Crowdsourced mapping of unexplored target space of kinase inhibitors.

Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound-kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.

Analysis of the GC-MS of volatile compounds and the phytochemical profile and antioxidant activities of some Bulgarian medicinal plants.

The study's objective was to investigate the volatile compounds, assess the total phenolic content and phenolic acids profile, determine the antioxidant capacity and evaluate the anthocyanin and flavonoid contents in stinging nettle (Urtica dioica L.), tansy (Tanacetum vulgare L.), bladder campion (Silene vulgaris (Moench) Garcke) and rosehip fruit (Rosa canina L. cv. Plovdiv 1). The total phenolic content ranged from 0.55±0.00 to 47.39±0.41 mg GAE/g dw, total flavonoids ranged from 0.45±0.02 to 17.27±0.45 mg QЕ/g dw and the total anthocyanins ranged from 0.94±0.23 to 58.11±2.85 mg/L. The results demonstrated that the selected research plants show auspiciously useful properties in fields like pharmacy, food preparation, cosmetics, etc. Furthermore, the most promising extraction methods in terms of bioactivity are decoction and tincture (U. dioica; T. vulgare; S. vulgaris) and tincture (R. canina). The current study could be regarded as a first detailed investigation of the biological activity and phytochemical composition of R. canina L. cv. Plovdiv 1.

Carotenoids, tocopherols, organic acids, charbohydrate and mineral content in different medicinal plant extracts.

Nettle (Urtica dioica L.), tansy (Tanacetum vulgare L.), bladder campion (Silene vulgaris (Moench) Garcke, waterpepper (Polygonum hydropiper L.), common centaury (Centaurium erythraea Pers.) and rose hip fruit (Rosa canina L. cv. Plovdiv 1) were used for preparation of different water extracts (infusion, decoction and microwave extract) and ethanol (tincture) extracts. Carotenoids (lutein, lycopene and ß-carotene), tocopherols (α-, γ- and δ-), organic acids (ascorbic, malic, fumaric and citric), five macro- and three microelements, sugars and uronic acids content in the obtained extracts were analyzed. Among the investigated plants, stinging nettle, bladder campion and rose hip fruit were evaluated as most potential with respect to bioactive compounds and microelements. The results showed that the selected six medicinal plants and their extracts can be presented as sources of dietary fibers and micronutrients, which may encourage further application as food supplements and beverages as well as to motivate plant use as a dietary alternative in different foods. The present study is a first detailed analysis with respect to sugar content of decoction, infusion and tincture of S. vulgaris.

Deep reinforcement learning for de novo drug design.

We have devised and implemented a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). On the basis of deep and reinforcement learning (RL) approaches, ReLeaSE integrates two deep neural networks-generative and predictive-that are trained separately but are used jointly to generate novel targeted chemical libraries. ReLeaSE uses simple representation of molecules by their simplified molecular-input line-entry system (SMILES) strings only. Generative models are trained with a stack-augmented memory network to produce chemically feasible SMILES strings, and predictive models are derived to forecast the desired properties of the de novo-generated compounds. In the first phase of the method, generative and predictive models are trained separately with a supervised learning algorithm. In the second phase, both models are trained jointly with the RL approach to bias the generation of new chemical structures toward those with the desired physical and/or biological properties. In the proof-of-concept study, we have used the ReLeaSE method to design chemical libraries with a bias toward structural complexity or toward compounds with maximal, minimal, or specific range of physical properties, such as melting point or hydrophobicity, or toward compounds with inhibitory activity against Janus protein kinase 2. The approach proposed herein can find a general use for generating targeted chemical libraries of novel compounds optimized for either a single desired property or multiple properties.