DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks.

BACKGROUND: In recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications. RESULTS: To mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index. CONCLUSION: The results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA . Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/ .

Emerging opportunities of using large language models for translation between drug molecules and indications.

A drug molecule is a substance that changes an organism's mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI.

Systems Biology for Drug Target Discovery in Acute Myeloid Leukemia.

Combining new therapeutics with all-trans-retinoic acid (ATRA) could improve the efficiency of acute myeloid leukemia (AML) treatment. Modeling the process of ATRA-induced differentiation based on the transcriptomic profile of leukemic cells resulted in the identification of key targets that can be used to increase the therapeutic effect of ATRA. The genome-scale transcriptome analysis revealed the early molecular response to the ATRA treatment of HL-60 cells. In this study, we performed the transcriptomic profiling of HL-60, NB4, and K562 cells exposed to ATRA for 3-72 h. After treatment with ATRA for 3, 12, 24, and 72 h, we found 222, 391, 359, and 1032 differentially expressed genes (DEGs) in HL-60 cells, as well as 641, 1037, 1011, and 1499 DEGs in NB4 cells. We also found 538 and 119 DEGs in K562 cells treated with ATRA for 24 h and 72 h, respectively. Based on experimental transcriptomic data, we performed hierarchical modeling and determined cyclin-dependent kinase 6 (CDK6), tumor necrosis factor alpha (TNF-alpha), and transcriptional repressor CUX1 as the key regulators of the molecular response to the ATRA treatment in HL-60, NB4, and K562 cell lines, respectively. Mapping the data of TMT-based mass-spectrometric profiling on the modeling schemes, we determined CDK6 expression at the proteome level and its down-regulation at the transcriptome and proteome levels in cells treated with ATRA for 72 h. The combination of therapy with a CDK6 inhibitor (palbociclib) and ATRA (tretinoin) could be an alternative approach for the treatment of acute myeloid leukemia (AML).

Connective Tissue Growth Factor: Regulation, Diseases, and Drug Discovery.

In drug discovery, selecting targeted molecules is crucial as the target could directly affect drug efficacy and the treatment outcomes. As a member of the CCN family, CTGF (also known as CCN2) is an essential regulator in the progression of various diseases, including fibrosis, cancer, neurological disorders, and eye diseases. Understanding the regulatory mechanisms of CTGF in different diseases may contribute to the discovery of novel drug candidates. Summarizing the CTGF-targeting and -inhibitory drugs is also beneficial for the analysis of the efficacy, applications, and limitations of these drugs in different disease models. Therefore, we reviewed the CTGF structure, the regulatory mechanisms in various diseases, and drug development in order to provide more references for future drug discovery.

Discovery of potent and novel dual NAMPT/BRD4 inhibitors for efficient treatment of hepatocellular carcinoma.

The NAPRT-induced increase in NAD+ levels was proposed as a mechanism contributing to hepatocellular carcinoma (HCC) resistance to NAMPT inhibitors. Thus, concurrently targeting NAMPT and NAPRT could be considered to overcome drug resistance. A BRD4 inhibitor downregulates the expression of NAPRT in HCC, and the combination of NAMPT inhibitors with BRD4 inhibitors simultaneously blocks NAD+ generation via salvage and the PH synthesis pathway. Moreover, the combination of the two agents significantly downregulated the expression of tumor-promoting genes and strongly promoted apoptosis. The present work identified various NAMPT/BRD4 dual inhibitors based on the multitargeted drug rationale. Among them, compound A2, which demonstrated the strongest effect, exhibited potent inhibition of NAMPT and BRD4 (IC50 = 35 and 58 nM, respectively). It significantly suppressed the growth and migration of HCC cells and facilitated their apoptosis. Furthermore, compound A2 also manifested a robust anticancer effect in HCCLM3 xenograft mouse models, with no apparent toxic effects. Our findings in this study provide an effective approach to target NAD+ metabolism for HCC treatment.

Elucidating the semantics-topology trade-off for knowledge inference-based pharmacological discovery.

