Multiple biological clocks govern a healthy pregnancy. These biological mechanisms produce immunologic, metabolomic, proteomic, genomic and microbiomic adaptations during the course of pregnancy. Modeling the chronology of these adaptations during full-term pregnancy provides the frameworks for future studies examining deviations implicated in pregnancy-related pathologies including preterm birth and preeclampsia. We performed a multiomics analysis of 51 samples from 17 pregnant women, delivering at term. The datasets included measurements from the immunome, transcriptome, microbiome, proteome and metabolome of samples obtained simultaneously from the same patients. Multivariate predictive modeling using the Elastic Net (EN) algorithm was used to measure the ability of each dataset to predict gestational age. Using stacked generalization, these datasets were combined into a single model. This model not only significantly increased predictive power by combining all datasets, but also revealed novel interactions between different biological modalities. Future work includes expansion of the cohort to preterm-enriched populations and in vivo analysis of immune-modulating interventions based on the mechanisms identified. Datasets and scripts for reproduction of results are available through: https://nalab.stanford.edu/multiomics-pregnancy/. Supplementary data are available at Bioinformatics online.
Testing zero variance components is one of the most challenging problems in the context of linear mixed-effects (LME) models. The usual asymptotic chi-square distribution of the likelihood ratio and score statistics under this null hypothesis is incorrect because the null is on the boundary of the parameter space. During the last two decades many tests have been proposed to overcome this difficulty, but these tests cannot be easily applied for testing multiple variance components, especially for testing a subset of them. We instead introduce a simple test statistic based on the variance least square estimator of variance components. With this comes a permutation procedure to approximate its finite sample distribution. The proposed test covers testing multiple variance components and any subset of them in LME models. Interestingly, our method does not depend on the distribution of the random effects and errors except for their mean and variance. We show, via simulations, that the proposed test has good operating characteristics with respect to Type I error and power. We conclude with an application of our process using real data from a study of the association of hyperglycemia and relative hyperinsulinemia.
17 January 2017 in Transportmetrica A: Transport Science
In many cities, worldwide public transit companies use smart card system to manage fare collection. Analysis of this acquisitive information provides a comprehensive insight of user's influence in the interactive public transit network. In this regard, analysis of temporal data, describing the time of entering to the public transit network is considered as the most substantial component of the data gathered from the smart cards. Classical distance-based techniques are not always suitable to analyze this time series data. A novel projection with intuitive visual map from higher dimension into a three-dimensional clock-like space is suggested to reveal the underlying temporal pattern of public transit users. This projection retains the temporal distance between any arbitrary pair of time-stamped data with meaningful visualization. Consequently, this information is fed into a hierarchical clustering algorithm as a method of data segmentation to discover the pattern of users.
16 June 2015 in Environmental Science & Technology
The frontier of the Production Possibility Set (PPS) consists of two types of full dimensional facets, efficient and weak facets. Identification of all facets of the PPS can be used in sensitivity and stability analysis, to find the closet target for inefficient Decision-Making Units (DMUs), and to determine the status of returns to scale of a DMU, among others. There has been a surge of articles on determining efficient facets in recent years. There are, however, many cases where knowledge of weak facets is required for a thorough analysis. This is the case, in particular, when the frontier of the PPS is constructed only of weak facets. The existing algorithms for finding weak facets either require knowledge of all extreme directions of the PPS or applicable only under some restrictions on the position of weak efficient DMUs. We provide a complete characterization of weak facets. Using this characterization, we then devise a different algorithm to find weak facets. We illustrate our algorithm using a numerical example.
An electronic nose (e-nose), or artificial olfaction, is a device that analyzes the air to quantify odor concentration using an array of gas sensors. This equipment is a monitoring tool for industrial firms. There is a shortage of an algorithm to address odor prediction challenges in an automatic fashion. These challenges include unreliable data transfer due to sensor malfunction or missing data due to anomalies in mobile data connection. Providing such an algorithm avoids human intervention in data handling, and elevates electronic nose towards smart nose. We address these challenges by proposing a data validation and data imputation method combined with a robust odor prediction machinery. Our proposed algorithm is successfully implemented on the e-nose equipment and is serving the industry currently.