‡We describe the use of singular value decomposition in transforming genome-wide expression data from genes 3 arrays space to reduced diagonalized ‘‘eigengenes’’ 3 ‘‘eigenarrays’’ space, where the eigengenes (or eigenarrays) are unique orthonormal superpositions of the genes (or arrays). Normalizing the data by filtering out the eigengenes (and eigenarrays) that are inferred to represent noise or experimental artifacts enables meaningful comparison of the expression of different genes across different arrays in different experiments. Sorting the data according to the eigengenes and eigenarrays gives a global picture of the dynamics of gene expression, in which individual genes and arrays appear to be classified into groups of similar regulation and function, or similar cellular state and biological phenotype, respectively. After normalization and sorting, the significant eigengenes and eigenarrays can be associated with observed genome-wide effects of regulators, or with measured samples, in which these regulators are overactive or underactive, respectively.

Singular Value Decomposition for Genome-Wide Expression Data Processing and Modeling

Liquid chromatography coupled to high-resolution mass spectrometry platforms are increasingly employed to comprehensively measure metabolome changes in systems biology and complex diseases. Over the past decade, several powerful computational pipelines have been developed for spectral processing, annotation, and analysis. However, significant obstacles remain with regard to parameter settings, computational efficiencies, batch effects, and functional interpretations. Here, we introduce MetaboAnalystR 3.0, a significantly improved pipeline with three key new features: (1) efficient parameter optimization for peak picking; (2) automated batch effect correction; and 3) more accurate pathway activity prediction. Our benchmark studies showed that this workflow was 20~100X faster compared to other well-established workflows and produced more biologically meaningful results. In summary, MetaboAnalystR 3.0 offers an efficient pipeline to support high-throughput global metabolomics in the open-source R environment.

/pdf/metaboanalystr-3-0-toward-an-optimized-workflow-for-global-2d4fcwcuun.pdf

MetaboAnalystR 3.0: Toward an Optimized Workflow for Global Metabolomics.

Taking the leap between analytical chemistry and artificial intelligence: A tutorial review.

To determine the location patterns of distant metastases at initial staging and outcomes of ovarian, uterine, and cervical cancer patients. Data were obtained from the SEER database from 2010 to 2015. Analyses were performed using Kaplan–Meier and multivariate Cox proportional hazard methods. Of 3035 patients (median age: 63, range: 17–95) with stage IV gynecologic cancer, ovarian, uterine, and cervical cancers were present in 42%, 40%, and 18% of the cohort. The proportion of lung, liver, bone and brain metastases were identified in 38%, 57%, 4%, and 1% of ovarian cancer patients, 62%, 22%, 13%, and 3% of uterine cancer patients, and 59%, 16%, 23%, and 2% of cervical cancer patients, respectively. The 5-year disease-specific survival for all patients was 19%. Those with liver metastases had survival rates of 26% compared to 15% for lung, 13% for bone, and 6% for brain (p < 0.0001). Patients with ovarian, uterine, and cervical cancers had survival rates of 28%, 12%, and 12%, respectively (p < 0.0001). On multivariate analysis, brain metastasis (HR = 1.64, 95% CI 1.21–2.22, p < 0.01), uterine (HR = 1.77, 95 CI 1.56–2.02, p < 0.0001) and cervical (HR = 1.35, 95% CI 1.11–1.63, p < 0.01) cancers, and lack of insurance (HR = 1.41, 95% CI 1.16–1.73, p < 0.001) were independent predictors for poorer survival. Age, year, region, and race did not affect prognosis. Stage IV ovarian cancer most frequently metastasizes to the liver, whereas uterine and cervical cancers spread more to the lung. Overall, these patients have poor prognosis, particularly those with uterine or cervical primary disease or brain metastases.

Ovarian, uterine, and cervical cancer patients with distant metastases at diagnosis: most common locations and outcomes.

Deep learning (DL), an emerging area of investigation in the fields of machine learning and artificial intelligence, has markedly advanced over the past years. DL techniques are being applied to assist medical professionals and researchers in improving clinical diagnosis, disease prediction and drug discovery. It is expected that DL will help to provide actionable knowledge from a variety of 'big data', including metabolomics data. In this review, we discuss the applicability of DL to metabolomics, while presenting and discussing several examples from recent research. We emphasize the use of DL in tackling bottlenecks in metabolomics data acquisition, processing, metabolite identification, as well as in metabolic phenotyping and biomarker discovery. Finally, we discuss how DL is used in genome-scale metabolic modelling and in interpretation of metabolomics data. The DL-based approaches discussed here may assist computational biologists with the integration, prediction and drawing of statistical inference about biological outcomes, based on metabolomics data.

