A SIGNIFICANCE TEST FOR THE LASSO

Network-based analysis of heterogeneous patient-matched brain and extracranial melanoma metastasis pairs reveals three homogeneous subgroups

Melanoma, the deadliest form of skin cancer, can metastasize to different organs. Molecular differences between brain and extracranial melanoma metastases are poorly understood. Here, promoter methylation and gene expression of 11 heterogeneous patient-matched pairs of brain and extracranial metastases were analyzed using melanoma-specific gene regulatory networks learned from public transcriptome and methylome data followed by network-based impact propagation of patient-specific alterations. This innovative data analysis strategy allowed to predict potential impacts of patient-specific driver candidate genes on other genes and pathways. The patient-matched metastasis pairs clustered into three robust subgroups with specific downstream targets with known roles in cancer, including melanoma (SG1: RBM38, BCL11B, SG2: GATA3, FES, SG3: SLAMF6, PYCARD). Patient subgroups and ranking of target gene candidates were confirmed in a validation cohort. Summarizing, computational network-based impact analyses of heterogeneous metastasis pairs predicted individual regulatory differences in melanoma brain metastases, cumulating into three consistent subgroups with specific downstream target genes.

Network Inference With the Lasso

Calculating confidence intervals and p-values of edges in networks is useful to decide their presence or absence and it is a natural way to quantify uncertainty. Since lasso estimation is often used to obtain edges in a network, and the underlying distribution of lasso estimates is discontinuous and has probability one at zero when the estimate is zero, obtaining p-values and confidence intervals is problematic. It is also not always desirable to use the lasso to select the edges because there are assumptions required for correct identification of network edges that may not be warranted for the data at hand. Here, we review three methods that either use a modified lasso estimate (desparsified or debiased lasso) or a method that uses the lasso for selection and then determines p-values without the lasso. We compare these three methods with popular methods to estimate Gaussian Graphical Models in simulations and conclude that the desparsified lasso and its bootstrapped version appear to be the best choices for selection and quantifying uncertainty with confidence intervals and p-values.

Integrated multiomic analysis reveals disulfidptosis subtypes in glioblastoma: implications for immunotherapy, targeted therapy, and chemotherapy

Introduction

Glioblastoma (GBM) presents significant challenges due to its malignancy and limited treatment options. Precision treatment requires subtyping patients based on prognosis. Disulfidptosis, a novel cell death mechanism, is linked to aberrant glucose metabolism and disulfide stress, particularly in tumors expressing high levels of SLC7A11. The exploration of disulfidptosis may provide a new perspective for precise diagnosis and treatment of glioblastoma.

Methods

Transcriptome sequencing was conducted on samples from GBM patients treated at Tiantan Hospital (January 2022 - December 2023). Data from CGGA and TCGA databases were collected. Consensus clustering based on disulfidptosis features categorized GBM patients into two subtypes (DRGclusters). Tumor immune microenvironment, response to immunotherapy, and drug sensitivity were analyzed. An 8-gene disulfidptosis-based subtype predictor was developed using LASSO machine learning algorithm and validated on CGGA dataset.

Results

Patients in DRGcluster A exhibited improved overall survival (OS) compared to DRGcluster B. DRGcluster subtypes showed differences in tumor immune microenvironment and response to immunotherapy. The predictor effectively stratified patients into high and low-risk groups. Significant differences in IC50 values for chemotherapy and targeted therapy were observed between risk groups.

Discussion

Disulfidptosis-based classification offers promise as a prognostic predictor for GBM. It provides insights into tumor immune microenvironment and response to therapy. The predictor aids in patient stratification and personalized treatment selection, potentially improving outcomes for GBM patients.

EFFICIENT ESTIMATION OF THE MAXIMAL ASSOCIATION BETWEEN MULTIPLE PREDICTORS AND A SURVIVAL OUTCOME

This paper develops a new approach to post-selection inference for screening high-dimensional predictors of survival outcomes. Post-selection inference for right-censored outcome data has been investigated in the literature, but much remains to be done to make the methods both reliable and computationally-scalable in high-dimensions. Machine learning tools are commonly used to provide predictions of survival outcomes, but the estimated effect of a selected predictor suffers from confirmation bias unless the selection is taken into account. The new approach involves the construction of semi-parametrically efficient estimators of the linear association between the predictors and the survival outcome, which are used to build a test statistic for detecting the presence of an association between any of the predictors and the outcome. Further, a stabilization technique reminiscent of bagging allows a normal calibration for the resulting test statistic, which enables the construction of confidence intervals for the maximal association between predictors and the outcome and also greatly reduces computational cost. Theoretical results show that this testing procedure is valid even when the number of predictors grows superpolynomially with sample size, and our simulations support this asymptotic guarantee at moderate sample sizes. The new approach is applied to the problem of identifying patterns in viral gene expression associated with the potency of an antiviral drug.

Regression calibration utilizing biomarkers developed from high-dimensional metabolites

Addressing systematic measurement errors in self-reported data is a critical challenge in association studies of dietary intake and chronic disease risk. The regression calibration method has been utilized for error correction when an objectively measured biomarker is available; however, biomarkers for only a few dietary components have been developed. This paper proposes to use high-dimensional objective measurements to construct biomarkers for many more dietary components and to estimate the diet disease associations. It also discusses the challenges in variance estimation in high-dimensional regression methods and presents a variety of techniques to address this issue, including cross-validation, degrees-of-freedom corrected estimators, and refitted cross-validation (RCV). Extensive simulation is performed to study the finite sample performance of the proposed estimators. The proposed method is applied to the Women's Health Initiative cohort data to examine the associations between the sodium/potassium intake ratio and the total cardiovascular disease.

Comparing Factors Associated with Increased Stimulant Use in Relation to HIV Status Using a Machine Learning and Prediction Modeling Approach

Stimulant use is an important driver of HIV/STI transmission among men who have sex with men (MSM). Evaluating factors associated with increased stimulant use is critical to inform HIV prevention programming efforts. This study seeks to use machine learning variable selection techniques to determine characteristics associated with increased stimulant use and whether these factors differ by HIV status. Data from a longitudinal cohort of predominantly Black/Latinx MSM in Los Angeles, CA was used. Every 6 months from 8/2014-12/2020, participants underwent STI testing and completed surveys evaluating the following: demographics, substance use, sexual risk behaviors, and last partnership characteristics. Least absolute shrinkage and selection operator (lasso) was used to select variables and create predictive models for an interval increase in self-reported stimulant use across study visits. Mixed-effects logistic regression was then used to describe associations between selected variables and the same outcome. Models were also stratified based on HIV status to evaluate differences in predictors associated with increased stimulant use. Among 2095 study visits from 467 MSM, increased stimulant use was reported at 20.9% (n = 438) visits. Increased stimulant use was positively associated with unstable housing (adjusted [a]OR 1.81; 95% CI 1.27-2.57), STI diagnosis (1.59; 1.14-2.21), transactional sex (2.30; 1.60-3.30), and last partner stimulant use (2.21; 1.62-3.00). Among MSM living with HIV, increased stimulant use was associated with binge drinking, vaping/cigarette use (aOR 1.99; 95% CI 1.36-2.92), and regular use of poppers (2.28; 1.38-3.76). Among HIV-negative MSM, increased stimulant use was associated with participating in group sex while intoxicated (aOR 1.81; 95% CI 1.04-3.18), transactional sex (2.53; 1.40-2.55), and last partner injection drug use (1.96; 1.02-3.74). Our findings demonstrate that lasso can be a useful tool for variable selection and creation of predictive models. These results indicate that risk behaviors associated with increased stimulant use may differ based on HIV status and suggest that co-substance use and partnership contexts should be considered in the development of HIV prevention/treatment interventions.

