A robust CETSA data analysis automation workflow for routine screening.

The Cellular Thermal Shift Assay (CETSA) enables the study of protein-ligand interactions in a cellular context. It provides valuable information on the binding affinity and specificity of both small and large molecule ligands in a relevant physiological context, hence forming a unique tool in drug discovery. Though high-throughput lab protocols exist for scaling up CETSA, subsequent data analysis and quality control remain laborious and limit experimental throughput. Here, we introduce a scalable and robust data analysis workflow which allows integration of CETSA into routine high throughput screening (HT-CETSA). This new workflow automates data analysis and incorporates quality control (QC), including outlier detection, sample and plate QC, and result triage. We describe the workflow and show its robustness against typical experimental artifacts, show scaling effects, and discuss the impact of data analysis automation by eliminating manual data processing steps.

SB-Net: Synergizing CNN and LSTM networks for uncovering retrosynthetic pathways in organic synthesis.

Retrosynthesis is vital in synthesizing target products, guiding reaction pathway design crucial for drug and material discovery. Current models often neglect multi-scale feature extraction, limiting efficacy in leveraging molecular descriptors. Our proposed SB-Net model, a deep-learning architecture tailored for retrosynthesis prediction, addresses this gap. SB-Net combines CNN and Bi-LSTM architectures, excelling in capturing multi-scale molecular features. It integrates parallel branches for processing one-hot encoded descriptors and ECFP, merging through dense layers. Experimental results demonstrate SB-Net's superiority, achieving 73.6 % top-1 and 94.6 % top-10 accuracy on USPTO-50k data. Versatility is validated on MetaNetX, with rates of 52.8 % top-1, 74.3 % top-3, 79.8 % top-5, and 83.5 % top-10. SB-Net's success in bioretrosynthesis prediction tasks indicates its efficacy. This research advances computational chemistry, offering a robust deep-learning model for retrosynthesis prediction. With implications for drug discovery and synthesis planning, SB-Net promises innovative and efficient pathways.

International Union of Basic and Clinical Pharmacology. CXV: The Class F of G Protein-Coupled Receptors.

The class F of G protein-coupled receptors (GPCRs) consists of ten Frizzleds (FZD1-10) and Smoothened (SMO). FZDs bind and are activated by secreted lipoglycoproteins of the Wingless/Int-1 (WNT) family and SMO is indirectly activated by the Hedgehog (Hh) family of morphogens acting on the transmembrane protein Patched (PTCH). The advance of our understanding of FZDs and SMO as dynamic transmembrane receptors and molecular machines, which emerged during the past 14 years since the first class F GPCR IUPHAR nomenclature report, justifies an update. This article focuses on the advances in molecular pharmacology and structural biology providing new mechanistic insight into ligand recognition, receptor activation mechanisms, signal initiation and signal specification. Furthermore, class F GPCRs continue to develop as drug targets, and novel technologies and tools such as genetically encoded biosensors and CRISP/Cas9 edited cell systems have contributed to refined functional analysis of these receptors. Also, advances in crystal structure analysis and cryogenic electron microscopy contribute to a rapid development of our knowledge about structure-function relationships providing a great starting point for drug development. Despite the progress questions and challenges remain to fully understand the complexity of the WNT/FZD and Hh/SMO signaling systems. Significance Statement The recent years of research have brought about substantial functional and structural insight into mechanisms of activation of Frizzleds and Smoothened. While the advance furthers our mechanistic understanding of ligand recognition, receptor activation, signal specification and initiation, broader opportunities emerge that allow targeting class F GPCRs for therapy and regenerative medicine employing both biologics and small molecule compounds.

Many locks to one key: N-acetylneuraminic acid binding to proteins.

Sialic acids play crucial roles in cell surface glycans of both eukaryotic and prokaryotic organisms, mediating various biological processes, including cell-cell interactions, development, immune response, oncogenesis and host-pathogen interactions. This review focuses on the ß-anomeric form of N-acetylneuraminic acid (Neu5Ac), particularly its binding affinity towards various proteins, as elucidated by solved protein structures. Specifically, we delve into the binding mechanisms of Neu5Ac to proteins involved in sequestering and transporting Neu5Ac in Gram-negative bacteria, with implications for drug design targeting these proteins as antimicrobial agents. Unlike the initial assumptions, structural analyses revealed significant variability in the Neu5Ac binding pockets among proteins, indicating diverse evolutionary origins and binding modes. By comparing these findings with existing structures from other systems, we can effectively highlight the intricate relationship between protein structure and Neu5Ac recognition, emphasizing the need for tailored drug design strategies to inhibit Neu5Ac-binding proteins across bacterial species.

