Resource

SemiBin

Nature Communications

SemiBin is a siamese deep neural network framework that incorporates information from reference genomes, able to extract better metagenome-assembled genomes (MAGs) in several host-associated and environmental habitats.

metaMIC

Genome Biology

metaMIC is a fully automated tool for identifying and correcting misassemblies of (meta)genomic assemblies with the following three steps.

nMAGMA

Briefings in Bioinformatics

nMAGMA uses Hi-C, eQTL, Gene regulatory interactions through topological overlap matrix (TOM) matrix calculated by WGCNA, as well as the physical-location-based mapping to get an expanded gene-wise annotation file of SNPs.

MAT²

Bioinformatics

MAT² can be used to recover the batch-effect free gene expression that can be used for downstream analysis. With contrastive learning, MAT² is able to take into account of the prior knowledge of cell types and define a more reasonable manifold space for cellular transcriptomes.

CSTEA

Nucleic Acids Research

CSTEA is a web server that provides both visualization and analysis of valuable time-series gene expression data on cell state transitions.CSTEA focuses on revealing important genes, key time points, and the mechanisms during the dynamic transition processes.

CMI2NI

Bioinformatics

CMI2NI is a software for inferring gene regulatory networks from gene expression data. It is a novel method using a new proposed concept of Conditional Mutual Inclusive Information (CMI2) which can accurately measure direct dependences between genes. Given the small size samples of gene expression data, CMI2NI can not only infer the correct topology of the regulation networks but also accurately quantify the dependence or regulation strength between genes. CMI2NI provides a useful tool to infer gene regulatory networks.

PCA-CMI

Bioinformatics

PCA-CMI is a MATLAB program for inferring gene regulatory networks from gene expression data. It is a novel method based on path consistency algorithm and conditional mutual information, which consider the non-linear dependence and topological structure of GRNs. In this algorithm, the (conditional) dependence between a pair of genes is represented by the CMI between them. With the general hypothesis of Gaussian distribution underlying gene expression data, CMI between a pair of genes is computed by a concise formula involving the covariance matrices of the related gene expression profiles.

NARROMI

Bioinformatics

NARROMI is software for improving accuracy of GRNs inference. It is a novel method combining ordinary differential equation based recursive optimization (RO) and information-theory based mutual information (MI). In this algorithm, both noisy regulations with low pair-wise correlations and redundant regulations from indirect regulators are removed by measuring MI and implementing RO, respectively. In particular, it is the first one to handle the redundancy problem in GRNs for model based network inference methods.