Using LASSO Regression to Estimate the Population-Level Impact of Pneumococcal Conjugate Vaccines

Pneumococcal conjugate vaccines (PCVs) protect against diseases caused by Streptococcus pneumoniae, such as meningitis, bacteremia, and pneumonia. It is challenging to estimate their population-level impact due to the lack of a perfect control population and the subtleness of signals when the endpoint-such as all-cause pneumonia-is nonspecific. Here we present a new approach for estimating the impact of PCVs: using least absolute shrinkage and selection operator (LASSO) regression to select variables in a synthetic control model to predict the counterfactual outcome for vaccine impact inference. We first used a simulation study based on hospitalization data from Mexico (2000-2013) to test the performance of LASSO and established methods, including the synthetic control model with Bayesian variable selection (SC). We found that LASSO achieved accurate and precise estimation, even in complex simulation scenarios where the association between the outcome and all control variables was noncausal. We then applied LASSO to real-world hospitalization data from Chile (2001-2012), Ecuador (2001-2012), Mexico (2000-2013), and the United States (1996-2005), and found that it yielded estimates of vaccine impact similar to SC. The LASSO method is accurate and easily implementable and can be applied to study the impact of PCVs and other vaccines.

How to apply variable selection machine learning algorithms with multiply imputed data: A missing discussion

Psychological researchers often use standard linear regression to identify relevant predictors of an outcome of interest, but challenges emerge with incomplete data and growing numbers of candidate predictors. Regularization methods like the LASSO can reduce the risk of overfitting, increase model interpretability, and improve prediction in future samples; however, handling missing data when using regularization-based variable selection methods is complicated. Using listwise deletion or an ad hoc imputation strategy to deal with missing data when using regularization methods can lead to loss of precision, substantial bias, and a reduction in predictive ability. In this tutorial, we describe three approaches for fitting a LASSO when using multiple imputation to handle missing data and illustrate how to implement these approaches in practice with an applied example. We discuss implications of each approach and describe additional research that would help solidify recommendations for best practices. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Incorporating interactions into structured life course modelling approaches: A simulation study and applied example of the role of access to green space and socioeconomic position on cardiometabolic health

Background

Structured life course modelling approaches (SLCMA) have been developed to understand how exposures across the lifespan relate to later health, but have primarily been restricted to single exposures. As multiple exposures can jointly impact health, here we: i) demonstrate how to extend SLCMA to include exposure interactions; ii) conduct a simulation study investigating the performance of these methods; and iii) apply these methods to explore associations of access to green space, and its interaction with socioeconomic position, with child cardiometabolic health.

Methods

We used three methods, all based on lasso regression, to select the most plausible life course model: visual inspection, information criteria and cross-validation. The simulation study assessed the ability of these approaches to detect the correct interaction term, while varying parameters which may impact power (e.g., interaction magnitude, sample size, exposure collinearity). Methods were then applied to data from a UK birth cohort.

Results

There were trade-offs between false negatives and false positives in detecting the true interaction term for different model selection methods. Larger sample size, lower exposure collinearity, centering exposures, continuous outcomes and a larger interaction effect all increased power. In our applied example we found little-to-no association between access to green space, or its interaction with socioeconomic position, and child cardiometabolic outcomes.

Conclusions

Incorporating interactions between multiple exposures is an important extension to SLCMA. The choice of method depends on the researchers' assessment of the risks of under- vs over-fitting. These results also provide guidance for improving power to detect interactions using these methods.

Sensitive Periods for the Effect of Child Maltreatment on Psychopathology Symptoms in Adolescence

Introduction

Child maltreatment is among the strongest risk factors for mental disorders. However, little is known about whether there are ages when children may be especially vulnerable to its effects. We sought to identify potential sensitive periods when exposure to the 2 most common types of maltreatment (neglect and harsh physical discipline) had a particularly detrimental effect on youth mental health.

Methods

Data came from the Future of Families and Child Wellbeing Study (FFCWS), a birth cohort oversampled from "fragile families" (n = 3,474). Maltreatment was assessed at 3, 5, and 9 years of age using an adapted version of the Parent-Child Conflict Tactics Scales (CTS-PC). Using least angle regression, we examined the relationship between repeated measures of exposure to maltreatment on psychopathology symptoms at age 15 years (Child Behavior Checklist; CBCL/6-18). For comparison, we evaluated the strength of evidence to support the existence of sensitive periods in relation to an accumulation of risk model.

Results

We identified sensitive periods for harsh physical discipline, whereby psychopathology symptom scores were highest among girls exposed at age 9 years (r2 = 0.67 internalizing symptoms; r2 = 1% externalizing symptoms) and among boys exposed at age 5 years (r2 = 0.41%). However, for neglect, the accumulation of risk model explained more variability in psychopathology symptoms for both boys and girls.

Conclusion

Child maltreatment may have differential effects based on the child's sex, type of exposure, and the age at which it occurs. These findings provide additional evidence for clinicians assessing the benefits and drawbacks of screening efforts and point toward possible mechanisms driving increased vulnerability to psychopathology.

Inference for a Large Directed Acyclic Graph with Unspecified Interventions

Statistical inference of directed relations given some unspecified interventions (i.e., the intervention targets are unknown) is challenging. In this article, we test hypothesized directed relations with unspecified interventions. First, we derive conditions to yield an identifiable model. Unlike classical inference, testing directed relations requires to identify the ancestors and relevant interventions of hypothesis-specific primary variables. To this end, we propose a peeling algorithm based on nodewise regressions to establish a topological order of primary variables. Moreover, we prove that the peeling algorithm yields a consistent estimator in low-order polynomial time. Second, we propose a likelihood ratio test integrated with a data perturbation scheme to account for the uncertainty of identifying ancestors and interventions. Also, we show that the distribution of a data perturbation test statistic converges to the target distribution. Numerical examples demonstrate the utility and effectiveness of the proposed methods, including an application to infer gene regulatory networks. The R implementation is available at https://github.com/chunlinli/intdag.

