Discovery of multitarget-directed ligands against Alzheimer's disease through systematic prediction of chemical-protein interactions

Emerging paradigms in Alzheimer's therapy

Alzheimer's disease is a neurodegenerative disorder that affects elderly, and its incidence is continuously increasing across the globe. Unfortunately, despite decades of research, a complete cure for Alzheimer's disease continues to elude us. The current medications are mainly symptomatic and slow the disease progression but do not result in reversal of all disease pathologies. The growing body of knowledge on the factors responsible for the onset and progression of the disease has resulted in the identification of new targets that could be targeted for treatment of Alzheimer's disease. This has opened new vistas for treatment of Alzheimer's disease that have moved away from chemotherapeutic agents modulating a single target to biologics and combinations that acted on multiple targets thereby offering better therapeutic outcomes. This review discusses the emerging directions in therapeutic interventions against Alzheimer's disease highlighting their merits that promise to change the treatment paradigm and challenges that limit their clinical translation.

Identification of Riluzole derivatives as novel calmodulin inhibitors with neuroprotective activity by a joint synthesis, biosensor, and computational guided strategy

The development of new molecules for the treatment of calmodulin related cardiovascular or neurodegenerative diseases is an interesting goal. In this work, we introduce a novel strategy with four main steps: (1) chemical synthesis of target molecules, (2) Förster Resonance Energy Transfer (FRET) biosensor development and in vitro biological assay of new derivatives, (3) Cheminformatics models development and in vivo activity prediction, and (4) Docking studies. This strategy is illustrated with a case study. Firstly, a series of 4-substituted Riluzole derivatives 1-3 were synthetized through a strategy that involves the construction of the 4-bromoriluzole framework and its further functionalization via palladium catalysis or organolithium chemistry. Next, a FRET biosensor for monitoring Ca2+-dependent CaM-ligands interactions has been developed and used for the in vitro assay of Riluzole derivatives. In particular, the best inhibition (80%) was observed for 4-methoxyphenylriluzole 2b. Besides, we trained and validated a new Networks Invariant, Information Fusion, Perturbation Theory, and Machine Learning (NIFPTML) model for predicting probability profiles of in vivo biological activity parameters in different regions of the brain. Next, we used this model to predict the in vivo activity of the compounds experimentally studied in vitro. Last, docking study conducted on Riluzole and its derivatives has provided valuable insights into their binding conformations with the target protein, involving calmodulin and the SK4 channel. This new combined strategy may be useful to reduce assay costs (animals, materials, time, and human resources) in the drug discovery process of calmodulin inhibitors.

Exploiting Natural Niches with Neuroprotective Properties: A Comprehensive Review

Natural products from mushrooms, plants, microalgae, and cyanobacteria have been intensively explored and studied for their preventive or therapeutic potential. Among age-related pathologies, neurodegenerative diseases (such as Alzheimer's and Parkinson's diseases) represent a worldwide health and social problem. Since several pathological mechanisms are associated with neurodegeneration, promising strategies against neurodegenerative diseases are aimed to target multiple processes. These approaches usually avoid premature cell death and the loss of function of damaged neurons. This review focuses attention on the preventive and therapeutic potential of several compounds derived from natural sources, which could be exploited for their neuroprotective effect. Curcumin, resveratrol, ergothioneine, and phycocyanin are presented as examples of successful approaches, with a special focus on possible strategies to improve their delivery to the brain.

Design, Synthesis, and Biological Evaluation of Novel Tetrahydroacridin Hybrids with Sulfur-Inserted Linkers as Potential Multitarget Agents for Alzheimer's Disease

Alzheimer's disease (AD) is a complex neurodegenerative disease that can lead to the loss of cognitive function. The progression of AD is regulated by multiple signaling pathways and their associated targets. Therefore, multitarget strategies theoretically have greater potential for treating AD. In this work, a series of new hybrids were designed and synthesized by the hybridization of tacrine (4, AChE: IC50 = 0.223 μM) with pyrimidone compound 5 (GSK-3β: IC50 = 3 μM) using the cysteamine or cystamine group as the connector. The biological evaluation results demonstrated that most of the compounds exhibited moderate to good inhibitory activities against acetylcholinesterase (AChE) and glycogen synthase kinase 3β (GSK-3β). The optimal compound 18a possessed potent dual AChE/GSK-3β inhibition (AChE: IC50 = 0.047 ± 0.002 μM, GSK-3β: IC50 = 0.930 ± 0.080 μM). Further molecular docking and enzymatic kinetic studies revealed that this compound could occupy both the catalytic anionic site and the peripheral anionic site of AChE. The results also showed a lack of toxicity to SH-SY5Y neuroblastoma cells at concentrations of up to 25 μM. Collectively, this work explored the structure-activity relationships of novel tetrahydroacridin hybrids with sulfur-inserted linkers, providing a reference for the further research and development of new multitarget anti-AD drugs.

Combining Deep Learning and Structural Modeling to Identify Potential Acetylcholinesterase Inhibitors from Hericium erinaceus

Alzheimer's disease (AD) is the most common type of dementia, affecting over 50 million people worldwide. Currently, most approved medications for AD inhibit the activity of acetylcholinesterase (AChE), but these treatments often come with harmful side effects. There is growing interest in the use of natural compounds for disease prevention, alleviation, and treatment. This trend is driven by the anticipation that these substances may incur fewer side effects than existing medications. This research presents a computational approach combining machine learning with structural modeling to discover compounds from medicinal mushrooms with a high potential to inhibit the activity of AChE. First, we developed a deep neural network capable of rapidly screening a vast number of compounds to indicate their potential to inhibit AChE activity. Subsequently, we applied deep learning models to screen the compounds in the BACMUSHBASE database, which catalogs the bioactive compounds from cultivated and wild mushroom varieties local to Thailand, resulting in the identification of five promising compounds. Next, the five identified compounds underwent molecular docking techniques to calculate the binding energy between the compounds and AChE. This allowed us to refine the selection to two compounds, erinacerin A and hericenone B. Further analysis of the binding energy patterns between these compounds and the target protein revealed that both compounds displayed binding energy profiles similar to the combined characteristics of donepezil and galanthamine, the prescription drugs for AD. We propose that these two compounds, derived from Hericium erinaceus (also known as lion's mane mushroom), are suitable candidates for further research and development into symptom-alleviating AD medications.

Design, synthesis and evaluation of aminothiazole derivatives as potential anti-Alzheimer's candidates

Aim: The objective of the present study was to design, synthesize and evaluate diverse Schiff bases and thiazolidin-4-one derivatives of aminothiazole as key pharmacophores possessing acetylcholinesterase inhibitory activity. Materials & methods: Two series of compounds (13 each) were synthesized and evaluated for their acetylcholinesterase inhibition and antioxidant activity. Molecular docking of all compounds was performed to provide an insight into their binding interactions. Results: Compounds 2j (IC50 = 0.03 μM) and 3e (IC50 = 1.58 μM) were found to be the best acetylcholinesterase inhibitors among compounds of their respective series. Molecular docking analysis supported the results of in vitro activity by displaying good docking scores with the binding pocket of human acetylcholinesterase (Protein Data Bank ID: 4EY7). Conclusion: Compound 2j emerged as a potential lead compound with excellent acetylcholinesterase inhibition, antioxidant and chelation activity.