Leveraging AI for synthesizing the deluge of biomedical knowledge has great potential for pharmacological discovery with applications including developing new therapeutics for untreated diseases and repurposing drugs as emergent pandemic treatments. Creating knowledge graph representations of interacting drugs, diseases, genes, and proteins enables discovery via embedding-based ML approaches and link prediction. Previously, it has been shown that these predictive methods are susceptible to biases from network structure, namely that they are driven not by discovering nuanced biological understanding of mechanisms, but based on high-degree hub nodes. In this work, we study the confounding effect of network topology on biological relation semantics by creating an experimental pipeline of knowledge graph semantic and topological perturbations. We show that the drop in drug repurposing performance from ablating meaningful semantics increases by 21% and 38% when mitigating topological bias in two networks. We demonstrate that new methods for representing knowledge and inferring new knowledge must be developed for making use of biomedical semantics for pharmacological innovation, and we suggest fruitful avenues for their development.

Targeting the cysteine biosynthesis pathway in microorganisms: Mechanism, structure, and drug discovery.

Owing to the global health crisis of resistant pathogenic infections, researchers are emphasizing the importance of novel prevention and control strategies. Existing antimicrobial drugs predominantly target a few pathways, and their widespread use has pervasively increased drug resistance. Therefore, it is imperative to develop new antimicrobial drugs with novel targets and chemical structures. The de novo cysteine biosynthesis pathway, one of the microbial metabolic pathways, plays a crucial role in pathogenicity and drug resistance. This pathway notably differs from that in humans, thereby representing an unexplored target for developing antimicrobial drugs. Herein, we have presented an overview of cysteine biosynthesis pathways and their roles in the pathogenicity of various microorganisms. Additionally, we have investigated the structure and function of enzymes involved in these pathways as well as have discussed drug design strategies and structure-activity relationships of the enzyme inhibitors. This review provides valuable insights for developing novel antimicrobials and offers new avenues to combat drug resistance.

Multicriteria decision making attributes and estimation of physicochemical properties of kidney cancer drugs via topological descriptors.

Based on topological descriptors, QSPR analysis is an incredibly helpful statistical method for examining many physical and chemical properties of compounds without demanding costly and time-consuming laboratory tests. Firstly, we discuss and provide research on kidney cancer drugs using topological indices and done partition of the edges of kidney cancer drugs which are based on the degree. Secondly, we examine the attributes of nineteen drugs casodex, eligard, mitoxanrone, rubraca, and zoladex, etc and among others, using linear QSPR model. The study in the article not only demonstrates a good correlation between TIs and physical characteristics with the QSPR model being the most suitable for predicting complexity, enthalpy, molar refractivity, and other factors and a best-fit model is attained in this study. This theoretical approach might benefit chemists and professionals in the pharmaceutical industry to forecast the characteristics of kidney cancer therapies. This leads towards new opportunities to paved the way for drug discovery and the formation of efficient and suitable treatment options in therapeutic targeting. We also employed multicriteria decision making techniques like COPRAS and PROMETHEE-II for ranking of said disease treatment drugs and physicochemical characteristics.

Research progress of autoimmune diseases based on induced pluripotent stem cells.

Autoimmune diseases can damage specific or multiple organs and tissues, influence the quality of life, and even cause disability and death. A 'disease in a dish' can be developed based on patients-derived induced pluripotent stem cells (iPSCs) and iPSCs-derived disease-relevant cell types to provide a platform for pathogenesis research, phenotypical assays, cell therapy, and drug discovery. With rapid progress in molecular biology research methods including genome-sequencing technology, epigenetic analysis, '-omics' analysis and organoid technology, large amount of data represents an opportunity to help in gaining an in-depth understanding of pathological mechanisms and developing novel therapeutic strategies for these diseases. This paper aimed to review the iPSCs-based research on phenotype confirmation, mechanism exploration, drug discovery, and cell therapy for autoimmune diseases, especially multiple sclerosis, inflammatory bowel disease, and type 1 diabetes using iPSCs and iPSCs-derived cells.

Computational drug repositioning with attention walking.