Deep learning meets metabolomics: a methodological perspective.

Sites of distant metastases and overall survival in ovarian cancer: A study of 1481 patients

WaveICA: A novel algorithm to remove batch effects for large-scale untargeted metabolomics data based on wavelet analysis.

Untargeted metabolomics based on liquid chromatography-mass spectrometry is affected by nonlinear batch effects, which cover up biological effects, result in nonreproducibility, and are difficult to be calibrate. In this study, we propose a novel deep learning model, called Normalization Autoencoder (NormAE), which is based on nonlinear autoencoders (AEs) and adversarial learning. An additional classifier and ranker are trained to provide adversarial regularization during the training of the AE model, latent representations are extracted by the encoder, and then the decoder reconstructs the data without batch effects. The NormAE method was tested on two real metabolomics data sets. After calibration by NormAE, the quality control samples (QCs) for both data sets gathered most closely in a PCA score plot (average distances decreased from 56.550 and 52.476 to 7.383 and 14.075, respectively) and obtained the highest average correlation coefficients (from 0.873 and 0.907 to 0.997 for both). Additionally, NormAE significantly improved biomarker discovery (median number of differential peaks increased from 322 and 466 to 1140 and 1622, respectively). NormAE was compared with four commonly used batch effect removal methods. The results demonstrated that using NormAE produces the best calibration results.

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data.

Blood glucose (BG) concentration of the human body serves as an important index for diagnosis of diabetes, and its detection methods need to be more efficient due to high mortality rates for diabetes. Typical household BG meters are invasive products based on electrochemistry and rely on finger pricks to procure blood, which might result in skin damage and bacterial infections. Moreover, such BG meters can only detect the BG concentration at a certain time while ignoring the BG level at other times. Recently, to achieve microinvasive, noninvasive and continuous glucose monitoring (CGM) by detecting body fluid, such as sweat or tears, the research direction has been gradually developing toward wearable devices. This review discusses the glucose detection mechanism of various electrochemical and optical glucose sensors, and briefly analyzes their advantages and challenges. Additionally, wearable products based on various principles that have appeared on the market are also summarized. Furthermore, based on the analysis, this review proposes a design concept for future research directions.

Blood glucose sensors and recent advances: A review

The tumor immune microenvironment is heterogeneous, and its impact on treatment responses is not well understood. It is still a challenge to analyze the interaction between malignant cells and the tumor microenvironment to apply suitable immunotherapy in lung adenocarcinoma. We performed the nonnegative matrix factorization method to 513 messenger RNA expression profiles of lung adenocarcinomas (LUADs) from The Cancer Genome Atlas (TCGA) to obtain an immune-related expression pattern. Subsequently, we characterized the immune-related gene signatures and clinical and survival characteristics. We used 576 patients from Gene Expression Omnibus to confirm our findings. Of the patients in the training cohort, 51% had a high immune enrichment score, high expression of immune cell signaling, cytolytic activity, and interferon (IFN)-related signatures (all P < .05). We denoted these as the Immune Class. We further subdivided the Immune Class into two subclasses based on the tumor microenvironment. These were denoted the Active Immune Class and Exhausted Immune Class. The former showed significant IFN, T-cells, M1 macrophage signatures, and better prognosis (all P < .05), while the latter presented an exhausted immune response with activated stromal enrichment, M2 macrophage signatures, and immunosuppressive factors such as WNT/transforming growth factor-β (all P < .05). Furthermore, we predicted the response of our immunophenotypes to immunological checkpoint inhibitors (P < .05). Our findings provide a novel insight into the immune-related state of LUAD and can identify the patients who will be receptive to suitable immunotherapeutic treatments.

Qilong Tan

Papers

Sites of distant metastases and overall survival in ovarian cancer: A study of 1481 patients

WaveICA: A novel algorithm to remove batch effects for large-scale untargeted metabolomics data based on wavelet analysis.

NormAE: Deep Adversarial Learning Model to Remove Batch Effects in Liquid Chromatography Mass Spectrometry-Based Metabolomics Data.

Blood glucose sensors and recent advances: A review

Identification immunophenotyping of lung adenocarcinomas based on the tumor microenvironment.