A genetic study to identify pathogenic mechanisms and drug targets for benign prostatic hyperplasia: a multi-omics Mendelian randomization study.

Benign prostatic hyperplasia (BPH) as a common geriatric disease in urology, the incidence and prevalence are rapidly increasing with the aging society, prompting an urgent need for effective prevention and treatment of BPH. However, limited therapeutic efficacy and higher risk of complications result in the treatment of BPH remaining challenging. The unclear pathogenic mechanism also hampers further exploration of therapeutic approaches for BPH. In this study, we used multi-omics methods to integrate genomics, transcriptomics, immunomics, and metabolomics data and identify biomolecules associated with BPH. We performed transcriptomic imputation, summary data-based Mendelian randomization (SMR), joint/conditional analysis, colocalization analysis, and FOCUS to explore high-confidence genes associated with BPH in blood and prostate tissue. Subsequently, three-step SMR was used to identify the DNA methylation sites regulating high-confidence genes to improve the pathogenic pathways of BPH. We also used cis-instruments of druggable genes to conduct SMR analysis to find potential drug targets for BPH. Finally, we used MR analysis to explore the immune pathways and metabolomics related to BPH. Multiple analytical methods identified BTN3A2 (Blood: TWAS Z score = 5.02912, TWAS P = 4.93 × 10-7; Prostate: TWAS Z score = 4.89, TWAS P = 1.01 × 10-6) and C4A (Blood: TWAS Z score = 4.90754, TWAS P = 9.22 × 10-7; Prostate: TWAS Z score = 5.084, TWAS P = 3.70 × 10-7) as high-confidence genes for BPH and identified the cg14345882-BTN3A2-BPH pathogenic pathway. We also used druggable gene data to identify 30 promising therapeutic target genes, including BTN3A2 and C4A. For MR analysis of immune pathways, we identified immune cell surface molecules as well as the inflammatory factor IL-17 (OR = 1.25, 95% CI = 1.09-1.43, PFDR = 0.12, Maximum likelihood) as risk factors for BPH. In addition, we found that disulfide levels of cysteinylglycine (OR = 1.11, 95% CI = 1.05-1.18, P = 5.18 × 10-4, Weighted median), oxidation levels of cysteinylglycine (OR = 1.09, 95% CI = 1.04-1.14, P = 3.87 × 10-4, Weighted median), and sebacate levels (OR = 1.05, 95% CI = 1.02-1.08, P = 3.0 × 10-4, Maximum likelihood) increase the risk of BPH. This multi-omics study explored biomolecules associated with BPH, improved the pathogenic pathways of BPH, and identified promising therapeutic targets. Our results provide evidence for future studies aimed at developing appropriate therapeutic interventions.

Graph neural pre-training based drug-target affinity prediction.

Computational drug-target affinity prediction has the potential to accelerate drug discovery. Currently, pre-training models have achieved significant success in various fields due to their ability to train the model using vast amounts of unlabeled data. However, given the scarcity of drug-target interaction data, pre-training models can only be trained separately on drug and target data, resulting in features that are insufficient for drug-target affinity prediction. To address this issue, in this paper, we design a graph neural pre-training-based drug-target affinity prediction method (GNPDTA). This approach comprises three stages. In the first stage, two pre-training models are utilized to extract low-level features from drug atom graphs and target residue graphs, leveraging a large number of unlabeled training samples. In the second stage, two 2D convolutional neural networks are employed to combine the extracted drug atom features and target residue features into high-level representations of drugs and targets. Finally, in the third stage, a predictor is used to predict the drug-target affinity. This approach fully utilizes both unlabeled and labeled training samples, enhancing the effectiveness of pre-training models for drug-target affinity prediction. In our experiments, GNPDTA outperforms other deep learning methods, validating the efficacy of our approach.

DrugReAlign: a multisource prompt framework for drug repurposing based on large language models.

