Prediction of drug sensitivity based on multi-omics data using deep learning and similarity network fusion approaches.

With the rapid development of multi-omics technologies and accumulation of large-scale bio-datasets, many studies have conducted a more comprehensive understanding of human diseases and drug sensitivity from multiple biomolecules, such as DNA, RNA, proteins and metabolites. Using single omics data is difficult to systematically and comprehensively analyze the complex disease pathology and drug pharmacology. The molecularly targeted therapy-based approaches face some challenges, such as insufficient target gene labeling ability, and no clear targets for non-specific chemotherapeutic drugs. Consequently, the integrated analysis of multi-omics data has become a new direction for scientists to explore the mechanism of disease and drug. However, the available drug sensitivity prediction models based on multi-omics data still have problems such as overfitting, lack of interpretability, difficulties in integrating heterogeneous data, and the prediction accuracy needs to be improved. In this paper, we proposed a novel drug sensitivity prediction (NDSP) model based on deep learning and similarity network fusion approaches, which extracts drug targets using an improved sparse principal component analysis (SPCA) method for each omics data, and construct sample similarity networks based on the sparse feature matrices. Furthermore, the fused similarity networks are put into a deep neural network for training, which greatly reduces the data dimensionality and weakens the risk of overfitting problem. We use three omics of data, RNA sequence, copy number aberration and methylation, and select 35 drugs from Genomics of Drug Sensitivity in Cancer (GDSC) for experiments, including Food and Drug Administration (FDA)-approved targeted drugs, FDA-unapproved targeted drugs and non-specific therapies. Compared with some current deep learning methods, our proposed method can extract highly interpretable biological features to achieve highly accurate sensitivity prediction of targeted and non-specific cancer drugs, which is beneficial for the development of precision oncology beyond targeted therapy.

2,3-Butanediol from the leachates of pine needles induces the resistance of Panax notoginseng to the leaf pathogen Alternaria panax.

Compared with the use of monocultures in the field, cultivation of medicinal herbs in forests is an effective strategy to alleviate disease. Chemical interactions between herbs and trees play an important role in disease suppression in forests. We evaluated the ability of leachates from needles of Pinus armandii to induce resistance in Panax notoginseng leaves, identified the components via gas chromatography-mass spectrometry (GC-MS), and then deciphered the mechanism of 2,3-Butanediol as the main component in the leachates responsible for resistance induction via RNA sequencing (RNA-seq). Prespraying leachates and 2,3-Butanediol onto leaves could induce the resistance of P. notoginseng to Alternaria panax. The RNA-seq results showed that prespraying 2,3-Butanediol onto leaves with or without A. panax infection upregulated the expression of large number of genes, many of which are involved in transcription factor activity and the mitogen-activated protein kinase (MAPK) signaling pathway. Specifically, 2,3-Butanediol spraying resulted in jasmonic acid (JA) -mediated induced systemic resistance (ISR) by activating MYC2 and ERF1. Moreover, 2,3-Butanediol induced systemic acquired resistance (SAR) by upregulating pattern-triggered immunity (PTI)- and effector-triggered immunity (ETI)-related genes and activated camalexin biosynthesis through activation of WRKY33. Overall, 2,3-Butanediol from the leachates of pine needles could activate the resistance of P. notoginseng to leaf disease infection through ISR, SAR and camalexin biosynthesis. Thus, 2,3-Butanediol is worth developing as a chemical inducer for agricultural production.

Dynamic Meta-data Network Sparse PCA for Cancer Subtype Biomarker Screening.

Previous research shows that each type of cancer can be divided into multiple subtypes, which is one of the key reasons that make cancer difficult to cure. Under these circumstances, finding a new target gene of cancer subtypes has great significance on developing new anti-cancer drugs and personalized treatment. Due to the fact that gene expression data sets of cancer are usually high-dimensional and with high noise and have multiple potential subtypes' information, many sparse principal component analysis (sparse PCA) methods have been used to identify cancer subtype biomarkers and subtype clusters. However, the existing sparse PCA methods have not used the known cancer subtype information as prior knowledge, and their results are greatly affected by the quality of the samples. Therefore, we propose the Dynamic Metadata Edge-group Sparse PCA (DM-ESPCA) model, which combines the idea of meta-learning to solve the problem of sample quality and uses the known cancer subtype information as prior knowledge to capture some gene modules with better biological interpretations. The experiment results on the three biological data sets showed that the DM-ESPCA model can find potential target gene probes with richer biological information to the cancer subtypes. Moreover, the results of clustering and machine learning classification models based on the target genes screened by the DM-ESPCA model can be improved by up to 22-23% of accuracies compared with the existing sparse PCA methods. We also proved that the result of the DM-ESPCA model is better than those of the four classic supervised machine learning models in the task of classification of cancer subtypes.

Appropriate Soil Heat Treatment Promotes Growth and Disease Suppression of Panax notoginseng by Interfering with the Bacterial Community.

