AlzPlatform: an Alzheimer's disease domain-specific chemogenomics knowledgebase for polypharmacology and target identification research

Pleiotropy and promiscuity in pharmacogenomics for the treatment of Alzheimer's disease and related risk factors

Patients with Alzheimer's disease are current consumers of polypharmacy with a high risk for drug–drug interactions. Antidementia drugs and other pharmacological treatments for vascular risk factors associated with dementia exert pleiotropic effects which are promiscuously regulated by different gene products. The aim of this review is to highlight the influence of genes involved in pharmacogenetics (i.e., pathogenic, mechanistic, metabolic, transporter and pleiotropic genes) as major determinants of response to treatment in Alzheimer's disease. Patients harboring poor or ultrarapid geno-phenotypes display more irregular profiles in drug efficacy and safety than extensive or intermediate metabolizers. Polymorphic variants of genes associated with lipid metabolism influence the therapeutic response to hypolipemic agents. Understanding these effects is very useful for optimizing polytherapy in dementia.

Have there been improvements in Alzheimer's disease drug discovery over the past 5 years?

INTRODUCTION

Alzheimer's disease (AD) is the most important neurodegenerative disorder with a global cost worldwide of over $700 billion. Pharmacological treatment accounts for 10-20% of direct costs; no new drugs have been approved during the past 15 years; and the available medications are not cost-effective. Areas covered: A massive scrutiny of AD-related PubMed publications (ps)(2013-2017) identified 42,053ps of which 8,380 (19.60%) were associated with AD treatments. The most prevalent pharmacological categories included neurotransmitter enhancers (11.38%), multi-target drugs (2.45%), anti-Amyloid agents (13.30%), anti-Tau agents (2.03%), natural products and derivatives (25.58%), novel drugs (8.13%), novel targets (5.66%), other (old) drugs (11.77%), anti-inflammatory drugs (1.20%), neuroprotective peptides (1.25%), stem cell therapy (1.85%), nanocarriers/nanotherapeutics (1.52%), and others (<1% each). Expert opinion: Unsuccessful outcomes in AD therapeutics are attributed to pathogenic misconceptions, erratic procedures in drug development and inappropriate regulations. Recommendations for the future are as follows: (i) the reconsideration of dominant pathogenic theories, (ii) the identification of reliable biomarkers, (iii) the redefinition of diagnostic criteria, (iv) new guidelines for disease management, (v) the reorientation of drug discovery programs, (vi) the updating of regulatory requirements, (vii) the introduction of pharmacogenomics in drug development and personalized treatments, and (viii) the implementation of preventive programs.

New potent and selective A1 adenosine receptor antagonists as potential tools for the treatment of gastrointestinal diseases

The synthesis of 9-alkyl substituted adenine derivatives presenting aromatic groups and cycloalkyl rings in 8- and N⁶-position, respectively, is reported. The compounds were tested with radioligand binding studies showing, in some cases, a low nanomolar A₁ adenosine receptor affinity and a very good selectivity versus the other adenosine receptor subtypes. Functional assays at human adenosine receptors and at a mouse ileum tissue preparation clearly demonstrate the antagonist profile of these molecules, with inhibitory potency at nanomolar level. A molecular modeling study, consisting in docking analysis at the recently reported A₁ adenosine receptor crystal structure, was performed for the interpretation of the obtained pharmacological results. The N⁶-cyclopentyl-9-methyl-8-phenyladenine (17), resulting the most active derivative of the series (K_i = 2.8 nM and IC₅₀ = 14 nM), was also very efficacious in counteracting the effect of the agonist CCPA on mouse ileum contractility. This new compound represents a tool for the development of new agents for the treatment of intestinal diseases as constipation and postoperative ileus.

Phytochemistry and pharmacology of the genus Leonurus: The herb to benefit the mothers and more

Plants belonging to the genus Leonurus, also named motherwort, are traditionally used for anti-gynecological disorder in East Asia, and for sedative in Europe. Chemical investigation of the genus Leonurus not only enriched the natural products library, but also enlarged the pharmacological application of this traditional herb. In this review, we systematically summarized the structures of 259 compounds isolated from the genus Leonurus, featured with 147 labdane diterpenoids. The reported bioactivity studies up to 2017 are presented in the second part, with the main focus on the isolated compounds and also concerning the extracts. In addition to the traditional uterine contraction and sedative activity, recently the cardiovascular protection effect of leonurine has drawn most attention. Other than that, neuroprotection, anti-inflammation, anti-cancer, anti-platelet aggregation and many other activities have been assigned to various compounds from the genus Leonurus. Among 70 bioactivity references cited in this review, 57% of them were concentrated on two alkaloids (leonurine and stachydrine), whereas only 20% are about the 147 diterpenoids. Anti-inflammation is the major bioactivity discovered so far for the labdane diterpenoids from the genus Leonurus, whose further therapeutic potential still remains for exploration.

