MMDAE-HGSOC: A novel method for high-grade serous ovarian cancer molecular subtypes classification based on multi-modal deep autoencoder.

High-grade serous ovarian cancer (HGSOC) is a type of ovarian cancer developed from serous tubal intraepithelial carcinoma. The intrinsic differences among molecular subtypes are closely associated with prognosis and pathological characteristics. At present, multi-omics data integration methods include early integration and late integration. Most existing HGSOC molecular subtypes classification methods are based on the early integration of multi-omics data. The mutual interference among multi-omics data is ignored, which affects the effectiveness of feature learning. High-dimensional multi-omics data contains genes unassociated with HGSOC molecular subtypes, resulting in redundant information, which is not conducive to model training. In this paper, we propose a multi-modal deep autoencoder learning method, MMDAE-HGSOC. MiRNA expression, DNA methylation, and copy number variation (CNV) are integrated with mRNA expression data to construct a multi-omics feature space. The multi-modal deep autoencoder network is used to learn the high-level feature representation of multi-omics data. The superposition LASSO (S-LASSO) regression algorithm is proposed to fully obtain the associated genes of HGSOC molecular subtypes. The experimental results show that MMDAE-HGSOC is superior to the existing classification methods. Finally, we analyze the enrichment gene ontology (GO) terms and biological pathways of these significant genes, which are discovered during the gene selection process.

[Characteristics of CO2 and N2O Emissions Under Two Land Use Types in the Loess Plateau of China].

To evaluate the emission characteristics of carbon dioxide (CO2) and nitrous oxide (N2O) in the Loess Plateau, a field in situ study was conducted from July 2017 to July 2018 under two land-use types (15 year old apple orchard and wheat field) using static chamber-gas chromatographic techniques. Four treatments were conducted in this experiment as follows:apple orchard with fertilization (AF), apple orchard without fertilization (ACK), wheat field with fertilization (WF), and wheat field without fertilization (WCK). The results showed that CO2 and N2O emissions varied significantly with the season, and the emission peaks appeared after rainfall and fertilization. The cumulative amount of CO2 and N2O emissions from the AF treatment were 7.14% and 461.4% higher than that of the WF treatment, respectively. However, the cumulative amount of CO2 emissions under the ACK treatment was 10.41% lower than that of the WCK treatment, whereas the cumulative amount of N2O emissions was 109.5% higher than that of the WCK treatment. The N2O emission flux from the orchard was significantly positively correlated with soil temperature and moisture (P<0.01). The CO2 emission fluxes from the orchard and wheat field were significantly positively correlated with topsoil temperature (P<0.05) but were not correlated with topsoil moisture. Thus, the combination of field management and environmental factors affected soil CO2 and N2O emissions. The fertilizer regime and soil hydrothermal conditions were the main factors influencing the characteristics of CO2 and N2O emissions under different land-use types.