In our greenhouse experiment, soil heat treatment groups (50, 80, and 121°C) significantly promoted growth and disease suppression of Panax notoginseng in consecutively cultivated soil (CCS) samples (p < 0.01), and 80°C worked better than 50°C and 121°C (p < 0.01). Furthermore, we found that heat treatment at 80°C changes the microbial diversity in CCS, and the inhibition ratios of culturable microorganisms, such as fungi and actinomycetes, were nearly 100%. However, the heat-tolerant bacterial community was preserved. The 16S rRNA gene and internal transcribed spacer (ITS) sequencing analyses indicated that the soil heat treatment had a greater effect on the Chao1 index and Shannon's diversity index of bacteria than fungi, and the relative abundances of Firmicutes and Proteobacteria were significantly higher than without heating (80 and 121°C, p < 0.05). Soil probiotic bacteria, such as Bacillus (67%), Sporosarcina (9%), Paenibacillus (6%), Paenisporosarcina (6%), and Cohnella (4%), remained in the soil after the 80°C and 121°C heat treatments. Although steam increased the relative abundances of most of the heat-tolerant microbes before sowing, richness and diversity gradually recovered to the level of CCS, regardless of fungi or bacteria, after replanting. Thus, we added heat-tolerant microbes (such as Bacillus) after steaming, which reduced the relative abundance of pathogens, recruited antagonistic bacteria, and provided a long-term protective effect compared to the steaming and Bacillus alone (p < 0.05). Taken together, the current study provides novel insight into sustainable agriculture in a consecutively cultivated system.

Appropriate nitrogen application enhances saponin synthesis and growth mediated by optimizing root nutrient uptake ability.

BACKGROUND: Cultivation of medicinal crops, which synthesize hundreds of substances for curative functions, was focused on the synthesis of secondary metabolites rather than biomass accumulation. Nutrition is an important restrict factor for plant growth and secondary metabolites, but little attention has been given to the plasticity of nutrient uptake and secondary metabolites synthesis response to soil nitrogen (N) change. METHODS: Two year-field experiments of Sanqi (Panax notoginseng), which can synthesize a high level of saponin in cells, were conducted to study the effects of N application on the temporal dynamics of biomass, nutrient absorption, root architecture and the relationships between these parameters and saponin synthesis. RESULTS: Increasing N fertilizer rates could improve the dry matter yields and nutrient absorption ability through increasing the maximum daily growth (or nutrient uptake) rate. Under suitable N level (225 kg/ha N), Sanqi restricted the root length and surface and enhanced the root diameter and N uptake rate per root length (NURI) to promote nutrient absorption, but the opposite status of Sanqi root architecture and NURI was found when soil N was deficient. Furthermore, increasing N rates could promote the accumulation of saponin in roots through improving the NURI, which showed a significant positive relationship with the content of saponin in the taproots. CONCLUSION: Appropriate N fertilizer rates could optimize both root architecture and nutrient uptake efficiency, then promote both the accumulation of dry matter and the synthesis of saponins.

[Effects of As stress on contents of saponin and flavonoid, key enzymes activities of Panax notoginseng and its proteomic analysis]. / ç ·èƒè¿«å¯¹ä¸‰ä¸ƒçš‚è‹·å’Œé»„é ®å«é‡ã€å ³é”®é ¶æ´»æ€§çš„å½±å“åŠå ¶è›‹ç™½è´¨ç»„åˆ†æž.

Field plot experiments were conducted to study the effect of two-year consecutive As stress [As(V): 0, 20, 80, 140, 200 and 260 mg·kg-1] on contents of As, saponin and flanovoids, the enzyme activities of phenylalanine ammonia lyase (PAL), chalcone synthase (CHS), and squalene synthase (SS) in main root, fibrous root and rhizome and shoot, and proteome of three-year old Panax notoginseng in Wenshan prefecture, Yunnan Province, China. The results showed that total saponin content of fibrous root decreased with increase in As treatment concentration. Total saponin contents of shoot and rhizome increased with 140 mg·kg-1 As treatment compared with control. SS activity of rhizome was higher than that of shoot. Flavonoid contents of diffe-rent plant parts decreased with increase in As treatment concentration. With 140 mg·kg-1 As treatment, activities of PAL and CHS in rhizome were higher than that in shoot. CHS activities in shoot and rhizome were lower, and PAL activities were higher than those of the control. As contents in different plant parts of P. notoginseng increased with increase in As treatment concentration. The highest As content was observed in fibrous root. With 140 mg·kg-1 As treatment, twenty-one diffe-rential proteins (ratio >2, P<0.05) were identified in the inoculated compared to the control. The down-regulated proteins included phosphoribulokinase, heat shock protein, NAD(P)-binding rossmann-fold superfamily proteinisoform, monodehydroascorbate reductase and cytochrome b6-f complex iron-sulfur subunit. The up-regulated proteins included CDC27 family protein, acidic endochitinase isoform, symbiosis receptor-like kinase precursor, isoflavone reductase-like protein, phospho-2-dehydro-3-deoxyheptonate aldolase, putative protein kinase superfamily protein, malate dehydrogenase, glyoxalase I isoform and glutamine synthetase cytosolic isozyme. In general, with two-year consecutive As stress, As contents in different plant parts of P. notoginseng increased, which not only affected the photosynthesis and energy, but also decreased the antioxidation and resilience, and induced the increased expression of protein involved in detoxication, resulted in decrease in the contents of flavonoid and saponin. The tolerant threshold value of P. notoginseng for As was 140 mg·kg-1.