Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

Receptor-interacting serine/threonine-protein kinase 1 (RIPK1) functions as a key regulator in inflammation and cell death and is involved in mediating a variety of inflammatory or degenerative diseases. A number of allosteric RIPK1 inhibitors (RIPK1i) have been developed, and some of them have already advanced into clinical evaluation. Recently, selective RIPK1i that interact with both the allosteric pocket and the ATP-binding site of RIPK1 have started to emerge. Here, we report the rational development of a new series of type-II RIPK1i based on the rediscovery of a reported but mechanistically atypical RIPK3i. We also describe the structure-guided lead optimization of a potent, selective, and orally bioavailable RIPK1i, 62, which exhibits extraordinary efficacies in mouse models of acute or chronic inflammatory diseases. Collectively, 62 provides a useful tool for evaluating RIPK1 in animal disease models and a promising lead for further drug development.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common monogenic cause of chronic kidney disease and the fourth leading cause of end-stage kidney disease, accounting for over 50% of prevalent cases requiring renal replacement therapy. There is a pressing need for improved therapy for ADPKD. Recent insights into the pathophysiology of ADPKD revealed that cyst cells undergo metabolic changes that up-regulate aerobic glycolysis in lieu of mitochondrial respiration for energy production, a process that ostensibly fuels their increased proliferation. The present work leverages this metabolic disruption as a way to selectively target cyst cells for apoptosis. This small-molecule therapeutic strategy utilizes 11beta-dichloro, a repurposed DNA-damaging anti-tumor agent that induces apoptosis by exacerbating mitochondrial oxidative stress. Here, we demonstrate that 11beta-dichloro is effective in delaying cyst growth and its associated inflammatory and fibrotic events, thus preserving kidney function in perinatal and adult mouse models of ADPKD. In both models, the cyst cells with homozygous inactivation of Pkd1 show enhanced oxidative stress following treatment with 11beta-dichloro and undergo apoptosis. Co-administration of the antioxidant vitamin E negated the therapeutic benefit of 11beta-dichloro in vivo, supporting the conclusion that oxidative stress is a key component of the mechanism of action. As a preclinical development primer, we also synthesized and tested an 11beta-dichloro derivative that cannot directly alkylate DNA, while retaining pro-oxidant features. This derivative nonetheless maintains excellent anti-cystic properties in vivo and emerges as the lead candidate for development.

The global cost-benefit analysis of pesticide use during the last 30 years has been characterized by a significant increase during the period from 1990 to 2007 followed by a decline. This observation can be attributed to several factors including, but not limited to, pest resistance, lack of novelty with respect to modes of action or classes of chemistry, and regulatory action. Due to current and projected increases of the global population, it is evident that the demand for food, and consequently, the usage of pesticides to improve yields will increase. Addressing these challenges and needs while promoting new crop protection agents through an increasingly stringent regulatory landscape requires the development and integration of infrastructures for innovative, cost- and time-effective discovery and development of novel and sustainable molecules. Significant advances in artificial intelligence (AI) and cheminformatics over the last two decades have improved the decision-making power of research scientists in the discovery of bioactive molecules. AI- and cheminformatics-driven molecule discovery offers the opportunity of moving experiments from the greenhouse to a virtual environment where thousands to billions of molecules can be investigated at a rapid pace, providing unbiased hypothesis for lead generation, optimization, and effective suggestions for compound synthesis and testing. To date, this is illustrated to a far lesser extent in the publicly available agrochemical research literature compared to drug discovery. In this review, we provide an overview of the crop protection discovery pipeline and how traditional, cheminformatics, and AI technologies can help to address the needs and challenges of agrochemical discovery towards rapidly developing novel and more sustainable products.

Time-split cross-validation is broadly recognized as the gold standard for validating predictive models intended for use in medicinal chemistry projects. Unfortunately this type of data is not broadly available outside of large pharmaceutical research organizations. Here we introduce the SIMPD (simulated medicinal chemistry project data) algorithm to split public data sets into training and test sets that mimic the differences observed in real-world medicinal chemistry project data sets. SIMPD uses a multi-objective genetic algorithm with objectives derived from an extensive analysis of the differences between early and late compounds in more than 130 lead-optimization projects run within the Novartis Institutes for BioMedical Research. Applying SIMPD to the real-world data sets produced training/test splits which more accurately reflect the differences in properties and machine-learning performance observed for temporal splits than other standard approaches like random or neighbor splits. We applied the SIMPD algorithm to bioactivity data extracted from ChEMBL and created 99 public data sets which can be used for validating machine-learning models intended for use in the setting of a medicinal chemistry project. The SIMPD code and simulated data sets are available under open-source/open-data licenses at github.com/rinikerlab/molecular_time_series.

