Raymond Ka Wai Wong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Raymond Ka Wai Wong has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
- Thomas C. M. Lee
Department of Statistics University of California 95616 Davis Davis CA
7 shared publications - Chinmay Hegde
New York University, New York, NY, USA
5 shared publications - Kejun He
Center for Applied Statistics, Institute of Statistics and Big Data, Renmin University of China , Beijing 100872
4 shared publications Thomas C. M. Lee
4 shared publications- Xiaojun Mao
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China
4 shared publications - Alper Adak
Department of Soil and Crop Sciences Texas A&M University College Station Texas USA
3 shared publications
Latest Publications
- Open Access
An open field phenomics resource for multimodal maize yield prediction across divergent environments
Temporal drone phenotyping captures crop development, but irregular flight schedules complicate comparisons across environments. We release curated imagery from 356 flights across 19 Genomes to Fields environments containing 1,180 maize ( Zea mays L.) hybrids. To evaluate its utility, we integrated functional principal components of vegetation index and weather trajectories with genomic information. Combinined genomic and phenomic kernels improved yield prediction, reaching correlations up to r = 0.501 for held-out hybrids in environments represented in training and 0.408 when environments were also withheld. Accumulated growing degree days offered no consistent predictive advantage over days after planting, and weather contributed modest, task-dependent gains. A transformer neural process learned directly from irregular observations, serving as a novel application of neural process models in agriculture. Mapping vegetation index functional principal components identified recurrent quantitative trait loci on chromosomes 3 and 7. This resource and its reproducible analyses guide the use of temporal spectral data for crop prediction and genetic discovery.
Open AccessAn open field phenomics resource for multimodal maize yield prediction across divergent environments
Temporal drone phenotyping captures crop development, but irregular flight schedules complicate comparisons across environments. We release curated imagery from 356 flights across 19 Genomes to Fields environments containing 1,180 maize ( Zea mays L.) hybrids. To evaluate its utility, we integrated functional principal components of vegetation index and weather trajectories with genomic information. Combinined genomic and phenomic kernels improved yield prediction, reaching correlations up to r = 0.501 for held-out hybrids in environments represented in training and 0.408 when environments were also withheld. Accumulated growing degree days offered no consistent predictive advantage over days after planting, and weather contributed modest, task-dependent gains. A transformer neural process learned directly from irregular observations, serving as a novel application of neural process models in agriculture. Mapping vegetation index functional principal components identified recurrent quantitative trait loci on chromosomes 3 and 7. This resource and its reproducible analyses guide the use of temporal spectral data for crop prediction and genetic discovery.
- Open Access
- 26 June 2026
- Published by Oxford University Press (OUP) in Genomics, Proteomics & Bioinformatics
Single-cell Multiomic and Spatiotemporal Dissection of the Liver Circadian Clock
Circadian rhythms are remarkably widespread across most organisms, regulating hormonal, metabolic, physiological, and behavioral oscillations through molecular clocks that orchestrate the rhythmic expression of thousands of genes. Here, we generate the first time-series single-nucleus RNA and ATAC multiomics data to simultaneously characterize gene expression and chromatin accessibility of mouse liver cells across the 24-hour cycle. We uncover pronounced cell-type-specific circadian programs, with hepatocytes displaying the strongest and most widespread rhythmicity at both the transcriptomic and epigenomic levels. Chromatin accessibility rhythms frequently precede or coincide with transcriptional rhythms, indicating coordinated regulation between chromatin state and gene activation. Across the genome, rhythmic gene expression is driven primarily by oscillations in the fraction of transcriptionally active (“bursting”) cells rather than changes in transcript output per cell, revealing burst frequency as a dominant mechanism of circadian control. By reconstructing spatial zonation of the liver lobule, we identify both genes and cis-regulatory elements (CREs) that are temporally, spatially, or spatiotemporally variable. We infer gene regulatory relationships linking transcription factors (TFs), CREs, and target genes, recapitulating core clock feedback loops and revealing spatiotemporally resolved regulatory logic underlying metabolic gene expression. Our findings apply to existing single-cell data of mouse and Drosophila brains and are validated by time-series single-molecule fluorescence in situ hybridization and vast amounts of orthogonal omics data. Altogether, our study constructs a comprehensive map of the time-series transcriptomic and epigenomic landscapes that elucidate the function and mechanism of the liver peripheral clocks.