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.

Artificial intelligence for dementia drug discovery and trials optimization

Drug discovery and clinical trial design for dementia have historically been challenging. In part these challenges have arisen from patient heterogeneity, length of disease course, and the tractability of a target for the brain. Applying big data analytics and machine learning tools for drug discovery and utilizing them to inform successful clinical trial design has the potential to accelerate progress. Opportunities arise at multiple stages in the therapy pipeline and the growing availability of large medical data sets opens possibilities for big data analyses to answer key questions in clinical and therapeutic challenges. However, before this goal is reached, several challenges need to be overcome and only a multi-disciplinary approach can promote data-driven decision-making to its full potential. Herein we review the current state of machine learning applications to clinical trial design and drug discovery, while presenting opportunities and recommendations that can break down the barriers to implementation.

Guanidines: Synthesis of Novel Histamine H3R Antagonists with Additional Breast Anticancer Activity and Cholinesterases Inhibitory Effect

This study examines the properties of novel guanidines, designed and synthesized as histamine H₃R antagonists/inverse agonists with additional pharmacological targets. We evaluated their potential against two targets viz., inhibition of MDA-MB-231, and MCF-7 breast cancer cells viability and inhibition of AChE/BuChE. ADS10310 showed micromolar cytotoxicity against breast cancer cells, combined with nanomolar affinity at hH₃R, and may represent a promising target for the development of an alternative method of cancer therapy. Some of the newly synthesized compounds showed moderate inhibition of BuChE in the single-digit micromolar concentration ranges. H₃R antagonist with additional AChE/BuChE inhibitory effect might improve cognitive functions in Alzheimer's disease. For ADS10310, several in vitro ADME-Tox parameters were evaluated and indicated that it is a metabolically stable compound with weak hepatotoxic activity and can be accepted for further studies.

Research trends and hotspots of neurodegenerative diseases employing network pharmacology: A bibliometric analysis

Background: Employing network pharmacology in neurodegenerative diseases (NDs) has been extensively studied recently. However, no comprehensive study has conducted on this subject employing bibliometrics so far. The purpose of this study was to find out the developmental trends and hotspots, and to predict potential research directions in this filed. Methods: Relevant research were collected from the Web of Science Core Collection Bibliometrics and visual analysis were executed using CiteSpace, VOSviewer, Histcite and R-bibliometrix. Results: A total of 420 English articles on network pharmacology in NDs published in 2008-2022 were obtained from the WOSCC database. From 2008 to 2022, annual publications showed a steady growing trend, especially in 2014-2022. China, Beijing Univ Chinese Med, Frontiers in Pharmacology, and Geerts H are the most prolific country, institution, journal, and author, respectively. China, Nucleic Acids Research, and Hopkins AL are the most highly cited country, journal, and author, respectively. Moreover, network pharmacology and Alzheimer's disease are the focal areas of current researches according to analysis of co-cited references and keywords. Finally, in the detection of burst keywords, systems pharmacology and database are new approaches to disease and drug research, while traditional Chinese medicine (TCM) and Alzheimer's disease are hot research directions. The above keywords are speculated to be the research frontiers. Conclusion: Network pharmacology and Alzheimers' disease are the main topics of researches on network pharmacology in NDs. Network pharmacology and the TCM treatment of Alzheimer's disease have been the recent research hotspots. To sum up, the potential for exploring TCM treatment of AD with network pharmacology is huge.

SPCMLMI: A structural perturbation-based matrix completion method to predict lncRNA–miRNA interactions

Accumulating evidence indicated that the interaction between lncRNA and miRNA is crucial for gene regulation, which can regulate gene transcription, further affecting the occurrence and development of many complex diseases. Accurate identification of interactions between lncRNAs and miRNAs is helpful for the diagnosis and therapeutics of complex diseases. However, the number of known interactions of lncRNA with miRNA is still very limited, and identifying their interactions through biological experiments is time-consuming and expensive. There is an urgent need to develop more accurate and efficient computational methods to infer lncRNA–miRNA interactions. In this work, we developed a matrix completion approach based on structural perturbation to infer lncRNA–miRNA interactions (SPCMLMI). Specifically, we first calculated the similarities of lncRNA and miRNA, including the lncRNA expression profile similarity, miRNA expression profile similarity, lncRNA sequence similarity, and miRNA sequence similarity. Second, a bilayer network was constructed by integrating the known interaction network, lncRNA similarity network, and miRNA similarity network. Finally, a structural perturbation-based matrix completion method was used to predict potential interactions of lncRNA with miRNA. To evaluate the prediction performance of SPCMLMI, five-fold cross validation and a series of comparison experiments were implemented. SPCMLMI achieved AUCs of 0.8984 and 0.9891 on two different datasets, which is superior to other compared methods. Case studies for lncRNA XIST and miRNA hsa-mir-195–5-p further confirmed the effectiveness of our method in inferring lncRNA–miRNA interactions. Furthermore, we found that the structural consistency of the bilayer network was higher than that of other related networks. The results suggest that SPCMLMI can be used as a useful tool to predict interactions between lncRNAs and miRNAs.

Dual Inhibitors of AChE and BACE-1 for Reducing Aβ in Alzheimer's Disease: From In Silico to In Vivo

Alzheimer's disease (AD) is a complex and widespread condition, still not fully understood and with no cure yet. Amyloid beta (Aβ) peptide is suspected to be a major cause of AD, and therefore, simultaneously blocking its formation and aggregation by inhibition of the enzymes BACE-1 (β-secretase) and AChE (acetylcholinesterase) by a single inhibitor may be an effective therapeutic approach, as compared to blocking one of these targets or by combining two drugs, one for each of these targets. We used our ISE algorithm to model each of the AChE peripheral site inhibitors and BACE-1 inhibitors, on the basis of published data, and constructed classification models for each. Subsequently, we screened large molecular databases with both models. Top scored molecules were docked into AChE and BACE-1 crystal structures, and 36 Molecules with the best weighted scores (based on ISE indexes and docking results) were sent for inhibition studies on the two enzymes. Two of them inhibited both AChE (IC₅₀ between 4-7 μM) and BACE-1 (IC₅₀ between 50-65 μM). Two additional molecules inhibited only AChE, and another two molecules inhibited only BACE-1. Preliminary testing of inhibition by F681-0222 (molecule 2) on APPswe/PS1dE9 transgenic mice shows a reduction in brain tissue of soluble Aβ42.

New Drug Design Avenues Targeting Alzheimer's Disease by Pharmacoinformatics-Aided Tools

Neurodegenerative diseases (NDD) have been of great interest to scientists for a long time due to their multifactorial character. Among these pathologies, Alzheimer's disease (AD) is of special relevance, and despite the existence of approved drugs for its treatment, there is still no efficient pharmacological therapy to stop, slow, or repair neurodegeneration. Existing drugs have certain disadvantages, such as lack of efficacy and side effects. Therefore, there is a real need to discover new drugs that can deal with this problem. However, as AD is multifactorial in nature with so many physiological pathways involved, the most effective approach to modulate more than one of them in a relevant manner and without undesirable consequences is through polypharmacology. In this field, there has been significant progress in recent years in terms of pharmacoinformatics tools that allow the discovery of bioactive molecules with polypharmacological profiles without the need to spend a long time and excessive resources on complex experimental designs, making the drug design and development pipeline more efficient. In this review, we present from different perspectives how pharmacoinformatics tools can be useful when drug design programs are designed to tackle complex diseases such as AD, highlighting essential concepts, showing the relevance of artificial intelligence and new trends, as well as different databases and software with their main results, emphasizing the importance of coupling wet and dry approaches in drug design and development processes.

Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system

CNS disorders are indications with a very high unmet medical needs, relatively smaller number of available drugs, and a subpar satisfaction level among patients and caregiver. Discovery of CNS drugs is extremely expensive affair with its own unique challenges leading to extremely high attrition rates and low efficiency. With explosion of data in information age, there is hardly any aspect of life that has not been touched by data driven technologies such as artificial intelligence (AI) and machine learning (ML). Drug discovery is no exception, emergence of big data via genomic, proteomic, biological, and chemical technologies has driven pharmaceutical giants to collaborate with AI oriented companies to revolutionise drug discovery, with the goal of increasing the efficiency of the process. In recent years many examples of innovative applications of AI and ML techniques in CNS drug discovery has been reported. Research on therapeutics for diseases such as schizophrenia, Alzheimer's and Parkinsonism has been provided with a new direction and thrust from these developments. AI and ML has been applied to both ligand-based and structure-based drug discovery and design of CNS therapeutics. In this review, we have summarised the general aspects of AI and ML from the perspective of drug discovery followed by a comprehensive coverage of the recent developments in the applications of AI/ML techniques in CNS drug discovery.

DL0410 Alleviates Memory Impairment in D-Galactose-Induced Aging Rats by Suppressing Neuroinflammation via the TLR4/MyD88/NF-κB Pathway

Oxidative stress and neuroinflammation have been demonstrated to be linked with Alzheimer's disease (AD). In this study, we examined the protective effects of DL0410 in aging rats and explored the underlying mechanism against oxidative damage and neuroinflammation, which was then validated in LPS-stimulated BV2 microglia. We firstly investigated the improvement effects of DL0410 on learning and memory abilities and explored the potential mechanisms in D-gal-induced aging rats. An 8-week treatment with DL0410 significantly improved the learning and cognitive function of D-gal-stimulated Alzheimer's-like rats in the Morris water maze test, step-down test, and novel object recognition test, and the therapeutic effect of DL0410 at 10 mg/kg was even better than that of donepezil. What is more, the results showed that DL0410 alleviated neuron injury, increased the number of synapses, and improved the level of postsynaptic density protein 95 (PSD95) in the hippocampus and cortex. Next, we examined the protective effects of DL0410 against oxidative damage and neuroinflammation. Our observations indicated that DL0410 reduced the production of harmful oxidation products and promoted the antioxidative system, decreased the levels of proinflammatory cytokines, including tumor necrosis factor α (TNF-α), interleukin 1β (IL-1β), and interleukin 6 (IL-6), and increased anti-inflammatory cytokines IL-10. Moreover, DL0410 inhibited the activation of astrocytes and microglia and suppressed the activation of the TLR4/MyD88/NF-κB signaling pathway. The anti-inflammation effect of DL0410 was further confirmed in LPS-stimulated BV2 cells, and the results showed that DL0410 reduced the level of inflammatory factors and inhibited the activation of the TLR4/MyD88/TRAF6/NF-κB signaling pathway in BV2 microglia. Molecular docking results indicated that DL0410 occupied the LPS recognition site in the TLR4/MD2 complex. Furthermore, the enhanced expression of claudin-1, claudin-5, occludin, CX43, and ZO-1 indicated that DL0410 protected the blood-brain barrier (BBB) integrity. Together, these results suggest that DL0410 exerts neuroprotective effects against hippocampus and cortex injury induced by D-galactose, and the possible mechanisms include antioxidative stress, antineuroinflammation, improving synaptic plasticity, and maintaining BBB integrity, which is mediated by the TLR4/MyD88/NF-κB signaling pathway inhibition. We suggest that DL0410 is a promising candidate for AD treatment.

Precision Psychiatry: Machine learning as a tool to find new pharmacological targets

There is an increasing amount of data arising from neurobehavioral sciences and medical records that cannot be adequately analyzed by traditional research methods. New drugs develop at a slow rate and seem unsatisfactory for the majority of neurobehavioral disorders. Machine learning (ML) techniques, instead, can incorporate psychopathological, computational, cognitive, and neurobiological underpinning knowledge leading to a refinement of detection, diagnosis, prognosis, treatment, research, and support. Machine and deep learning methods are currently used to accelerate the process of discovering new pharmacological targets and drugs.

OBJECTIVE

The present work reviews current evidence regarding the contribution of machine learning to the discovery of new drug targets.

METHODS

Scientific articles from PubMed, SCOPUS, EMBASE, and Web of Science Core Collection published until May 2021 were included in this review.

RESULTS

The most significant areas of research are schizophrenia, depression and anxiety, Alzheimer´s disease, and substance use disorders. ML techniques have pinpointed target gene candidates and pathways, new molecular substances, and several biomarkers regarding psychiatric disorders. Drug repositioning studies using ML have identified multiple drug candidates as promising therapeutic agents.

CONCLUSION

Next-generation ML techniques and subsequent deep learning may power new findings regarding the discovery of new pharmacological agents by bridging the gap between biological data and chemical drug information.

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

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

Neuroprotective Potential of Ellagic Acid: A Critical Review

Ellagic acid (EA) is a dietary polyphenol present in various fruits, vegetables, herbs, and nuts. It exists either independently or as part of complex structures, such as ellagitannins, which release EA and several other metabolites including urolithins following absorption. During the past few decades, EA has drawn considerable attention because of its vast range of biological activities as well as its numerous molecular targets. Several studies have reported that the oxidative stress-lowering potential of EA accounts for its broad-spectrum pharmacological attributes. At the biochemical level, several mechanisms have also been associated with its therapeutic action, including its efficacy in normalizing lipid metabolism and lipidemic profile, regulating proinflammatory mediators, such as IL-6, IL-1β, and TNF-α, upregulating nuclear factor erythroid 2-related factor 2 and inhibiting NF-κB action. EA exerts appreciable neuroprotective activity by its free radical-scavenging action, iron chelation, initiation of several cell signaling pathways, and alleviation of mitochondrial dysfunction. Numerous in vivo studies have also explored the neuroprotective attribute of EA against various neurotoxins in animal models. Despite the increasing number of publications with experimental evidence, a critical analysis of available literature to understand the full neuroprotective potential of EA has not been performed. The present review provides up-to-date, comprehensive, and critical information regarding the natural sources of EA, its bioavailability, metabolism, neuroprotective activities, and underlying mechanisms of action in order to encourage further studies to define the clinical usefulness of EA for the management of neurological disorders.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

Identification of Multi-Target Anti-AD Chemical Constituents From Traditional Chinese Medicine Formulae by Integrating Virtual Screening and In Vitro Validation