Drug repurposing is a promising approach in the field of drug discovery owing to its efficiency and cost-effectiveness. Most current drug repurposing models rely on specific datasets for training, which limits their predictive accuracy and scope. The number of both market-approved and experimental drugs is vast, forming an extensive molecular space. Due to limitations in parameter size and data volume, traditional drug-target interaction (DTI) prediction models struggle to generalize well within such a broad space. In contrast, large language models (LLMs), with their vast parameter sizes and extensive training data, demonstrate certain advantages in drug repurposing tasks. In our research, we introduce a novel drug repurposing framework, DrugReAlign, based on LLMs and multi-source prompt techniques, designed to fully exploit the potential of existing drugs efficiently. Leveraging LLMs, the DrugReAlign framework acquires general knowledge about targets and drugs from extensive human knowledge bases, overcoming the data availability limitations of traditional approaches. Furthermore, we collected target summaries and target-drug space interaction data from databases as multi-source prompts, substantially improving LLM performance in drug repurposing. We validated the efficiency and reliability of the proposed framework through molecular docking and DTI datasets. Significantly, our findings suggest a direct correlation between the accuracy of LLMs' target analysis and the quality of prediction outcomes. These findings signify that the proposed framework holds the promise of inaugurating a new paradigm in drug repurposing.

Causal relationship between fertility nutrients supplementation and PCOS risk: a Mendelian randomization study.

Background: Polycystic ovary syndrome (PCOS), a prevalent endocrine disorder in women of reproductive age, is mainly ameliorated through drugs or lifestyle changes, with limited treatment options. To date, numerous researchers have found that fertility nutrient supplements may benefit female reproductive health, but their direct impact on polycystic ovary syndrome risk remains unclear. Methods: Our research employs Mendelian Randomization to assess how fertility nutrients affect PCOS risk. Initially, we reviewed 49 nutrients and focused on 10: omega-3 fatty acids, calcium, dehydroepiandrosterone, vitamin D, betaine, D-Inositol, berberine, curcumin, epigallocatechin gallate, and metformin. Using methodologies of Inverse Variance Weighting and Mendelian Randomization-Egger regression, we examined their potential causal relationships with PCOS risk. Results: Our findings indicate omega-3 fatty acids reduced PCOS risk (OR=0.73, 95% CI: 0.57-0.94, P=0.016), whereas betaine increased it (OR=2.60, 95% CI: 1.09-6.17, P=0.031). No definitive causal relations were observed for calcium, dehydroepiandrosterone, vitamin D, D-Inositol, and metformin (P>0.05). Drug target Mendelian Randomization analysis suggested that increased expression of the berberine target gene BIRC5 in various tissues may raise PCOS risk (OR: 3.00-4.88; P: 0.014-0.018), while elevated expressions of curcumin target gene CBR1 in Stomach and epigallocatechin gallate target gene AHR in Adrenal Gland were associated with reduced PCOS risk (OR=0.48, P=0.048; OR=0.02, P=0.018, respectively). Conclusions: Our research reveals that specific fertility nutrients supplementation, such as omega-3 fatty acids, berberine, and curcumin, may reduce the risk of PCOS by improving metabolic and reproductive abnormalities associated with it.

Another decade of antimalarial drug discovery: New targets, tools and molecules.

Malaria remains a devastating but preventable infectious disease that disproportionately affects the African continent. Emerging resistance to current frontline therapies means that not only are new treatments urgently required, but also novel validated antimalarial targets to circumvent cross-resistance. Fortunately, tremendous efforts have been made by the global drug discovery community over the past decade. In this chapter, we will highlight some of the antimalarial drug discovery and development programmes currently underway across the globe, charting progress in the identification of new targets and the development of new classes of drugs to prosecute them. These efforts have been complemented by the development of valuable tools to accelerate target validation such as the NOD scid gamma (NSG) humanized mouse efficacy model and progress in predictive modelling and open-source software. Among the medicinal chemistry programmes that have been conducted over the past decade are those targeting Plasmodium falciparum ATPase4 (ATP4) and acetyl-CoA synthetase (AcAS) as well as proteins disrupting parasite protein translation such as the aminoacyl-tRNA synthetases (aaRSs) and eukaryotic elongation factor 2 (eEF2). The benefits and challenges of targeting Plasmodium kinases will be examined, with a focus on Plasmodium cyclic GMP-dependent protein kinase (PKG), cyclin-dependent-like protein kinase 3 (CLK3) and phosphatidylinositol 4-kinase (PI4K). The chapter concludes with a survey of incipient drug discovery centres in Africa and acknowledges the value of recent international meetings in galvanizing and uniting the antimalarial drug discovery community.

Development of a disulfidptosis-related prognostic model for endometrial cancer with potential therapeutic target.