- 26 June 2026
- Published by Oxford University Press (OUP) in Genomics, Proteomics & Bioinformatics
Open AccessSingle-cell Multiomic and Spatiotemporal Dissection of the Liver Circadian Clock
Circadian rhythms are remarkably widespread across most organisms, regulating hormonal, metabolic, physiological, and behavioral oscillations through molecular clocks that orchestrate the rhythmic expression of thousands of genes. Here, we generate the first time-series single-nucleus RNA and ATAC multiomics data to simultaneously characterize gene expression and chromatin accessibility of mouse liver cells across the 24-hour cycle. We uncover pronounced cell-type-specific circadian programs, with hepatocytes displaying the strongest and most widespread rhythmicity at both the transcriptomic and epigenomic levels. Chromatin accessibility rhythms frequently precede or coincide with transcriptional rhythms, indicating coordinated regulation between chromatin state and gene activation. Across the genome, rhythmic gene expression is driven primarily by oscillations in the fraction of transcriptionally active (“bursting”) cells rather than changes in transcript output per cell, revealing burst frequency as a dominant mechanism of circadian control. By reconstructing spatial zonation of the liver lobule, we identify both genes and cis-regulatory elements (CREs) that are temporally, spatially, or spatiotemporally variable. We infer gene regulatory relationships linking transcription factors (TFs), CREs, and target genes, recapitulating core clock feedback loops and revealing spatiotemporally resolved regulatory logic underlying metabolic gene expression. Our findings apply to existing single-cell data of mouse and Drosophila brains and are validated by time-series single-molecule fluorescence in situ hybridization and vast amounts of orthogonal omics data. Altogether, our study constructs a comprehensive map of the time-series transcriptomic and epigenomic landscapes that elucidate the function and mechanism of the liver peripheral clocks.
- Open Access
cyclinbayes: Bayesian Causal Discovery with Linear Non-Gaussian Directed Acyclic and Cyclic Graphical Models
We introduce cyclinbayes, an open-source R package for discovering linear causal relationships with both acyclic and cyclic structures. The package employs scalable Bayesian approaches with spike-and-slab priors to learn directed acyclic graphs (DAGs) and directed cyclic graphs (DCGs) under non-Gaussian noise. A central feature of cyclinbayes is comprehensive uncertainty quantification, including posterior edge inclusion probabilities, posterior probabilities of network motifs, and posterior probabilities over entire graph structures. Our implementation addresses two limitations in existing software: (1) while methods for linear non-Gaussian DAG learning are available in R and Python, they generally lack proper uncertainty quantification, and (2) reliable implementations for linear non-Gaussian DCG remain scarce. The package implements computationally efficient hybrid MCMC algorithms that scale to large datasets. Beyond uncertainty quantification, we propose a new decision-theoretic approach to summarize posterior samples of graphs, yielding principled point estimates based on posterior expected loss such as posterior expected structural Hamming distance and structural intervention distance. The package, a supplementary material, and a tutorial are available on GitHub at https://github.com/roblee01/cyclinbayes.
Open Accesscyclinbayes: Bayesian Causal Discovery with Linear Non-Gaussian Directed Acyclic and Cyclic Graphical Models
We introduce cyclinbayes, an open-source R package for discovering linear causal relationships with both acyclic and cyclic structures. The package employs scalable Bayesian approaches with spike-and-slab priors to learn directed acyclic graphs (DAGs) and directed cyclic graphs (DCGs) under non-Gaussian noise. A central feature of cyclinbayes is comprehensive uncertainty quantification, including posterior edge inclusion probabilities, posterior probabilities of network motifs, and posterior probabilities over entire graph structures. Our implementation addresses two limitations in existing software: (1) while methods for linear non-Gaussian DAG learning are available in R and Python, they generally lack proper uncertainty quantification, and (2) reliable implementations for linear non-Gaussian DCG remain scarce. The package implements computationally efficient hybrid MCMC algorithms that scale to large datasets. Beyond uncertainty quantification, we propose a new decision-theoretic approach to summarize posterior samples of graphs, yielding principled point estimates based on posterior expected loss such as posterior expected structural Hamming distance and structural intervention distance. The package, a supplementary material, and a tutorial are available on GitHub at https://github.com/roblee01/cyclinbayes.