Drug repositioning aims to identify new therapeutic indications for approved medications. Recently, the importance of computational drug repositioning has been highlighted because it can reduce the costs, development time, and risks compared to traditional drug discovery. Most approaches in this area use networks for systematic analysis. Inferring drug-disease associations is then defined as a link prediction problem in a heterogeneous network composed of drugs and diseases. In this article, we present a novel method of computational drug repositioning, named drug repositioning with attention walking (DRAW). DRAW proceeds as follows: first, a subgraph enclosing the target link for prediction is extracted. Second, a graph convolutional network captures the structural features of the labeled nodes in the subgraph. Third, the transition probabilities are computed using attention mechanisms and converted into random walk profiles. Finally, a multi-layer perceptron takes random walk profiles and predicts whether a target link exists. As an experiment, we constructed two heterogeneous networks with drug-drug similarities based on chemical structures and anatomical therapeutic chemical classification (ATC) codes. Using 10-fold cross-validation, DRAW achieved an area under the receiver operating characteristic (ROC) curve of 0.903 and outperformed state-of-the-art methods. Moreover, we demonstrated the results of case studies for selected drugs and diseases to further confirm the capability of DRAW to predict drug-disease associations.

De novo generation of multi-target compounds using deep generative chemistry.

Polypharmacology drugs-compounds that inhibit multiple proteins-have many applications but are difficult to design. To address this challenge we have developed POLYGON, an approach to polypharmacology based on generative reinforcement learning. POLYGON embeds chemical space and iteratively samples it to generate new molecular structures; these are rewarded by the predicted ability to inhibit each of two protein targets and by drug-likeness and ease-of-synthesis. In binding data for >100,000 compounds, POLYGON correctly recognizes polypharmacology interactions with 82.5% accuracy. We subsequently generate de-novo compounds targeting ten pairs of proteins with documented co-dependency. Docking analysis indicates that top structures bind their two targets with low free energies and similar 3D orientations to canonical single-protein inhibitors. We synthesize 32 compounds targeting MEK1 and mTOR, with most yielding >50% reduction in each protein activity and in cell viability when dosed at 1-10 µM. These results support the potential of generative modeling for polypharmacology.

Patient-derived tumoroids and proteomic signatures: tools for early drug discovery.

Onco-virotherapy is an emergent treatment for cancer based on viral vectors. The therapeutic activity is based on two different mechanisms including tumor-specific oncolysis and immunostimulatory properties. In this study, we evaluated onco-virotherapy in vitro responses on immunocompetent non-small cell lung cancer (NSCLC) patient-derived tumoroids (PDTs) and healthy organoids. PDTs are accurate tools to predict patient's clinical responses at the in vitro stage. We showed that onco-virotherapy could exert specific antitumoral effects by producing a higher number of viral particles in PDTs than in healthy organoids. In the present work, we used multiplex protein screening, based on proximity extension assay to highlight different response profiles. Our results pointed to the increase of proteins implied in T cell activation, such as IFN-γ following onco-virotherapy treatment. Based on our observation, oncolytic viruses-based therapy responders are dependent on several factors: a high PD-L1 expression, which is a biomarker of greater immune response under immunotherapies, and the number of viral particles present in tumor tissue, which is dependent to the metabolic state of tumoral cells. Herein, we highlight the use of PDTs as an alternative in vitro model to assess patient-specific responses to onco-virotherapy at the early stage of the preclinical phases.

Studies on Comprehensive Total Synthesis of Natural and Pseudo-Natural Products for Drug Discovery.

Natural products are important for the development of pharmaceuticals and agrochemicals; thus, their synthesis and medicinal chemistry research is critical. Developing a total synthesis pathway for natural products confirms their structure and provides the opportunity to modify the structure in a targeted manner. A simple modification of a single oxidation step can increase the biological activity, or the complexity of the molecule can alter the property. Herein, we discuss the asymmetric total synthesis of dihydroisocoumarin-type natural products, the creation of novel antibacterial compounds through partial structural modification, and the development of antioxidants with high activity and low toxicity through dimerization strategies.

Phytochemical evaluation of Ziziphus mucronata and Xysmalobium undulutum towards the discovery and development of anti-malarial drugs.

