arXiv subjects

Zihuai He

Publications and source records attributed to Zihuai He.

15 recordsLinked to original sources

arXiv2026

Learning the Optimal Composite Mediator: Closed-Form Solution and Inference

Understanding how an exposure transmits its effect through high-dimensional intermediaries is a central problem in observational research. We study the problem of finding a composite mediator that maximises the indirect effect of an exposure on an outcome in a linear structural equation model. Although the objective is non-convex in the weight vector, a geometric argument yields a closed-form global solution: the optimal weight bisects the angle between two computable path vectors in a weighted inner product space, recovered via two linear solves. The resulting algorithm, MaxIE, runs at the same cost as ordinary least squares -- orders of magnitude lower than numerical optimisation -- with a dual formulation for settings where mediators outnumber observations. The same path vectors yield a test for the global null that no composite mediator exists, with t(p-1) in the classical and t(n-2) in the dual regime. Power is characterised analytically as a function of the population path angle; simulations confirm size control and the power characterisation. Applied to a UK Biobank proteomics dataset (n=38,383, p=2,916), the method rejects the global null (p-value = 6.4e-9) and identifies the optimal proteomic composite mediating age's effect on dementia.

stat.ME↗

arXiv2025

Refining Genetic Discoveries of Group Knockoffs via A Feature-level Filter

Identifying variants that carry substantial information on the trait of interest remains a core topic in genetic studies. In analyzing the EADB-UKBB dataset to identify genetic variants associated with Alzheimer's disease (AD), however, we recognize that both existing marginal association tests and conditional independence tests using existing knockoff filters suffer either power loss or lack of informativeness, especially when strong correlations exist among variants. To address these limitations, we propose a new feature-versus-group (FVG) filter that achieves balance between the power and precision in identifying important features from a set of strongly correlated features using group knockoffs. In extensive simulation studies, the FVG filter controls the expected proportion of false discoveries and identifies important features in smaller catching sets without large power loss. Applying the proposed method to the EADB-UKBB dataset, we discover important variants from 89 loci (similar to the most powerful group knockoff filter) with catching sets of substantially smaller size and higher purity and verify the biological informativeness of our discoveries.

stat.AP↗

arXiv2025

A Generalized Genetic Random Field Method for the Genetic Association Analysis of Sequencing Data

With the advance of high-throughput sequencing technologies, it has become feasible to investigate the influence of the entire spectrum of sequencing variations on complex human diseases. Although association studies utilizing the new sequencing technologies hold great promise to unravel novel genetic variants, especially rare genetic variants that contribute to human diseases, the statistical analysis of high-dimensional sequencing data remains a challenge. Advanced analytical methods are in great need to facilitate high-dimensional sequencing data analyses. In this article, we propose a generalized genetic random field (GGRF) method for association analyses of sequencing data. Like other similarity-based methods (e.g., SIMreg and SKAT), the new method has the advantages of avoiding the need to specify thresholds for rare variants and allowing for testing multiple variants acting in different directions and magnitude of effects. The method is built on the generalized estimating equation framework and thus accommodates a variety of disease phenotypes (e.g., quantitative and binary phenotypes). Moreover, it has a nice asymptotic property, and can be applied to small-scale sequencing data without need for small-sample adjustment. Through simulations, we demonstrate that the proposed GGRF attains an improved or comparable power over a commonly used method, SKAT, under various disease scenarios, especially when rare variants play a significant role in disease etiology. We further illustrate GGRF with an application to a real dataset from the Dallas Heart Study. By using GGRF, we were able to detect the association of two candidate genes, ANGPTL3 and ANGPTL4, with serum triglyceride.

stat.ME↗

arXiv2025

Repurposing Foundation Model for Generalizable Medical Time Series Classification