Prognosis biomarkers for endometrial cancer (EC) are in need. Recent evidence demonstrated the critical role of disulfidptosis, a novel cell death modality, in cancer. However, limited studies have developed a disulfidptosis-related gene model for EC. Disulfidptosis prognosis score of EC (disulfidptosis-PSEC) were constructed using disulfidptosis-related differently expression genes with the RNA data of 544 EC patients from The Cancer Genome Atlas (TCGA) dataset. Model was evaluated using time-dependent receiver operating characteristic curve analysis for overall survival (OS) and disease-free survival (DFS), along with the hazard ratio (HR) between risk groups. Then, the cellular and molecular profile for different risk groups were performed, along with drug target inference. Disulfidptosis-PSEC demonstrated outstanding prognostic value for OS and DFS, with 5-year area under curve of 0.71 (95% CI, 0.58-0.75) and 0.69 (95% CI, 0.62-0.76), respectively. Low risk group demonstrated better survival with an HR of 0.38 (95% CI, 0.24-0.59) and 0.46 (95% CI, 0.32-0.66) for OS and DFS, respectively. The model was independent of TCGA subtype. Low risk group were featured with more immune cell infiltration and less gene mutation. Serval drug targets, and the therapeutic value of serotonin receptor among copy number (CN)-low subpopulation, were identified. Disulfidptosis-PSEC was a potential prognosis biomarker for EC with targetable biological process.

N-terminal domain of androgen receptor is a major therapeutic barrier and potential pharmacological target for treating castration resistant prostate cancer: a comprehensive review.

The incidence rate of prostate cancer (PCa) has risen by 3% per year from 2014 through 2019 in the United States. An estimated 34,700 people will die from PCa in 2023, corresponding to 95 deaths per day. Castration resistant prostate cancer (CRPC) is the leading cause of deaths among men with PCa. Androgen receptor (AR) plays a critical role in the development of CRPC. N-terminal domain (NTD) is the essential functional domain for AR transcriptional activation, in which modular activation function-1 (AF-1) is important for gene regulation and protein interactions. Over last 2 decades drug discovery against NTD has attracted interest for CRPC treatment. However, NTD is an intrinsically disordered domain without stable three-dimensional structure, which has so far hampered the development of drugs targeting this highly dynamic structure. Employing high throughput cell-based assays, small-molecule NTD inhibitors exhibit a variety of unexpected properties, ranging from specific binding to NTD, blocking AR transactivation, and suppressing oncogenic proliferation, which prompts its evaluation in clinical trials. Furthermore, molecular dynamics simulations reveal that compounds can induce the formation of collapsed helical states. Nevertheless, our knowledge of NTD structure has been limited to the primary sequence of amino acid chain and a few secondary structure motif, acting as a barrier for computational and pharmaceutical analysis to decipher dynamic conformation and drug-target interaction. In this review, we provide an overview on the sequence-structure-function relationships of NTD, including the polymorphism of mono-amino acid repeats, functional elements for transcription regulation, and modeled tertiary structure of NTD. Moreover, we summarize the activities and therapeutic potential of current NTD-targeting inhibitors and outline different experimental methods contributing to screening novel compounds. Finally, we discuss current directions for structure-based drug design and potential breakthroughs for exploring pharmacological motifs and pockets in NTD, which could contribute to the discovery of new NTD inhibitors.

Staphylococcus aureus SOS response: Activation, impact, and drug targets.

Staphylococcus aureus is a common cause of diverse infections, ranging from superficial to invasive, affecting both humans and animals. The widespread use of antibiotics in clinical treatments has led to the emergence of antibiotic-resistant strains and small colony variants. This surge presents a significant challenge in eliminating infections and undermines the efficacy of available treatments. The bacterial Save Our Souls (SOS) response, triggered by genotoxic stressors, encompasses host immune defenses and antibiotics, playing a crucial role in bacterial survival, invasiveness, virulence, and drug resistance. Accumulating evidence underscores the pivotal role of the SOS response system in the pathogenicity of S. aureus. Inhibiting this system offers a promising approach for effective bactericidal treatments and curbing the evolution of antimicrobial resistance. Here, we provide a comprehensive review of the activation, impact, and key proteins associated with the SOS response in S. aureus. Additionally, perspectives on therapeutic strategies targeting the SOS response for S. aureus, both individually and in combination with traditional antibiotics are proposed.