Double bias correction for high-dimensional sparse additive hazards regression with covariate measurement errors

We propose an inferential procedure for additive hazards regression with high-dimensional survival data, where the covariates are prone to measurement errors. We develop a double bias correction method by first correcting the bias arising from measurement errors in covariates through an estimating function for the regression parameter. By adopting the convex relaxation technique, a regularized estimator for the regression parameter is obtained by elaborately designing a feasible loss based on the estimating function, which is solved via linear programming. Using the Neyman orthogonality, we propose an asymptotically unbiased estimator which further corrects the bias caused by the convex relaxation and regularization. We derive the convergence rate of the proposed estimator and establish the asymptotic normality for the low-dimensional parameter estimator and the linear combination thereof, accompanied with a consistent estimator for the variance. Numerical experiments are carried out on both simulated and real datasets to demonstrate the promising performance of the proposed double bias correction method.

Updates to data versions and analytic methods influence the reproducibility of results from epigenome-wide association studies

Biomedical research has grown increasingly cooperative through the sharing of consortia-level epigenetic data. Since consortia preprocess data prior to distribution, new processing pipelines can lead to different versions of the same dataset. Similarly, analytic frameworks evolve to incorporate cutting-edge methods and best practices. However, it remains unknown how different data and analytic versions alter the results of epigenome-wide analyses, which could influence the replicability of epigenetic associations. Thus, we assessed the impact of these changes using data from the Avon Longitudinal Study of Parents and Children (ALSPAC) cohort. We analysed DNA methylation from two data versions, processed using separate preprocessing and analytic pipelines, examining associations between seven childhood adversities or prenatal smoking exposure and DNA methylation at age 7. We performed two sets of analyses: (1) epigenome-wide association studies (EWAS); (2) Structured Life Course Modelling Approach (SLCMA), a two-stage method that models time-dependent effects. SLCMA results were also compared across two analytic versions. Data version changes impacted both EWAS and SLCMA analyses, yielding different associations at conventional p-value thresholds. However, the magnitude and direction of associations was generally consistent between data versions, regardless of p-values. Differences were especially apparent in analyses of childhood adversity, while smoking associations were more consistent using significance thresholds. SLCMA analytic versions similarly altered top associations, but time-dependent effects remained concordant. Alterations to data and analytic versions influenced the results of epigenome-wide analyses. Our findings highlight that magnitude and direction are better measures for replication and stability than p-value thresholds.

Importance of Social Determinants in Screening for Depression

IMPORTANCE

The most common screening tool for depression is the Patient Health Questionnaire-9 (PHQ-9). Despite extensive research on the clinical and behavioral implications of the PHQ-9, data are limited on the relationship between PHQ-9 scores and social determinants of health and disease.

OBJECTIVE

To assess the relationship between the PHQ-9 at intake and other measurements intended to assess social determinants of health.

DESIGN, SETTING, AND PARTICIPANTS

Cross-sectional analyses of 2502 participants from the Baseline Health Study (BHS), a prospective cohort of adults selected to represent major demographic groups in the US; participants underwent deep phenotyping on demographic, socioeconomic, clinical, laboratory, functional, and imaging findings.

INTERVENTIONS

None.

MAIN OUTCOMES AND MEASURES

Cross-sectional measures of clinical and socioeconomic status (SES).

RESULTS

In addition to a host of clinical and biological factors, higher PHQ-9 scores were associated with female sex, younger participants, people of color, and Hispanic ethnicity. Multiple measures of low SES, including less education, being unmarried, not currently working, and lack of insurance, were also associated with higher PHQ-9 scores across the entire spectrum of PHQ-9 scores. A summative score of SES, which was the 6th most predictive factor, was associated with higher PHQ-9 score after adjusting for 150 clinical, lab testing, and symptomatic characteristics.

CONCLUSIONS AND RELEVANCE

Our findings underscore that depression should be considered a comorbidity when social determinants of health are addressed, and both elements should be considered when designing appropriate interventions.

Association of Life-Course Neighborhood Deprivation With Frailty and Frailty Progression From Ages 70 to 82 Years in the Lothian Birth Cohort 1936

Neighborhood features have been postulated to be key predictors of frailty. However, evidence is mainly limited to cross-sectional studies without indication of long-term impact. We explored how neighborhood social deprivation (NSD) across the life course is associated with frailty and frailty progression among older Scottish adults. Participants (n = 323) were persons selected from the Lothian Birth Cohort 1936 with historical measures of NSD in childhood (1936-1955), young adulthood (1956-1975), and mid- to late adulthood (1976-2014). Frailty was measured 5 times between the ages of 70 and 82 years using the Frailty Index. Confounder-adjusted life-course models were assessed using a structured modeling approach; associations were estimated for frailty at baseline using linear regression and for frailty progression using linear mixed-effects models. Accumulation was the most appropriate life-course model for males; greater accumulated NSD was associated with higher frailty at baseline (b = 0.017, 95% confidence interval: 0.005, 0.029). Among females, the mid- to late adulthood sensitive period was the best-fitting life-course model, and higher NSD in this period was associated with widening frailty trajectories (b = 0.005, 95% confidence interval: 0.0004, 0.009). To our knowledge, this is the first investigation of the life-course impact of NSD on frailty in a cohort of older adults. Policies designed to address deprivation and inequalities across the full life course may support healthy aging.

Evaluating methods for Lasso selective inference in biomedical research: a comparative simulation study

Background

Variable selection for regression models plays a key role in the analysis of biomedical data. However, inference after selection is not covered by classical statistical frequentist theory, which assumes a fixed set of covariates in the model. This leads to over-optimistic selection and replicability issues.

Methods

We compared proposals for selective inference targeting the submodel parameters of the Lasso and its extension, the adaptive Lasso: sample splitting, selective inference conditional on the Lasso selection (SI), and universally valid post-selection inference (PoSI). We studied the properties of the proposed selective confidence intervals available via R software packages using a neutral simulation study inspired by real data commonly seen in biomedical studies. Furthermore, we present an exemplary application of these methods to a publicly available dataset to discuss their practical usability.

Results

Frequentist properties of selective confidence intervals by the SI method were generally acceptable, but the claimed selective coverage levels were not attained in all scenarios, in particular with the adaptive Lasso. The actual coverage of the extremely conservative PoSI method exceeded the nominal levels, and this method also required the greatest computational effort. Sample splitting achieved acceptable actual selective coverage levels, but the method is inefficient and leads to less accurate point estimates.

The choice of inference method had a large impact on the resulting interval estimates, thereby necessitating that the user is acutely aware of the goal of inference in order to interpret and communicate the results.

Conclusions

Despite violating nominal coverage levels in some scenarios, selective inference conditional on the Lasso selection is our recommended approach for most cases. If simplicity is strongly favoured over efficiency, then sample splitting is an alternative. If only few predictors undergo variable selection (i.e. up to 5) or the avoidance of false positive claims of significance is a concern, then the conservative approach of PoSI may be useful. For the adaptive Lasso, SI should be avoided and only PoSI and sample splitting are recommended. In summary, we find selective inference useful to assess the uncertainties in the importance of individual selected predictors for future applications.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-022-01681-y.