Distinct functional and molecular profiles between physiological and pathological atrial enlargement offer potential new therapeutic opportunities for atrial fibrillation.

Atrial fibrillation (AF) remains challenging to prevent and treat. A key feature of AF is atrial enlargement. However, not all atrial enlargement progresses to AF. Atrial enlargement in response to physiological stimuli such as exercise is typically benign and reversible. Understanding the differences in atrial function and molecular profile underpinning pathological and physiological atrial remodelling will be critical for identifying new strategies for AF. The discovery of molecular mechanisms responsible for pathological and physiological ventricular hypertrophy has uncovered new drug targets for heart failure. Studies in the atria have been limited in comparison. Here, we characterised mouse atria from 1) a pathological model (cardiomyocyte-specific transgenic (Tg) that develops dilated cardiomyopathy [DCM] and AF due to reduced protective signalling [PI3K]; DCM-dnPI3K), and 2) a physiological model (cardiomyocyte-specific Tg with an enlarged heart due to increased insulin-like growth factor 1 receptor; IGF1R). Both models presented with an increase in atrial mass, but displayed distinct functional, cellular, histological and molecular phenotypes. Atrial enlargement in the DCM-dnPI3K Tg, but not IGF1R Tg, was associated with atrial dysfunction, fibrosis and a heart failure gene expression pattern. Atrial proteomics identified protein networks related to cardiac contractility, sarcomere assembly, metabolism, mitochondria, and extracellular matrix which were differentially regulated in the models; many co-identified in atrial proteomics data sets from human AF. In summary, physiological and pathological atrial enlargement are associated with distinct features, and the proteomic dataset provides a resource to study potential new regulators of atrial biology and function, drug targets and biomarkers for AF.

Imaging Assays to Detect DNA Damage in Trypanosome Parasites Using γH2A.

Diseases caused by trypanosomatid parasites remain a significant unmet medical need for millions of people globally. Trypanosomatid parasites such as Trypanosoma cruzi and subspecies of Trypanosoma brucei cause Chagas disease and human African trypanosomiasis (HAT), respectively. Although efforts to find novel treatments have been successful for HAT, Chagas disease is still treated with decades-old therapies that suffer from long treatment durations and severe safety concerns. We recently described the identification and characterization of the cyanotriazole compound class that kills trypanosomes, in vitro and in vivo, by selective inhibition of the trypanosome nuclear topoisomerase II enzyme. To evaluate whether inhibition of the topoisomerase II enzyme led to parasite death due to lethal double-strand DNA breaks, we developed assays for detecting DNA damage in both intracellular amastigotes of T. cruzi and bloodstream-form T. brucei by using the canonical DNA damage marker γH2A. Herein, this article describes the protocols for detecting DNA damage using an immunofluorescence assessment of γH2A by microscopy in trypanosome parasites. Key features • Immunofluorescence-based assay to detect the γH2A response in T. brucei and T. cruzi parasites. • Robust DNA damage pathway-based cellular assays to evaluate topoisomerase II poisons' ability to cause DNA damage. • A 384-well plate-based T. cruzi protocol allows high-resolution and high-throughput evaluation of compounds that cause DNA damage by measuring γH2A in intracellular parasites. • This assay could be modifiable for evaluation of DNA damage responses in various intracellular and extracellular eukaryotic pathogens.

Network Pharmacology Reveals Key Targets and Pathways of Madhuca longifolia for Potential Alzheimer's Disease Treatment.