Lipid-lowering drugs and risk of rapid renal function decline: a mendelian randomization study.

BACKGROUND: Chronic kidney disease (CKD) patients face the risk of rapid kidney function decline leading to adverse outcomes like dialysis and mortality. Lipid metabolism might contribute to acute kidney function decline in CKD patients. Here, we utilized the Mendelian Randomization approach to investigate potential causal relationships between drug target-mediated lipid phenotypes and rapid renal function decline. METHODS: In this study, we utilized two methodologies: summarized data-based Mendelian randomization (SMR) and inverse variance-weighted Mendelian randomization (IVW-MR), to approximate exposure to lipid-lowering drugs. This entailed leveraging expression quantitative trait loci (eQTL) for drug target genes and genetic variants proximal to drug target gene regions, which encode proteins associated with low-density lipoprotein (LDL) cholesterol, as identified in genome-wide association studies. The objective was to investigate causal associations with the progression of rapid kidney function decline. RESULTS: The SMR analysis revealed a potential association between high expression of PCSK9 and rapid kidney function decline (OR = 1.11, 95% CI= [1.001-1.23]; p = 0.044). Similarly, IVW-MR analysis demonstrated a negative association between LDL cholesterol mediated by HMGCR and kidney function decline (OR = 0.74, 95% CI = 0.60-0.90; p = 0.003). CONCLUSION: Genetically predicted inhibition of HMGCR is linked with the progression of kidney function decline, while genetically predicted PCSK9 inhibition is negatively associated with kidney function decline. Future research should incorporate clinical trials to validate the relevance of PCSK9 in preventing kidney function decline.

A comprehensive survey of drug-target interaction analysis in allopathy and siddha medicine.

Effective drug delivery is the cornerstone of modern healthcare, ensuring therapeutic compounds reach their intended targets efficiently. This paper explores the potential of personalized and holistic healthcare, driven by the synergy between traditional and allopathic medicine systems, with a specific focus on the vast reservoir of medicinal compounds found in plants rooted in the historical legacy of traditional medicine. Motivated by the desire to unlock the therapeutic potential of medicinal plants and bridge the gap between traditional and allopathic medicine, this survey delves into in-silico computational approaches for studying Drug-Target Interactions (DTI) within the contexts of allopathy and siddha medicine. The contributions of this survey are multifaceted: it offers a comprehensive overview of in-silico methods for DTI analysis in both systems, identifies common challenges in DTI studies, provides insights into future directions to advance DTI analysis, and includes a comparative analysis of DTI in allopathy and siddha medicine. The findings of this survey highlight the pivotal role of in-silico computational approaches in advancing drug research and development in both allopathy and siddha medicine, emphasizing the importance of integrating these methods to drive the future of personalized healthcare.

Predicting drug-target interactions by measuring confidence with consistent causal neighborhood interventions.

Predicting drug-target interactions (DTI) is a crucial stage in drug discovery and development. Understanding the interaction between drugs and targets is essential for pinpointing the specific relationship between drug molecules and targets, akin to solving a link prediction problem using information technology. While knowledge graph (KG) and knowledge graph embedding (KGE) methods have been rapid advancements and demonstrated impressive performance in drug discovery, they often lack authenticity and accuracy in identifying DTI. This leads to increased misjudgment rates and reduced efficiency in drug development. To address these challenges, our focus lies in refining the accuracy of DTI prediction models through KGE, with a specific emphasis on causal intervention confidence measures (CI). These measures aim to assess triplet scores, enhancing the precision of the predictions. Comparative experiments conducted on three datasets and utilizing 9 KGE models reveal that our proposed confidence measure approach via causal intervention, significantly improves the accuracy of DTI link prediction compared to traditional approaches. Furthermore, our experimental analysis delves deeper into the embedding of intervention values, offering valuable insights for guiding the design and development of subsequent drug development experiments. As a result, our predicted outcomes serve as valuable guidance in the pursuit of more efficient drug development processes.

MFF-DTA: Multi-scale feature fusion for drug-target affinity prediction.