Alzheimer's disease (AD) is a neurodegenerative disease that seriously threatens the health of the elderly. At present, no drugs have been proven to cure or delay the progression of the disease. Due to the multifactorial aetiology of this disease, the multi-target-directed ligand (MTDL) approach provides an innovative and promising idea in search for new drugs against AD. In order to find potential multi-target anti-AD drugs from traditional Chinese medicine (TCM) formulae, a compound database derived from anti-AD Chinese herbal formulae was constructed and predicted by the anti-AD multi-target drug prediction platform established in our laboratory. By analyzing the results of virtual screening, 226 chemical constituents with 3 or more potential AD-related targets were collected, from which 16 compounds that were predicted to combat AD through various mechanisms were chosen for biological validation. Several cell models were established to validate the anti-AD effects of these compounds, including KCl, Aβ, okadaic acid (OA), SNP and H₂O₂ induced SH-SY5Y cell model and LPS induced BV2 microglia model. The experimental results showed that 12 compounds including Nonivamide, Bavachromene and 3,4-Dimethoxycinnamic acid could protect model cells from AD-related damages and showed potential anti-AD activity. Furthermore, the potential targets of Nonivamide were investigated by molecular docking study and analysis with CDOCKER revealed the possible binding mode of Nonivamide with its predicted targets. In summary, 12 potential multi-target anti-AD compounds have been found from anti-AD TCM formulae by comprehensive application of computational prediction, molecular docking method and biological validation, which laid a theoretical and experimental foundation for in-depth study, also providing important information and new research ideas for the discovery of anti-AD compounds from traditional Chinese medicine.

DL0410 ameliorates cognitive disorder in SAMP8 mice by promoting mitochondrial dynamics and the NMDAR-CREB-BDNF pathway

Alzheimer's disease (AD) is a worldwide problem and there are no effective drugs for AD treatment. Previous studies show that DL0410 is a multi-target, anti-AD agent. In this study, we investigated the therapeutic effect of DL0410 and its action mechanism in SAMP8 mice. DL0410 (1-10 mg·kg^-1·d^-1) was orally administered to 8-month-old SAMP mice (SAMP8) for 8 weeks. We showed that DL0410 administration effectively ameliorated the cognitive deficits in the Morris water maze test, novel object recognition test, and nest building test. We revealed that DL0410 dose-dependently increased the expression levels of the mitochondrial proteins (PGC-1α, Mitofusin 2, OPA1, and Drp1), and subsequently ameliorated the processes of mitochondrial biosynthesis, fusion, and fission in the cortex and hippocampus of SAMP8 mice. Furthermore, DL0410 administration promoted the expression of synaptic proteins (synaptophysin and PSD95) in the brain of SAMP8 mice, and upregulated the protein phosphorylation in NMDAR-CAMKII/CAMKIV-CREB pathway responsible for the synaptic plasticity. DL0410 administration dose-dependently increased the expression of BDNF and TrkB, and the neurotrophic effect was mediated via the ERK1/2 and PI3K-AKT-GSK-3β pathways. DL0410 administration upregulated Bcl-2, increased the Bcl-2/Bax ratio and the level of caspase 3 and PARP-1, alleviating neuronal apoptosis. We proposed that the NMDAR-CREB-BDNF pathway might establish a positive feedback loop between synaptic plasticity and neurotrophy, with CREB at the center. In summary, DL0410 promotes synaptic function and neuronal survival, thus ameliorating cognitive deficits in SAMP8 mice via improved mitochondrial dynamics and increased activity of the NMDAR-CREB-BDNF pathway. DL0410 is a promising candidate to treat aging-related AD, and deserves more research and development in future.

Histamine H3 receptor and cholinesterases as synergistic targets for cognitive decline: Strategies to the rational design of multitarget ligands

The role of histamine and acetylcholine in cognitive functions suggests that compounds able to increase both histaminergic and cholinergic neurotransmissions in the brain should be considered as promising therapeutic options. For this purpose, dual inhibitors of histamine H₃ receptors (H₃ R) and cholinesterases (ChEs) have been designed and assessed. In this context, this paper reviews the strategies used to obtain dual H₃ R/ChEs ligands using multitarget design approaches. Hybrid compounds designed by linking tacrine or flavonoid motifs to H₃ R antagonists were obtained with high affinity for both targets, and compounds designed by merging the H₃ R antagonist pharmacophore with known anticholinesterase molecules were also reported. These reports strongly suggest that key modifications in the lipophilic region (including a second basic group) seem to be a strategy to reach novel compounds, allied with longer linker groups to a basic region. Some compounds have already demonstrated efficacy in memory models, although the pharmacokinetic and toxicity profile should be considered when designing further compounds. In conclusion, the key features to be considered when designing novel H₃ R/ChEs inhibitors with improved pharmacological profile were herein summarized.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Network Pharmacology-Based Prediction of Catalpol and Mechanisms against Stroke

Aim

To apply the network pharmacology method to screen the target of catalpol prevention and treatment of stroke, and explore the pharmacological mechanism of Catalpol prevention and treatment of stroke.

Methods

PharmMapper, GeneCards, DAVID, and other databases were used to find key targets. We selected hub protein and catalpol which were screened for molecular docking verification. Based on the results of molecular docking, the ITC was used to determine the binding coefficient between the highest scoring protein and catalpol. The GEO database and ROC curve were used to evaluate the correlation between key targets.

Results

27 key targets were obtained by mapping the predicted catalpol-related targets to the disease. Hub genes (ALB, CASP3, MAPK1 (14), MMP9, ACE, KDR, etc.) were obtained in the key target PPI network. The results of KEGG enrichment analysis showed that its signal pathway was involved in angiogenic remodeling such as VEGF, neurotrophic factors, and inflammation. The results of molecular docking showed that ACE had the highest docking score. Therefore, the ITC was used for the titration of ACE and catalpol. The results showed that catalpol had a strong binding force with ACE.

Conclusion

Network pharmacology combined with molecular docking predicts key genes, proteins, and signaling pathways for catalpol in treating stroke. The strong binding force between catalpol and ACE was obtained by using ITC, and the results of molecular docking were verified to lay the foundation for further research on the effect of catalpol on ACE. ROC results showed that the AUC values of the key targets are all >0.5. This article uses network pharmacology to provide a reference for a more in-depth study of catalpol's mechanism and experimental design.