BACKGROUND: The development of resistance by Plasmodium falciparum is a burdening hazard that continues to undermine the strides made to alleviate malaria. As such, there is an increasing need to find new alternative strategies. This study evaluated and validated 2 medicinal plants used in traditional medicine to treat malaria. METHODS: Inspired by their ethnobotanical reputation of being effective against malaria, Ziziphus mucronata and Xysmalobium undulutum were collected and sequentially extracted using hexane (HEX), ethyl acetate (ETA), Dichloromethane (DCM) and methanol (MTL). The resulting crude extracts were screened for their anti-malarial and cytotoxic potential using the parasite lactate dehydrogenase (pLDH) and 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, respectively. This was followed by isolating the active compounds from the DCM extract of Z. mucronata using silica gel chromatography and structural elucidation using spectroscopic techniques (NMR: 1H, 12C, and DEPT). The active compounds were then targeted against P. falciparum heat shock protein 70-1 (PfHsp70-1) using Autodock Vina, followed by in vitro validation assays using ultraviolet-visible (UV-VIS) spectroscopy and the malate dehydrogenase (MDH) chaperone activity assay. RESULTS: The extracts except those of methanol displayed anti-malarial potential with varying IC50 values, Z. mucronata HEX (11.69 ± 3.84 µg/mL), ETA (7.25 ± 1.41 µg/mL), DCM (5.49 ± 0.03 µg/mL), and X. undulutum HEX (4.9 ± 0.037 µg/mL), ETA (17.46 ± 0.024 µg/mL) and DCM (19.27 ± 0.492 µg/mL). The extracts exhibited minimal cytotoxicity except for the ETA and DCM of Z. mucronata with CC50 values of 10.96 and 10.01 µg/mL, respectively. Isolation and structural characterization of the active compounds from the DCM extracts revealed that betulinic acid (19.95 ± 1.53 µg/mL) and lupeol (7.56 ± 2.03 µg/mL) were responsible for the anti-malarial activity and had no considerable cytotoxicity (CC50 > µg/mL). Molecular docking suggested strong binding between PfHsp70-1, betulinic acid (- 6.8 kcal/mol), and lupeol (- 6.9 kcal/mol). Meanwhile, the in vitro validation assays revealed the disruption of the protein structural elements and chaperone function. CONCLUSION: This study proves that X undulutum and Z. mucronata have anti-malarial potential and that betulinic acid and lupeol are responsible for the activity seen on Z. mucronata. They also make a case for guided purification of new phytochemicals in the other extracts and support the notion of considering medicinal plants to discover new anti-malarials.

Reductionism and proxy failure: From neuroscience to target-based drug discovery.

Reductionist methodologies reduce phenomena to some of their lower-level components. Researchers gradually shift their focus away from observing the actual object of study toward investigating and optimizing such lower-level proxies. Following reductionism, these proxies progressively diverge further from the original object of study. We vividly illustrate this in the evolution of target-based drug discovery from rational and phenotypic drug discovery.

Quantifying Antibody-Dependent Cellular Cytotoxicity in a Tumor Spheroid Model: Application for Drug Discovery.

Monoclonal antibody-based immunotherapy targeting tumor antigens is now a mainstay of cancer treatment. One of the clinically relevant mechanisms of action of the antibodies is antibody-dependent cellular cytotoxicity (ADCC), where the antibody binds to the cancer cells and engages the cellular component of the immune system, e.g., natural killer (NK) cells, to kill the tumor cells. The effectiveness of these therapies could be improved by identifying adjuvant compounds that increase the sensitivity of the cancer cells or the potency of the immune cells. In addition, undiscovered drug interactions in cancer patients co-medicated for previous conditions or cancer-associated symptoms may determine the success of the antibody therapy; therefore, such unwanted drug interactions need to be eliminated. With these goals in mind, we created a cancer ADCC model and describe here a simple protocol to find ADCC-modulating drugs. Since 3D models such as cancer cell spheroids are superior to 2D cultures in predicting in vivo responses of tumors to anticancer therapies, spheroid co-cultures of EGFP-expressing HER2+ JIMT-1 breast cancer cells and the NK92.CD16 cell lines were set up and induced with Trastuzumab, a monoclonal antibody clinically approved against HER2-positive breast cancer. JIMT-1 spheroids were allowed to form in cell-repellent U-bottom 96-well plates. On day 3, NK cells and Trastuzumab were added. The spheroids were then stained with Annexin V-Alexa 647 to measure apoptotic cell death, which was quantitated in the peripheral zone of the spheroids with an automated microscope. The applicability of our assay to identify ADCC-modulating molecules is demonstrated by showing that Sunitinib, a receptor tyrosine kinase inhibitor approved by the FDA against metastatic cancer, almost completely abolishes ADCC. The generation of the spheroids and image acquisition and analysis pipelines are compatible with high-throughput screening for ADCC-modulating compounds in cancer cell spheroids.