Personalized optimal nutrition lifestyle for self obesity management using metaalgorithms

Precision medicine applies machine learning methods to estimate the personalized optimal treatment decision based on individual information, such as genetic data and medical history. The main purpose of self obesity management is to develop a personalized optimal life plan that is easy to implement and adhere to, thereby reducing the incidence of obesity and obesity-related diseases. The methodology comprises three components. First, we apply catboost, random forest and lasso covariance test to evaluate the importance of individual features in forecasting body mass index. Second, we apply metaalgorithms to estimate the personalized optimal decision on alcohol, vegetable, high caloric food and daily water intake respectively for each individual. Third, we propose new metaalgorithms named SX and SXwint learners to compute the personalized optimal decision and compare their performances with other prevailing metalearners. We find that people who receive individualized optimal treatment options not only have lower obesity levels than others, but also have lower obesity levels than those who receive ’one-for-all’ treatment options. In conclusion, all metaalgorithms are effective at estimating the personalized optimal decision, where SXwint learner shows the best performance on daily water intake.

Statistical Modeling of Sensitive Period Effects Using the Structured Life Course Modeling Approach (SLCMA)

Sensitive periods are times during development when life experiences can have a greater impact on outcomes than at other periods during the life course. However, a dearth of sophisticated methods for studying time-dependent exposure-outcome relationships means that sensitive periods are often overlooked in research studies in favor of more simplistic and easier-to-use hypotheses such as ever being exposed, or the effect of an exposure accumulated over time. The structured life course modeling approach (SLCMA; pronounced "slick-mah") allows researchers to model complex life course hypotheses, such as sensitive periods, to determine which hypothesis best explains the amount of variation between a repeated exposure and an outcome. The SLCMA makes use of the least angle regression (LARS) variable selection technique, a type of least absolute shrinkage and selection operator (LASSO) estimation procedure, to yield a parsimonious model for the exposure-outcome relationship of interest. The results of the LARS procedure are complemented with a post-selection inference method, called selective inference, which provides unbiased effect estimates, confidence intervals, and p-values for the final explanatory model. In this chapter, we provide a brief overview of the genesis of this sensitive period modeling approach and provide a didactic step-by-step user's guide to implement the SLCMA in sensitive- period research. R code to complete the SLCMA is available on our GitHub page at: https://github.com/thedunnlab/SLCMA-pipeline .

Thinking of Me or Thinking of You? Behavioral Correlates of Self vs. Other Centered Worry and Reappraisal in Late-Life

Psychotherapeutic approaches in late-life anxiety have limited effect on reducing worry severity. The self-referential processing of worry contents (self- vs. other-focused worry) and reappraisal styles (internal vs. external locus of control) are important elements in psychotherapy, but little is known about these processes in late-life. We aimed to characterize severe worry from a self-referential processing perspective. We recruited 104 older adults with various levels of worry and used a personalized task to induce and reappraise worry. We analyzed the association between (1) worry severity/frequency for worry content (self- or other-focused) and (2) for reappraisal style (internal vs. external locus of control) with clinical inventories measuring anxiety, worry, depression, rumination, neuroticism, emotion regulation strategies, perceived stress, and physical illness burden. Higher self-worry severity was associated with higher scores of clinical inventories of worry, depression, perceived stress, and neuroticism, whereas other-worry severity did not show any association. Greater self-worry frequency was associated with higher medical burden. External locus of control in reappraisal statements was associated with lower worry severity in men. Overall, more severe and frequent self-focused worry was associated with a greater psychological and physiological burden. These results are useful in tailoring psychotherapy for older adults with severe worry.

Development and Validation of Ischemic Events Related Signature After Carotid Endarterectomy

Background: Ischemic events after carotid endarterectomy (CEA) in carotid artery stenosis patients are unforeseeable and alarming. Therefore, we aimed to establish a novel model to prevent recurrent ischemic events after CEA.

Methods: Ninety-eight peripheral blood mononuclear cell samples were collected from carotid artery stenosis patients. Based on weighted gene co-expression network analysis, we performed whole transcriptome correlation analysis and extracted the key module related to ischemic events. The biological functions of the 292 genes in the key module were annotated via GO and KEGG enrichment analysis, and the protein-protein interaction (PPI) network was constructed via the STRING database and Cytoscape software. The enrolled samples were divided into train (n = 66), validation (n = 28), and total sets (n = 94). In the train set, the random forest algorithm was used to identify critical genes for predicting ischemic events after CEA, and further dimension reduction was performed by LASSO logistic regression. A diagnosis model was established in the train set and verified in the validation and total sets. Furthermore, fifty peripheral venous blood samples from patients with carotid stenosis in our hospital were used as an independent cohort to validation the model by RT-qPCR. Meanwhile, GSEA, ssGSEA, CIBERSORT, and MCP-counter were used to enrichment analysis in high- and low-risk groups, which were divided by the median risk score.

Results: We established an eight-gene model consisting of PLSCR1, ECRP, CASP5, SPTSSA, MSRB1, BCL6, FBP1, and LST1. The ROC-AUCs and PR-AUCs of the train, validation, total, and independent cohort were 0.891 and 0.725, 0.826 and 0.364, 0.869 and 0.654, 0.792 and 0.372, respectively. GSEA, ssGSEA, CIBERSORT, and MCP-counter analyses further revealed that high-risk patients presented enhanced immune signatures, which indicated that immunotherapy may improve clinical outcomes in these patients.

Conclusion: An eight-gene model with high accuracy for predicting ischemic events after CEA was constructed. This model might be a promising tool to facilitate the clinical management and postoperative surveillance of carotid artery stenosis patients.

Integrated Analysis of Multi-Omics Alteration, Immune Profile, and Pharmacological Landscape of Pyroptosis-Derived lncRNA Pairs in Gastric Cancer

Background: Recent evidence demonstrates that pyroptosis-derived long non-coding RNAs (lncRNAs) have profound impacts on the initiation, progression, and microenvironment of tumors. However, the roles of pyroptosis-derived lncRNAs (PDLs) in gastric cancer (GC) remain elusive.

Methods: We comprehensively analyzed the multi-omics data of 839 GC patients from three independent cohorts. The previous gene set enrichment analysis embedding algorithm was utilized to identify PDLs. A gene pair pipeline was developed to facilitate clinical translation via qualitative relative expression orders. The LASSO algorithm was used to construct and validate a pyroptosis-derived lncRNA pair prognostics signature (PLPPS). The associations between PLPPS and multi-omics alteration, immune profile, and pharmacological landscape were further investigated.

Results: A total of 350 PDLs and 61,075 PDL pairs in the training set were generated. Cox regression revealed 15 PDL pairs associated with overall survival, which were utilized to construct the PLPPS model via the LASSO algorithm. The high-risk group demonstrated adverse prognosis relative to the low-risk group. Remarkably, genomic analysis suggested that the lower tumor mutation burden and gene mutation frequency (e.g., TTN, MUC16, and LRP1B) were found in the high-risk group patients. The copy number variants were not significantly different between the two groups. Additionally, the high-risk group possessed lower immune cell infiltration abundance and might be resistant to a few chemotherapeutic drugs (including cisplatin, paclitaxel, and gemcitabine).

Conclusion: PDLs were closely implicated in the biological process and prognosis of GC, and our PLPPS model could serve as a promising tool to advance prognostic management and personalized treatment of GC patients.