Medical time series (MedTS) classification suffers from poor generalizability in real-world deployment due to inter- and intra-dataset heterogeneity, such as varying numbers of channels, signal lengths, task definitions, and patient characteristics. To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets. FORMED combines the backbone with a novel classifier comprising two components: (1) task-specific channel embeddings and label queries, dynamically sized to match any number of channels and target classes, and (2) a shared decoding attention layer, jointly trained across datasets to capture medical domain knowledge through task-agnostic feature-query interactions. After repurposing, FORMED achieves seamless adaptation to unseen MedTS datasets through lightweight label query training (0.1% of parameters), eliminating the need for full fine-tuning or architectural redesign. We evaluate FORMED on 5 diverse MedTS datasets, benchmarking against 11 Task-Specific Models (TSM) and 4 Task-Specific Adaptation (TSA) methods. Our results demonstrate FORMED's dominant performance, achieving up to 35% absolute improvement in F1-score (on ADFTD dataset) over specialized baselines. Further analysis reveals consistent generalization across varying channel configurations, time series lengths, and clinical tasks, which are key challenges in real-world deployment. By decoupling domain-invariant representation learning from task-specific adaptation, FORMED establishes a scalable and resource-efficient paradigm for foundation model repurposing in healthcare. This approach prioritizes clinical adaptability over rigid task-centric design, offering a practical pathway for real-world implementation.

cs.LG↗

arXiv2024

ScAtt: an Attention based architecture to analyze Alzheimer's disease at cell type level from single-cell RNA-sequencing data

Alzheimer's disease (AD) is a pervasive neurodegenerative disorder that leads to memory and behavior impairment severe enough to interfere with daily life activities. Understanding this disease pathogenesis can drive the development of new targets and strategies to prevent and treat AD. Recent advances in high-throughput single-cell RNA sequencing technology (scRNA-seq) have enabled the generation of massive amounts of transcriptomic data at the single-cell level provided remarkable insights into understanding the molecular pathogenesis of Alzheimer's disease. In this study, we introduce ScAtt, an innovative Attention-based architecture, devised specifically for the concurrent identification of cell-type specific AD-related genes and their associated gene regulatory network. ScAtt incorporates a flexible model capable of capturing nonlinear effects, leading to the detection of AD-associated genes that might be overlooked by traditional differentially expressed gene (DEG) analyses. Moreover, ScAtt effectively infers a gene regulatory network depicting the combined influences of genes on the targeted disease, as opposed to examining correlations among genes in conventional gene co-expression networks. In an application to 95,186 single-nucleus transcriptomes from 17 hippocampus samples, ScAtt shows substantially better performance in modeling quantitative changes in expression levels between AD and healthy controls. Consequently, ScAtt performs better than existing methods in the identification of AD-related genes, with more unique discoveries and less overlap between cell types. Functional enrichments of the corresponding gene modules detected from gene regulatory network show significant enrichment of biologically meaningful AD-related pathways across different cell types.

q-bio.MN↗

arXiv2024

Second-order group knockoffs with applications to GWAS

Conditional testing via the knockoff framework allows one to identify -- among large number of possible explanatory variables -- those that carry unique information about an outcome of interest, and also provides a false discovery rate guarantee on the selection. This approach is particularly well suited to the analysis of genome wide association studies (GWAS), which have the goal of identifying genetic variants which influence traits of medical relevance. While conditional testing can be both more powerful and precise than traditional GWAS analysis methods, its vanilla implementation encounters a difficulty common to all multivariate analysis methods: it is challenging to distinguish among multiple, highly correlated regressors. This impasse can be overcome by shifting the object of inference from single variables to groups of correlated variables. To achieve this, it is necessary to construct "group knockoffs." While successful examples are already documented in the literature, this paper substantially expands the set of algorithms and software for group knockoffs. We focus in particular on second-order knockoffs, for which we describe correlation matrix approximations that are appropriate for GWAS data and that result in considerable computational savings. We illustrate the effectiveness of the proposed methods with simulations and with the analysis of albuminuria data from the UK Biobank. The described algorithms are implemented in an open-source Julia package Knockoffs.jl, for which both R and Python wrappers are available.

stat.ME↗

arXiv2024

A Powerful and Precise Feature-level Filter using Group Knockoffs

Selecting important features that have substantial effects on the response with provable type-I error rate control is a fundamental concern in statistics, with wide-ranging practical applications. Existing knockoff filters, although shown to provide theoretical guarantee on false discovery rate (FDR) control, often struggle to strike a balance between high power and precision in pinpointing important features when there exist large groups of strongly correlated features. To address this challenge, we develop a new filter using group knockoffs to achieve both powerful and precise selection of important features. Via experiments of simulated data and analysis of a real Alzheimer's disease genetic dataset, it is found that the proposed filter can not only control the proportion of false discoveries but also identify important features with comparable power and greater precision than the existing group knockoffs filter.