- Open Access
Distributional Data Analysis Uncovers Hundreds of Novel and Heritable Phenomic Features from Temporal Cotton and Maize Drone Imagery
Genomic and phenomic analyses suggest additional heritable phenomic features can improve modeling of important end traits like senescence or yield. Field phenotyping generally uses trait values averaged across individual experimental units (plants or numerous plants within plots), ignoring the full distributional pattern of collected measures. Images of plants or plots, as captured by drones (unoccupied aerial vehicles / UAVs / drones), can be viewed as individual distribution functions that capture biological information. This study introduces and validates distributional data analysis in two crops and experiment types – cotton ( Gossypium hirsutum L.) single plant vegetation index (VI) analysis and maize ( Zea mays L.) plot-level yield predictions. In both crops, the concept of within-day variance decomposition was demonstrated. In cotton, genotypes exerted significant influences on temporal quantile functions of VIs. Maize yield prediction using distributional data with elastic-net regression indicated improvements in yield prediction between 12.7%-21.6% with quantiles outside the conventionally used median responsible for added predictive power. A novel data visualization method for per-pixel heritability allowed distributional features to be explainable and interpretable. These results have implications for future plant phenomic studies, indicating that distributional data analysis applied across temporal imagery captures novel, heritable, and interpretable biological signal that is lost when working with conventional measures of central tendency such as mean or median summary values of experimental units. Significance: Repeated aerial imaging of agricultural experiments produces image data sets that capture plant development in high spatial and temporal resolutions. Frequently, images are summarized by measures of central tendency, such as mean or median values. Here, functional data distributional methods were applied to cotton ( Gossypium hirsutum L.) and maize ( Zea mays L.) image data, capturing more information than standard approaches. Cotton genotypes significantly impacted distributional spectral data while in maize, distributional data enabled more accurate predictions of grain yield versus models trained with median data alone. Distributional data were more explainable by genetics, with novel data visualization techniques able to shine light on specific parts of plant imagery with high and low genetic variance.
Open AccessDistributional Data Analysis Uncovers Hundreds of Novel and Heritable Phenomic Features from Temporal Cotton and Maize Drone Imagery
Genomic and phenomic analyses suggest additional heritable phenomic features can improve modeling of important end traits like senescence or yield. Field phenotyping generally uses trait values averaged across individual experimental units (plants or numerous plants within plots), ignoring the full distributional pattern of collected measures. Images of plants or plots, as captured by drones (unoccupied aerial vehicles / UAVs / drones), can be viewed as individual distribution functions that capture biological information. This study introduces and validates distributional data analysis in two crops and experiment types – cotton ( Gossypium hirsutum L.) single plant vegetation index (VI) analysis and maize ( Zea mays L.) plot-level yield predictions. In both crops, the concept of within-day variance decomposition was demonstrated. In cotton, genotypes exerted significant influences on temporal quantile functions of VIs. Maize yield prediction using distributional data with elastic-net regression indicated improvements in yield prediction between 12.7%-21.6% with quantiles outside the conventionally used median responsible for added predictive power. A novel data visualization method for per-pixel heritability allowed distributional features to be explainable and interpretable. These results have implications for future plant phenomic studies, indicating that distributional data analysis applied across temporal imagery captures novel, heritable, and interpretable biological signal that is lost when working with conventional measures of central tendency such as mean or median summary values of experimental units. Significance: Repeated aerial imaging of agricultural experiments produces image data sets that capture plant development in high spatial and temporal resolutions. Frequently, images are summarized by measures of central tendency, such as mean or median values. Here, functional data distributional methods were applied to cotton ( Gossypium hirsutum L.) and maize ( Zea mays L.) image data, capturing more information than standard approaches. Cotton genotypes significantly impacted distributional spectral data while in maize, distributional data enabled more accurate predictions of grain yield versus models trained with median data alone. Distributional data were more explainable by genetics, with novel data visualization techniques able to shine light on specific parts of plant imagery with high and low genetic variance.
- Open Access
- 1 January 2025
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 19 (2) , 4312-4355
Balancing weights for non-monotone missing data
Balancing weights have been widely applied to single or monotone missingness due to empirical advantages over likelihood-based methods and inverse probability weighting approaches. This paper considers non-monotone missing data under the complete-case missing variable condition (CCMV), a case of missing not at random (MNAR). Using relationships between each missing pattern and the complete-case subsample, we construct a weighted estimator for estimation, where the weight is a sum of ratios of the conditional probability of observing a particular missing pattern versus that of observing the complete-case, given the variables observed in the corresponding missing pattern. However, plug-in estimators of the propensity odds can be unbounded and lead to unstable estimation. Using further relations between propensity odds and balancing of moments across response patterns, we employ tailored loss functions, each encouraging empirical balance across patterns to estimate propensity odds flexibly using a functional basis expansion. We propose two penalizations to control propensity odds model smoothness and empirical imbalance. We study the asymptotic properties of the proposed estimators and show that they are consistent under mild smoothness assumptions. Asymptotic normality and efficiency are developed. Simulation results show the superior performance of the proposed method.
