arXiv subjects

Xuekui Zhang

Publications and source records attributed to Xuekui Zhang.

18 recordsLinked to original sources

arXiv2025

Estimation of Bivariate Normal Distributions from Marginal Summaries in Clinical Trials

In certain privacy-sensitive scenarios within fields such as clinical trial simulations, federated learning, and distributed learning, researchers often face the challenge of estimating correlations between variables without access to individual-level data. To address this issue, we propose a novel method to estimate the correlation of bivariate normal variables using marginal information from multiple datasets. The method, based on maximum likelihood estimation (MLE), accommodates datasets with varying sample sizes and avoids reliance on sensitive information such as sample covariances, making it particularly suitable for privacy-restricted settings. Extensive simulation studies demonstrate the proposed method's effectiveness in accurately estimating correlations and its robustness across diverse data configurations.

stat.ME↗

arXiv2025

Estimating the Joint Distribution of Two Binary Variables with Marginal Statistics

Clinical trial simulation (CTS) is critical in new drug development, providing insight into safety and efficacy while guiding trial design. Achieving realistic outcomes in CTS requires an accurately estimated joint distribution of the underlying variables. However, privacy concerns and data availability issues often restrict researchers to marginal summary-level data of each variable, making it challenging to estimate the joint distribution due to the lack of access to individual-level data or relational summaries between variables. We propose a novel approach based on the method of maximum likelihood that estimates the joint distribution of two binary variables using only marginal summary data. By leveraging numerical optimization and accommodating varying sample sizes across studies, our method preserves privacy while bypassing the need for granular or relational data. Through an extensive simulation study covering a diverse range of scenarios and an application to a real-world dataset, we demonstrate the accuracy, robustness, and practicality of our method. This method enhances the generation of realistic simulated data, thereby improving decision-making processes in drug development.

stat.ME↗

arXiv2024

Adaptive Phase 2/3 Design with Dose Optimization

FDA's Project Optimus initiative for oncology drug development emphasizes selecting a dose that optimizes both efficacy and safety. When an inferentially adaptive Phase 2/3 design with dose selection is implemented to comply with the initiative, the conventional inverse normal combination test is commonly used for Type I error control. However, indiscriminate application of this overly conservative test can lead to substantial increase in sample size and timeline delays, which undermines the appeal of the adaptive approach. This, in turn, frustrates drug developers regarding Project Optimus. The inflation of Type I error depends on the probability of selecting a dose with better long-term efficacy outcome at end of the study based on limited follow-up data at dose selection. In this paper, we discuss the estimation of this probability and its impact on Type I error control in realistic settings. Incorporating it explicitly into the two methods we have proposed result in improved designs, potentially motivating drug developers to adhere more closely to an initiative that has the potential to revolutionize oncology drug development.

stat.AP↗

arXiv2024

HiCat: A Semi-Supervised Approach for Cell Type Annotation

We introduce HiCat (Hybrid Cell Annotation using Transformative embeddings), a novel semi-supervised pipeline for annotating cell types from single-cell RNA sequencing data. HiCat fuses the strengths of supervised learning for known cell types with unsupervised learning to identify novel types. This hybrid approach incorporates both reference and query genomic data for feature engineering, enhancing the embedding learning process, increasing the effective sample size for unsupervised techniques, and improving the transferability of the supervised model trained on reference data when applied to query datasets. The pipeline follows six key steps: (1) removing batch effects using Harmony to generate a 50-dimensional principal component embedding; (2) applying UMAP for dimensionality reduction to two dimensions to capture crucial data patterns; (3) conducting unsupervised clustering of cells with DBSCAN, yielding a one-dimensional cluster membership vector; (4) merging the multi-resolution results of the previous steps into a 53-dimensional feature space that encompasses both reference and query data; (5) training a CatBoost model on the reference dataset to predict cell types in the query dataset; and (6) resolving inconsistencies between the supervised predictions and unsupervised cluster labels. When benchmarked on 10 publicly available genomic datasets, HiCat surpasses other methods, particularly in differentiating and identifying multiple new cell types. Its capacity to accurately classify novel cell types showcases its robustness and adaptability within intricate biological datasets.

