A deep learning method for drug-target affinity prediction based on sequence interaction information mining.

Background: A critical aspect of in silico drug discovery involves the prediction of drug-target affinity (DTA). Conducting wet lab experiments to determine affinity is both expensive and time-consuming, making it necessary to find alternative approaches. In recent years, deep learning has emerged as a promising technique for DTA prediction, leveraging the substantial computational power of modern computers. Methods: We proposed a novel sequence-based approach, named KC-DTA, for predicting drug-target affinity (DTA). In this approach, we converted the target sequence into two distinct matrices, while representing the molecule compound as a graph. The proposed method utilized k-mers analysis and Cartesian product calculation to capture the interactions and evolutionary information among various residues, enabling the creation of the two matrices for target sequence. For molecule, it was represented by constructing a molecular graph where atoms serve as nodes and chemical bonds serve as edges. Subsequently, the obtained target matrices and molecule graph were utilized as inputs for convolutional neural networks (CNNs) and graph neural networks (GNNs) to extract hidden features, which were further used for the prediction of binding affinity. Results: In order to evaluate the effectiveness of the proposed method, we conducted several experiments and made a comprehensive comparison with the state-of-the-art approaches using multiple evaluation metrics. The results of our experiments demonstrated that the KC-DTA method achieves high performance in predicting drug-target affinity (DTA). The findings of this research underscore the significance of the KC-DTA method as a valuable tool in the field of in silico drug discovery, offering promising opportunities for accelerating the drug development process. All the data and code are available for access on https://github.com/syc2017/KCDTA.

Chromosomal-level genome of velvet bean (Mucuna pruriens) provides resources for L-DOPA synthetic research and development.

Mucuna pruriens, commonly called velvet bean, is the main natural source of levodopa (L-DOPA), which has been marketed as a psychoactive drug for the clinical management of Parkinson's disease and dopamine-responsive dystonia. Although velvet bean is a very important plant species for food and pharmaceutical manufacturing, the lack of genetic and genomic information about this species severely hinders further molecular research thereon and biotechnological development. Here, we reported the first velvet bean genome, with a size of 500.49 Mb and 11 chromosomes encoding 28,010 proteins. Genomic comparison among legume species indicated that velvet bean speciated ∼29 Ma from soybean clade, without specific genome duplication. Importantly, we identified 21 polyphenol oxidase coding genes that catalyse l-tyrosine to L-DOPA in velvet bean, and two subfamilies showing tandem expansion on Chr3 and Chr7 after speciation. Interestingly, disease-resistant and anti-pathogen gene families were found contracted in velvet bean, which might be related to the expansion of polyphenol oxidase. Our study generated a high-quality genomic reference for velvet bean, an economically important agricultural and medicinal plant, and the newly reported L-DOPA biosynthetic genes could provide indispensable information for the biotechnological and sustainable development of an environment-friendly L-DOPA biosynthesis processing method.

The Chromosome Level Genome and Genome-wide Association Study for the Agronomic Traits of Panax Notoginseng.

The Chinese ginseng Panax notoginseng is a domesticated herb with significant medicinal and economic value. Here we report a chromosome-level P. notoginseng genome assembly with a high (∼79%) repetitive sequence content. The juxtaposition with the widely distributed, closely related Korean ginseng (Panax ginseng) genome revealed contraction of plant defense genes (in particular R-genes) in the P. notoginseng genome. We also investigated the reasons for the larger genome size of Panax species, revealing contributions from two Panax-specific whole-genome duplication events and transposable element expansion. Transcriptome data and comparative genome analysis revealed the candidate genes involved in the ginsenoside synthesis pathway. We also performed a genome-wide association study on 240 cultivated P. notoginseng individuals and identified the associated genes with dry root weight (63 genes) and stem thickness (168 genes). The P. notoginseng genome represents a critical step toward harnessing the full potential of an economically important and enigmatic plant.