Accurately predicting drug-target affinity is crucial in expediting the discovery and development of new drugs, which is a complex and risky process. Identifying these interactions not only aids in screening potential compounds but also guides further optimization. To address this, we propose a multi-perspective feature fusion model, MFF-DTA, which integrates chemical structure, biological sequence, and other data to comprehensively capture drug-target affinity features. The MFF-DTA model incorporates multiple feature learning components, each of which is capable of extracting drug molecular features and protein target information, respectively. These components are able to obtain key information from both global and local perspectives. Then, these features from different perspectives are efficiently combined using specific splicing strategies to create a comprehensive representation. Finally, the model uses the fused features to predict drug-target affinity. Comparative experiments show that MFF-DTA performs optimally on the Davis and KIBA data sets. Ablation experiments demonstrate that removing specific components results in the loss of unique information, thus confirming the effectiveness of the MFF-DTA design. Improvements in DTA prediction methods will decrease costs and time in drug development, enhancing industry efficiency and ultimately benefiting patients.

Screening of promising molecules against potential drug targets in Yersinia pestis by integrative pan and subtractive genomics, docking and simulation approach.

This study focuses on Yersinia pestis, the bacterium responsible for plague, which posed a severe threat to public health in history. Despite the availability of antibiotics treatment, the emergence of antibiotic resistance in this pathogen has increased challenges of controlling the infections and plague outbreaks. The development of new drug targets and therapies is urgently needed. This research aims to identify novel protein targets from 28 Y. pestis strains by the integrative pan-genomic and subtractive genomics approach. Additionally, it seeks to screen out potential safe and effective alternative therapies against these targets via high-throughput virtual screening. Targets should lack homology to human, gut microbiota, and known human 'anti-targets', while should exhibit essentiality for pathogen's survival and virulence, druggability, antibiotic resistance, and broad spectrum across multiple pathogenic bacteria. We identified two promising targets: the aminotransferase class I/class II domain-containing protein and 3-oxoacyl-[acyl-carrier-protein] synthase 2. These proteins were modeled using AlphaFold2, validated through several structural analyses, and were subjected to molecular docking and ADMET analysis. Molecular dynamics simulations determined the stability of the ligand-target complexes, providing potential therapeutic options against Y. pestis.

NR0B2 Is a Key Factor for Gastric Diseases: A GEO Database Analysis Combined with Drug-Target Mendelian Randomization.

Small Heterodimer Partner (SHP; NR0B2) is an orphan receptor that acts as a transcriptional regulator, controlling various metabolic processes, and is a potential therapeutic target for cancer. Examining the correlation between the expression of NR0B2 and the risk of gastric diseases could open a new path for treatment and drug development. The Gene Expression Omnibus (GEO) database was utilized to explore NR0B2 gene expression profiles in gastric diseases. Co-expressed genes were identified through Weighted Correlation Network Analysis (WGCNA), and GO enrichment was performed to identify potential pathways. The Xcell method was employed to analyze immune infiltration relationships. To determine the potential causal relationship between NR0B2 expression and gastric diseases, we identified six single-nucleotide polymorphisms (SNPs) as a proxy for NR0B2 expression located within 100 kilobases of NR0B2 and which are associated with triglyceride homeostasis and performed drug-target Mendelian randomization (MR). Bioinformatics analysis revealed that NR0B2 expression levels were reduced in gastric cancer and increased in gastritis. GO analysis and Gene Set Enrichment Analysis (GSEA) showed that NR0B2 is widely involved in oxidation-related processes. Immune infiltration analyses found that NR0B2 was associated with Treg. Prognostic analyses showed that a low expression of NR0B2 is a risk factor for the poor prognoses of gastric cancer. MR analyses revealed that NR0B2 expression is associated with a risk of gastric diseases (NR0B2 vs. gastric cancer, p = 0.006, OR: 0.073, 95%CI: 0.011-0.478; NR0B2 vs. gastric ulcer, p = 0.03, OR: 0.991, 95%CI: 0.984-0.999; NR0B2 vs. other gastritis, p = 0.006, OR:3.82, 95%CI: 1.468-9.942). Our study confirms the causal relationship between the expression of NR0B2 and the risk of gastric diseases, and highlights its role in the progression of gastric cancer. The present study opens new avenues for exploring the potential of drugs that either activate or inhibit the NR0B2 receptor in the treatment of gastric diseases.

Identification of autophagy-related signatures in doxorubicin-induced cardiotoxicity.