Network Pharmacology-Based Analysis of Xiao-Xu-Ming Decoction on the Treatment of Alzheimer's Disease

Alzheimer's disease (AD) has become a worldwide disease that is harmful to human health and brings a heavy economic burden to healthcare system. Xiao-Xu-Ming Decoction (XXMD) has been widely used to treat stroke and other neurological diseases for more than 1000 years in China. However, the synergistic mechanism of the constituents in XXMD for the potential treatment of AD is still unclear. Therefore, the present study aimed to predict the potential targets and uncover the material basis of XXMD for the potential treatment of AD. A network pharmacology-based method, which combined data collection, drug-likeness filtering and absorption, distribution, metabolism, excretion and toxicity (ADME/T) properties filtering, target prediction and network analysis, was used to decipher the effect and potential targets of XXMD for the treatment of AD. Then, the acetylcholinesterase (AChE) inhibitory assay was used to screen the potential active constituents in XXMD for the treatment of AD, and the molecular docking was furtherly used to identify the binding ability of active constituents with AD-related target of AChE. Finally, three in vitro cell models were applied to evaluate the neuroprotective effects of potential lead compounds in XXMD. Through the China Natural Products Database, Traditional Chinese Medicine Systems Pharmacology (TCMSP) Database, Traditional Chinese Medicine (TCM)-Database @Taiwan and literature, a total of 1481 compounds in XXMD were finally collected. After ADME/T properties filtering, 908 compounds were used for the further study. Based on the prediction data, the constituents in XXMD formula could interact with 41 AD-related targets. Among them, cyclooxygenase-2 (COX-2), estrogen receptor α (ERα) and AChE were the major targets. The constituents in XXMD were found to have the potential to treat AD through multiple AD-related targets. 62 constituents in it were found to interact with more than or equal to 10 AD-related targets. The prediction results were further validated by in vitro biology experiment, resulting in several potential anti-AD multitarget-directed ligands (MTDLs), including two AChE inhibitors with the IC₅₀ values ranging from 4.83 to 10.22 μM. Moreover, fanchinoline was furtherly found to prevent SH-SY5Y cells from the cytotoxicities induced by sodium nitroprusside, sodium dithionate and potassium chloride. In conclusion, XXMD was found to have the potential to treat AD by targeting multiple AD-related targets and canonical pathways. Fangchinoline and dauricine might be the potential lead compounds in XXMD for the treatment of AD.

CGINet: graph convolutional network-based model for identifying chemical-gene interaction in an integrated multi-relational graph

Background

Elucidation of interactive relation between chemicals and genes is of key relevance not only for discovering new drug leads in drug development but also for repositioning existing drugs to novel therapeutic targets. Recently, biological network-based approaches have been proven to be effective in predicting chemical-gene interactions.

Results

We present CGINet, a graph convolutional network-based method for identifying chemical-gene interactions in an integrated multi-relational graph containing three types of nodes: chemicals, genes, and pathways. We investigate two different perspectives on learning node embeddings. One is to view the graph as a whole, and the other is to adopt a subgraph view that initial node embeddings are learned from the binary association subgraphs and then transferred to the multi-interaction subgraph for more focused learning of higher-level target node representations. Besides, we reconstruct the topological structures of target nodes with the latent links captured by the designed substructures. CGINet adopts an end-to-end way that the encoder and the decoder are trained jointly with known chemical-gene interactions. We aim to predict unknown but potential associations between chemicals and genes as well as their interaction types.

Conclusions

We study three model implementations CGINet-1/2/3 with various components and compare them with baseline approaches. As the experimental results suggest, our models exhibit competitive performances on identifying chemical-gene interactions. Besides, the subgraph perspective and the latent link both play positive roles in learning much more informative node embeddings and can lead to improved prediction.

Design and synthesis of multi-target directed 1,2,3-triazole-dimethylaminoacryloyl-chromenone derivatives with potential use in Alzheimer's disease

To discover multifunctional agents for the treatment of Alzheimer's disease (AD), a new series of 1,2,3-triazole-chromenone derivatives were designed and synthesized based on the multi target-directed ligands approach. The in vitro biological activities included acetylcholinesterase (AChE) and butyrylcholinesterase (BuChE) inhibition as well as anti-Aβ aggregation, neuroprotective effects, and metal-chelating properties. The results indicated a highly selective BuChE inhibitory activity with an IC₅₀ value of 21.71 μM for compound 10h as the most potent compound. Besides, compound 10h could inhibit self-induced Aβ_1–42 aggregation and AChE-induced Aβ aggregation with 32.6% and 29.4% inhibition values, respectively. The Lineweaver–Burk plot and molecular modeling study showed that compound 10h targeted both the catalytic active site (CAS) and peripheral anionic site (PAS) of BuChE. It should be noted that compound 10h was able to chelate biometals. Thus, the designed scaffold could be considered as multifunctional agents in AD drug discovery developments.

Harnessing endophenotypes and network medicine for Alzheimer's drug repurposing

Following two decades of more than 400 clinical trials centered on the "one drug, one target, one disease" paradigm, there is still no effective disease-modifying therapy for Alzheimer's disease (AD). The inherent complexity of AD may challenge this reductionist strategy. Recent observations and advances in network medicine further indicate that AD likely shares common underlying mechanisms and intermediate pathophenotypes, or endophenotypes, with other diseases. In this review, we consider AD pathobiology, disease comorbidity, pleiotropy, and therapeutic development, and construct relevant endophenotype networks to guide future therapeutic development. Specifically, we discuss six main endophenotype hypotheses in AD: amyloidosis, tauopathy, neuroinflammation, mitochondrial dysfunction, vascular dysfunction, and lysosomal dysfunction. We further consider how this endophenotype network framework can provide advances in computational and experimental strategies for drug-repurposing and identification of new candidate therapeutic strategies for patients suffering from or at risk for AD. We highlight new opportunities for endophenotype-informed, drug discovery in AD, by exploiting multi-omics data. Integration of genomics, transcriptomics, radiomics, pharmacogenomics, and interactomics (protein-protein interactions) are essential for successful drug discovery. We describe experimental technologies for AD drug discovery including human induced pluripotent stem cells, transgenic mouse/rat models, and population-based retrospective case-control studies that may be integrated with multi-omics in a network medicine methodology. In summary, endophenotype-based network medicine methodologies will promote AD therapeutic development that will optimize the usefulness of available data and support deep phenotyping of the patient heterogeneity for personalized medicine in AD.

Systems pharmacology-based approach to investigate the mechanisms of Danggui-Shaoyao-san prescription for treatment of Alzheimer's disease

Background

Alzheimer’s disease (AD) is the most common cause of dementia in the elderly, characterized by a progressive and irreversible loss of memory and cognitive abilities. Currently, the prevention and treatment of AD still remains a huge challenge. As a traditional Chinese medicine (TCM) prescription, Danggui-Shaoyao-san decoction (DSS) has been demonstrated to be effective for alleviating AD symptoms in animal experiments and clinical applications. However, due to the complex components and biological actions, its underlying molecular mechanism and effective substances are not yet fully elucidated.

Methods

In this study, we firstly systematically reviewed and summarized the molecular effects of DSS against AD based on current literatures of in vivo studies. Furthermore, an integrated systems pharmacology framework was proposed to explore the novel anti-AD mechanisms of DSS and identify the main active components. We further developed a network-based predictive model for identifying the active anti-AD components of DSS by mapping the high-quality AD disease genes into the global drug-target network.

Results

We constructed a global drug-target network of DSS consisting 937 unique compounds and 490 targets by incorporating experimental and computationally predicted drug–target interactions (DTIs). Multi-level systems pharmacology analyses revealed that DSS may regulate multiple biological pathways related to AD pathogenesis, such as the oxidative stress and inflammatory reaction processes. We further conducted a network-based statistical model, drug-likeness analysis, human intestinal absorption (HIA) and blood-brain barrier (BBB) penetration prediction to uncover the key ani-AD ingredients in DSS. Finally, we highlighted 9 key ingredients and validated their synergistic role against AD through a subnetwork.

