Data science in science最新文献

Machine learning is revolutionizing health research by enabling scalable analysis across complex datasets. The All of Us Research Program offers unprecedented access to a wealth of health data. To harness this potential, researchers must navigate the All of Us database structure, develop machine learning skills, and apply coding effectively. This paper presents case studies designed to impart these skills using the All of Us Researcher Workbench. Our case studies cover critical topics, such as dataset selection, data cleaning, machine learning applications, and visualization in Python, which together provide the foundation of a targeted training program. Evaluated through pre- and post-program surveys, the program significantly boosted participants' machine learning competencies. By detailing our approach and findings, we aim to guide researchers in harnessing the full potential of the All of Us dataset, thereby advancing precision medicine.

In mediation analysis, the exposure often influences the mediating effect, i.e., there is an interaction between exposure and mediator on the dependent variable. When the mediator is high-dimensional, it is necessary to identify non-zero mediators $\left(M\right)$ and exposure-by-mediator ( $X$ -by- $M$ ) interactions. Although several high-dimensional mediation methods can naturally handle $X$ -by- $M$ interactions, research is scarce in preserving the underlying hierarchical structure between the main effects and the interactions. To fill the knowledge gap, we develop the XMInt procedure to select $M$ and $X$ -by- $M$ interactions in the high-dimensional mediators setting while preserving the hierarchical structure. Our proposed method employs a sequential regularization-based forward-selection approach to identify the mediators and their hierarchically preserved interaction with exposure. Our numerical experiments showed promising selection results. Further, we applied our method to ADNI morphological data and examined the role of cortical thickness and subcortical volumes on the effect of amyloid-beta accumulation on cognitive performance, which could be helpful in understanding the brain compensation mechanism.

We use a geometric approach to jointly characterize tumor shape and intensity along the tumor contour, as captured in magnetic resonance images, in the context of glioblastoma multiforme. Key properties of the proposed shape+intensity representation include invariance to translation, scale, rotation and reparameterization, which enable objective characterization and comparison of these crucial tumor features. The representation further allows the user to tune the emphasis of the shape and intensity components during registration, comparison and statistical summarization (averaging, computation of overall variance and exploration of variability via principal component analysis). In addition, we define a composite distance that is able to integrate shape and intensity information from two imaging modalities. The proposed framework can be integrated with distance-based clustering for the purpose of discovering groups of subjects with distinct survival prognosis. When applied to a cohort of subjects with glioblastoma multiforme, we discover groups with large median survival differences. We further tie the subjects' cluster memberships to tumor heterogeneity. Our results suggest that tumor shape variation plays an important role in disease prognosis.

Optical imaging of genetically encoded calcium indicators is a powerful tool to record the activity of a large number of neurons simultaneously over a long period of time from freely behaving animals. However, determining the exact time at which a neuron spikes and estimating the underlying firing rate from calcium fluorescence data remains challenging, especially for calcium imaging data obtained from a longitudinal study. We propose a multi-trial time-varying ${\ell }_0$ penalized method to jointly detect spikes and estimate firing rates by robustly integrating evolving neural dynamics across trials. Our simulation study shows that the proposed method performs well in both spike detection and firing rate estimation. We demonstrate the usefulness of our method on calcium fluorescence trace data from two studies, with the first study showing differential firing rate functions between two behaviors and the second study showing evolving firing rate functions across trials due to learning.

There is no gold standard for the diagnosis of Alzheimer's disease (AD), except from autopsies, which motivates the use of unsupervised learning. A mixture of regressions is an unsupervised method that can simultaneously identify clusters from multiple biomarkers while learning within-cluster demographic effects. Cerebrospinal fluid (CSF) biomarkers for AD have detection limits, which create additional challenges. We apply a mixture of regressions with a multivariate truncated Gaussian distribution (also called a censored multivariate Gaussian mixture of regressions or a mixture of multivariate tobit regressions) to over 3,000 participants from the Emory Goizueta Alzheimer's Disease Research Center and Emory Healthy Brain Study to examine amyloid-beta peptide 1-42 (Abeta42), total tau protein and phosphorylated tau protein in CSF with known detection limits. We address three gaps in the literature on mixture of regressions with a truncated multivariate Gaussian distribution: software availability; inference; and clustering accuracy. We discovered three clusters that tend to align with an AD group, a normal control profile and non-AD pathology. The CSF profiles differed by race, gender and the genetic marker ApoE4, highlighting the importance of considering demographic factors in unsupervised learning with detection limits. Notably, African American participants in the AD-like group had significantly lower tau burden.

The Singular Spectrum Analysis (SSA) is a useful tool for extracting signals from noisy time series. However, the structural insights provided by SSA are significantly influenced by the choice of window length. While the conventional approach, recommending a larger window length, excels with short to moderately-sized time series, it becomes computationally burdensome for longer time series, potentially amplifying mean squared reconstruction errors. This study addresses this methodological gap by introducing an adaptive sequential SSA method that iteratively selects an optimal window length for efficient extraction of essential eigen-sequences (signals) with minimal reconstruction error. This proposed method is versatile, catering to both short-moderate and lengthy time series. Simulation studies demonstrate its efficacy in scenarios where observed data stem from the sum of two sinusoidal functions and noise. Real data analysis on 6-day heart rate data from a young adult e-cigarette user reveals a distinct clustering of vaping events in the scatter plot of the first and third eigen-sequences, indicating the potential of developing "digital biomarkers" for vaping behavior based on extracted eigen-sequences in future studies. In conclusion, the adaptive sequential SSA method offers a robust and flexible approach for signal extraction in diverse time series applications.