annotation.terms


        require(GCModeller);
                               

#' tools for make ontology term annotation based on the proteins sequence data
imports "annotation.terms" from "seqtoolkit";

.NET clr type export
genome_vector: GenomeVector	基因组代谢酶注释结果

.NET clr function exports
as.data.frame.rankterm	RankTerm:
as.data.frame.koassignmentcandidate	KOAssignmentCandidate: 用于存储一个查询基因的KO分配候选
as.data.frame.bidirectionalbesthit	BiDirectionalBesthit: Best hit result from the binary direction blastp result. Ortholog mapping result.
as.data.frame.myvacog	MyvaCOG: Protein cog category using myva database.
removes_proteinIDSuffix	Removes the numeric suffix (usually representing an exon index) from protein identifiers.
read_rankterms	read the given table file as rank term object
rank_term	create the rank term annotation objects from the given parallel data vectors
geneNames	try parse gene names from the product description strings
assign_ko	do KO number assign based on the bbh alignment result.
assign.COG	assign the COG functional category for each query gene by keeping the best identity COG hit
assign_terms	assign the top term by score ranking
m8_metabolic_terms	extract the metabolic function term annotation from the diamond m8 format alignment result data
term_table	make the term annotation table of each gene from a given set of the term annotation result group
assign.Pfam	assign the pfam protein domain annotation for the query protein sequence
assign.GO	assign the gene ontology(GO) term annotation for the query gene
write.id_maps	save the id mapping solver data into a text file
read.MyvaCOG	read the myva COG hits annotation data from a csv table file
read.id_maps	read the id mappings text data as the secondary id mapping solver object
synonym	query the id synonyms of the given id list from the id mapping solver object
read_vfdb_seqs	read VFDB fasta sequence database
write_simple_vfdb	save the VFDB virulence factor sequence data as a simple fasta format sequence file
make_vectors	make the genomics metabolic vector data from the given term annotation result collection
write_genomes_jsonl	write the genomics metabolic vector data into a jsonl text file
tfidf_vectorizer	make embedding of the genomics metabolic model