Conclusion

Overall, this study proposed an integrative systems pharmacology approach to disclose the therapeutic mechanisms of DSS against AD, which also provides novel in silico paradigm for investigating the effective substances of complex TCM prescription.

DL0410 attenuates oxidative stress and neuroinflammation via BDNF/TrkB/ERK/CREB and Nrf2/HO-1 activation

Oxidative stress and neuroinflammation have been deeply associated with Alzheimer's disease. DL0410 is a novel acetylcholinesterase inhibitor with potential anti-oxidative effects in AD-related animal models, while the specific mechanism has not been fully clarified. In this study, DL0410 was predicted to be related to the modification of cell apoptosis, oxidation-reduction process, inflammatory response and ERK1/ERK2 cascade by in silico target fishing and GO enrichment analysis. Then the possible protective effects of DL0410 were evaluated by hydrogen peroxide (H₂O₂)-induced oxidative stress model and lipopolysaccharides (LPS)-induced neuroinflammation model H₂O₂ decreased the viability of SH-SY5Y cells, induced malondialdehyde (MDA) accumulation, mitochondrial membrane potential (Δψm) loss and cell apoptosis, which could be reversed by DL0410 dose-dependently, indicating that DL0410 protected SH-SY5Y cells against H₂O₂-mediated oxidative stress. Western blot analysis showed that DL0410 increased the H₂O₂-triggered down-regulated TrkB, ERK and CREB phosphorylation and the expression of BDNF. In addition, TrkB inhibitor ANA-12, ERK inhibitor SCH772984 and CREB inhibitor 666-15 eliminated the inhibition of DL0410 on MDA accumulation and Δψm loss. Furthermore, DL0410 attenuates inflammatory responses and ROS production in LPS-treated BV2 cells, which is responsible for Nrf2 and HO-1 up-regulation. The present study demonstrates that DL0410 is a potential activator of the BDNF/TrkB/ERK/CREB and Nrf2/HO-1 pathway and may be a potential candidate for regulating oxidative stress and neuroinflammatory response in the brain. Together, the results showed that DL0410 is a promising drug candidate for treating AD and possibly other nervous system diseases associated with oxidative stress and neuroinflammation.

DL0410 ameliorates cognitive deficits in APP/PS1 transgenic mice by promoting synaptic transmission and reducing neuronal loss

At present, few available drugs can be used to either improve pathological features or prevent the progression of Alzheimer's disease (AD). DL0410 ((1,1'-([1,1'-biphenyl]-4,4'-diyl) bis (3-(piperidin-1-yl) propan-1-one) dihydrochloride) is a multiple-target small molecule that has been found to reverse cognitive impairment in different animal models of AD. In this study we evaluated the cognition-improving effects of DL0410 in APP/PS1 transgenic mice and explored the underlying mechanisms. APP/PS1 transgenic mice were administered DL0410 (3, 10, 30 mg· kg-1· d-1, ig) for 2 months. We found that DL0410 administration significantly ameliorated cognitive deficits in both the nest-building and Morris water maze tests. In electrophysiological analysis of hippocampal slices, we showed that DL0410 administration significantly enhanced the field EPSP slope and HFS-induced LTP in CA1 area. Furthermore, we revealed that DL0410 administration significantly increased the phosphorylation of AKT and the activity of GSK-3β in the hippocampus and cortex. Moreover, DL0410 administration dose-dependently increased the expression level of phosphorylated ERK1/2 in the hippocampus and cortex. In addition, DL0410 dose-dependently decreased the neuronal loss by decreasing the production of Aβ deposition, inhibited glial overactivation, and the production of inflammatory cytokines such as TNF-α, IL-1β, and IL-6. We conclude that DL0410 ameliorates cognitive deficits in APP/PS1 transgenic mice by promoting synaptic transmission via activating the AKT/GSK-3β and MAPK/ERK signaling pathway and reducing neuronal loss. DL0410 may be an effective agent for AD treatment in the future.

Rapid, quantitative therapeutic screening for Alzheimer's enzymes enabled by optimal signal transduction with transistors

We show that commercially sourced n-channel silicon field-effect transistors (nFETs) operating above their threshold voltage with closed loop feedback to maintain a constant channel current allow a pH readout resolution of (7.2 ± 0.3) × 10-3 at a bandwidth of 10 Hz, or ≈3-fold better than the open loop operation commonly employed by integrated ion-sensitive field-effect transistors (ISFETs). We leveraged the improved nFET performance to measure the change in solution pH arising from the activity of a pathological form of the kinase Cdk5, an enzyme implicated in Alzheimer's disease, and showed quantitative agreement with previous measurements. The improved pH resolution was realized while the devices were operated in a remote sensing configuration with the pH sensing element off-chip and connected electrically to the FET gate terminal. We compared these results with those measured by using a custom-built dual-gate 2D field-effect transistor (dg2DFET) fabricated with 2D semi-conducting MoS2 channels and a signal amplification of 8. Under identical solution conditions the nFET performance approached the dg2DFETs pH resolution of (3.9 ± 0.7) × 10-3. Finally, using the nFETs, we demonstrated the effectiveness of a custom polypeptide, p5, as a therapeutic agent in restoring the function of Cdk5. We expect that the straight-forward modifications to commercially sourced nFETs demonstrated here will lower the barrier to widespread adoption of these remote-gate devices and enable sensitive bioanalytical measurements for high throughput screening in drug discovery and precision medicine applications.

Protective effects of chondroitin sulphate nano-selenium on a mouse model of Alzheimer's disease

In this study, the effect of chondroitin sulphate nano-selenium (CS@Se) on Alzheimer's disease (AD) in mice was investigated. CS@Se alleviated anxiety and improved the spatial learning and memory impairment in AD mice. CS@Se significantly reduced cell oedema and pyknosis, protected the mitochondria, and improved abnormal changes in the ultrastructure of hippocampal neuron synapses of AD mice. Moreover, CS@Se significantly increased the levels of superoxide dismutase(SOD), glutathione peroxidase (GSH-Px), Na⁺/K⁺-ATPase assay (Na⁺/K⁺-ATPase) and acetyltransferase (ChAT), and decreased the levels of malondialdehyde (MDA) and acetylcholinesterase (ChAE) in AD mice. Western blot results showed that CS@Se can attenuate excessive phosphorylation of tau (Ser396/Ser404) by regulating the expression of glycogen synthase kinase-3 beta (GSK-3β). In addition, CS@Se can activate the extracellular signal-regulated kinase 1/2 (ERK 1/2) and p38 mitogen-activated protein kinase (p38 MAPK) signalling pathways to inhibit nuclear transcription factor kappa B (NF-κB) nuclear translocation, thereby regulating the expression of pro-inflammatory cytokines. In summary, CS@Se can reduce oxidative stress damage, inhibit excessive tau phosphorylation, reduce inflammation to delay AD development, and increase the learning and memory capacities of AD mice.