The Mechanisms of Bushen-Yizhi Formula as a Therapeutic Agent against Alzheimer's Disease

Bushen-Yizhi prescription (BSYZ) has been an effective traditional Chinese medicine (TCM) prescription in treating Alzheimer’s disease (AD) for hundreds of years. However, the underlying mechanisms have not been fully elucidated yet. In this work, a systems pharmacology approach was developed to reveal the underlying molecular mechanisms of BSYZ in treating AD. First, we obtained 329 candidate compounds of BSYZ by in silico ADME/T filter analysis and 138 AD-related targets were predicted by our in-house WEGA algorithm via mapping predicted targets into AD-related proteins. In addition, we elucidated the mechanisms of BSYZ action on AD through multiple network analysis, including compound-target network analysis and target-function network analysis. Furthermore, several modules regulated by BSYZ were incorporated into AD-related pathways to uncover the therapeutic mechanisms of this prescription in AD treatment. Finally, further verification experiments also demonstrated the therapeutic effects of BSYZ on cognitive dysfunction in APP/PS1 mice, which was possibly via regulating amyloid-β metabolism and suppressing neuronal apoptosis. In conclusion, we provide an integrative systems pharmacology approach to illustrate the underlying therapeutic mechanisms of BSYZ formula action on AD.

Isolation, Synthesis and AChE Inhibitory Potential of Some Novel Cinnamyl Esters of Taraxerol, the Major Metabolite of the Mangrove Bruguiera cylindrica

Systematic chemical screening of the leaves of Bruguiera cylindrica, the tree mangrove of Rhizophoraceae family, afforded five single and pure compounds. The structures of the isolated compounds were established by their spectroscopic data as taraxerol (1), 3β-(E)-coumaroyltaraxerol (2), 3β-(Z)-coumaroyltaraxerol (3), β-sitosterol (4), and eicosanol (5). In view of significant accumulation and interesting biological activities, taraxerol (1) was chemically transformed to synthesize a series of ten cinnamyl esters in very good to excellent yields. The synthesized analogues along with the parent compound were evaluated for their AChE inhibitory potential, BBB permeability and cytotoxicity against Neuro 2A cell line. Among the tested samples, compound 9 showed promising AChE inhibition with significantly low IC₅₀ values, low cytotoxicity and high BBB permeability. Hence, compound 9 can be considered as a lead molecule for further development as potent AChE inhibitor.

The efficacy and safety of cilostazol as an alternative to aspirin in Chinese patients with aspirin intolerance after coronary stent implantation: a combined clinical study and computational system pharmacology analysis

Dual antiplatelet therapy (DAT) with aspirin and clopidogrel is the standard regimen to achieve rapid platelet inhibition and prevent thrombotic events. Currently, little information is available regarding alternative antiplatelet therapy in patients with an allergy or intolerance to aspirin. Although cilostazol is already a common alternative to aspirin in clinical practice in China, its efficacy and safety remain to be determined. We retrospectively analyzed 613 Chinese patients who had undergone primary percutaneous coronary intervention (PCI). Among them, 405 patients received standard DAT (aspirin plus clopidogrel) and 205 patients were identified with intolerance to aspirin and received alternative DAT (cilostazol plus clopidogrel). There were no significant differences between the two groups in their baseline clinical characteristics. The main outcomes of the study included major adverse cardiac events (MACEs) and bleeding events during 12 months of follow-up. The MACEs endpoint was reached in 10 of 205 patients treated with cilostazol (4.9%) and in 34 of 408 patients treated with aspirin (8.3%). No statistically significant difference was observed in MACEs between the two groups. However, patients in the cilostazol group had less restenosis than did patients in the aspirin group (1.5% vs 4.9%, P=0.035). The occurrence of bleeding events tended to be lower in the cilostazol group (0.49% vs 2.7%, P=0.063). These clinical observations were further analyzed using network system pharmacology analysis, and the outcomes were consistent with clinical observations and preclinical data reports. We conclude that in Chinese patients with aspirin intolerance undergoing coronary stent implantation, the combination of clopidogrel with cilostazol may be an efficacious and safe alternative to the standard DAT regimen.