q-bio.BM↗

arXiv2024

Minor Issues Escalated to Critical Levels in Large Samples: A Permutation-Based Fix

In the big data era, the need to reevaluate traditional statistical methods is paramount due to the challenges posed by vast datasets. While larger samples theoretically enhance accuracy and hypothesis testing power without increasing false positives, practical concerns about inflated Type-I errors persist. The prevalent belief is that larger samples can uncover subtle effects, necessitating dual consideration of p-value and effect size. Yet, the reliability of p-values from large samples remains debated. This paper warns that larger samples can exacerbate minor issues into significant errors, leading to false conclusions. Through our simulation study, we demonstrate how growing sample sizes amplify issues arising from two commonly encountered violations of model assumptions in real-world data and lead to incorrect decisions. This underscores the need for vigilant analytical approaches in the era of big data. In response, we introduce a permutation-based test to counterbalance the effects of sample size and assumption discrepancies by neutralizing them between actual and permuted data. We demonstrate that this approach effectively stabilizes nominal Type I error rates across various sample sizes, thereby ensuring robust statistical inferences even amidst breached conventional assumptions in big data. For reproducibility, our R codes are publicly available at: \url{https://github.com/ubcxzhang/bigDataIssue}.

stat.ME↗

arXiv2023

BOSS -- Biomarker Optimal Segmentation System

Motivation: Precision medicine is a major trend in the future of medicine. It aims to provide tailored medical treatment and prevention strategies based on an individual's unique characteristics and needs. Biomarker is the primary source of patients' unique features used in precision medicine. We often need to investigate many cutoff values of a continuous biomarker to find the optimal one and test if it can help segment patients into two groups with significantly different clinical outcomes. This requires multiple testing adjustments on tests conducted on overlapped data. The permutation-based approach is often a preferred solution, since it does not suffer the limitations of state-of-art theoretical methods. However, permutation is computationally expensive and limits its application scenarios, such as web applications requiring a fast response or the analysis of genomic study requiring to repeat analysis many times on tens of thousands of genes. Results: We proposed a novel method BOSS, Biomarker Optimal Segmentation System, to solve this problem. In simulation studies, we found BOSS's statistical power and type I error control are both non-inferior to the permutation approach, and it is hundreds of times faster than permutation. To illustrate our method, we applied BOSS to real data and revealed potentially converging biomarkers that have referential importance in exploring synergy and target-matched therapies in lung adenocarcinoma. Availability: An R package, boss, is being developed and will be available on CRAN

stat.ME↗

arXiv2022

Essential Number of Principal Components and Nearly Training-Free Model for Spectral Analysis

Through a study of multi-gas mixture datasets, we show that in multi-component spectral analysis, the number of functional or non-functional principal components required to retain the essential information is the same as the number of independent constituents in the mixture set. Due to the mutual in-dependency among different gas molecules, near one-to-one projection from the principal component to the mixture constituent can be established, leading to a significant simplification of spectral quantification. Further, with the knowledge of the molar extinction coefficients of each constituent, a complete principal component set can be extracted from the coefficients directly, and few to none training samples are required for the learning model. Compared to other approaches, the proposed methods provide fast and accurate spectral quantification solutions with a small memory size needed.

cs.LG↗

arXiv2022

Novel Modelling Strategies for High-frequency Stock Trading Data

Full electronic automation in stock exchanges has recently become popular, generating high-frequency intraday data and motivating the development of near real-time price forecasting methods. Machine learning algorithms are widely applied to mid-price stock predictions. Processing raw data as inputs for prediction models (e.g., data thinning and feature engineering) can primarily affect the performance of the prediction methods. However, researchers rarely discuss this topic. This motivated us to propose three novel modelling strategies for processing raw data. We illustrate how our novel modelling strategies improve forecasting performance by analyzing high-frequency data of the Dow Jones 30 component stocks. In these experiments, our strategies often lead to statistically significant improvement in predictions. The three strategies improve the F1 scores of the SVM models by 0.056, 0.087, and 0.016, respectively.

