src/hg/makeDb/doc/hg19.txt 1.61
1.61 2009/11/11 01:07:36 hiram
done with hg19 46-way track, once again
Index: src/hg/makeDb/doc/hg19.txt
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/makeDb/doc/hg19.txt,v
retrieving revision 1.60
retrieving revision 1.61
diff -b -B -U 4 -r1.60 -r1.61
--- src/hg/makeDb/doc/hg19.txt 9 Nov 2009 19:17:24 -0000 1.60
+++ src/hg/makeDb/doc/hg19.txt 11 Nov 2009 01:07:36 -0000 1.61
@@ -4428,9 +4428,9 @@
hg19 canFamPoodle1 > rbest.log 2>&1 &
# real 811m27.965s
##############################################################################
-## 46-Way Multiz (WORKING - 2009-06-09 - Hiram)
+## 46-Way Multiz (DONE - 2009-06-09,2009-11-10 - Hiram)
mkdir /hive/data/genomes/hg19/bed/multiz46way
cd /hive/data/genomes/hg19/bed/multiz46way
# starting with the 46way tree created from 44 way tree
@@ -5497,9 +5497,9 @@
--prune=`cat notPlacentals.list` \
tree_4d.46way.nh > tree_4d.46way.placental.nh
#############################################################################
-# phastCons 46-way (WORKING - 2009-09-21 - Hiram)
+# phastCons 46-way (DONE - 2009-09-21,2009-11-10 - Hiram)
# was unable to split the full chrom MAF files, now working on the
# maf files as they were split up during multiz
# split 46way mafs into 10M chunks and generate sufficient statistics
@@ -5683,26 +5683,14 @@
gensub2 ../run.cons/ss.list single ../run.cons/template jobList
para -ram=8g create jobList
para try ... check ... push ... etc.
-
-# second run on swarm parasol: the failed jobs have empty bed file results
-# Completed: 575 of 580 jobs
-# Crashed: 5 jobs
-# CPU time in finished jobs: 42049s 700.81m 11.68h 0.49d 0.001 y
-# IO & Wait Time: 19735s 328.92m 5.48h 0.23d 0.001 y
-# Average job time: 107s 1.79m 0.03h 0.00d
-# Longest finished job: 267s 4.45m 0.07h 0.00d
-# Submission to last job: 479s 7.98m 0.13h 0.01d
-
-# first run on hgwdev parasol:
-# Completed: 574 of 579 jobs
-# Crashed: 5 jobs
-# CPU time in finished jobs: 53050s 884.17m 14.74h 0.61d 0.002 y
-# IO & Wait Time: 6633s 110.55m 1.84h 0.08d 0.000 y
-# Average job time: 104s 1.73m 0.03h 0.00d
-# Longest finished job: 248s 4.13m 0.07h 0.00d
-# Submission to last job: 4121s 68.68m 1.14h 0.05d
+# Completed: 581 of 581 jobs
+# CPU time in finished jobs: 41877s 697.95m 11.63h 0.48d 0.001 y
+# IO & Wait Time: 39172s 652.87m 10.88h 0.45d 0.001 y
+# Average job time: 139s 2.32m 0.04h 0.00d
+# Longest finished job: 329s 5.48m 0.09h 0.00d
+# Submission to last job: 2240s 37.33m 0.62h 0.03d
# create Most Conserved track
cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
cut -f1 ../../../../chrom.sizes | while read C
@@ -5717,16 +5705,16 @@
# load into database
ssh hgwdev
cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
time nice -n +19 hgLoadBed hg19 phastConsElements46way mostConserved.bed
- # Loaded 6514710 elements of size 6
- # real 1m33.113s
+ # Loaded 5163775 elements of size 6
+ # real 1m44.439s
# Try for 5% overall cov, and 70% CDS cov
featureBits hg19 -enrichment refGene:cds phastConsElements46way
# --rho 0.3 --expected-length 45 --target-coverage 0.3
- # refGene:cds 1.186%, phastConsElements46way 5.872%,
- # both 0.877%, cover 73.92%, enrich 12.59x
+ # refGene:cds 1.187%, phastConsElements46way 5.065%,
+ # both 0.884%, cover 74.46%, enrich 14.70x
# Create merged posterier probability file and wiggle track data files
cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
mkdir downloads
@@ -5771,28 +5759,28 @@
# real 52m36.142s
# -rw-rw-r-- 1 21667535139 Oct 20 13:59 phastCons46way.bw
mkdir /gbdb/hg19/bbi
ln -s `pwd`/phastCons46way.bw /gbdb/hg19/bbi
- # loading bigWig table:
+ # if you wanted to use the bigWig file, loading bigWig table:
hgsql hg19 -e 'drop table if exists phastCons46way; \
create table phastCons46way (fileName varchar(255) not null); \
insert into phastCons46way values
("/gbdb/hg19/bbi/phastCons46way.bw");'
- # Using the bigWig file instead of this database table:
# Load gbdb and database with wiggle.
-# ssh hgwdev
-# cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
-# ln -s `pwd`/phastCons46way.wib /gbdb/hg19/multiz46way/phastCons46way.wib
-# time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
-# phastCons46way phastCons46way.wig
+ ssh hgwdev
+ cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
+ ln -s `pwd`/phastCons46way.wib /gbdb/hg19/multiz46way/phastCons46way.wib
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phastCons46way phastCons46way.wig
+ # real 1m45.381s
# Create histogram to get an overview of all the data
ssh hgwdev
cd /hive/data/genomes/hg19/bed/multiz46way/cons/all
time nice -n +19 hgWiggle -doHistogram -db=hg19 \
-hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
- pc46 > histogram.data 2>&1
+ phastCons46way > histogram.data 2>&1
# real 7m37.212s
# create plot of histogram:
@@ -5835,42 +5823,44 @@
gensub2 ../run.cons/ss.list single ../run.cons/template jobList
para -ram=8g create jobList
para try ... check ... push ... etc.