The COVID-19 pandemic has stimulated collaborative drug discovery efforts in academia and the industry with the aim of developing therapies and vaccines that target SARS-CoV-2. Several novel therapies have been approved and deployed in the last three years. However, their clinical application has revealed limitations due to the rapid emergence of viral variants. Therefore, the development of next-generation SARS-CoV-2 therapeutic agents with a high potency and safety profile remains a high priority for global health. Increasing awareness of the \"back to nature\" approach for improving human health has prompted renewed interest in natural products, especially dietary polyphenols, as an additional therapeutic strategy to treat SARS-CoV-2 patients, owing to its good safety profile, exceptional nutritional value, health-promoting benefits (including potential antiviral properties), affordability, and availability. Herein, we describe the biological properties and pleiotropic molecular mechanisms of dietary polyphenols curcumin, resveratrol, and gossypol as inhibitors against SARS-CoV-2 and its variants as observed in in vitro and in vivo studies. Based on the advantages and disadvantages of dietary polyphenols and to obtain maximal benefits, several strategies such as nanotechnology (e.g., curcumin-incorporated nanofibrous membranes with antibacterial-antiviral ability), lead optimization (e.g., a methylated analog of curcumin), combination therapies (e.g., a specific combination of plant extracts and micronutrients), and broad-spectrum activities (e.g., gossypol broadly inhibits coronaviruses) have also been emphasized as positive factors in the facilitation of anti-SARS-CoV-2 drug development to support effective long-term pandemic management and control.

UNASSIGNED: Delineate structure-based inhibition of colony-stimulating factor-1 receptor (CSF1R) by small molecule CSF1R inhibitors in clinical development for target identification and potential lead optimization in cancer therapeutics since CSF1R is a novel predictive biomarker for immunotherapy in cancer.
UNASSIGNED: Compounds were in silico modelled by induced fit docking protocol in a molecular operating environment (MOE, MOE.v.2015). The 3-dimensional (3D) X-ray crystallized structure of CSF1R kinase (Protein Databank, ID 4R7H) was obtained from Research Collaboratory for Structural Bioinformatics (RSCB) Protein Databank. The 3D conformers of edicotinib, DCC-3014, ARRY-382, BLZ-945, chiauranib, dovitinib, and sorafenib were obtained from PubChem Database. These structures were modelled in Amber10:EHT molecular force field, and quick prep application was used to correct and optimize the structures for missing residues, H-counts, termini capping, and alternates. The binding site was defined within the vicinity of the co-crystallized ligand of CSF1R kinase. The compounds were docked by the triangular matcher placement method and ranked by the London dG scoring function. The docked poses were further refined by the induced fit method. The pose with the lowest binding score (ΔG) was used to model the ligand interaction profile in Discovery Studio Visualizer v17.2. The co-crystallized ligand was docked in its apo conformation, and root-mean-square deviation was computed to validate the docking protocol.
UNASSIGNED: All 7 CSF1R inhibitors interact with residue Met637 exhibiting selectivity except for edicotinib. The inhibitors maintain CSF1R in an auto-inhibitory conformation by interacting with Asp797 of the Asp-Phe-Gly (DFG) motif and/or hindering the conserved salt bridge formed between Glu633 and Lys616 thus stabilizing the activation loop, or interacting with tryptophan residue (Trp550) in the juxtamembrane domain. DCC-3014, ARRY-382, BLZ-945, and sorafenib bind with the lowest binding energy with CSF1R kinase.
UNASSIGNED: Pyrimidines are potent inhibitors that interact with CSF1R residues. DCC-3014 and ARRY-382 exhibit exceptional pharmaceutical potential exhibiting great structural stability and affinity.

Identification and optimization of small molecules that bind to and modulate protein function is a crucial step in the early stages of drug development. For decades, this process has benefitted greatly from the use of computational models that can provide insights into molecular binding affinity and optimization. Over the past several years, various types of deep learning models have shown great potential in improving and enhancing the performance of traditional computational methods. In this chapter, we provide an overview of recent deep learning-based developments with applications in drug discovery. We classify these methods into four subcategories dependent on the task each method is aiming to solve. For each subcategory, we provide the general framework of the approach and discuss individual methods.

The exploration of non-toxic and cost-effective dietary components, such as epigallocatechin 3-gallate and myricetin, for health improvement and disease treatment has recently attracted substantial research attention. The recent COVID-19 pandemic has provided a unique opportunity for the investigation and identification of dietary components capable of treating viral infections, as well as gathering the evidence needed to address the major challenges presented by public health emergencies. Dietary components hold great potential as a starting point for further drug development for the treatment and prevention of SARS-CoV-2 infection owing to their good safety, broad-spectrum antiviral activities, and multi-organ protective capacity. Here, we review current knowledge of the characteristics-chemical composition, bioactive properties, and putative mechanisms of action-of natural bioactive dietary flavonoids with the potential for targeting SARS-CoV-2 and its variants. Notably, we present promising strategies (combination therapy, lead optimization, and drug delivery) to overcome the inherent deficiencies of natural dietary flavonoids, such as limited bioavailability and poor stability.

Explainable machine learning is increasingly used in drug discovery to help rationalize compound property predictions. Feature attribution techniques are popular choices to identify which molecular substructures are responsible for a predicted property change. However, established molecular feature attribution methods have so far displayed low performance for popular deep learning algorithms such as graph neural networks (GNNs), especially when compared with simpler modeling alternatives such as random forests coupled with atom masking. To mitigate this problem, a modification of the regression objective for GNNs is proposed to specifically account for common core structures between pairs of molecules. The presented approach shows higher accuracy on a recently-proposed explainability benchmark. This methodology has the potential to assist with model explainability in drug discovery pipelines, particularly in lead optimization efforts where specific chemical series are investigated.