Inference for sparse linear regression based on the leave-one-covariate-out solution path

We propose a new measure of variable importance in high-dimensional regression based on the change in the LASSO solution path when one covariate is left out. The proposed procedure provides a novel way to calculate variable importance and conduct variable screening. In addition, our procedure allows for the construction of p-values for testing whether each coe cient is equal to zero as well as for testing hypotheses involving multiple regression coefficients simultaneously; bootstrap techniques are used to construct the null distribution. For low-dimensional linear models, our method can achieve higher power than the t-test. Extensive simulations are provided to show the effectiveness of our method. In the high-dimensional setting, our proposed solution path based test achieves greater power than some other recently developed high-dimensional inference methods. We extend our method to logistic regression and demonstrate in simulation that our leave-one-covariate-out solution path tests can provide accurate p-values.

Exposure to early childhood maltreatment and its effect over time on social cognition

Social cognitive deficits can have many negative consequences, spanning social withdrawal to psychopathology. Prior work has shown that child maltreatment may associate with poorer social cognitive skills in later life. However, no studies have examined this association from early childhood into adolescence. Using data from the Avon Longitudinal Study of Parents and Children (ALSPAC; n = 4,438), we examined the association between maltreatment (caregiver physical or emotional abuse; sexual or physical abuse), assessed repeatedly (every 1-3 years) from birth to age 9, and social cognitive skills at ages 7.5, 10.5, and 14 years. We evaluated the role of both the developmental timing (defined by age at exposure) and accumulation of maltreatment (defined as the number of occasions exposed) using a least angle regression variable selection procedure, followed by structural equation modeling. Among females, accumulation of maltreatment explained the most variation in social cognitive skills. For males, no significant associations were found. These findings underscore the importance of early intervention to minimize the accumulation of maltreatment and showcase the importance of prospective studies to understand the development of social cognition over time.

Leveraging pleiotropic association using sparse group variable selection in genomics data

Background

Genome-wide association studies (GWAS) have identified genetic variants associated with multiple complex diseases. We can leverage this phenomenon, known as pleiotropy, to integrate multiple data sources in a joint analysis. Often integrating additional information such as gene pathway knowledge can improve statistical efficiency and biological interpretation. In this article, we propose statistical methods which incorporate both gene pathway and pleiotropy knowledge to increase statistical power and identify important risk variants affecting multiple traits.

Methods

We propose novel feature selection methods for the group variable selection in multi-task regression problem. We develop penalised likelihood methods exploiting different penalties to induce structured sparsity at a gene (or pathway) and SNP level across all studies. We implement an alternating direction method of multipliers (ADMM) algorithm for our penalised regression methods. The performance of our approaches are compared to a subset based meta analysis approach on simulated data sets. A bootstrap sampling strategy is provided to explore the stability of the penalised methods.

Results

Our methods are applied to identify potential pleiotropy in an application considering the joint analysis of thyroid and breast cancers. The methods were able to detect eleven potential pleiotropic SNPs and six pathways. A simulation study found that our method was able to detect more true signals than a popular competing method while retaining a similar false discovery rate.

Conclusion

We developed feature selection methods for jointly analysing multiple logistic regression tasks where prior grouping knowledge is available. Our method performed well on both simulation studies and when applied to a real data analysis of multiple cancers.

Comparative Gene Expression Analysis Reveals Similarities and Differences of Chronic Myeloid Leukemia Phases

Chronic myeloid leukemia (CML) is a slowly progressing blood cancer that primarily affects elderly people. Without successful treatment, CML progressively develops from the chronic phase through the accelerated phase to the blast crisis, and ultimately to death. Nowadays, the availability of targeted tyrosine kinase inhibitor (TKI) therapies has led to long-term disease control for the vast majority of patients. Nevertheless, there are still patients that do not respond well enough to TKI therapies and available targeted therapies are also less efficient for patients in accelerated phase or blast crises. Thus, a more detailed characterization of molecular alterations that distinguish the different CML phases is still very important. We performed an in-depth bioinformatics analysis of publicly available gene expression profiles of the three CML phases. Pairwise comparisons revealed many differentially expressed genes that formed a characteristic gene expression signature, which clearly distinguished the three CML phases. Signaling pathway expression patterns were very similar between the three phases but differed strongly in the number of affected genes, which increased with the phase. Still, significant alterations of MAPK, VEGF, PI3K-Akt, adherens junction and cytokine receptor interaction signaling distinguished specific phases. Our study also suggests that one can consider the phase-wise CML development as a three rather than a two-step process. This is in accordance with the phase-specific expression behavior of 24 potential major regulators that we predicted by a network-based approach. Several of these genes are known to be involved in the accumulation of additional mutations, alterations of immune responses, deregulation of signaling pathways or may have an impact on treatment response and survival. Importantly, some of these genes have already been reported in relation to CML (e.g., AURKB, AZU1, HLA-B, HLA-DMB, PF4) and others have been found to play important roles in different leukemias (e.g., CDCA3, RPL18A, PRG3, TLX3). In addition, increased expression of BCL2 in the accelerated and blast phase indicates that venetoclax could be a potential treatment option. Moreover, a characteristic signaling pathway signature with increased expression of cytokine and ECM receptor interaction pathway genes distinguished imatinib-resistant patients from each individual CML phase. Overall, our comparative analysis contributes to an in-depth molecular characterization of similarities and differences of the CML phases and provides hints for the identification of patients that may not profit from an imatinib therapy, which could support the development of additional treatment strategies.

A novel necroptosis-related LncRNA signature for prediction of prognosis and therapeutic responses of head and neck squamous cell carcinoma

Background: Long non-coding RNAs (lncRNAs) play an essential role in the occurrence and prognosis of tumors, and it has great potential as biomarkers of tumors. However, the roles of Necroptosis-related lncRNA (NRLs) in Head and neck squamous cell carcinoma (HNSCC) remain elusive. Methods: We comprehensively analyzed the gene expression and clinical information of 964 HNSCC in four cohorts. LASSO regression was utilized to construct a necroptosis-related lncRNA prognosis signature (NLPS). We used univariate and multivariate regression to assess the independent prognostic value of NLPS. Based on the optimal cut-off, patients were divided into high- and low-risk groups. In addition, the immune profile, multi-omics alteration, and pharmacological landscape of NLPS were further revealed. Results: A total of 21 NRLs associated with survival were identified by univariate regression in four cohorts. We constructed and validated a best prognostic model (NLPS). Compared to the low-risk group, patients in the high group demonstrated a more dismal prognosis. After adjusting for clinical features by multivariate analysis, NLPS still displayed independent prognostic value. Additionally, further analysis found that patients in the low-risk group showed more abundant immune cell infiltration and immunotherapy response. In contrast, patients in the high-risk group were more sensitive to multiple chemotherapeutic agents. Conclusion: As a promising tool, the establishment of NLPS provides guidance and assistance in the clinical management and personalized treatment of HNSCC.

