make embedding of the genomics metabolic model

tfidf_vectorizer {annotation.terms}

R Documentation

make embedding of the genomics metabolic model

Description

Usage

tfidf_vectorizer(annotations,
    L2.norm = FALSE,
    union.contigs = 1000,
    hierarchical = FALSE);

Arguments

annotations

a collection of the GenomeVector genomics metabolic vector data for make the tf-idf embedding.

L2.norm

do L2 normalized of the generated embedding matrix data?. [as boolean]

union.contigs

the minimum number of the contigs in one taxonomy group for merge the genome vectors. [as integer]

hierarchical

build the hierarchical taxonomy embedding model?. [as boolean]

env

the R# runtime environment object. [as Environment]

Authors

seqtoolkit

Value

a data frame object of the genomics metabolic model embedding result: each row is one genome(the row name is the taxonomy name), and each column is a metabolic function term, the cell value is the tf-idf weight of the corresponding term in the corresponding genome;

this function returns a R# error message object if the input vector data can not be cast to a collection of the GenomeVector object.

clr value class

any kind

[Package annotation.terms version 1.0.0.0 Index]