GCDB: a glaucomatous chemogenomics database for in silico drug discovery

Glaucoma is a group of neurodegenerative diseases that can cause irreversible blindness. The current medications, which mainly reduce intraocular pressure to slow the progression of disease, may have local and systemic side effects. Recently, medications with possible neuroprotective effects have attracted much attention. To assist in the identification of new glaucoma drugs, we created a glaucomatous chemogenomics database (GCDB; http://cadd.pharmacy.nankai.edu.cn/gcdb/home) in which various glaucoma-related chemogenomics data records are assembled, including 275 genes, 105 proteins, 83 approved or clinical trial drugs, 90 206 chemicals associated with 213 093 records of reported bioactivities from 22 324 corresponding bioassays and 5630 references. Moreover, an improved chemical similarity ensemble approach computational algorithm was incorporated in the GCDB to identify new targets and design new drugs. Further, we demonstrated the application of GCDB in a case study screening two chemical libraries, Maybridge and Specs, to identify interactions between small molecules and glaucoma-related proteins. Finally, six and four compounds were selected from the final hits for in vitro human glucocorticoid receptor (hGR) and adenosine A3 receptor (A3AR) inhibitory assays, respectively. Of these compounds, six were shown to have inhibitory activities against hGR, with IC50 values ranging from 2.92-28.43 μM, whereas one compoundshowed inhibitory activity against A3AR, with an IC50 of 6.15 μM. Overall, GCDB will be helpful in target identification and glaucoma chemogenomics data exchange and sharing, and facilitate drug discovery for glaucoma treatment.

ProSelection: A Novel Algorithm to Select Proper Protein Structure Subsets for in Silico Target Identification and Drug Discovery Research

Molecular docking is widely applied to computer-aided drug design and has become relatively mature in the recent decades. Application of docking in modeling varies from single lead compound optimization to large-scale virtual screening. The performance of molecular docking is highly dependent on the protein structures selected. It is especially challenging for large-scale target prediction research when multiple structures are available for a single target. Therefore, we have established ProSelection, a docking preferred-protein selection algorithm, in order to generate the proper structure subset(s). By the ProSelection algorithm, protein structures of "weak selectors" are filtered out whereas structures of "strong selectors" are kept. Specifically, the structure which has a good statistical performance of distinguishing active ligands from inactive ligands is defined as a strong selector. In this study, 249 protein structures of 14 autophagy-related targets are investigated. Surflex-dock was used as the docking engine to distinguish active and inactive compounds against these protein structures. Both t test and Mann-Whitney U test were used to distinguish the strong from the weak selectors based on the normality of the docking score distribution. The suggested docking score threshold for active ligands (SDA) was generated for each strong selector structure according to the receiver operating characteristic (ROC) curve. The performance of ProSelection was further validated by predicting the potential off-targets of 43 U.S. Federal Drug Administration approved small molecule antineoplastic drugs. Overall, ProSelection will accelerate the computational work in protein structure selection and could be a useful tool for molecular docking, target prediction, and protein-chemical database establishment research.

Coordinated Splicing of Regulatory Detained Introns within Oncogenic Transcripts Creates an Exploitable Vulnerability in Malignant Glioma

Glioblastoma (GBM) is a devastating malignancy with few therapeutic options. We identify PRMT5 in an in vivo GBM shRNA screen and show that PRMT5 knockdown or inhibition potently suppresses in vivo GBM tumors, including patient-derived xenografts. Pathway analysis implicates splicing in cellular PRMT5 dependency, and we identify a biomarker that predicts sensitivity to PRMT5 inhibition. We find that PRMT5 deficiency primarily disrupts the removal of detained introns (DIs). This impaired DI splicing affects proliferation genes, whose downregulation coincides with cell cycle defects, senescence and/or apoptosis. We further show that DI programs are evolutionarily conserved and operate during neurogenesis, suggesting that they represent a physiological regulatory mechanism. Collectively, these findings reveal a PRMT5-regulated DI-splicing program as an exploitable cancer vulnerability.

Valorisation of softwood bark through extraction of utilizable chemicals. A review

Softwood bark is an important source for producing chemicals and materials as well as bioenergy. Extraction is regarded as a key technology for obtaining chemicals in general, and valorizing bark as a source of such chemicals in particular. In this paper, properties of 237 compounds identified in various studies dealing with extraction of softwood bark were described. Finally, some challenges and perspectives on the production of chemicals from bark are discussed.

