A multi-modal neural network that takes advantage of the high-dimensionality of spatial transcriptomics data and the high-definition of image data to achieve interpretable high-definition dimension reduction. Further details and tutorials can be found here.
A computational pipeline for detecting Copy Number Alterations (CNAs) from spatial transcriptomic RNA matrix by integrating images and spatial coordinates.
A software package based on the EM-test for efficient feature screening in high-dimensional count data, such as single-cell RNA-seq. FS4Clustering identifies cluster-relevant features to substantially improve clustering accuracy.
A comprehensive benchmark framework that takes advantage of a large collection of synthetic and real-world spatial transcriptomics datasets to evaluate algorithms for spatially variable gene identification, aiming to guide method selection and stimulate future method development.
A CNA detection algorithm for scATAC-seq data. AtaCNA extends CNA detection to one million base pair resolution.
A statistical method for the direct selection of cell-type markers for downstream clustering which avoids double-dipping.
A computational toolkit that provides a wide spectrum of tools for analyzing full-length transcriptome data, including read mapping, novel isoform identification, gene fusion detection, and isoform expression quantification.
A gene fusion detection algorithm for scRNA-seq data. scFusion is currently the only tool that enables gene fusion detection at single-cell resolution.
An R package for detecting copy number variations with high throughput sequencing data.
A perl pipeline for detecting copy number variations by normalizing the high throughput sequencing data.
A Python package for simulating structural variation data with GC-biases.
An R package for differential network analysis based on the penalized D-trace loss.
An R package for Bayesian variable selection in Quantile Regression based on the empirical likelihood.
Xilab