Culinary herbs and spices are widely used as a traditional medicine in the treatment of diabetes and its complications, and there are several scientific studies in the literature supporting the use of these medicinal plants. However, there is often a lack of knowledge on the bioactive compounds of these herbs and spices and their mechanisms of action. The aim of this study was to use inverse virtual screening to provide insights into the bioactive compounds of common herbs and spices, and their potential molecular mechanisms of action in the treatment of diabetes. In this study, a library of over 2300 compounds derived from 30 common herbs and spices were screened in silico with the DIA-DB web server against 18 known diabetes drug targets. Over 900 compounds from the herbs and spices library were observed to have potential anti-diabetic activity and liquorice, hops, fennel, rosemary, and fenugreek were observed to be particularly enriched with potential anti-diabetic compounds. A large percentage of the compounds were observed to be potential polypharmacological agents regulating three or more anti-diabetic drug targets and included compounds such as achillin B from yarrow, asparasaponin I from fenugreek, bisdemethoxycurcumin from turmeric, carlinoside from lemongrass, cinnamtannin B1 from cinnamon, crocin from saffron and glabridin from liquorice. The major targets identified for the herbs and spices compounds were dipeptidyl peptidase-4 (DPP4), intestinal maltase-glucoamylase (MGAM), liver receptor homolog-1 (NR5A2), pancreatic alpha-amylase (AM2A), peroxisome proliferator-activated receptor alpha (PPARA), protein tyrosine phosphatase non-receptor type 9 (PTPN9), and retinol binding protein-4 (RBP4) with over 250 compounds observed to be potential inhibitors of these particular protein targets. Only bay leaves, liquorice and thyme were found to contain compounds that could potentially regulate all 18 protein targets followed by black pepper, cumin, dill, hops and marjoram with 17 protein targets. In most cases more than one compound within a given plant could potentially regulate a particular protein target. It was observed that through this multi-compound-multi target regulation of these specific protein targets that the major anti-diabetic effects of reduced hyperglycemia and hyperlipidemia of the herbs and spices could be explained. The results of this study, taken together with the known scientific literature, indicated that the anti-diabetic potential of common culinary herbs and spices was the result of the collective action of more than one bioactive compound regulating and restoring several dysregulated and interconnected diabetic biological processes.

Virtual screening has become a widely used technique for helping in drug discovery processes. The key to this success is its ability to aid in the identification of novel bioactive compounds by screening large molecular databases. Several web servers have emerged in the last few years supplying platforms to guide users in screening publicly accessible chemical databases in a reasonable time. In this review, we discuss a representative set of online virtual screening servers and their underlying similarity algorithms. Other related topics, such as molecular representation or freely accessible databases are also treated. The most relevant contributions to this review arise from critical discussions concerning the pros and cons of servers and algorithms, and the challenges that future works must solve in a virtual screening framework.

De novo drug design is a stationary way to build novel ligands in the confined pocket of receptor by assembling the atoms or fragments, while molecular dynamics (MD) simulation is a dynamical way to study the interaction mechanism between the ligands and receptors based on the molecular force field. De novo drug design and MD simulation are effective tools for novel drug discovery. With the development of technology, deep learning methods, and interpretable machine learning (IML) have emerged in the research area of drug design. Deep learning methods and IML can be used further to improve the efficiency and accuracy of de novo drug design and MD simulations. The application summary of deep learning methods for de novo drug design, MD simulations, and IML can further promote the technical development of drug discovery. In this article, two major workflow methods and the related components of classical algorithm and deep learning are described for de novo drug design from a new perspective. The application progress of deep learning is also summarized for MD simulations. Furthermore, IML is introduced for the deep learning model interpretability of de novo drug design and MD simulations. Our paper deals with an interesting topic about deep learning applications of de novo drug design and MD simulations for the scientific community. This article is categorized under: Data Science > Chemoinformatics Data Science > Artificial Intelligence/Machine Learning

Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements. In this sense, learning tools are becoming a commodity but, to be able to assist doctors on a daily basis, it is essential to fully understand how models can be interpreted. In this survey, we analyse current machine learning models and other in-silico tools as applied to medicine—specifically, to cancer research—and we discuss their interpretability, performance and the input data they are fed with. Artificial neural networks (ANN), logistic regression (LR) and support vector machines (SVM) have been observed to be the preferred models. In addition, convolutional neural networks (CNNs), supported by the rapid development of graphic processing units (GPUs) and high-performance computing (HPC) infrastructures, are gaining importance when image processing is feasible. However, the interpretability of machine learning predictions so that doctors can understand them, trust them and gain useful insights for the clinical practice is still rarely considered, which is a factor that needs to be improved to enhance doctors’ predictive capacity and achieve individualised therapies in the near future.

Artificial intelligence can train the related known drug data into deep learning models for drug design, while classical algorithms can design drugs through established and predefined procedures. Both deep learning and classical algorithms have their merits for drug design. Here, the webserver WADDAICA is built to employ the advantage of deep learning model and classical algorithms for drug design. The WADDAICA mainly contains two modules. In the first module, WADDAICA provides deep learning models for scaffold hopping of compounds to modify or design new novel drugs. The deep learning model which is used in WADDAICA shows a good scoring power based on the PDBbind database. In the second module, WADDAICA supplies functions for modifying or designing new novel drugs by classical algorithms. WADDAICA shows better Pearson and Spearman correlations of binding affinity than Autodock Vina that is considered to have the best scoring power. Besides, WADDAICA supplies a friendly and convenient web interface for users to submit drug design jobs. We believe that WADDAICA is a useful and effective tool to help researchers to modify or design novel drugs by deep learning models and classical algorithms. WADDAICA is free and accessible at https://bqflab.github.io or https://heisenberg.ucam.edu:5000 .