- 1 January 2025
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 19 (2) , 4312-4355
Open AccessBalancing weights for non-monotone missing data
Balancing weights have been widely applied to single or monotone missingness due to empirical advantages over likelihood-based methods and inverse probability weighting approaches. This paper considers non-monotone missing data under the complete-case missing variable condition (CCMV), a case of missing not at random (MNAR). Using relationships between each missing pattern and the complete-case subsample, we construct a weighted estimator for estimation, where the weight is a sum of ratios of the conditional probability of observing a particular missing pattern versus that of observing the complete-case, given the variables observed in the corresponding missing pattern. However, plug-in estimators of the propensity odds can be unbounded and lead to unstable estimation. Using further relations between propensity odds and balancing of moments across response patterns, we employ tailored loss functions, each encouraging empirical balance across patterns to estimate propensity odds flexibly using a functional basis expansion. We propose two penalizations to control propensity odds model smoothness and empirical imbalance. We study the asymptotic properties of the proposed estimators and show that they are consistent under mild smoothness assumptions. Asymptotic normality and efficiency are developed. Simulation results show the superior performance of the proposed method.
- 2 January 2024
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 119 (545) , 791
Handbook of Matching and Weighting Adjustments for Causal Inference
- 2 January 2024
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 119 (545) , 791
Handbook of Matching and Weighting Adjustments for Causal Inference
- 1 January 2024
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 34 (4) , 2015-2042
Multivariate Varying-coefficient Models via Tensor Decomposition
- 1 January 2024
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 34 (4) , 2015-2042
Multivariate Varying-coefficient Models via Tensor Decomposition
- Open Access
- 22 June 2023
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 79 (4) , 2933-2946
Hierarchical Nuclear Norm Penalization for Multi-View Data Integration
The prevalence of data collected on the same set of samples from multiple sources (i.e., multi-view data) has prompted significant development of data integration methods based on low-rank matrix factorizations. These methods decompose signal matrices from each view into the sum of shared and individual structures, which are further used for dimension reduction, exploratory analyses, and quantifying associations across views. However, existing methods have limitations in modeling partially-shared structures due to either too restrictive models, or restrictive identifiability conditions. To address these challenges, we propose a new formulation for signal structures that include partially-shared signals based on grouping the views into so-called hierarchical levels with identifiable guarantees under suitable conditions. The proposed hierarchy leads us to introduce a new penalty, hierarchical nuclear norm (HNN), for signal estimation. In contrast to existing methods, HNN penalization avoids scores and loadings factorization of the signals and leads to a convex optimization problem, which we solve using a dual forward–backward algorithm. We propose a simple refitting procedure to adjust the penalization bias and develop an adapted version of bi-cross-validation for selecting tuning parameters. Extensive simulation studies and analysis of the genotype-tissue expression data demonstrate the advantages of our method over existing alternatives.
- 22 June 2023
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 79 (4) , 2933-2946
Open AccessHierarchical Nuclear Norm Penalization for Multi-View Data Integration
The prevalence of data collected on the same set of samples from multiple sources (i.e., multi-view data) has prompted significant development of data integration methods based on low-rank matrix factorizations. These methods decompose signal matrices from each view into the sum of shared and individual structures, which are further used for dimension reduction, exploratory analyses, and quantifying associations across views. However, existing methods have limitations in modeling partially-shared structures due to either too restrictive models, or restrictive identifiability conditions. To address these challenges, we propose a new formulation for signal structures that include partially-shared signals based on grouping the views into so-called hierarchical levels with identifiable guarantees under suitable conditions. The proposed hierarchy leads us to introduce a new penalty, hierarchical nuclear norm (HNN), for signal estimation. In contrast to existing methods, HNN penalization avoids scores and loadings factorization of the signals and leads to a convex optimization problem, which we solve using a dual forward–backward algorithm. We propose a simple refitting procedure to adjust the penalization bias and develop an adapted version of bi-cross-validation for selecting tuning parameters. Extensive simulation studies and analysis of the genotype-tissue expression data demonstrate the advantages of our method over existing alternatives.