stat.AP↗

arXiv2022

Dynamics of Fecal Coliform Bacteria along Canada's Coast

The vast coastline provides Canada with a flourishing seafood industry including bivalve shellfish production. To sustain a healthy bivalve molluscan shellfish production, the Canadian Shellfish Sanitation Program was established to monitor the health of shellfish harvesting habitats, and fecal coliform bacteria data have been collected at nearly 15,000 marine sample sites across six coastal provinces in Canada since 1979. We applied Functional Principal Component Analysis and subsequent correlation analyses to find annual variation patterns of bacteria levels at sites in each province. The overall magnitude and the seasonality of fecal contamination were modelled by functional principal component one and two, respectively. The amplitude was related to human and warm-blooded animal activities; the seasonality was strongly correlated with river discharge driven by precipitation and snow melt in British Columbia, but such correlation in provinces along the Atlantic coast could not be properly evaluated due to lack of data during winter.

stat.AP↗

arXiv2022

Handling highly correlated genes in prediction analysis of genomic studies

Background: Selecting feature genes to predict phenotypes is one of the typical tasks in analyzing genomics data. Though many general-purpose algorithms were developed for prediction, dealing with highly correlated genes in the prediction model is still not well addressed. High correlation among genes introduces technical problems, such as multi-collinearity issues, leading to unreliable prediction models. Furthermore, when a causal gene (whose variants have an actual biological effect on a phenotype) is highly correlated with other genes, most algorithms select the feature gene from the correlated group in a purely data-driven manner. Since the correlation structure among genes could change substantially when condition changes, the prediction model based on not correctly selected feature genes is unreliable. Therefore, we aim to keep the causal biological signal in the prediction process and build a more robust prediction model. Method: We propose a grouping algorithm, which treats highly correlated genes as a group and uses their common pattern to represent the group's biological signal in feature selection. Our novel grouping algorithm can be integrated into existing prediction algorithms to enhance their prediction performance. Our proposed grouping method has two advantages. First, using the gene group's common patterns makes the prediction more robust and reliable under condition change. Second, it reports whole correlated gene groups as discovered biomarkers for prediction tasks, allowing researchers to conduct follow-up studies to identify causal genes within the identified groups. Result: Using real benchmark scRNA-seq datasets with simulated cell phenotypes, we demonstrate our novel method significantly outperforms standard models in both (1) prediction of cell phenotypes and (2) feature gene selection.

stat.AP↗

arXiv2021

A systematic evaluation of methods for cell phenotype classification using single-cell RNA sequencing data

Background: Single-cell RNA sequencing (scRNA-seq) yields valuable insights about gene expression and gives critical information about complex tissue cellular composition. In the analysis of single-cell RNA sequencing, the annotations of cell subtypes are often done manually, which is time-consuming and irreproducible. Garnett is a cell-type annotation software based the on elastic net method. Besides cell-type annotation, supervised machine learning methods can also be applied to predict other cell phenotypes from genomic data. Despite the popularity of such applications, there is no existing study to systematically investigate the performance of those supervised algorithms in various sizes of scRNA-seq data sets. Methods and Results: This study evaluates 13 popular supervised machine learning algorithms to classify cell phenotypes, using published real and simulated data sets with diverse cell sizes. The benchmark contained two parts. In the first part, we used real data sets to assess the popular supervised algorithms' computing speed and cell phenotype classification performance. The classification performances were evaluated using AUC statistics, F1-score, precision, recall, and false-positive rate. In the second part, we evaluated gene selection performance using published simulated data sets with a known list of real genes. Conclusion: The study outcomes showed that ElasticNet with interactions performed best in small and medium data sets. NB was another appropriate method for medium data sets. In large data sets, XGB works excellent. Ensemble algorithms were not significantly superior to individual machine learning methods. Adding interactions to ElasticNet can help, and the improvement was significant in small data sets.