Discovery of Multitarget-Directed Ligands Against Influenza A Virus From Compound Yizhihao Through a Predictive System for Compound-Protein Interactions

Influenza A virus (IAV) is a threat to public health due to its high mutation rate and resistance to existing drugs. In this investigation, 15 targets selected from an influenza virus–host interaction network were successfully constructed as a multitarget virtual screening system for new drug discovery against IAV using Naïve Bayesian, recursive partitioning, and CDOCKER methods. The predictive accuracies of the models were evaluated using training sets and test sets. The system was then used to predict active constituents of Compound Yizhihao (CYZH), a Chinese medicinal compound used to treat influenza. Twenty-eight compounds with multitarget activities were selected for subsequent in vitro evaluation. Of the four compounds predicted to be active on neuraminidase (NA), chlorogenic acid, and orientin showed inhibitory activity in vitro. Linarin, sinensetin, cedar acid, isoliquiritigenin, sinigrin, luteolin, chlorogenic acid, orientin, epigoitrin, and rupestonic acid exhibited significant effects on TNF-α expression, which is almost consistent with predicted results. Results from a cytopathic effect (CPE) reduction assay revealed acacetin, indirubin, tryptanthrin, quercetin, luteolin, emodin, and apigenin had protective effects against wild-type strains of IAV. Quercetin, luteolin, and apigenin had good efficacy against resistant IAV strains in CPE reduction assays. Finally, with the aid of Gene Ontology biological process analysis, the potential mechanisms of CYZH action were revealed. In conclusion, a compound-protein interaction-prediction system was an efficient tool for the discovery of novel compounds against influenza, and the findings from CYZH provide important information for its usage and development.

LncRNA-miRNA interaction prediction through sequence-derived linear neighborhood propagation method with information combination

BACKGROUND

Researchers discover lncRNAs can act as decoys or sponges to regulate the behavior of miRNAs. Identification of lncRNA-miRNA interactions helps to understand the functions of lncRNAs, especially their roles in complicated diseases. Computational methods can save time and reduce cost in identifying lncRNA-miRNA interactions, but there have been only a few computational methods.

RESULTS

In this paper, we propose a sequence-derived linear neighborhood propagation method (SLNPM) to predict lncRNA-miRNA interactions. First, we calculate the integrated lncRNA-lncRNA similarity and the integrated miRNA-miRNA similarity by combining known lncRNA-miRNA interactions, lncRNA sequences and miRNA sequences. We consider two similarity calculation strategies respectively, namely similarity-based information combination (SC) and interaction profile-based information combination (PC). Second, the integrated lncRNA similarity-based graph and the integrated miRNA similarity-based graph are respectively constructed, and the label propagation processes are implemented on two graphs to score lncRNA-miRNA pairs. Finally, the weighted averages of their outputs are adopted as final predictions. Therefore, we construct two editions of SLNPM: sequence-derived linear neighborhood propagation method based on similarity information combination (SLNPM-SC) and sequence-derived linear neighborhood propagation method based on interaction profile information combination (SLNPM-PC). The experimental results show that SLNPM-SC and SLNPM-PC predict lncRNA-miRNA interactions with higher accuracy compared with other state-of-the-art methods. The case studies demonstrate that SLNPM-SC and SLNPM-PC help to find novel lncRNA-miRNA interactions for given lncRNAs or miRNAs.

CONCLUSION

The study reveals that known interactions bring the most important information for lncRNA-miRNA interaction prediction, and sequences of lncRNAs (miRNAs) also provide useful information. In conclusion, SLNPM-SC and SLNPM-PC are promising for lncRNA-miRNA interaction prediction.

Synthesis of Novel Baicalein Amino Acid Derivatives and Biological Evaluation as Neuroprotective Agents

Baicalein, a famously effective component of the traditional Chinese medicine Rhizoma Huang Qin (Scutellaria altissima L.), has been proved to have potent neuroprotection and anti-platelet aggregation effects with few side effects. Meanwhile, recent studies have revealed that the introduction of amino acid to baicalein could improve its neuroprotective activity. In the present study, a series of novel baicalein amino acid derivatives were designed, synthesized, and screened for their neuroprotective effect against tert-butyl, hydroperoxide-induced, SH-SY5Y neurotoxicity cells and toxicity on the normal H9C2 cell line by standard methylthiazol tetrazolium (MTT) assay. In addition, all of the newly synthesized compounds were characterized by ¹H-NMR, ¹³C-NMR, and high resolution mass spectrometry (HR-MS). The results showed that most of the compounds provided more potent neuroprotection than baicalein, and were equivalent to the positive drug edaravin. They showed no obvious cytotoxicity on normal H9C2 cells. Notably, the most active compound 8 displayed the highest protective effect (50% effective concentration (EC₅₀) = 4.31 μM) against tert-butyl, hydroperoxide-induced, SH-SY5Y neurotoxicity cells, which was much better than the baicalein (EC₅₀ = 24.77 μM) and edaravin (EC₅₀ = 5.62 μM). Further research on the chick chorioallantoic membrane (CAM) model indicated that compound 8 could significantly increase angiogenesis, which might promote neurovascular proliferation. The detection of apoptosis analysis showed that compound 8 could dramatically alleviate morphological manifestations of cell damage. Moreover, the benzyloxycarbonyl (cbz)-protected baicalein amino acid derivatives showed better neuroprotective activity than the t-Butyloxy carbonyl (boc)-protected derivatives.

Competing Endogenous RNA and Coexpression Network Analysis for Identification of Potential Biomarkers and Therapeutics in association with Metastasis Risk and Progression of Prostate Cancer

Prostate cancer (PCa) is the most frequently diagnosed malignant neoplasm in men. Despite the high incidence, the underlying pathogenic mechanisms of PCa are still largely unknown, which limits the therapeutic options and leads to poor prognosis. Herein, based on the expression profiles from The Cancer Genome Atlas (TCGA) database, we investigated the interactions between long noncoding RNA (lncRNA) and mRNA by constructing a competing endogenous RNA network. Several competing endogenous RNAs could participate in the tumorigenesis of PCa. Six lncRNA signatures were identified as potential candidates associated with stage progression by the Kolmogorov-Smirnov test. In addition, 32 signatures from the coexpression network had potential diagnostic value for PCa lymphatic metastasis using machine learning algorithms. By targeting the coexpression network, the antifungal compound econazole was screened out for PCa treatment. Econazole could induce growth restraint, arrest the cell cycle, lead to apoptosis, inhibit migration, invasion, and adhesion in PC3 and DU145 cell lines, and inhibit the growth of prostate xenografts in nude mice. This systematic characterization of lncRNAs, microRNAs, and mRNAs in the risk of metastasis and progression of PCa will aid in the identification of candidate prognostic biomarkers and potential therapeutic drugs.