PURPOSE: Doxorubicin is an antibiotic drug used clinically to treat infectious diseases and tumors. Unfortunately, it is cardiotoxic. Autophagy is a cellular self-decomposition process that is essential for maintaining homeostasis in the internal environment. Accordingly, the present study was proposed to characterize the autophagy-related signatures of doxorubicin-induced cardiotoxicity. METHODS: Datasets related to doxorubicin-induced cardiotoxicity were retrieved by searching the GEO database and differentially expressed genes (DEGs) were identified. DEGs were taken to intersect with autophagy-related genes to obtain autophagy-related signatures, and Gene Ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis and protein-protein interaction (PPI) network were performed on them. Further, construction of miRNA-hub gene networks and identification of target drugs to reveal potential molecular mechanisms and therapeutic strategies. Animal models of doxorubicin-induced cardiotoxicity were constructed to validate differences in gene expression for autophagy-related signatures. RESULTS: PBMC and heart samples from the GSE37260 dataset were selected for analysis. There were 995 and 2357 DEGs in PBMC and heart samples, respectively, and they had 23 intersecting genes with autophagy-related genes. RT-qPCR confirmed the differential expression of 23 intersecting genes in doxorubicin-induced cardiotoxicity animal models in general agreement with the bioinformatics results. An autophagy-related signatures consisting of 23 intersecting genes is involved in mediating processes and pathways such as autophagy, oxidative stress, apoptosis, protein ubiquitination and phosphorylation. Moreover, Akt1, Hif1a and Mapk3 are hub genes in autophagy-associated signatures and their upstream miRNAs are mainly rno-miR-1188-5p, rno-miR-150-3p and rno-miR-326-3p, and their drugs are mainly CHEMBL55802, Carboxyamidotriazole and 3-methyladenine. CONCLUSION: This study identifies for the first-time autophagy-related signatures in doxorubicin's cardiotoxicity, which could provide potential molecular mechanisms and therapeutic strategies for doxorubicin-induced cardiotoxicity.

ß-arrestin2: an emerging player and potential therapeutic target in inflammatory immune diseases.

ß-arrestin2, a pivotal protein within the arrestin family, is localized in the cytoplasm, plasma membrane and nucleus, and regulates G protein-coupled receptors (GPCRs) signaling. Recent evidence shows that ß-arrestin2 plays a dual role in regulating GPCRs by mediating desensitization and internalization, and by acting as a scaffold for the internalization, kinase activation, and the modulation of various signaling pathways, including NF-κB, MAPK, and TGF-ß pathways of non-GPCRs. Earlier studies have identified that ß-arrestin2 is essential in regulating immune cell infiltration, inflammatory factor release, and inflammatory cell proliferation. Evidently, ß-arrestin2 is integral to the pathological mechanisms of inflammatory immune diseases, such as inflammatory bowel disease, sepsis, asthma, rheumatoid arthritis, organ fibrosis, and tumors. Research on the modulation of ß-arrestin2 offers a promising strategy for the development of pharmaceuticals targeting inflammatory immune diseases. This review meticulously describes the roles of ß-arrestin2 in cells associated with inflammatory immune responses and explores its pathological relevance in various inflammatory immune diseases.

Drug-target interaction prediction with collaborative contrastive learning and adaptive self-paced sampling strategy.

BACKGROUND: Drug-target interaction (DTI) prediction plays a pivotal role in drug discovery and drug repositioning, enabling the identification of potential drug candidates. However, most previous approaches often do not fully utilize the complementary relationships among multiple biological networks, which limits their ability to learn more consistent representations. Additionally, the selection strategy of negative samples significantly affects the performance of contrastive learning methods. RESULTS: In this study, we propose CCL-ASPS, a novel deep learning model that incorporates Collaborative Contrastive Learning (CCL) and Adaptive Self-Paced Sampling strategy (ASPS) for drug-target interaction prediction. CCL-ASPS leverages multiple networks to learn the fused embeddings of drugs and targets, ensuring their consistent representations from individual networks. Furthermore, ASPS dynamically selects more informative negative sample pairs for contrastive learning. Experiment results on the established dataset demonstrate that CCL-ASPS achieves significant improvements compared to current state-of-the-art methods. Moreover, ablation experiments confirm the contributions of the proposed CCL and ASPS strategies. CONCLUSIONS: By integrating Collaborative Contrastive Learning and Adaptive Self-Paced Sampling, the proposed CCL-ASPS effectively addresses the limitations of previous methods. This study demonstrates that CCL-ASPS achieves notable improvements in DTI predictive performance compared to current state-of-the-art approaches. The case study and cold start experiments further illustrate the capability of CCL-ASPS to effectively predict previously unknown DTI, potentially facilitating the identification of new drug-target interactions.