Novel ferroptosis-related gene signature as a potential prognostic tool for gastric cancer

Objectives

Gastric cancer (GC) is a major global health concern and is difficult to diagnose in the early stage. Ferroptosis is an iron-dependent, novel form of non-apoptotic cell death. In recent years, inducing the upregulation of ferroptosis-related genes has become a promising therapeutic alternative for cancers, especially those resistant to traditional treatments. However, the relationship between ferroptosis-related genes and GC remains to be further elucidated.

Methods

In the present study, mRNA expression profiles and corresponding clinical data of patients with GC were retrieved from The Cancer Genome Atlas and used as test data. A multigene signature was constructed using the least absolute shrinkage and selection operator Cox regression model. Data of patients with GC from ‘GSE84426’ in the Gene Expression Omnibus database were used as Training data for validation.

Results

More than half ferroptosis-related genes were differentially expressed in GC tissues and adjacent normal tissue samples (58.43%) in the test data. Univariate Cox regression analysis showed that 16 differentially expressed genes were related to the prognosis of GC (all p < 0.05). Expression profiles of the 16 DGEs were analysed using LASSO Cox regression, and a prognostic model was established by selecting the 10 best genes for λ. These 10 genes were used to construct a 10-gene signature and stratify patients into two risk groups. Based on the median risk score in the test data, patients with GC were divided into high- and low-risk groups ( p < 0.001). Risk score was an independent predictor for overall survival in multivariate Cox regression analyses ( p < 0.001 and <0.01 in the test and training data, respectively; hazard ratio >1). Receiver operating characteristic curve analysis confirmed the predictive capacity of the 10-gene signature. Functional analysis revealed that tumour-infiltrating lymphocytes, antigen-presenting cell co-stimulation, and cytokine-cytokine receptors were enriched; however, the immune status differed between the two risk groups.

Conclusion

The novel ferroptosis-related gene signature can be used for GC prognosis. In addition, ferroptosis may provide a novel alternative for the diagnosis and treatment of GC.

Wavelet Screening: a novel approach to analyzing GWAS data

Background

Traditional methods for single-variant genome-wide association study (GWAS) incur a substantial multiple-testing burden because of the need to test for associations with a vast number of single-nucleotide polymorphisms (SNPs) simultaneously. Further, by ignoring more complex joint effects of nearby SNPs within a given region, these methods fail to consider the genomic context of an association with the outcome.

Results

To address these shortcomings, we present a more powerful method for GWAS, coined ‘Wavelet Screening’ (WS), that greatly reduces the number of tests to be performed. This is achieved through the use of a sliding-window approach based on wavelets to sequentially screen the entire genome for associations. Wavelets are oscillatory functions that are useful for analyzing the local frequency and time behavior of signals. The signals can then be divided into different scale components and analyzed separately. In the current setting, we consider a sequence of SNPs as a genetic signal, and for each screened region, we transform the genetic signal into the wavelet space. The null and alternative hypotheses are modeled using the posterior distribution of the wavelet coefficients. WS is enhanced by using additional information from the regression coefficients and by taking advantage of the pyramidal structure of wavelets. When faced with more complex genetic signals than single-SNP associations, we show via simulations that WS provides a substantial gain in power compared to both the traditional GWAS modeling and another popular regional association test called SNP-set (Sequence) Kernel Association Test (SKAT). To demonstrate feasibility, we applied WS to a large Norwegian cohort (N=8006) with genotypes and information available on gestational duration.

Conclusions

WS is a powerful and versatile approach to analyzing whole-genome data and lends itself easily to investigating various omics data types. Given its broader focus on the genomic context of an association, WS may provide additional insight into trait etiology by revealing genes and loci that might have been missed by previous efforts.

A comparison of covariate selection techniques applied to pre-exposure prophylaxis (PrEP) drug concentration data in men and transgender women at risk for HIV

Pre-exposure prophylaxis (PrEP) containing antiretrovirals tenofovir disoproxil fumarate (TDF) or tenofovir alafenamide (TAF) can reduce the risk of acquiring HIV. Concentrations of intracellular tenofovir-diphosphate (TFV-DP) measured in dried blood spots (DBS) have been used to quantify PrEP adherence; although even under directly observed dosing, unexplained between-subject variation remains. Here, we wish to identify patient-specific factors associated with TFV-DP levels. Data from the iPrEX Open Label Extension (OLE) study were used to compare multiple covariate selection methods for determining demographic and clinical covariates most important for drug concentration estimation. To allow for the possibility of non-linear relationships between drug concentration and explanatory variables, the component selection and smoothing operator (COSSO) was implemented. We compared COSSO to LASSO, a commonly used machine learning approach, and traditional forward and backward selection. Training (N = 387) and test (N = 166) datasets were utilized to compare prediction accuracy across methods. LASSO and COSSO had the best predictive ability for the test data. Both predicted increased drug concentration with increases in age and self-reported adherence, the latter with a steeper trajectory among Asians. TFV-DP reductions were associated with increasing eGFR, hemoglobin and transgender status. COSSO also predicted lower TFV-DP with increasing weight and South American countries. COSSO identified non-linear relationships between log(TFV-DP) and adherence, weight and eGFR, with differing trajectories for some races. COSSO identified non-linear log(TFV-DP) trajectories with a subset of covariates, which may better explain variation and enhance prediction. Future research is needed to examine differences identified in trajectories by race and country.

Regularized Ordinal Regression and the ordinalNet R Package

Regularization techniques such as the lasso (Tibshirani 1996) and elastic net (Zou and Hastie 2005) can be used to improve regression model coefficient estimation and prediction accuracy, as well as to perform variable selection. Ordinal regression models are widely used in applications where the use of regularization could be beneficial; however, these models are not included in many popular software packages for regularized regression. We propose a coordinate descent algorithm to fit a broad class of ordinal regression models with an elastic net penalty. Furthermore, we demonstrate that each model in this class generalizes to a more flexible form, that can be used to model either ordered or unordered categorical response data. We call this the elementwise link multinomial-ordinal (ELMO) class, and it includes widely used models such as multinomial logistic regression (which also has an ordinal form) and ordinal logistic regression (which also has an unordered multinomial form). We introduce an elastic net penalty class that applies to either model form, and additionally, this penalty can be used to shrink a non-ordinal model toward its ordinal counterpart. Finally, we introduce the R package ordinalNet, which implements the algorithm for this model class.

Quantifying the impact of COVID-19 on e-bike safety in China via multi-output and clustering-based regression models

The impacts of COVID-19 on travel demand, traffic congestion, and traffic safety are attracting heated attention. However, the influence of the pandemic on electric bike (e-bike) safety has not been investigated. This paper fills the research gap by analyzing how COVID-19 affects China's e-bike safety based on a province-level dataset containing e-bike safety metrics, socioeconomic information, and COVID-19 cases from 2017 to 2020. Multi-output regression models are adopted to investigate the overall impact of COVID-19 on e-bike safety in China. Clustering-based regression models are used to examine the heterogeneous effects of COVID-19 and the other explanatory variables in different provinces/municipalities. This paper confirms the high relevance between COVID-19 and the e-bike safety condition in China. The number of COVID-19 cases has a significant negative effect on the number of e-bike fatalities/injuries at the country level. Moreover, two clusters of provinces/municipalities are identified: one (cluster 1) with lower and the other (cluster 2 that includes Hubei province) higher number of e-bike fatalities/injuries. In the clustering-based regressions, the absolute coefficients of the COVID-19 feature for cluster 2 are much larger than those for cluster 1, indicating that the pandemic could significantly reduce e-bike safety issues in provinces with more e-bike fatalities/injuries.