Novel 4-thiazolidinone derivatives as agonists of benzodiazepine receptors: Design, synthesis and pharmacological evaluation

A new series of 4-chloro-N-(2-(substitutedphenyl)-4-oxothiazolidin-3-yl)-2-phenoxybenzamide derivatives were designed, synthesized and biologically evaluated as anticonvulsant agents. The designed compounds have the main essential functional groups for binding to the benzodiazepine receptors and 4-thiazolidinone ring as an anticonvulsant pharmacophore. Some of the new synthesized compounds showed considerable anticonvulsant activity in electroshock and pentylenetetrazole-induced lethal convulsion tests. Compound 5i, 4-chloro-N-(2-(4-methoxyphenyl)-4-oxothiazolidin-3-yl)-2-phenoxybenzamide, with the best activity was selected for evaluation of other benzodiazepine pharmacological effects. This compound induced significant sedative-hypnotic activity. However, it does not impair the learning and memory in the experimental condition. Flumazenil was able to antagonize the sedative-hypnotic and anticonvulsant effects of compound 5i indicating that benzodiazepine receptors are highly involved in the pharmacological properties of the novel compounds.

Open chemoinformatic resources to explore the structure, properties and chemical space of molecules

Open chemoinformatic servers facilitate analysis of chemical space and structure–activity relationships.

StemCellCKB: An Integrated Stem Cell-Specific Chemogenomics KnowledgeBase for Target Identification and Systems-Pharmacology Research

Given the capacity of self-renewal and multilineage differentiation, stem cells are promising sources for use in regenerative medicines as well as in the clinical treatment of certain hematological malignancies and degenerative diseases. Complex networks of cellular signaling pathways largely determine stem cell fate and function. Small molecules that modulate these pathways can provide important biological and pharmacological insights. However, it is still challenging to identify the specific protein targets of these compounds, to explore the changes in stem cell phenotypes induced by compound treatment and to ascertain compound mechanisms of action. To facilitate stem cell related small molecule study and provide a better understanding of the associated signaling pathways, we have constructed a comprehensive domain-specific chemogenomics resource, called StemCellCKB ( http://www.cbligand.org/StemCellCKB/ ). This new cloud-computing platform describes the chemical molecules, genes, proteins, and signaling pathways implicated in stem cell regulation. StemCellCKB is also implemented with web applications designed specifically to aid in the identification of stem cell relevant protein targets, including TargetHunter, a machine-learning algorithm for predicting small molecule targets based on molecular fingerprints, and HTDocking, a high-throughput docking module for target prediction and systems-pharmacology analyses. We have systematically tested StemCellCKB to verify data integrity. Target-prediction accuracy has also been validated against the reported known target/compound associations. This proof-of-concept example demonstrates that StemCellCKB can (1) accurately predict the macromolecular targets of existing stem cell modulators and (2) identify novel small molecules capable of probing stem cell signaling mechanisms, for use in systems-pharmacology studies. StemCellCKB facilitates the exploration and exchange of stem cell chemogenomics data among members of the broader research community.

Cardiovascular Disease Chemogenomics Knowledgebase-guided Target Identification and Drug Synergy Mechanism Study of an Herbal Formula

Combination therapy is a popular treatment for various diseases in the clinic. Among the successful cases, Traditional Chinese Medicinal (TCM) formulae can achieve synergistic effects in therapeutics and antagonistic effects in toxicity. However, characterizing the underlying molecular synergisms for the combination of drugs remains a challenging task due to high experimental expenses and complication of multicomponent herbal medicines. To understand the rationale of combination therapy, we investigated Sini Decoction, a well-known TCM consisting of three herbs, as a model. We applied our established diseases-specific chemogenomics databases and our systems pharmacology approach TargetHunter to explore synergistic mechanisms of Sini Decoction in the treatment of cardiovascular diseases. (1) We constructed a cardiovascular diseases-specific chemogenomics database, including drugs, target proteins, chemicals, and associated pathways. (2) Using our implemented chemoinformatics tools, we mapped out the interaction networks between active ingredients of Sini Decoction and their targets. (3) We also in silico predicted and experimentally confirmed that the side effects can be alleviated by the combination of the components. Overall, our results demonstrated that our cardiovascular disease-specific database was successfully applied for systems pharmacology analysis of a complicated herbal formula in predicting molecular synergetic mechanisms, and led to better understanding of a combinational therapy.