A multi-view feature representation for predicting drugs combination synergy based on ensemble and multi-task attention models.

This paper proposes a novel multi-view ensemble predictor model that is designed to address the challenge of determining synergistic drug combinations by predicting both the synergy score value values and synergy class label of drug combinations with cancer cell lines. The proposed methodology involves representing drug features through four distinct views: Simplified Molecular-Input Line-Entry System (SMILES) features, molecular graph features, fingerprint features, and drug-target features. On the other hand, cell line features are captured through four views: gene expression features, copy number features, mutation features, and proteomics features. To prevent overfitting of the model, two techniques are employed. First, each view feature of a drug is paired with each corresponding cell line view and input into a multi-task attention deep learning model. This multi-task model is trained to simultaneously predict both the synergy score value and synergy class label. This process results in sixteen input view features being fed into the multi-task model, producing sixteen prediction values. Subsequently, these prediction values are utilized as inputs for an ensemble model, which outputs the final prediction value. The 'MVME' model is assessed using the O'Neil dataset, which includes 38 distinct drugs combined across 39 distinct cancer cell lines to output 22,737 drug combination pairs. For the synergy score value, the proposed model scores a mean square error (MSE) of 206.57, a root mean square error (RMSE) of 14.30, and a Pearson score of 0.76. For the synergy class label, the model scores 0.90 for accuracy, 0.96 for precision, 0.57 for kappa, 0.96 for the area under the ROC curve (ROC-AUC), and 0.88 for the area under the precision-recall curve (PR-AUC).

Recent advances in studies on FtsZ inhibitors.

With the abuse of antibiotics, multidrug resistant strains continue to emerge and spread rapidly. Therefore, there is an urgent need to develop new antimicrobial drugs. As a highly conserved cell division protein in bacteria, filamenting temperature-sensitive mutant Z (FtsZ) has been identified as a potential antimicrobial target. This paper reviews the structure, function, and action mechanism of FtsZ and a variety of natural and synthetic compounds targeting FtsZ, including 3-MBA derivatives, taxane derivatives, cinnamaldehyde, curcumin, quinoline and quinazoline derivatives, aromatic compounds, purpurin, and totarol. From these studies, FtsZ has a clear supporting role in the field of antimicrobial drug discovery. The urgent need and interest of antibacterial drugs will contribute to the discovery of new clinical drugs targeting FtsZ.

SSR-DTA: Substructure-aware multi-layer graph neural networks for drug-target binding affinity prediction.

Accurate prediction of drug-target binding affinity (DTA) is essential in the field of drug discovery. Recently, scientists have been attempting to utilize artificial intelligence prediction to screen out a significant number of ineffective compounds, thereby mitigating labor and financial losses. While graph neural networks (GNNs) have been applied to DTA, existing GNNs have limitations in effectively extracting substructural features across various sizes. Functional groups play a crucial role in modulating molecular properties, but existing GNNs struggle with feature extraction from certain motifs due to scale mismatches. Additionally, sequence-based models for target proteins lack the integration of structural information. To address these limitations, we present SSR-DTA, a multi-layer graph network capable of adapting to diverse structural sizes, which can extract richer biological features, thereby improving the robustness and accuracy of predictions. Multi-layer GNNs enable the capture of molecular motifs across different scales, ranging from atomic to macrocyclic motifs. Furthermore, we introduce BiGNN to simultaneously learn sequence and structural information. Sequence information corresponds to the primary structure of proteins, while graph information represents the tertiary structure. BiGNN assimilates richer information compared to sequence-based methods while mitigating the impact of errors from predicted structures, resulting in more accurate predictions. Through rigorous experimental evaluations conducted on four benchmark datasets, we demonstrate the superiority of SSR-DTA over state-of-the-art models. Particularly, in comparison to state-of-the-art models, SSR-DTA demonstrates an impressive 20% reduction in mean squared error on the Davis dataset and a 5% reduction on the KIBA dataset, underscoring its potential as a valuable tool for advancing DTA prediction.