Computational Probing the Methylation Sites Related to EGFR Inhibitor-Responsive Genes

The emergence of drug resistance is one of the main obstacles to the treatment of lung cancer patients with EGFR inhibitors. Here, to further understand the mechanism of EGFR inhibitors in lung cancer and offer novel therapeutic targets for anti-EGFR-inhibitor resistance via the deep mining of pharmacogenomics data, we associated DNA methylation with drug sensitivities for uncovering the methylation sites related to EGFR inhibitor sensitivity genes. Specifically, we first introduced a grouped regularized regression model (Group Least Absolute Shrinkage and Selection Operator, group lasso) to detect the genes that were closely related to EGFR inhibitor effectiveness. Then, we applied the classical regression model (lasso) to identify the methylation sites associated with the above drug sensitivity genes. The new model was validated on the well-known cancer genomics resource: CTRP. GeneHancer and Encyclopedia of DNA Elements (ENCODE) database searches indicated that the predicted methylation sites related to EGFR inhibitor sensitivity genes were related to regulatory elements. Moreover, the correlation analysis on sensitivity genes and predicted methylation sites suggested that the methylation sites located in the promoter region were more correlated with the expression of EGFR inhibitor sensitivity genes than those located in the enhancer region and the TFBS. Meanwhile, we performed differential expression analysis of genes and predicted methylation sites and found that changes in the methylation level of some sites may affect the expression of the corresponding EGFR inhibitor-responsive genes. Therefore, we supposed that the effectiveness of EGFR inhibitors in lung cancer may be improved by methylation modification in their sensitivity genes.

Learning epistatic gene interactions from perturbation screens

The treatment of complex diseases often relies on combinatorial therapy, a strategy where drugs are used to target multiple genes simultaneously. Promising candidate genes for combinatorial perturbation often constitute epistatic genes, i.e., genes which contribute to a phenotype in a non-linear fashion. Experimental identification of the full landscape of genetic interactions by perturbing all gene combinations is prohibitive due to the exponential growth of testable hypotheses. Here we present a model for the inference of pairwise epistatic, including synthetic lethal, gene interactions from siRNA-based perturbation screens. The model exploits the combinatorial nature of siRNA-based screens resulting from the high numbers of sequence-dependent off-target effects, where each siRNA apart from its intended target knocks down hundreds of additional genes. We show that conditional and marginal epistasis can be estimated as interaction coefficients of regression models on perturbation data. We compare two methods, namely glinternet and xyz, for selecting non-zero effects in high dimensions as components of the model, and make recommendations for the appropriate use of each. For data simulated from real RNAi screening libraries, we show that glinternet successfully identifies epistatic gene pairs with high accuracy across a wide range of relevant parameters for the signal-to-noise ratio of observed phenotypes, the effect size of epistasis and the number of observations per double knockdown. xyz is also able to identify interactions from lower dimensional data sets (fewer genes), but is less accurate for many dimensions. Higher accuracy of glinternet, however, comes at the cost of longer running time compared to xyz. The general model is widely applicable and allows mining the wealth of publicly available RNAi screening data for the estimation of epistatic interactions between genes. As a proof of concept, we apply the model to search for interactions, and potential targets for treatment, among previously published sets of siRNA perturbation screens on various pathogens. The identified interactions include both known epistatic interactions as well as novel findings.

A Structured Approach to Evaluating Life-Course Hypotheses: Moving Beyond Analyses of Exposed Versus Unexposed in the -Omics Context

The structured life-course modeling approach (SLCMA) is a theory-driven analytical method that empirically compares multiple prespecified life-course hypotheses characterizing time-dependent exposure-outcome relationships to determine which theory best fits the observed data. In this study, we performed simulations and empirical analyses to evaluate the performance of the SLCMA when applied to genomewide DNA methylation (DNAm). Using simulations (n = 700), we compared 5 statistical inference tests used with SLCMA, assessing the familywise error rate, statistical power, and confidence interval coverage to determine whether inference based on these tests was valid in the presence of substantial multiple testing and small effects-2 hallmark challenges of inference from -omics data. In the empirical analyses (n = 703), we evaluated the time-dependent relationship between childhood abuse and genomewide DNAm. In simulations, selective inference and the max-|t|-test performed best: Both controlled the familywise error rate and yielded moderate statistical power. Empirical analyses using SLCMA revealed time-dependent effects of childhood abuse on DNAm. Our findings show that SLCMA, applied and interpreted appropriately, can be used in high-throughput settings to examine time-dependent effects underlying exposure-outcome relationships over the life course. We provide recommendations for applying the SLCMA in -omics settings and encourage researchers to move beyond analyses of exposed versus unexposed individuals.

Evaluating the Effectiveness of Personalized Medicine With Software

We present methodological advances in understanding the effectiveness of personalized medicine models and supply easy-to-use open-source software. Personalized medicine involves the systematic use of individual patient characteristics to determine which treatment option is most likely to result in a better average outcome for the patient. Why is personalized medicine not done more in practice? One of many reasons is because practitioners do not have any easy way to holistically evaluate whether their personalization procedure does better than the standard of care, termed improvement. Our software, "Personalized Treatment Evaluator" (the R package PTE), provides inference for improvement out-of-sample in many clinical scenarios. We also extend current methodology by allowing evaluation of improvement in the case where the endpoint is binary or survival. In the software, the practitioner inputs 1) data from a single-stage randomized trial with one continuous, incidence or survival endpoint and 2) an educated guess of a functional form of a model for the endpoint constructed from domain knowledge. The bootstrap is then employed on data unseen during model fitting to provide confidence intervals for the improvement for the average future patient (assuming future patients are similar to the patients in the trial). One may also test against a null scenario where the hypothesized personalization are not more useful than a standard of care. We demonstrate our method's promise on simulated data as well as on data from a randomized comparative trial investigating two treatments for depression.

A practical guide to selecting models for exploration, inference, and prediction in ecology

Selecting among competing statistical models is a core challenge in science. However, the many possible approaches and techniques for model selection, and the conflicting recommendations for their use, can be confusing. We contend that much confusion surrounding statistical model selection results from failing to first clearly specify the purpose of the analysis. We argue that there are three distinct goals for statistical modeling in ecology: data exploration, inference, and prediction. Once the modeling goal is clearly articulated, an appropriate model selection procedure is easier to identify. We review model selection approaches and highlight their strengths and weaknesses relative to each of the three modeling goals. We then present examples of modeling for exploration, inference, and prediction using a time series of butterfly population counts. These show how a model selection approach flows naturally from the modeling goal, leading to different models selected for different purposes, even with exactly the same data set. This review illustrates best practices for ecologists and should serve as a reminder that statistical recipes cannot substitute for critical thinking or for the use of independent data to test hypotheses and validate predictions.