stat.ME↗

arXiv2024

Controlled Variable Selection from Summary Statistics Only? A Solution via GhostKnockoffs and Penalized Regression

Identifying which variables do influence a response while controlling false positives pervades statistics and data science. In this paper, we consider a scenario in which we only have access to summary statistics, such as the values of marginal empirical correlations between each dependent variable of potential interest and the response. This situation may arise due to privacy concerns, e.g., to avoid the release of sensitive genetic information. We extend GhostKnockoffs (He et al. [2022]) and introduce variable selection methods based on penalized regression achieving false discovery rate (FDR) control. We report empirical results in extensive simulation studies, demonstrating enhanced performance over previous work. We also apply our methods to genome-wide association studies of Alzheimer's disease, and evidence a significant improvement in power.

stat.ME↗

arXiv2023

Summary Statistics Knockoffs Inference with Family-wise Error Rate Control

Testing multiple hypotheses of conditional independence with provable error rate control is a fundamental problem with various applications. To infer conditional independence with family-wise error rate (FWER) control when only summary statistics of marginal dependence are accessible, we adopt GhostKnockoff to directly generate knockoff copies of summary statistics and propose a new filter to select features conditionally dependent to the response with provable FWER control. In addition, we develop a computationally efficient algorithm to greatly reduce the computational cost of knockoff copies generation without sacrificing power and FWER control. Experiments on simulated data and a real dataset of Alzheimer's disease genetics demonstrate the advantage of proposed method over the existing alternatives in both statistical power and computational efficiency.

stat.ME↗

arXiv2023

Robust inference with GhostKnockoffs in genome-wide association studies

Genome-wide association studies (GWASs) have been extensively adopted to depict the underlying genetic architecture of complex diseases. Motivated by GWASs' limitations in identifying small effect loci to understand complex traits' polygenicity and fine-mapping putative causal variants from proxy ones, we propose a knockoff-based method which only requires summary statistics from GWASs and demonstrate its validity in the presence of relatedness. We show that GhostKnockoffs inference is robust to its input Z-scores as long as they are from valid marginal association tests and their correlations are consistent with the correlations among the corresponding genetic variants. The property generalizes GhostKnockoffs to other GWASs settings, such as the meta-analysis of multiple overlapping studies and studies based on association test statistics deviated from score tests. We demonstrate GhostKnockoffs' performance using empirical simulation and a meta-analysis of nine European ancestral genome-wide association studies and whole exome/genome sequencing studies. Both results demonstrate that GhostKnockoffs identify more putative causal variants with weak genotype-phenotype associations that are missed by conventional GWASs.

stat.ME↗

arXiv2022

Ensembling improves stability and power of feature selection for deep learning models

With the growing adoption of deep learning models in different real-world domains, including computational biology, it is often necessary to understand which data features are essential for the model's decision. Despite extensive recent efforts to define different feature importance metrics for deep learning models, we identified that inherent stochasticity in the design and training of deep learning models makes commonly used feature importance scores unstable. This results in varied explanations or selections of different features across different runs of the model. We demonstrate how the signal strength of features and correlation among features directly contribute to this instability. To address this instability, we explore the ensembling of feature importance scores of models across different epochs and find that this simple approach can substantially address this issue. For example, we consider knockoff inference as they allow feature selection with statistical guarantees. We discover considerable variability in selected features in different epochs of deep learning training, and the best selection of features doesn't necessarily occur at the lowest validation loss, the conventional approach to determine the best model. As such, we present a framework to combine the feature importance of trained models across different hyperparameter settings and epochs, and instead of selecting features from one best model, we perform an ensemble of feature importance scores from numerous good models. Across the range of experiments in simulated and various real-world datasets, we demonstrate that the proposed framework consistently improves the power of feature selection.

cs.LG↗

arXiv2022

Improving genetic risk prediction across diverse population by disentangling ancestry representations