Madhuca longifolia, commonly known as the mahua tree, has been traditionally used in medicine due to its anti-inflammatory, anti-diabetic, and antimicrobial properties. Its active compounds help in managing diabetes, alleviating cognitive impairment associated with Alzheimer's disease. Nonetheless, the exact neuroprotective mechanism of Madhuca longifolia against Alzheimer's disease remains unclear. This study looked into possible methods by which Madhuca longifolia protects against Alzheimer's disease using network pharmacology, molecular docking and molecular dynamic simulations studies. By applying pre-screening of active constituents, target prediction, Gene Ontology (GO) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathway enrichment analysis, our study found that Madhuca longifolia is related to eight active ingredients (Ascorbic acid, Riboflavin, Pantothenic acid, (4 R)-2beta,3beta,23-trihydroxy-oleana-5,12-dien-28-oic acid, Quercetin, Nicotinic acid, Bassiaic acid Thiamine) and 272 common gene targets, with significant involvement in pathways such as PI3K-Akt signaling and neuroactive ligand-receptor interaction. Network analysis demonstrated how Madhuca longifolia can prevent AD by modifying important signalling networks, which may be one of the molecular mechanisms driving the plant's effectiveness against the disease. Molecular docking studies revealed that there were robust binding abilities of Quercetin, Riboflavin and Pantothenic acid to key target proteins AKT1, JUN, and STAT3. Later, molecular dynamic simulations was done to examine the successful activity of the active compounds against potential targets, and it was found that AKT1 and AKT1-Quercetin complex became stable at 260 ps. It may be seen through the study that quercetin may act as a good inhibitor for treatment. This thorough investigation provides a strong basis for future research and development efforts by advancing our understanding of Madhuca longifolia medicinal potential in Alzheimer's disease.

Thymoquinone, artemisinin, and thymol attenuate proliferation of lung cancer cells as Sphingosine kinase 1 inhibitors.

Sphingosine-1-phosphate (S1P) formed via catalytic actions of sphingosine kinase 1 (SphK1) behaves as a pro-survival substance and activates downstream target molecules associated with various pathologies, including initiation, inflammation, and progression of cancer. Here, we aimed to investigate the SphK1 inhibitory potentials of thymoquinone (TQ), Artemisinin (AR), and Thymol (TM) for the therapeutic management of lung cancer. We implemented docking, molecular dynamics (MD) simulations, enzyme inhibition assay, and fluorescence measurement studies to estimate binding affinity and SphK1 inhibitory potential of TQ, AR, and TM. We further investigated the anti-cancer potential of these compounds on non-small cell lung cancer (NSCLC) cell lines (H1299 and A549), followed by estimation of mitochondrial ROS, mitochondrial membrane potential depolarization, and cleavage of DNA by comet assay. Enzyme activity and fluorescence binding studies suggest that TQ, AR, and TM significantly inhibit the activity of SphK1 with IC50 values of 35.52 µM, 42.81 µM, and 53.68 µM, respectively, and have an excellent binding affinity. TQ shows cytotoxic effect and anti-proliferative potentials on H1299 and A549 with an IC50 value of 27.96 µM and 54.43 µM, respectively. Detection of mitochondrial ROS and mitochondrial membrane potential depolarization shows promising TQ-induced oxidative stress on H1299 and A549 cell lines. Comet assay shows promising TQ-induced oxidative DNA damage. In conclusion, TQ, AR, and TM act as potential inhibitors for SphK1, with a strong binding affinity. In addition, the cytotoxicity of TQ is linked to oxidative stress due to mitochondrial ROS generation. Overall, our study suggests that TQ is a promising inhibitor of SphK1 targeting lung cancer therapy.

Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery.

INTRODUCTION: Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy - profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology. AREAS COVERED: This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples. EXPERT OPINION: Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms - which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

Applications of CRISPR in Parasitology.

Clustered Regions of Interspersed Palindromic Repeat (CRISPR)-based techniques have been utilized in various research areas, including agriculture, biotechnology, and medicine. With the use of a short sequence guide RNA and CRISPR-associated (Cas) protein, this technique allows for robust, site-specific manipulation of the genome, aiding researchers in making important biomedical discoveries and scientific advancements. In this review, we explored the applications of CRISPR/Cas systems in the field of parasitology for the identification and validation of novel functional genes, diagnosis of parasitic infections, reduction of parasite virulence, and the disruption of disease transmission. We also discussed how CRISPR can be used for the development of therapeutics, vaccines, and drug discovery. Furthermore, the challenges and future perspectives of this technology are also highlighted.