Targeting HIV/HCV Coinfection Using a Machine Learning-Based Multiple Quantitative Structure-Activity Relationships (Multiple QSAR) Method

Human immunodeficiency virus type-1 and hepatitis C virus (HIV/HCV) coinfection occurs when a patient is simultaneously infected with both human immunodeficiency virus type-1 (HIV-1) and hepatitis C virus (HCV), which is common today in certain populations. However, the treatment of coinfection is a challenge because of the special considerations needed to ensure hepatic safety and avoid drug–drug interactions. Multitarget inhibitors with less toxicity may provide a promising therapeutic strategy for HIV/HCV coinfection. However, the identification of one molecule that acts on multiple targets simultaneously by experimental evaluation is costly and time-consuming. In silico target prediction tools provide more opportunities for the development of multitarget inhibitors. In this study, by combining Naïve Bayes (NB) and support vector machine (SVM) algorithms with two types of molecular fingerprints, MACCS and extended connectivity fingerprints 6 (ECFP6), 60 classification models were constructed to predict compounds that were active against 11 HIV-1 targets and four HCV targets based on a multiple quantitative structure–activity relationships (multiple QSAR) method. Five-fold cross-validation and test set validation were performed to measure the performance of the 60 classification models. Our results show that the 60 multiple QSAR models appeared to have high classification accuracy in terms of the area under the ROC curve (AUC) values, which ranged from 0.83 to 1 with a mean value of 0.97 for the HIV-1 models and from 0.84 to 1 with a mean value of 0.96 for the HCV models. Furthermore, the 60 models were used to comprehensively predict the potential targets of an additional 46 compounds, including 27 approved HIV-1 drugs, 10 approved HCV drugs and nine selected compounds known to be active against one or more targets of HIV-1 or HCV. Finally, 20 hits, including seven approved HIV-1 drugs, four approved HCV drugs, and nine other compounds, were predicted to be HIV/HCV coinfection multitarget inhibitors. The reported bioactivity data confirmed that seven out of nine compounds actually interacted with HIV-1 and HCV targets simultaneously with diverse binding affinities. The remaining predicted hits and chemical-protein interaction pairs with the potential ability to suppress HIV/HCV coinfection are worthy of further experimental investigation. This investigation shows that the multiple QSAR method is useful in predicting chemical-protein interactions for the discovery of multitarget inhibitors and provides a unique strategy for the treatment of HIV/HCV coinfection.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Pharmacokinetics, excretion and metabolites analysis of DL0410, a dual‑acting cholinesterase inhibitor and histamine‑3 receptor antagonist

DL0410, a dual‑action cholinesterase inhibitor and histamine‑3 receptor antagonist with a novel structural scaffold, may be a potential candidate for the treatment of Alzheimer's disease (AD). To the best of the authors' knowledge, this is the first study to demonstrate a reliable method for the measurement of DL0410 in rat plasma, brain, bile, urine and feces samples, and identification of its primary metabolites. The pharmacokinetic properties of DL0410 were analyzed by liquid chromatography‑mass spectrometry at oral doses of 25, 50 and 100 mg/kg and intravenous dose of 5 mg/kg. The investigation of the excretion and metabolism of DL0410 was determined following liquid‑liquid extraction for biliary, urinary and fecal samples. Finally, the cytochrome (CY)P450 isoforms involved in the production of DL0410 metabolites with recombinant human cytochrome P450 enzymes were characterized. The results suggested that DL0410 was not well absorbed; however, was distributed to the entorhinal cortex and hippocampus of the brain. A total of two common metabolites of the reduction of DL0140 in the bile, urine and feces were identified and CYP2D6 was involved in this reaction. The pharmacokinetic results of DL0410 provided information for the illustration of its pharmacodynamic properties, mechanism of action and promoted its continued evaluation as a therapeutic agent for AD treatment.

QSAR-Co: An Open Source Software for Developing Robust Multitasking or Multitarget Classification-Based QSAR Models

Quantitative structure-activity relationships (QSAR) modeling is a well-known computational technique with wide applications in fields such as drug design, toxicity predictions, nanomaterials, etc. However, QSAR researchers still face certain problems to develop robust classification-based QSAR models, especially while handling response data pertaining to diverse experimental and/or theoretical conditions. In the present work, we have developed an open source standalone software "QSAR-Co" (available to download at https://sites.google.com/view/qsar-co ) to setup classification-based QSAR models that allow mining the response data coming from multiple conditions. The software comprises two modules: (1) the Model development module and (2) the Screen/Predict module. This user-friendly software provides several functionalities required for developing a robust multitasking or multitarget classification-based QSAR model using linear discriminant analysis or random forest techniques, with appropriate validation, following the principles set by the Organisation for Economic Co-operation and Development (OECD) for applying QSAR models in regulatory assessments.

In silico Identification and Mechanism Exploration of Hepatotoxic Ingredients in Traditional Chinese Medicine

BACKGROUNDS AND AIMS

Recently, a growing number of hepatotoxicity cases aroused by Traditional Chinese Medicine (TCM) have been reported, causing increasing concern. To date, the reported predictive models for drug induced liver injury show low prediction accuracy and there are still no related reports for hepatotoxicity evaluation of TCM systematically. Additionally, the mechanism of herb induced liver injury (HILI) still remains unknown. The aim of the study was to identify potential hepatotoxic ingredients in TCM and explore the molecular mechanism of TCM against HILI.

MATERIALS AND METHODS

In this study, we developed consensus models for HILI prediction by integrating the best single classifiers. The consensus model with best performance was applied to identify the potential hepatotoxic ingredients from the Traditional Chinese Medicine Systems Pharmacology database (TCMSP). Systems pharmacology analyses, including multiple network construction and KEGG pathway enrichment, were performed to further explore the hepatotoxicity mechanism of TCM.

RESULTS

16 single classifiers were built by combining four machine learning methods with four different sets of fingerprints. After systematic evaluation, the best four single classifiers were selected, which achieved a Matthews correlation coefficient (MCC) value of 0.702, 0.691, 0.659, and 0.717, respectively. To improve the predictive capacity of single models, consensus prediction method was used to integrate the best four single classifiers. Results showed that the consensus model C-3 (MCC = 0.78) outperformed the four single classifiers and other consensus models. Subsequently, 5,666 potential hepatotoxic compounds were identified by C-3 model. We integrated the top 10 hepatotoxic herbs and discussed the hepatotoxicity mechanism of TCM via systems pharmacology approach. Finally, Chaihu was selected as the case study for exploring the molecular mechanism of hepatotoxicity.

CONCLUSION

Overall, this study provides a high accurate approach to predict HILI and an in silico perspective into understanding the hepatotoxicity mechanism of TCM, which might facilitate the discovery and development of new drugs.

Network Pharmacology and Reverse Molecular Docking-Based Prediction of the Molecular Targets and Pathways for Avicularin Against Cancer

AIM AND OBJECTIVE

Avicularin has been found to inhibit the proliferation of HepG-2 cells in vitro in the screening of our laboratory. We intended to explain the molecular mechanism of this effect. Therefore, the combined methods of reverse molecular docking and network pharmacology were used in order to illuminate the molecular mechanisms for Avicularin against cancer.

MATERIALS AND METHODS

Potential targets associated with anti-tumor effects of Avicularin were screened by reverse molecular docking, then a protein database was established through constructing the drugprotein network from literature mining data, and the protein-protein network was built through an in-depth exploration of the relationships between the proteins, and then the network topology analysis was performed. Additionally, gene function and signaling pathways were analyzed by Go bio-enrichment and KEGG Pathway.

RESULTS

The result showed that Avicularin was closely related to 16 targets associated with cancer, and it may significantly influence the pro-survival signals in MAPK signaling pathway that can activate and regulate a series of cellular activities and participate in the regulation of cell proliferation, differentiation, transformation and apoptosis.

CONCLUSION

The network pharmacology strategy used herein provided a powerful means for the mechanisms of action for bioactive ingredients.