| DisjointSet {SynExtend} | R Documentation |
PairSummaries objects.
Takes in a PairSummaries object and return a list of identifiers organized into single linkage clusters.
DisjointSet(Pairs,
Verbose = FALSE)
Pairs |
A |
Verbose |
Logical indicating whether to print progress bars and messages. Defaults to |
Takes in a PairSummaries object and return a list of identifiers organized into single linkage clusters.
Returns a list of character vectors representing IDs of sequence features, typically genes.
Nicholas Cooley npc19@pitt.edu
FindSynteny, Synteny-class, PairSummaries, FindSets
DBPATH <- system.file("extdata",
"VignetteSeqs.sqlite",
package = "SynExtend")
Syn <- FindSynteny(dbFile = DBPATH)
GeneCalls <- vector(mode = "list",
length = ncol(Syn))
GeneCalls[[1L]] <- gffToDataFrame(GFF = system.file("extdata",
"GCA_006740685.1_ASM674068v1_genomic.gff.gz",
package = "SynExtend"),
Verbose = TRUE)
GeneCalls[[2L]] <- gffToDataFrame(GFF = system.file("extdata",
"GCA_000956175.1_ASM95617v1_genomic.gff.gz",
package = "SynExtend"),
Verbose = TRUE)
GeneCalls[[3L]] <- gffToDataFrame(GFF = system.file("extdata",
"GCA_000875775.1_ASM87577v1_genomic.gff.gz",
package = "SynExtend"),
Verbose = TRUE)
names(GeneCalls) <- seq(length(GeneCalls))
Links <- NucleotideOverlap(SyntenyObject = Syn,
GeneCalls = GeneCalls,
LimitIndex = FALSE,
Verbose = TRUE)
PredictedPairs <- PairSummaries(SyntenyLinks = Links,
DBPATH = DBPATH,
PIDs = FALSE,
AcceptContigNames = TRUE,
Verbose = TRUE)
PresentSeqs <- ExtractBy(x = PredictedPairs,
Method = "all",
DBPATH = DBPATH,
Verbose = TRUE)
Clusters <- DisjointSet(Pairs = PredictedPairs,
Verbose = TRUE)
SeqsByClusters <- ExtractBy(x = PredictedPairs,
y = Clusters,
Method = "clusters",
DBPATH = DBPATH,
Verbose = TRUE)
# Alternatively the same seqs can be accessed from the NCBI FTP site
# And gene calls can be accessed with the rtracklayer
## Not run:
DBPATH <- tempfile()
FNAs <- c("ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/006/740/685/GCA_006740685.1_ASM674068v1/GCA_006740685.1_ASM674068v1_genomic.fna.gz",
"ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/956/175/GCA_000956175.1_ASM95617v1/GCA_000956175.1_ASM95617v1_genomic.fna.gz",
"ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/875/775/GCA_000875775.1_ASM87577v1/GCA_000875775.1_ASM87577v1_genomic.fna.gz")
for (m1 in seq_along(FNAs)) {
X <- readDNAStringSet(filepath = FNAs[m1])
X <- X[order(width(X),
decreasing = TRUE)]
Seqs2DB(seqs = X,
type = "XStringSet",
dbFile = DBPATH,
identifier = as.character(m1),
verbose = TRUE)
}
GeneCalls <- vector(mode = "list",
length = ncol(Syn))
GeneCalls[[1L]] <- rtracklayer::import(system.file("extdata",
"GCA_006740685.1_ASM674068v1_genomic.gff.gz",
package = "SynExtend"))
GeneCalls[[2L]] <- rtracklayer::import(system.file("extdata",
"GCA_000956175.1_ASM95617v1_genomic.gff.gz",
package = "SynExtend"))
GeneCalls[[3L]] <- rtracklayer::import(system.file("extdata",
"GCA_000875775.1_ASM87577v1_genomic.gff.gz",
package = "SynExtend"))
names(GeneCalls) <- seq(length(GeneCalls))
Links <- NucleotideOverlap(SyntenyObject = Syn,
GeneCalls = GeneCalls,
LimitIndex = FALSE,
Verbose = TRUE)
PredictedPairs <- PairSummaries(SyntenyLinks = Links,
DBPATH = DBPATH,
PIDs = FALSE,
AcceptContigNames = TRUE,
Verbose = TRUE)
PresentSeqs <- ExtractBy(x = PredictedPairs,
Method = "all",
DBPATH = DBPATH,
Verbose = TRUE)
Clusters <- DisjointSet(Pairs = PredictedPairs,
Verbose = TRUE)
SeqsByClusters <- ExtractBy(x = PredictedPairs,
y = Clusters,
Method = "clusters",
DBPATH = DBPATH,
Verbose = TRUE)
## End(Not run)