DR.SC - Joint Dimension Reduction and Spatial Clustering
Joint dimension reduction and spatial clustering is conducted for Single-cell RNA sequencing and spatial transcriptomics data, and more details can be referred to Wei Liu, Xu Liao, Yi Yang, Huazhen Lin, Joe Yeong, Xiang Zhou, Xingjie Shi and Jin Liu. (2022) <doi:10.1093/nar/gkac219>. It is not only computationally efficient and scalable to the sample size increment, but also is capable of choosing the smoothness parameter and the number of clusters as well.
Last updated 11 months ago
dimension-reductionselfsupervisedspatial-clusteringspatial-transcriptomicsopenblascpp
6.12 score 5 stars 2 dependents 29 scripts 396 downloadsProFAST - Probabilistic Factor Analysis for Spatially-Aware Dimension Reduction
Probabilistic factor analysis for spatially-aware dimension reduction across multi-section spatial transcriptomics data with millions of spatial locations. More details can be referred to Wei Liu, et al. (2023) <doi:10.1101/2023.07.11.548486>.
Last updated 10 months ago
openblascpp
5.73 score 2 stars 1 dependents 12 scripts 193 downloadsGFM - Generalized Factor Model
Generalized factor model is implemented for ultra-high dimensional data with mixed-type variables. Two algorithms, variational EM and alternate maximization, are designed to implement the generalized factor model, respectively. The factor matrix and loading matrix together with the number of factors can be well estimated. This model can be employed in social and behavioral sciences, economy and finance, and genomics, to extract interpretable nonlinear factors. More details can be referred to Wei Liu, Huazhen Lin, Shurong Zheng and Jin Liu. (2021) <doi:10.1080/01621459.2021.1999818>.
Last updated 5 months ago
approximate-factor-modelfeature-extractionnonlinear-dimension-reductionnumber-of-factorsopenblascpp
5.68 score 2 stars 2 dependents 9 scripts 213 downloadsILSE - Linear Regression Based on 'ILSE' for Missing Data
Linear regression when covariates include missing values by embedding the correlation information between covariates. Especially for block missing data, it works well. 'ILSE' conducts imputation and regression simultaneously and iteratively. More details can be referred to Huazhen Lin, Wei Liu and Wei Lan. (2021) <doi:10.1080/07350015.2019.1635486>.
Last updated 1 years ago
fimlilselinear-regressionmissing-dataopenblascpp
4.95 score 2 stars 3 scripts 233 downloadsSpaCOAP - High-Dimensional Spatial Covariate-Augmented Overdispersed Poisson Factor Model
A spatial covariate-augmented overdispersed Poisson factor model is proposed to perform efficient latent representation learning method for high-dimensional large-scale spatial count data with additional covariates.
Last updated 8 months ago
openblascppopenmp
4.30 score 165 downloadsCOAP - High-Dimensional Covariate-Augmented Overdispersed Poisson Factor Model
A covariate-augmented overdispersed Poisson factor model is proposed to jointly perform a high-dimensional Poisson factor analysis and estimate a large coefficient matrix for overdispersed count data. More details can be referred to Liu et al. (2024) <doi:10.1093/biomtc/ujae031>.
Last updated 9 months ago
openblascppopenmp
4.18 score 1 dependents 573 downloadsCMGFM - Interpretable Multi-Omics Representation Learning via Covariate-Augumented Generalized Factor Model
Covariate-augumented generalized factor model is designed to account for cross-modal heterogeneity, capture nonlinear dependencies among the data, incorporate additional information, and provide excellent interpretability while maintaining high computational efficiency.
Last updated 7 months ago
openblascppopenmp
4.00 score 1 stars 534 downloadsMultiCOAP - High-Dimensional Covariate-Augmented Overdispersed Multi-Study Poisson Factor Model
We introduce factor models designed to jointly analyze high-dimensional count data from multiple studies by extracting study-shared and specified factors. Our factor models account for heterogeneous noises and overdispersion among counts with augmented covariates. We propose an efficient and speedy variational estimation procedure for estimating model parameters, along with a novel criterion for selecting the optimal number of factors and the rank of regression coefficient matrix. More details can be referred to Liu et al. (2024) <doi:10.48550/arXiv.2402.15071>.
Last updated 3 months ago
openblascppopenmp
3.18 score 1 dependents 4 scripts 214 downloadsMMGFM - Multi-Study Multi-Modality Generalized Factor Model
We introduce a generalized factor model designed to jointly analyze high-dimensional multi-modality data from multiple studies by extracting study-shared and specified factors. Our factor models account for heterogeneous noises and overdispersion among modality variables with augmented covariates. We propose an efficient and speedy variational estimation procedure for estimating model parameters, along with a novel criterion for selecting the optimal number of factors. More details can be referred to Liu et al. (2024) <doi:10.48550/arXiv.2408.10542>.
Last updated 5 months ago
openblascppopenmp
3.00 score 6 scripts 178 downloadsRMFM - Robust Matrix Factor Model
We introduce a robust matrix factor model that explicitly incorporates tail behavior and employs a mean-shift term to avoid efficiency losses through pre-centering of observed matrices. More details on the methods related to our paper are currently under submission. A full reference to the paper will be provided in future versions once the paper is published.
Last updated 3 months ago
openblascppopenmp
2.00 score 207 downloads