- 3 June 2023
- Published by Oxford University Press (OUP) in Journal of Experimental Botany
- Vol. 74 (17) , 5307-5326
Phenomic data-driven biological prediction of maize through field-based high-throughput phenotyping integration with genomic data
High throughput phenotyping (HTP) has expanded the dimensionality of data in plant research, however HTP has resulted in few novel biological discoveries to date. Field based high-throughput phenotyping (FHTP), using small unoccupied aerial vehicles (UAV) equipped with imaging sensors can be deployed routinely to monitor segregating plant population interactions with the environment under biologically meaningful conditions. Here, flowering dates and plant height, important phenological fitness traits, were collected on 520 segregating recombinant maize inbred lines (RILs) in both irrigated and drought stress trials in 2018. Using UAV phenomic, SNP genomic, as well as combined data, flowering times were predicted using several scenarios. Untested genotypes were predicted with 0.58, 0.59 and 0.41 prediction ability for anthesis, silking and terminal plant height using genomic data; but prediction ability increased 0.77, 0.76 and 0.58 when phenomic and genomic data were used together. Using the phenomic data in a genome-wide association study, a heat related candidate gene (GRMZM2G083810; hsp18f) was discovered using temporal reflectance phenotypes belonging to flowering times (both irrigated and drought) trials where heat stress also peaked. Thus, a relation between plants and abiotic stresses belonging to a specific time of growth was revealed only through use of temporal phenomic data. Overall, this study showed that (i) it is possible to predict complex traits using high dimensional phenomic data between different environments, and (ii) temporal phenomic data can reveal time-dependent association between genotypes and abiotic stresses, which can help understand mechanisms to develop resilient plants.
- 3 June 2023
- Published by Oxford University Press (OUP) in Journal of Experimental Botany
- Vol. 74 (17) , 5307-5326
Phenomic data-driven biological prediction of maize through field-based high-throughput phenotyping integration with genomic data
High throughput phenotyping (HTP) has expanded the dimensionality of data in plant research, however HTP has resulted in few novel biological discoveries to date. Field based high-throughput phenotyping (FHTP), using small unoccupied aerial vehicles (UAV) equipped with imaging sensors can be deployed routinely to monitor segregating plant population interactions with the environment under biologically meaningful conditions. Here, flowering dates and plant height, important phenological fitness traits, were collected on 520 segregating recombinant maize inbred lines (RILs) in both irrigated and drought stress trials in 2018. Using UAV phenomic, SNP genomic, as well as combined data, flowering times were predicted using several scenarios. Untested genotypes were predicted with 0.58, 0.59 and 0.41 prediction ability for anthesis, silking and terminal plant height using genomic data; but prediction ability increased 0.77, 0.76 and 0.58 when phenomic and genomic data were used together. Using the phenomic data in a genome-wide association study, a heat related candidate gene (GRMZM2G083810; hsp18f) was discovered using temporal reflectance phenotypes belonging to flowering times (both irrigated and drought) trials where heat stress also peaked. Thus, a relation between plants and abiotic stresses belonging to a specific time of growth was revealed only through use of temporal phenomic data. Overall, this study showed that (i) it is possible to predict complex traits using high dimensional phenomic data between different environments, and (ii) temporal phenomic data can reveal time-dependent association between genotypes and abiotic stresses, which can help understand mechanisms to develop resilient plants.
- 18 April 2023
- Published by Taylor & Francis in Technometrics
- Vol. 65 (4) , 524-536
Bayesian Nonlinear Tensor Regression with Functional Fused Elastic Net Prior
Tensor regression methods have been widely used to predict a scalar response from covariates in the form of a multiway array. In many applications, the regions of tensor covariates used for prediction are often spatially connected with unknown shapes and discontinuous jumps on the boundaries. Moreover, the relationship between the response and the tensor covariates can be nonlinear. In this article, we develop a nonlinear Bayesian tensor additive regression model to accommodate such spatial structure. A functional fused elastic net prior is proposed over the additive component functions to comprehensively model the nonlinearity and spatial smoothness, detect the discontinuous jumps, and simultaneously identify the active regions. The great flexibility and interpretability of the proposed method against the alternatives are demonstrated by a simulation study and an analysis on facial feature data. Supplementary Materials for this article are available online.
- 18 April 2023
- Published by Taylor & Francis in Technometrics
- Vol. 65 (4) , 524-536
Bayesian Nonlinear Tensor Regression with Functional Fused Elastic Net Prior
Tensor regression methods have been widely used to predict a scalar response from covariates in the form of a multiway array. In many applications, the regions of tensor covariates used for prediction are often spatially connected with unknown shapes and discontinuous jumps on the boundaries. Moreover, the relationship between the response and the tensor covariates can be nonlinear. In this article, we develop a nonlinear Bayesian tensor additive regression model to accommodate such spatial structure. A functional fused elastic net prior is proposed over the additive component functions to comprehensively model the nonlinearity and spatial smoothness, detect the discontinuous jumps, and simultaneously identify the active regions. The great flexibility and interpretability of the proposed method against the alternatives are demonstrated by a simulation study and an analysis on facial feature data. Supplementary Materials for this article are available online.