LassoNet: Neural Networks with Feature Sparsity

Much work has been done recently to make neural networks more interpretable, and one approach is to arrange for the network to use only a subset of the available features. In linear models, Lasso (or ℓ ₁-regularized) regression assigns zero weights to the most irrelevant or redundant features, and is widely used in data science. However the Lasso only applies to linear models. Here we introduce LassoNet, a neural network framework with global feature selection. Our approach achieves feature sparsity by allowing a feature to participate in a hidden unit only if its linear representative is active. Unlike other approaches to feature selection for neural nets, our method uses a modified objective function with constraints, and so integrates feature selection with the parameter learning directly. As a result, it delivers an entire regularization path of solutions with a range of feature sparsity. In experiments with real and simulated data, LassoNet significantly outperforms state-of-the-art methods for feature selection and regression. The LassoNet method uses projected proximal gradient descent, and generalizes directly to deep networks. It can be implemented by adding just a few lines of code to a standard neural network.

Predictive model of multiple emergency department visits among adults: analysis of the data from the National Survey of Drug Use and Health (NSDUH)

Background

In this methodological paper, we use a novel, predictive approach to examine how demographics, substance use, mental and other health indicators predict multiple visits (≥3) to emergency departments (ED) within a year.

Methods

State-of-the-art predictive methods were used to evaluate predictive ability and factors predicting multiple visits to ED within a year and to identify factors that influenced the strength of the prediction. The analysis used public-use datasets from the 2015–2018 National Surveys on Drug Use and Health (NSDUH), which used the same questionnaire on the variables of interest. Analysis focused on adults aged ≥18 years. Several predictive models (regressions, trees, and random forests) were validated and compared on independent datasets.

Results

Predictive ability on a test set for multiple ED visits (≥3 times within a year) measured as the area under the receiver operating characteristic (ROC) reached 0.8, which is good for a national survey. Models revealed consistency in predictive factors across the 4 survey years. The most influential variables for predicting ≥3 ED visits per year were fair/poor self-rated health, being nervous or restless/fidgety, having a lower income, asthma, heart condition/disease, having chronic obstructive pulmonary disease (COPD), nicotine dependence, African-American race, female sex, having diabetes, and being of younger age (18–20).

Conclusions

The findings reveal the need to address behavioral and mental health contributors to ED visits and reinforce the importance of developing integrated care models in primary care settings to improve mental health for medically vulnerable patients. The presented modeling approach can be broadly applied to national and other large surveys.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-021-06221-w.

Bayesian Estimation for Gaussian Graphical Models: Structure Learning, Predictability, and Network Comparisons

Gaussian graphical models (GGM; "networks") allow for estimating conditional dependence structures that are encoded by partial correlations. This is accomplished by identifying non-zero relations in the inverse of the covariance matrix. In psychology the default estimation method uses ℓ1-regularization, where the accompanying inferences are restricted to frequentist objectives. Bayesian methods remain relatively uncommon in practice and methodological literatures. To date, they have not yet been used for estimation and inference in the psychological network literature. In this work, I introduce Bayesian methodology that is specifically designed for the most common psychological applications. The graphical structure is determined with posterior probabilities that can be used to assess conditional dependent and independent relations. Additional methods are provided for extending inference to specific aspects within- and between-networks, including partial correlation differences and Bayesian methodology to quantify network predictability. I first demonstrate that the decision rule based on posterior probabilities can be calibrated to the desired level of specificity. The proposed techniques are then demonstrated in several illustrative examples. The methods have been implemented in the R package BGGM.

Inference of phenotype-relevant transcriptional regulatory networks elucidates cancer type-specific regulatory mechanisms in a pan-cancer study

Reconstruction of transcriptional regulatory networks (TRNs) is a powerful approach to unravel the gene expression programs involved in healthy and disease states of a cell. However, these networks are usually reconstructed independent of the phenotypic (or clinical) properties of the samples. Therefore, they may confound regulatory mechanisms that are specifically related to a phenotypic property with more general mechanisms underlying the full complement of the analyzed samples. In this study, we develop a method called InPheRNo to identify "phenotype-relevant" TRNs. This method is based on a probabilistic graphical model that models the simultaneous effects of multiple transcription factors (TFs) on their target genes and the statistical relationship between the target genes' expression and the phenotype. Extensive comparison of InPheRNo with related approaches using primary tumor samples of 18 cancer types from The Cancer Genome Atlas reveals that InPheRNo can accurately reconstruct cancer type-relevant TRNs and identify cancer driver TFs. In addition, survival analysis reveals that the activity level of TFs with many target genes could distinguish patients with poor prognosis from those with better prognosis.

Predicting access to healthful food retailers with machine learning

Many U.S. households lack access to healthful food and rely on inexpensive, processed food with low nutritional value. Surveying access to healthful food is costly and finding the factors that affect access remains convoluted owing to the multidimensional nature of socioeconomic variables. We utilize machine learning with census tract data to predict the modified Retail Food Environment Index (mRFEI), which refers to the percentage of healthful food retailers in a tract and agnostically extract the features of no access-corresponding to a "food desert" and low access-corresponding to a "food swamp." Our model detects food deserts and food swamps with a prediction accuracy of 72% out of the sample. We find that food deserts and food swamps are intrinsically different and require separate policy attention. Food deserts are lightly populated rural tracts with low ethnic diversity, whereas swamps are predominantly small, densely populated, urban tracts, with more non-white residents who lack vehicle access. Overall access to healthful food retailers is mainly explained by population density, presence of black population, property value, and income. We also show that our model can be used to obtain sensible predictions of access to healthful food retailers for any U.S. census tract.

Integrating transcriptomes and somatic mutations to identify RNA methylation regulators as a prognostic marker in hepatocellular carcinoma

BACKGROUND

RNA methylation modifying plays an important role in the occurrence and progression of a range of human cancers including hepatocellular carcinoma (HCC), which is characterized by a mass of genetic and epigenetic alterations. However, the treatment targeting these alterations is limited.

METHODS

We used comprehensive bioinformatics analysis to analyze the correlation between cancer-associated RNA methylation regulators and HCC malignant features in network datasets.

RESULTS

We identified two HCC subgroups (cluster 1 and 2), which had clearly distinct clinicopathological, biofunctional and prognostic characteristics, by consensus clustering. The cluster 2 subgroup correlated with malignancy of the primary tumor, higher tumor stage, higher histopathological grade and higher frequency of TP53 mutation, as well as with shorter survival when compared with cluster 1. Gene enrichment indicated that the cluster 2 correlated to the tumor malignancy signaling and biological processes. Based on these findings, an 11-gene risk signature was built, which not only was an independent prognostic marker but also had an excellent power to predict the tumor features.

CONCLUSIONS

Our study indicated that RNA methylation regulators are vital for HCC malignant progression and provide an important evidence for RNA methylation, methylation regulators are actionable targets for anticancer drug discovery.