Multi-year analysis of the global preclinical antibacterial pipeline: trends and gaps.

Antimicrobial resistance (AMR) is a major global health threat estimated to have caused the deaths of 1.27 million people in 2019, which is more than HIV/AIDS and malaria deaths combined. AMR also has significant consequences on the global economy. If not properly addressed, AMR could immensely impact the world's economy, further increasing the poverty burden in low- and middle-income countries. To mitigate the risk of a post-antibiotic society, where the ability to effectively treat common bacterial infections is being severely threatened, it is necessary to establish a continuous supply of new and novel antibacterial medicines. However, there are gaps in the current pipeline that will prove difficult to address, given the time required to develop new agents. To understand the status of upstream antibiotic development and the challenges faced by drug developers in the early development stage, the World Health Organization has regularly assessed the preclinical and clinical antibacterial development pipeline. The review identifies potential new classes of antibiotics or novel mechanisms of action that can better address resistant bacterial strains. This proactive approach is necessary to stay ahead of evolving resistance patterns and to support the availability of effective treatment options. This review examines the trends in preclinical development and attempts to identify gaps and potential opportunities to overcome the numerous hurdles in the early stages of the antibacterial research and development space.

Computational approaches for lead compound discovery in dipeptidyl peptidase-4 inhibition using machine learning and molecular dynamics techniques.

The prediction of possible lead compounds from already-known drugs that may present DPP-4 inhibition activity imply a advantage in the drug development in terms of time and cost to find alternative medicines for the treatment of Type 2 Diabetes Mellitus (T2DM). The inhibition of dipeptidyl peptidase-4 (DPP-4) has been one of the most explored strategies to develop potential drugs against this condition. A diverse dataset of molecules with known experimental inhibitory activity against DPP-4 was constructed and used to develop predictive models using different machine-learning algorithms. Model M36 is the most promising one based on the internal and external performance showing values of Q2CV = 0.813, and Q2EXT = 0.803. The applicability domain evaluation and Tropsha's analysis were conducted to validate M36, indicating its robustness and accuracy in predicting pIC50 values for organic molecules within the established domain. The physicochemical properties of the ligands, including electronegativity, polarizability, and van der Waals volume were relevant to predict the inhibition process. The model was then employed in the virtual screening of potential DPP4 inhibitors, finding 448 compounds from the DrugBank and 9 from DiaNat with potential inhibitory activity. Molecular docking and molecular dynamics simulations were used to get insight into the ligand-protein interaction. From the screening and the favorable molecular dynamic results, several compounds including Skimmin (pIC50 = 3.54, Binding energy = -8.86 kcal/mol), bergenin (pIC50 = 2.69, Binding energy = -13.90 kcal/mol), and DB07272 (pIC50 = 3.97, Binding energy = -25.28 kcal/mol) seem to be promising hits to be tested and optimized in the treatment of T2DM. This results imply a important reduction in cost and time on the application of this drugs because all the information about the its metabolism is already available.

Small molecule agents against alopecia: Potential targets and related pathways.

Alopecia has emerged as a global concern, extending beyond the middle-aged and elderly population and increasingly affecting younger individuals. Despite its growing prevalence, the treatment options and effective drugs for alopecia remain limited due to the incomplete understanding of its underlying mechanisms. Therefore, it is urgent to explore the pathogenesis of alopecia and discover novel and safer therapeutic agents. This review provided an overview of the prevailing clinical disorders of alopecia, and the key pathways and targets involved in hair growth process. Additionally, it discusses FDA-approved drugs and clinical candidates for the treatment of alopecia, and explores small molecule compounds with anti-alopecia potential in the drug discovery phase. These endeavors are expected to provide researchers with valuable scientific insights and practical information for anti-alopecia drug discovery.

Synthesis, Anticancer Activity, and Molecular Docking of New 1,2,3-Triazole Linked Tetrahydrocurcumin Derivatives.

