thackl / kmer-scripts Goto Github PK

• R
  • ggplot2

install.packages("ggplot2")

kmer-plot --help
kmer-plot MODE [OPT=VAL ...] [name=]FILE [[name=]FILE ...]

# kcov mode
kmer-plot kcov

[name=]FILE         jellyfish hash or two column count histogram (count abundance).
                    name is optional, should be enclosed in escaped \",
                    e.g. \"Set1\"=set1.jf

out="kcov.pdf"      output file name, supports .png, .pdf, .ps.
coverage.max=300    coverage axix maximum, 0 is data max.
count.max=0         count axis maximum, 0 is data max.
anscombe=FALSE      display Anscombe transformed data (variance stabilization)


theme=c("gg","bw","classic")   choose one.
plot.lines=!anscombe           draw line graph, TRUE or FALSE, default opposite of anscombe=.
plot.bars=anscombe             draw bar graph, TRUE or FALSE, default same as anscombe=.
plot.facet=F                   draw multiple sets facetted
plot.lines.width=.5            ...
plot.peaks=!anscombe
plot.peak.labels=plot.peaks
plot.peak.points=plot.peaks
plot.peak.ranges=plot.peaks
peak.size.min=10000
peak.label.angle=0
peak.label.hjust=.5
peak.label.size=3
width=10
height=6

# gccov mode
kmer-plot gccov
[name=]FILE         character separated file with one row per contig, 4 or 5
                    columns: (id length GC coverage [taxonomic-group])

sep="\t"            column-separator
out="gccov.pdf"     output file name, supports .png, .pdf, .ps.
coverage.max=300    coverage axix maximum, 0 is data max.
length.min=1000     minimum length of contigs to display/use in sum of length
tax.occ.min=1       minimum occurance of a taxon to display
bin.num=100         number of bins for total length histogram
tax.ignore=FALSE    ignore taxonomy column (color by length)
length.min.scatter=0     minimum length for contigs to display in scatter plot,
                         still counted in sum of length
jitter=FALSE        add jitter to better visualize fully overlapping data points
sample.scatter=0    only display this random fraction of data points in scatter
width=10
height=6

# download http://www.ncbi.nlm.nih.gov/sra/?term=ERR008613
# get 500 Mbp read data
head -n 10000000 ../raw/ERR008613_1.fastq > ERR008613-h10M_1.fq
head -n 10000000 ../raw/ERR008613_2.fastq > ERR008613-h10M_2.fq
# count kmers
jellyfish count -t 10 -C -m 19 -s 1G ERR008613-250_* -o e-coli.jf
jellyfish histo e-coli.jf > e-coli.tsv

# plot distribution
kmer-plot kcov e-coli.tsv plot.peaks=F theme=gg coverage.max=200 width=5 height=3 out=e-coli-kcov.png

kmer-plot kcov AB-m19.tsv coverage.max=1200 height=3 width=9 anscombe=F out=AB-kcov.png
kmer-plot kcov AB-m19.tsv plot.peaks=T coverage.max=1200 height=3 width=9 anscombe=T out=AB-kcov-ansc.png

kmer-plot kcov width=7 height=3 out=dm-kcov.png \
 \"diploid-clonal\"=dm-il-raw-m19-histo.tsv \
 \"diploid-mix\"=dm-gen-bgi-pe-raw-m19.tsv

kmer-plot kcov width=8 height=5 anscombe=T plot.facet=TRUE out=dm-kcov-facet.png \
 \"diploid-clonal\"=dm-il-raw-m19-histo.tsv \
 \"diploid-mix\"=dm-gen-bgi-pe-raw-m19.tsv

kmer-plot gccov <(cut -f1-4 tg.genome-nn-stats-franks-taxa.tsv) palette=Dark2 coverage.max=200 out=tg-gccov.png
kmer-plot gccov <(cut -f1- tg.genome-nn-stats-franks-taxa.tsv) palette=Dark2 coverage.max=200 out=tg-gccov-tax.png