q-bio.GN↗

arXiv2021

Multi-Stage Graph Peeling Algorithm for Probabilistic Core Decomposition

Mining dense subgraphs where vertices connect closely with each other is a common task when analyzing graphs. A very popular notion in subgraph analysis is core decomposition. Recently, Esfahani et al. presented a probabilistic core decomposition algorithm based on graph peeling and Central Limit Theorem (CLT) that is capable of handling very large graphs. Their proposed peeling algorithm (PA) starts from the lowest degree vertices and recursively deletes these vertices, assigning core numbers, and updating the degree of neighbour vertices until it reached the maximum core. However, in many applications, particularly in biology, more valuable information can be obtained from dense sub-communities and we are not interested in small cores where vertices do not interact much with others. To make the previous PA focus more on dense subgraphs, we propose a multi-stage graph peeling algorithm (M-PA) that has a two-stage data screening procedure added before the previous PA. After removing vertices from the graph based on the user-defined thresholds, we can reduce the graph complexity largely and without affecting the vertices in subgraphs that we are interested in. We show that M-PA is more efficient than the previous PA and with the properly set filtering threshold, can produce very similar if not identical dense subgraphs to the previous PA (in terms of graph density and clustering coefficient).

stat.ML↗

arXiv2020

The Optimal Design of Clinical Trials with Potential Biomarker Effects, A Novel Computational Approach

As a future trend of healthcare, personalized medicine tailors medical treatments to individual patients. It requires to identify a subset of patients with the best response to treatment. The subset can be defined by a biomarker (e.g. expression of a gene) and its cutoff value. Topics on subset identification have received massive attention. There are over 2 million hits by keyword searches on Google Scholar. However, how to properly incorporate the identified subsets/biomarkers to design clinical trials is not trivial and rarely discussed in the literature, which leads to a gap between research results and real-world drug development. To fill in this gap, we formulate the problem of clinical trial design into an optimization problem involving high-dimensional integration, and propose a novel computational solution based on Monte-Carlo and smoothing methods. Our method utilizes the modern techniques of General-Purpose computing on Graphics Processing Units for large-scale parallel computing. Compared to the standard method in three-dimensional problems, our approach is more accurate and 133 times faster. This advantage increases when dimensionality increases. Our method is scalable to higher-dimensional problems since the precision bound is a finite number not affected by dimensionality. Our software will be available on GitHub and CRAN, which can be applied to guide the design of clinical trials to incorporate the biomarker better. Although our research is motivated by the design of clinical trials, the method can be used widely to solve other optimization problems involving high-dimensional integration.

stat.ME↗

arXiv2020

Optimal Study Design for Reducing Variances of Coefficient Estimators in Change-Point Models

In longitudinal studies, we observe measurements of the same variables at different time points to track the changes in their pattern over time. In such studies, scheduling of the data collection waves (i.e. time of participants' visits) is often pre-determined to accommodate ease of project management and compliance. Hence, it is common to schedule those visits at equally spaced time intervals. However, recent publications based on simulated experiments indicate that the power of studies and the precision of model parameter estimators is related to the participants' visiting schemes. In this paper, we consider the longitudinal studies that investigate the changing pattern of a disease outcome, (e.g. the accelerated cognitive decline of senior adults). Such studies are often analyzed by the broken-stick model, consisting of two segments of linear models connected at an unknown change-point. We formulate this design problem into a high-dimensional optimization problem and derive its analytical solution. Based on this solution, we propose an optimal design of the visiting scheme that maximizes the power (i.e. reduce the variance of estimators) to identify the onset of accelerated decline. Using both simulation studies and evidence from real data, we demonstrate our optimal design outperforms the standard equally-spaced design. Applying our novel design to plan the longitudinal studies, researchers can improve the power of detecting pattern change without collecting extra data.

stat.ME↗

arXiv2019

Logistic Box-Cox Regression to Assess the Shape and Median Effect under Uncertainty about Model Specification