Cancer is one of the deadliest diseases to humanity. There is significant progress in treating this disease, but developing some drugs that can fight this disease remains a challenge in the field of medical research. Thirteen new 1,2,3-triazole linked tetrahydrocurcumin derivatives were synthesized by click reaction, including a 1,3-dipolar cycloaddition reaction of tetrahydrocurcumin baring mono-alkyne with azides in good yields, and their in vitro anticancer activity against four cancer cell lines, including human cervical carcinoma (HeLa), human lung adenocarcinoma (A549), human hepatoma carcinoma (HepG2), and human colon carcinoma (HCT-116) were investigated using MTT(3-(4,5-dimethylthiazole-2-yl)-2,5-diphenyltetraz-olium bromide) assay. The newly synthesized compounds had their structures identified using NMR HRMS and IR techniques. Some of prepared compounds, including compounds 4g and 4k, showed potent cytotoxic activity against four cancer cell lines compared to the positive control of cisplatin and tetrahydrocurcumin. Compound 4g exhibited anticancer activity with a IC50 value of 1.09 ± 0.17 µM against human colon carcinoma HCT-116 and 45.16 ± 0.92 µM against A549 cell lines compared to the positive controls of tetrahydrocurcumin and cisplatin. Moreover, further biological examination in HCT-116 cells showed that compound 4g can arrest the cell cycle at the G1 phase. A docking study revealed that the potential mechanism by which 4g exerts its anti-colon cancer effect may be through inhabiting the binding of APC-Asef. Compound 4g can be used as a promising lead for further exploration of potential anticancer agents.

From pixels to druggable leads: A CADD strategy for the design and synthesis of potent DDR1 inhibitors.

BACKGROUND AND OBJECTIVE: While numerous in silico tools exist for target-based drug discovery, the inconsistent integration of in vitro data with predictive models hinders research and development productivity. This is particularly apparent during the Hit-to-Lead stage, where unreliable in-silico tools often lead to suboptimal lead selection. Herein, we address this challenge by presenting a CADD-guided pipeline that successfully integrates rational drug design with in-silico hits to identify a promising DDR1 lead. METHODS: 2 × 1000 ns MD simulations along with their respective FEL and MMPBSA analyses were employed to guide the rational design and synthesis of 12 novel compounds which were evaluated for their DDR inhibition. RESULTS: The molecular dynamics investigation of the initial hit led to the identification of key structural features within the DDR1 binding pocket. The identified key features were used to guide the rational design and synthesis of twelve novel derivatives. SAR analysis, biological evaluation, molecular dynamics, and free energy calculations were carried out for the synthesized derivatives to understand their mechanism of action. Compound 4c exhibited the strongest inhibition and selectivity for DDR1, with an IC50 of 0.11 µM. CONCLUSIONS: The MD simulations led to the identification of a key hydrophobic groove in the DDR1 binding pocket. The integrated approach of SAR analysis with molecular dynamics led to the identification of compound 4c as a promising lead for further development of potent and selective DDR1 inhibitors. Moreover, this work establishes a protocol for translating in silico hits to real world bioactive druggable leads.

Evaluation of a Covalent Library of Diverse Warheads (CovLib) Binding to JNK3, USP7, or p53.

Purpose: Over the last few years, covalent fragment-based drug discovery has gained significant importance. Thus, striving for more warhead diversity, we conceived a library consisting of 20 covalently reacting compounds. Our covalent fragment library (CovLib) contains four different warhead classes, including five α-cyanoacacrylamides/acrylates (CA), three epoxides (EO), four vinyl sulfones (VS), and eight electron-deficient heteroarenes with a leaving group (SNAr/SN). Methods: After predicting the theoretical solubility of the fragments by LogP and LogS during the selection process, we determined their experimental solubility using a turbidimetric solubility assay. The reactivities of the different compounds were measured in a high-throughput 5,5'-dithiobis-(2-nitrobenzoic acid) DTNB assay, followed by a (glutathione) GSH stability assay. We employed the CovLib in a (differential scanning fluorimetry) DSF-based screening against different targets: c-Jun N-terminal kinase 3 (JNK3), ubiquitin-specific protease 7 (USP7), and the tumor suppressor p53. Finally, the covalent binding was confirmed by intact protein mass spectrometry (MS). Results: In general, the purchased fragments turned out to be sufficiently soluble. Additionally, they covered a broad spectrum of reactivity. All investigated α-cyanoacrylamides/acrylates and all structurally confirmed epoxides turned out to be less reactive compounds, possibly due to steric hindrance and reversibility (for α-cyanoacrylamides/acrylates). The SNAr and vinyl sulfone fragments are either highly reactive or stable. DSF measurements with the different targets JNK3, USP7, and p53 identified reactive fragment hits causing a shift in the melting temperatures of the proteins. MS confirmed the covalent binding mode of all these fragments to USP7 and p53, while additionally identifying the SNAr-type electrophile SN002 as a mildly reactive covalent hit for p53. Conclusion: The screening and target evaluation of the CovLib revealed first interesting hits. The highly cysteine-reactive fragments VS004, SN001, SN006, and SN007 covalently modify several target proteins and showed distinct shifts in the melting temperatures up to +5.1 °C and -9.1 °C.

