Machine learning-based integration develops a multiple programmed cell death signature for predicting the clinical outcome and drug sensitivity in colorectal cancer.

Tumorigenesis and treatment are closely associated with various programmed cell death (PCD) patterns. However, the coregulatory role of multiple PCD patterns in colorectal cancer (CRC) remains unknown. In this study, we developed a multiple PCD index (MPCDI) based on 19 PCD patterns using two machine learning algorithms for risk stratification, prognostic prediction, construction of nomograms, immune cell infiltration analysis, and chemotherapeutic drug sensitivity analysis. As a result, in the TCGA-COAD, GSE17536, and GSE29621 cohorts, the MPCDI can effectively distinguished survival outcomes in CRC patients and served as an independent factor for CRC patients. We then explored the immune infiltration landscape in two groups using the nine algorithms and found more overall immune infiltration in the high-MPCDI group. TIDE scores suggested that the increased immune evasion potential and immune checkpoint inhibition therapy may be less effective in the high-MPCDI group. Immunophenoscores indicated that anti-PD1, anti-cytotoxic T-lymphocyte associated antigen 4 (anti-CTLA4), and anti-PD1-CTLA4 combination therapies are less effective in the high-MPCDI group. In addition, the high-MPCDI group was more sensitive to AZD1332, Foretinib, and IGF1R_3801, and insensitive to AZD3759, AZD5438, AZD6482, Erlotinib, GSK591, IAP_5620, and Picolinici-acid, which suggests that the MPCDI can guide drug selection for CRC patients. As a new clinical classifier, the MPCDI can more accurately distinguish CRC patients who benefit from immunotherapy and develop personalized treatment strategies for CRC patients.

A novel generation adversarial network framework with characteristics aggregation and diffusion for brain disease classification and feature selection.

Imaging genetics provides unique insights into the pathological studies of complex brain diseases by integrating the characteristics of multi-level medical data. However, most current imaging genetics research performs incomplete data fusion. Also, there is a lack of effective deep learning methods to analyze neuroimaging and genetic data jointly. Therefore, this paper first constructs the brain region-gene networks to intuitively represent the association pattern of pathogenetic factors. Second, a novel feature information aggregation model is constructed to accurately describe the information aggregation process among brain region nodes and gene nodes. Finally, a deep learning method called feature information aggregation and diffusion generative adversarial network (FIAD-GAN) is proposed to efficiently classify samples and select features. We focus on improving the generator with the proposed convolution and deconvolution operations, with which the interpretability of the deep learning framework has been dramatically improved. The experimental results indicate that FIAD-GAN can not only achieve superior results in various disease classification tasks but also extract brain regions and genes closely related to AD. This work provides a novel method for intelligent clinical decisions. The relevant biomedical discoveries provide a reliable reference and technical basis for the clinical diagnosis, treatment and pathological analysis of disease.

Feature aggregation graph convolutional network based on imaging genetic data for diagnosis and pathogeny identification of Alzheimer's disease.

The roles of brain regions activities and gene expressions in the development of Alzheimer's disease (AD) remain unclear. Existing imaging genetic studies usually has the problem of inefficiency and inadequate fusion of data. This study proposes a novel deep learning method to efficiently capture the development pattern of AD. First, we model the interaction between brain regions and genes as node-to-node feature aggregation in a brain region-gene network. Second, we propose a feature aggregation graph convolutional network (FAGCN) to transmit and update the node feature. Compared with the trivial graph convolutional procedure, we replace the input from the adjacency matrix with a weight matrix based on correlation analysis and consider common neighbor similarity to discover broader associations of nodes. Finally, we use a full-gradient saliency graph mechanism to score and extract the pathogenetic brain regions and risk genes. According to the results, FAGCN achieved the best performance among both traditional and cutting-edge methods and extracted AD-related brain regions and genes, providing theoretical and methodological support for the research of related diseases.

Shape-tunable polymeric Janus nanoparticles with hollow cavities derived from polymerization induced self-assembly based crosslinked vesicles.

The fabrication of shape-tunable polymeric Janus nanoparticles with hollow cavities derived from polymerization induced self-assembly based crosslinked vesicles is reported for the first time in this work. These novel polymeric JNPs can be applied to an extensive range of applications, wherein nanoparticles with controllable hollow morphologies are needed.

[Determination of volatile nitrosamines in urine through gas chromatography-mass spectrometry].

OBJECTIVE: To establish a detection method based on gas chromatography-mass spectrometry (GC-MS) for concentrations of volatile nitrosamine compounds in urine, and apply it to the test of real samples. METHODS: Target compounds dichloromethane in urine samples was extracted with dichloromethane through liquid-liquid extraction, then the dichloromethane extract was filtrated, evaporated with nitrogen at 40°C to dryness, and the volume was set with 0.2 ml dichloromethane. Analysis of nine volatile nitroso-compounds were performed with GC-MS under selected ion monitoring mode, external reference method was used for quantification, and the detection limit, repeatability and sensitivity were evaluated. In addition, nine volatile nitroso-compounds of 92 urine samples in a town of Anhui province were measured. RESULTS: A good linear range of 2 - 200 ng/ml (with correlation coefficient 0.9985 - 0.9999) were obtained for the above mentioned nine kinds of analyte, and the lowest examination concentration was 0.05 - 0.50 ng/ml. The addition standard recoveries were 68%-102% with the RSD of 0.4% - 5.5% (n = 3). The detection limits were 0.001 - 0.013 ng/ml urine. The detection rate of N-nitrosodimethylamine (NDMA), N-nitrosomethylethylamine (NMEA), N-nitrosodiethylamine (NDEA), N-nitrosodi-n-propylamine (NDPA), N-nitrosopyrrolidine (NPYR), N-nitrosomorpholine (NMOR), N-nitrosopiperidine (NPIP), N-nitrosodi-n-butylamine (NDBA) and N-nitrosodiphenylamine (NDPhA) were 71% (65), 74% (68), 65% (60), 80% (73), 92% (85), 78% (72), 76% (70), 87% (80), 98% (90), respectively, with the results (0.27 ± 0.12), (0.75 ± 0.29), (0.06 ± 0.02), (0.16 ± 0.07), (23.66 ± 5.18), (1.01 ± 0.35), (0.38 ± 0.11), (2.47 ± 0.52) and (15.13 ± 3.48) nmol/g creatinine. CONCLUSIONS: A gas chromatography-mass spectrometry detect method was developed for low level volatile nitrosamines in urine samples.