The shape of the relationship between a continuous exposure variable and a binary disease variable is often central to epidemiologic investigations. This paper investigates a number of issues surrounding inference and the shape of the relationship. Presuming that the relationship can be expressed in terms of regression coefficients and a shape parameter, we investigate how well the shape can be inferred in settings which might typify epidemiologic investigations and risk assessment. We also consider a suitable definition of the median effect of exposure, and investigate how precisely this can be inferred. This is done both in the case of using a model acknowledging uncertainty about the shape parameter and in the case of ignoring this uncertainty and using a two-step method, where in step one we transform the predictor and in step two we fit a simple linear model with transformed predictor. All these investigations require a family of exposure-disease relationships indexed by a shape parameter. For this purpose, we employ a family based on the Box-Cox transformation.

stat.ME↗

arXiv2019

Model-based clustering for identifying disease-associated SNPs in case-control genome-wide association studies

Genome-wide association studies (GWASs) aim to detect genetic risk factors for complex human diseases by identifying disease-associated single-nucleotide polymorphisms (SNPs). The traditional SNP-wise approach along with multiple testing adjustment is over-conservative and lack of power in many GWASs. In this article, we proposed a model-based clustering method that transforms the challenging high-dimension-small-sample-size problem to low-dimension-large-sample-size problem and borrows information across SNPs by grouping SNPs into three clusters. We pre-specify the patterns of clusters by minor allele frequencies of SNPs between cases and controls, and enforce the patterns with prior distributions. In the simulation studies our proposed novel model outperform traditional SNP-wise approach by showing better controls of false discovery rate (FDR) and higher sensitivity. We re-analyzed two real studies to identifying SNPs associated with severe bortezomib-induced peripheral neuropathy (BiPN) in patients with multiple myeloma (MM). The original analysis in the literature failed to identify SNPs after FDR adjustment. Our proposed method not only detected the reported SNPs after FDR adjustment but also discovered a novel BiPN-associated SNP rs4351714 that has been reported to be related to MM in another study.

stat.ME↗

arXiv2019

Simultaneous prediction of multiple outcomes using revised stacking algorithms

Motivation: HIV is difficult to treat because its virus mutates at a high rate and mutated viruses easily develop resistance to existing drugs. If the relationships between mutations and drug resistances can be determined from historical data, patients can be provided personalized treatment according to their own mutation information. The HIV Drug Resistance Database was built to investigate the relationships. Our goal is to build a model using data in this database, which simultaneously predicts the resistance of multiple drugs using mutation information from sequences of viruses for any new patient. Results: We propose two variations of a stacking algorithm which borrow information among multiple prediction tasks to improve multivariate prediction performance. The most attractive feature of our proposed methods is the flexibility with which complex multivariate prediction models can be constructed using any univariate prediction models. Using cross-validation studies, we show that our proposed methods outperform other popular multivariate prediction methods. Availability: An R package will be made available.

q-bio.QM↗

arXiv2009

PICS: Probabilistic Inference for ChIP-seq

ChIP-seq, which combines chromatin immunoprecipitation with massively parallel short-read sequencing, can profile in vivo genome-wide transcription factor-DNA association with higher sensitivity, specificity and spatial resolution than ChIP-chip. While it presents new opportunities for research, ChIP-seq poses new challenges for statistical analysis that derive from the complexity of the biological systems characterized and the variability and biases in its digital sequence data. We propose a method called PICS (Probabilistic Inference for ChIP-seq) for extracting information from ChIP-seq aligned-read data in order to identify regions bound by transcription factors. PICS identifies enriched regions by modeling local concentrations of directional reads, and uses DNA fragment length prior information to discriminate closely adjacent binding events via a Bayesian hierarchical t-mixture model. Its per-event fragment length estimates also allow it to remove from analysis regions that have atypical lengths. PICS uses pre-calculated, whole-genome read mappability profiles and a truncated t-distribution to adjust binding event models for reads that are missing due to local genome repetitiveness. It estimates uncertainties in model parameters that can be used to define confidence regions on binding event locations and to filter estimates. Finally, PICS calculates a per-event enrichment score relative to a control sample, and can use a control sample to estimate a false discovery rate. We compared PICS to the alternative methods MACS, QuEST, and CisGenome, using published GABP and FOXA1 data sets from human cell lines, and found that PICS' predicted binding sites were more consistent with computationally predicted binding motifs.

q-bio.GN↗