Induction of steatosis in primary human hepatocytes recapitulates key pathophysiological aspects of metabolic dysfunction-associated steatotic liver disease.

BACKGROUND & AIMS: Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most common cause of chronic liver disease. Its limited treatment options warrant novel pre-clinical models for target selection and drug validation. We have established and extensively characterized a primary human steatotic hepatocyte in vitro model system that could guide treatment strategies for MASLD. METHODS: Cryopreserved primary human hepatocytes from five donors varying in sex and ethnicity were cultured with free fatty acids (FFA) in 3D collagen sandwich for 7 days and the development of MASLD was followed by assessing classical hepatocellular functions. As proof of concept, the effects of the drug Firsocostat (GS-0976) on in vitro MASLD phenotypes were evaluated. RESULTS: Incubation with FFA induced steatosis, insulin resistance, mitochondrial dysfunction, inflammation, and alterations in prominent human gene signatures similar to patients with MASLD, indicating the recapitulation of human MASLD in this system. As the application of Firsocostat rescued clinically observed fatty liver disease pathologies, it highlights the ability of the in vitro system to test drug efficacy and potentially characterize their mode of action. CONCLUSIONS: Altogether, our human MASLD in vitro model system could guide the development and validation of novel targets and drugs for the treatment of MASLD. IMPACT AND IMPLICATIONS: Due to low drug efficacy and high toxicity, a clinical treatment option for MASLD is limited. To facilitate earlier stop-go decisions in drug development, we have established a primary human steatotic hepatocyte in vitro model. As the model recapitulates clinically relevant MASLD characteristics at high phenotypic resolution, it can serve as a pre-screening platform and guide target identification and validation in MASLD therapy.

Screening Targets and Therapeutic Drugs for Alzheimer's Disease Based on Deep Learning Model and Molecular Docking.

Background: Alzheimer's disease (AD) is a neurodegenerative disorder caused by a complex interplay of various factors. However, a satisfactory cure for AD remains elusive. Pharmacological interventions based on drug targets are considered the most cost-effective therapeutic strategy. Therefore, it is paramount to search potential drug targets and drugs for AD. Objective: We aimed to provide novel targets and drugs for the treatment of AD employing transcriptomic data of AD and normal control brain tissues from a new perspective. Methods: Our study combined the use of a multi-layer perceptron (MLP) with differential expression analysis, variance assessment and molecular docking to screen targets and drugs for AD. Results: We identified the seven differentially expressed genes (DEGs) with the most significant variation (ANKRD39, CPLX1, FABP3, GABBR2, GNG3, PPM1E, and WDR49) in transcriptomic data from AD brain. A newly built MLP was used to confirm the association between the seven DEGs and AD, establishing these DEGs as potential drug targets. Drug databases and molecular docking results indicated that arbaclofen, baclofen, clozapine, arbaclofen placarbil, BML-259, BRD-K72883421, and YC-1 had high affinity for GABBR2, and FABP3 bound with oleic, palmitic, and stearic acids. Arbaclofen and YC-1 activated GABAB receptor through PI3K/AKT and PKA/CREB pathways, respectively, thereby promoting neuronal anti-apoptotic effect and inhibiting p-tau and Aß formation. Conclusions: This study provided a new strategy for the identification of targets and drugs for the treatment of AD using deep learning. Seven therapeutic targets and ten drugs were selected by using this method, providing new insight for AD treatment.