed maintain their predictive power to a large degree when applied to industry data. Moreover, we observed that deep learning derived machine learning models outperformed comparable models, which were trained by other machine learning algorithms, when applied to internal pharmaceutical company datasets. To our knowledge, this is the first large-scale study evaluating the potential of machine learning and especially deep learning directly at the level of industry-scale settings and moreover investigating the transferability of publicly learned target prediction models towards industrial bioactivity prediction pipelines.

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

The modes of action (MoAs) of drugs frequently are unknown, because many are small molecules initially identified from phenotypic screens, giving rise to the need to elucidate their MoAs. In addition, the high attrition rate for candidate drugs in preclinical studies due to intolerable toxicity has motivated the development of computational approaches to predict drug candidate (cyto)toxicity as early as possible in the drug-discovery process. Here, we provide detailed instructions for capitalizing on bioactivity predictions to elucidate the MoAs of small molecules and infer their underlying phenotypic effects. We illustrate how these predictions can be used to infer the underlying antidepressive effects of marketed drugs. We also provide the necessary functionalities to model cytotoxicity data using single and ensemble machine-learning algorithms. Finally, we give detailed instructions on how to calculate confidence intervals for individual predictions using the conformal prediction framework. © 2019 by John Wiley & Sons, Inc.

Freely Accessible Chemical Database Resources of Compounds for In Silico Drug Discovery

BACKGROUND

In silico drug discovery has been proved to be a solidly established key component in early drug discovery. However, this task is hampered by the limitation of quantity and quality of compound databases for screening. In order to overcome these obstacles, freely accessible database resources of compounds have bloomed in recent years. Nevertheless, how to choose appropriate tools to treat these freely accessible databases is crucial. To the best of our knowledge, this is the first systematic review on this issue.

OBJECTIVE

The existed advantages and drawbacks of chemical databases were analyzed and summarized based on the collected six categories of freely accessible chemical databases from literature in this review.

RESULTS

Suggestions on how and in which conditions the usage of these databases could be reasonable were provided. Tools and procedures for building 3D structure chemical libraries were also introduced.

CONCLUSION

In this review, we described the freely accessible chemical database resources for in silico drug discovery. In particular, the chemical information for building chemical database appears as attractive resources for drug design to alleviate experimental pressure.

Machine learning approaches and databases for prediction of drug-target interaction: a survey paper

The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug–target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.

Current computational methods for predicting protein interactions of natural products

Natural products (NPs) are an indispensable source of drugs and they have a better coverage of the pharmacological space than synthetic compounds, owing to their high structural diversity. The prediction of their interaction profiles with druggable protein targets remains a major challenge in modern drug discovery. Experimental (off-)target predictions of NPs are cost- and time-consuming, whereas computational methods, on the other hand, are much faster and cheaper. As a result, computational predictions are preferentially used in the first instance for NP profiling, prior to experimental validations. This review covers recent advances in computational approaches which have been developed to aid the annotation of unknown drug-target interactions (DTIs), by focusing on three broad classes, namely: ligand-based, target-based, and target-ligand-based (hybrid) approaches. Computational DTI prediction methods have the potential to significantly advance the discovery and development of novel selective drugs exhibiting minimal side effects. We highlight some inherent caveats of these methods which must be overcome to enable them to realize their full potential, and a future outlook is given.

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

Reliable Target Prediction of Bioactive Molecules Based on Chemical Similarity Without Employing Statistical Methods

The prediction of biological targets of bioactive molecules from machine-readable materials can be routinely performed by computational target prediction tools (CTPTs). However, the prediction of biological targets of bioactive molecules from non-digital materials (e.g., printed or handwritten documents) has not been possible due to the complex nature of bioactive molecules and impossibility of employing computations. Improving the target prediction accuracy is the most important challenge for computational target prediction. A minimum structure is identified for each group of neighbor molecules in the proposed method. Each group of neighbor molecules represents a distinct structural class of molecules with the same function in relation to the target. The minimum structure is employed as a query to search for molecules that perfectly satisfy the minimum structure of what is guessed crucial for the targeted activity. The proposed method is based on chemical similarity, but only molecules that perfectly satisfy the minimum structure are considered. Structurally related bioactive molecules found with the same minimum structure were considered as neighbor molecules of the query molecule. The known target of the neighbor molecule is used as a reference for predicting the target of the neighbor molecule with an unknown target. A lot of information is needed to identify the minimum structure, because it is necessary to know which part(s) of the bioactive molecule determines the precise target or targets responsible for the observed phenotype. Therefore, the predicted target based on the minimum structure without employing the statistical significance is considered as a reliable prediction. Since only molecules that perfectly (and not partly) satisfy the minimum structure are considered, the minimum structure can be used without similarity calculations in non-digital materials and with similarity calculations (perfect similarity) in machine-readable materials. Nine tools (PASS online, PPB, SEA, TargetHunter, PharmMapper, ChemProt, HitPick, SuperPred, and SPiDER), which can be used for computational target prediction, are compared with the proposed method for 550 target predictions. The proposed method, SEA, PPB, and PASS online, showed the best quality and quantity for the accurate predictions.

Opportunities and Challenges in Phenotypic Screening for Neurodegenerative Disease Research

Toxic misfolded proteins potentially underly many neurodegenerative diseases, but individual targets which regulate these proteins and their downstream detrimental effects are often unknown. Phenotypic screening is an unbiased method to screen for novel targets and therapeutic molecules and span the range from primitive model organisms such as Sacchaomyces cerevisiae, which allow for high-throughput screening to patient-derived cell-lines that have a close connection to the disease biology but are limited in screening capacity. This perspective will review current phenotypic models, as well as the chemical screening strategies most often employed. Advances in in 3D cell cultures, high-content screens, robotic microscopy, CRISPR screening, and use of machine learning methods to process the enormous amount of data generated by these screens are certain to change the paradigm for phenotypic screening and will be discussed.

Multi-channel PINN: investigating scalable and transferable neural networks for drug discovery

Analysis of compound–protein interactions (CPIs) has become a crucial prerequisite for drug discovery and drug repositioning. In vitro experiments are commonly used in identifying CPIs, but it is not feasible to discover the molecular and proteomic space only through experimental approaches. Machine learning’s advances in predicting CPIs have made significant contributions to drug discovery. Deep neural networks (DNNs), which have recently been applied to predict CPIs, performed better than other shallow classifiers. However, such techniques commonly require a considerable volume of dense data for each training target. Although the number of publicly available CPI data has grown rapidly, public data is still sparse and has a large number of measurement errors. In this paper, we propose a novel method, Multi-channel PINN, to fully utilize sparse data in terms of representation learning. With representation learning, Multi-channel PINN can utilize three approaches of DNNs which are a classifier, a feature extractor, and an end-to-end learner. Multi-channel PINN can be fed with both low and high levels of representations and incorporates each of them by utilizing all approaches within a single model. To fully utilize sparse public data, we additionally explore the potential of transferring representations from training tasks to test tasks. As a proof of concept, Multi-channel PINN was evaluated on fifteen combinations of feature pairs to investigate how they affect the performance in terms of highest performance, initial performance, and convergence speed. The experimental results obtained indicate that the multi-channel models using protein features performed better than single-channel models or multi-channel models using compound features. Therefore, Multi-channel PINN can be advantageous when used with appropriate representations. Additionally, we pretrained models on a training task then finetuned them on a test task to figure out whether Multi-channel PINN can capture general representations for compounds and proteins. We found that there were significant differences in performance between pretrained models and non-pretrained models.