Risk prediction models using genetic data have seen increasing traction in genomics. However, most of the polygenic risk models were developed using data from participants with similar (mostly European) ancestry. This can lead to biases in the risk predictors resulting in poor generalization when applied to minority populations and admixed individuals such as African Americans. To address this bias, largely due to the prediction models being confounded by the underlying population structure, we propose a novel deep-learning framework that leverages data from diverse population and disentangles ancestry from the phenotype-relevant information in its representation. The ancestry disentangled representation can be used to build risk predictors that perform better across minority populations. We applied the proposed method to the analysis of Alzheimer's disease genetics. Comparing with standard linear and nonlinear risk prediction methods, the proposed method substantially improves risk prediction in minority populations, particularly for admixed individuals.

cs.LG↗

arXiv2021

Deep neural networks with controlled variable selection for the identification of putative causal genetic variants

Deep neural networks (DNN) have been used successfully in many scientific problems for their high prediction accuracy, but their application to genetic studies remains challenging due to their poor interpretability. In this paper, we consider the problem of scalable, robust variable selection in DNN for the identification of putative causal genetic variants in genome sequencing studies. We identified a pronounced randomness in feature selection in DNN due to its stochastic nature, which may hinder interpretability and give rise to misleading results. We propose an interpretable neural network model, stabilized using ensembling, with controlled variable selection for genetic studies. The merit of the proposed method includes: (1) flexible modelling of the non-linear effect of genetic variants to improve statistical power; (2) multiple knockoffs in the input layer to rigorously control false discovery rate; (3) hierarchical layers to substantially reduce the number of weight parameters and activations to improve computational efficiency; (4) de-randomized feature selection to stabilize identified signals. We evaluated the proposed method in extensive simulation studies and applied it to the analysis of Alzheimer disease genetics. We showed that the proposed method, when compared to conventional linear and nonlinear methods, can lead to substantially more discoveries.

cs.LG↗

arXiv2015

A Weighted U Statistic for Genetic Association Analyses of Sequencing Data

With advancements in next generation sequencing technology, a massive amount of sequencing data are generated, offering a great opportunity to comprehensively investigate the role of rare variants in the genetic etiology of complex diseases. Nevertheless, this poses a great challenge for the statistical analysis of high-dimensional sequencing data. The association analyses based on traditional statistical methods suffer substantial power loss because of the low frequency of genetic variants and the extremely high dimensionality of the data. We developed a weighted U statistic, referred to as WU-seq, for the high-dimensional association analysis of sequencing data. Based on a non-parametric U statistic, WU-SEQ makes no assumption of the underlying disease model and phenotype distribution, and can be applied to a variety of phenotypes. Through simulation studies and an empirical study, we showed that WU-SEQ outperformed a commonly used SKAT method when the underlying assumptions were violated (e.g., the phenotype followed a heavy-tailed distribution). Even when the assumptions were satisfied, WU-SEQ still attained comparable performance to SKAT. Finally, we applied WU-seq to sequencing data from the Dallas Heart Study (DHS), and detected an association between ANGPTL 4 and very low density lipoprotein cholesterol.

stat.ME↗

arXiv2014

Modeling and Testing for Joint Association Using a Genetic Random Field Model

Substantial progress has been made in identifying single genetic variants predisposing to common complex diseases. Nonetheless, the genetic etiology of human diseases remains largely unknown. Human complex diseases are likely influenced by the joint effect of a large number of genetic variants instead of a single variant. The joint analysis of multiple genetic variants considering linkage disequilibrium (LD) and potential interactions can further enhance the discovery process, leading to the identification of new disease-susceptibility genetic variants. Motivated by the recent development in spatial statistics, we propose a new statistical model based on the random field theory, referred to as a genetic random field model (GenRF), for joint association analysis with the consideration of possible gene-gene interactions and LD. Using a pseudo-likelihood approach, a GenRF test for the joint association of multiple genetic variants is developed, which has the following advantages: 1. considering complex interactions for improved performance; 2. natural dimension reduction; 3. boosting power in the presence of LD; 4. computationally efficient. Simulation studies are conducted under various scenarios. Compared with a commonly adopted kernel machine approach, SKAT, GenRF shows overall comparable performance and better performance in the presence of complex interactions. The method is further illustrated by an application to the Dallas Heart Study.

stat.ME↗