A Perspective on Implementing a Quantitative Systems Pharmacology Platform for Drug Discovery and the Advancement of Personalized Medicine

Drug candidates exhibiting well-defined pharmacokinetic and pharmacodynamic profiles that are otherwise safe often fail to demonstrate proof-of-concept in phase II and III trials. Innovation in drug discovery and development has been identified as a critical need for improving the efficiency of drug discovery, especially through collaborations between academia, government agencies, and industry. To address the innovation challenge, we describe a comprehensive, unbiased, integrated, and iterative quantitative systems pharmacology (QSP)-driven drug discovery and development strategy and platform that we have implemented at the University of Pittsburgh Drug Discovery Institute. Intrinsic to QSP is its integrated use of multiscale experimental and computational methods to identify mechanisms of disease progression and to test predicted therapeutic strategies likely to achieve clinical validation for appropriate subpopulations of patients. The QSP platform can address biological heterogeneity and anticipate the evolution of resistance mechanisms, which are major challenges for drug development. The implementation of this platform is dedicated to gaining an understanding of mechanism(s) of disease progression to enable the identification of novel therapeutic strategies as well as repurposing drugs. The QSP platform will help promote the paradigm shift from reactive population-based medicine to proactive personalized medicine by focusing on the patient as the starting and the end point.

One for All? Hitting Multiple Alzheimer's Disease Targets with One Drug

HIGHLIGHTS Many AD target combinations are being explored for multi-target drug design.New databases and models increase the potential of computational drug designLiraglutide and other antidiabetics are strong candidates for repurposing to AD.Donecopride a dual 5-HT/AChE inhibitor shows promise in pre-clinical studies Alzheimer's Disease is a complex and multifactorial disease for which the mechanism is still not fully understood. As new insights into disease progression are discovered, new drugs must be designed to target those aspects of the disease that cause neuronal damage rather than just the symptoms currently addressed by single target drugs. It is becoming possible to target several aspects of the disease pathology at once using multi-target drugs (MTDs). Intended as an introduction for non-experts, this review describes the key MTD design approaches, namely structure-based, in silico, and data-mining, to evaluate what is preventing compounds progressing through the clinic to the market. Repurposing current drugs using their off-target effects reduces the cost of development, time to launch, and the uncertainty associated with safety and pharmacokinetics. The most promising drugs currently being investigated for repurposing to Alzheimer's Disease are rasagiline, originally developed for the treatment of Parkinson's Disease, and liraglutide, an antidiabetic. Rational drug design can combine pharmacophores of multiple drugs, systematically change functional groups, and rank them by virtual screening. Hits confirmed experimentally are rationally modified to generate an effective multi-potent lead compound. Examples from this approach are ASS234 with properties similar to rasagiline, and donecopride, a hybrid of an acetylcholinesterase inhibitor and a 5-HT4 receptor agonist with pro-cognitive effects. Exploiting these interdisciplinary approaches, public-private collaborative lead factories promise faster delivery of new drugs to the clinic.

Polypharmacology: in silico methods of ligand design and development

How to design a ligand to bind multiple targets, rather than to a single target, is the focus of this review. Rational polypharmacology draws on knowledge that is both broad ranging and hierarchical. Computer-aided multitarget ligand design methods are described according to their nested knowledge level. Ligand-only and then receptor-ligand strategies are first described; followed by the metabolic network viewpoint. Subsequently strategies that view infectious diseases as multigenomic targets are discussed, and finally the disease level interpretation of medicinal therapy is considered. As yet there is no consensus on how best to proceed in designing a multitarget ligand. The current methodologies are bought together in an attempt to give a practical overview of how polypharmacology design might be best initiated.

In Vitro and In Vivo Characterization of the Alkaloid Nuciferine

Rationale

The sacred lotus (Nelumbo nucifera) contains many phytochemicals and has a history of human use. To determine which compounds may be responsible for reported psychotropic effects, we used in silico predictions of the identified phytochemicals. Nuciferine, an alkaloid component of Nelumbo nucifera and Nymphaea caerulea, had a predicted molecular profile similar to antipsychotic compounds. Our study characterizes nuciferine using in vitro and in vivo pharmacological assays.

Methods

Nuciferine was first characterized in silico using the similarity ensemble approach, and was followed by further characterization and validation using the Psychoactive Drug Screening Program of the National Institute of Mental Health. Nuciferine was then tested in vivo in the head-twitch response, pre-pulse inhibition, hyperlocomotor activity, and drug discrimination paradigms.

