In testing stage, co-information and co-information based permutation test are conducted sequentially to search epistatic interactions within the retained SNPs, with the results then ranked by their p-values.
To address these problems, a three-stage method, epiMiner (epistasis Miner), is proposed based on co-information theory.
In [1], Bell described the co-information lattice, used it to show how to express the probability density under a general hypergraphical model, and then used this to derive the lattice of dependent component analysis algorithms.
For further characterizing broader epistasis landscape, a visualizing stage is designed to dynamically construct epistasis networks by linking pairs of the retained SNPs if their co-information values with respect to the phenotype are stronger than thresholds.
Comment Large sample variance estimates for (hat {F} x,y)) and (hat {S} x,y)) are conceptually straightforward in that they follow standard methods based on obtaining the co-information matrix with dimensions that vary as a function of the proportion of censored observations.
In screening stage, Co-Information Index (CII) is employed to visualize and rank contributions of individual SNPs to the phenotype, with the number of top ranking SNPs retained to next stage specified by users directly or a support vector machine classifier automatically.
In fact, GloVe is more flexible than word2vec since GloVe explicitly utilizes word word co-occurrence information (word2vec uses co-occurrence information implicitly).
Weighted networks have the advantage of preserving the continuous nature of co-expression and co-methylation information, which is particularly useful when studying module preservation.
In addition, a co-expression analysis of BcWRKYs was performed to explore the co-regulatory information of WRKY TFs.
Gene co-expression databases have been developed for other species, but gene co-expression information for plants is currently limited.