Results

Nuciferine shares a receptor profile similar to aripiprazole-like antipsychotic drugs. Nuciferine was an antagonist at 5-HT_2A, 5-HT_2C, and 5-HT_2B, an inverse agonist at 5-HT₇, a partial agonist at D_2, D₅ and 5-HT₆, an agonist at 5-HT_1A and D₄ receptors, and inhibited the dopamine transporter. In rodent models relevant to antipsychotic drug action, nuciferine blocked head-twitch responses and discriminative stimulus effects of a 5-HT_2A agonist, substituted for clozapine discriminative stimulus, enhanced amphetamine induced locomotor activity, inhibited phencyclidine (PCP)-induced locomotor activity, and rescued PCP-induced disruption of prepulse inhibition without induction of catalepsy.

Conclusions

The molecular profile of nuciferine was similar but not identical to that shared with several approved antipsychotic drugs suggesting that nuciferine has atypical antipsychotic-like actions.

Advances in recent patent and clinical trial drug development for Alzheimer's disease

Alzheimer's disease (AD) is a progressive neurodegenerative disease, involving a large number of genes, proteins and their complex interactions. Currently, no effective therapeutic agents are available to either stop or reverse the progression of this disease, likely due to its polygenic nature. The complicated pathophysiology of AD remains unresolved. Although it has been hypothesized that the amyloid β cascade and the hyper-phosphorylated tau protein may be primarily involved, other mechanisms, such as oxidative stress, deficiency of central cholinergic neurotransmitter, mitochondrial dysfunction and inflammation have also been implicated. The main focus of this review is to document current therapeutic agents in clinical trials and patented candidate compounds under development based on their main mechanisms of action. It also discusses the relationship between the recent understanding of key targets and the development of potential therapeutic agents for the treatment of AD.

A novel strategy of profiling the mechanism of herbal medicines by combining network pharmacology with plasma concentration determination and affinity constant measurement

Herbal medicines have long been widely used in the treatment of various complex diseases in China.

Alzheimer's disease drug development based on Computer-Aided Drug Design

Alzheimer's disease (AD) is a common neurodegenerative disorder characterized by the excessive deposition of amyloids in the brain. The pathological features mainly include the extracellular amyloid plaques and intracellular neurofibrillary tangles, which are the production of amyloid precursor protein (APP) processed by the α-, β- and γ-secretases. Based on the amyloid cascade hypotheses of AD, a large number of amyloid-β agents and secretase inhibitors against AD have been recently developed by using computational methods. This review article describes pathophysiology of AD and the structure of the Aβ plaques, β- and γ-secretases, and discusses the recent advances in the development of the amyloid agents for AD therapy and diagnosis by using Computer-Aided Drug Design approach.

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

To determine chemical-protein interactions (CPI) is costly, time-consuming, and labor-intensive. In silico prediction of CPI can facilitate the target identification and drug discovery. Although many in silico target prediction tools have been developed, few of them could predict active molecules against multitarget for a single disease. In this investigation, naive Bayesian (NB) and recursive partitioning (RP) algorithms were applied to construct classifiers for predicting the active molecules against 25 key targets toward Alzheimer's disease (AD) using the multitarget-quantitative structure-activity relationships (mt-QSAR) method. Each molecule was initially represented with two kinds of fingerprint descriptors (ECFP6 and MACCS). One hundred classifiers were constructed, and their performance was evaluated and verified with internally 5-fold cross-validation and external test set validation. The range of the area under the receiver operating characteristic curve (ROC) for the test sets was from 0.741 to 1.0, with an average of 0.965. In addition, the important fragments for multitarget against AD given by NB classifiers were also analyzed. Finally, the validated models were employed to systematically predict the potential targets for six approved anti-AD drugs and 19 known active compounds related to AD. The prediction results were confirmed by reported bioactivity data and our in vitro experimental validation, resulting in several multitarget-directed ligands (MTDLs) against AD, including seven acetylcholinesterase (AChE) inhibitors ranging from 0.442 to 72.26 μM and four histamine receptor 3 (H3R) antagonists ranging from 0.308 to 58.6 μM. To be exciting, the best MTDL DL0410 was identified as an dual cholinesterase inhibitor with IC50 values of 0.442 μM (AChE) and 3.57 μM (BuChE) as well as a H3R antagonist with an IC50 of 0.308 μM. This investigation is the first report using mt-QASR approach to predict chemical-protein interaction for a single disease and discovering highly potent MTDLs. This protocol may be useful for in silico multitarget prediction of other diseases.