-XXX - running Wed Oct 28 11:22:38 PDT 2009
-# Completed: 539 of 580 jobs
-# Crashed: 41 jobs
-# CPU time in finished jobs: 19518s 325.30m 5.42h 0.23d 0.001 y
-# IO & Wait Time: 19782s 329.70m 5.50h 0.23d 0.001 y
-# Average job time: 73s 1.22m 0.02h 0.00d
-# Longest finished job: 157s 2.62m 0.04h 0.00d
-# Submission to last job: 1989s 33.15m 0.55h 0.02d
-
- # the 41 crashed jobs are due to empty bed file results.
-# bed/chrUn_gl000237.00/chrUn_gl000237.00.1-45866.bed is empty
-# ... etc
+# Completed: 581 of 581 jobs
+# CPU time in finished jobs: 17077s 284.62m 4.74h 0.20d 0.001 y
+# IO & Wait Time: 73693s 1228.21m 20.47h 0.85d 0.002 y
+# Average job time: 156s 2.60m 0.04h 0.00d
+# Longest finished job: 402s 6.70m 0.11h 0.00d
+# Submission to last job: 2322s 38.70m 0.65h 0.03d
# create Most Conserved track
cd /hive/data/genomes/hg19/bed/multiz46way/cons/primates
- ../all/bedCat.sh > mostConserved.bed
+ cut -f1 ../../../../chrom.sizes | while read C
+do
+ ls -d bed/${C}.[0-9][0-9] 2> /dev/null | while read D
+ do
+ cat ${D}/${C}*.bed
+ done | awk 'BEGIN{ ID=1 }{printf "%s\t%d\t%d\t%s.%d\t%d\t%s\n", "'${C}'", $2, $3, "'${C}'", ID, $5, $6; ++ID}'
+done > mostConserved.bed
+ # ~ 1 minute
+
featureBits hg19 mostConserved.bed
# 146285948 bases of 2897316137 (5.049%) in intersection
# load into database
ssh hgwdev
cd /hive/data/genomes/hg19/bed/multiz46way/cons/primates
time nice -n +19 hgLoadBed hg19 phastConsElements46wayPrimates \
mostConserved.bed
- # Loaded 844990 elements of size 6
+ # Loaded 725627 elements of size 6
# real 0m8.583s
# verify coverage
featureBits hg19 phastConsElements46wayPrimates
# 116785954 bases of 2897316137 (4.031%) in intersection
# --rho 0.3 --expected-length 45 --target-coverage 0.3
featureBits hg19 -enrichment refGene:cds phastConsElements46wayPrimates
# refGene:cds 1.186%, phastConsElements46wayPrimates 4.031%,
- # both 0.730%, cover 61.55%, enrich 15.27x
+ # both 0.730%, cover 61.54%, enrich 15.27x
featureBits hg19 -enrichment knownGene:cds phastConsElements46wayPrimates
# knownGene:cds 1.252%, phastConsElements46wayPrimates 4.031%,
# both 0.743%, cover 59.31%, enrich 14.71x
@@ -5917,30 +5907,27 @@
zcat downloads/*.wigFix.gz \
| wigToBigWig stdin ../../../../chrom.sizes phastCons46wayPrimates.bw
ln -s `pwd`/phastCons46wayPrimates.bw /gbdb/hg19/bbi
- # loading bigWig table:
+ # if desired to use the bigWig file, loading bigWig table:
hgsql hg19 -e 'drop table if exists phastCons46wayPrimates; \
create table phastCons46wayPrimates \
(fileName varchar(255) not null); \
insert into phastCons46wayPrimates values
("/gbdb/hg19/bbi/phastCons46wayPrimates.bw");'
## load table with wiggle data
- ## not done now, using the bigWig file instead
-# ssh hgwdev
-# cd /hive/data/genomes/hg19/bed/multiz46way/cons/primates
-# ln -s `pwd`/phastCons46wayPrimates.wib \
-# /gbdb/hg19/multiz46way/phastCons46wayPrimates.wib
-# time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
-# phastCons46wayPrimates phastCons46wayPrimates.wig
- # Instead, temporary load into a table so we can do the histogram
- hgLoadWiggle hg19 pc46 phastCons46wayPrimates.wig
+ ssh hgwdev
+ cd /hive/data/genomes/hg19/bed/multiz46way/cons/primates
+ ln -s `pwd`/phastCons46wayPrimates.wib \
+ /gbdb/hg19/multiz46way/phastCons46wayPrimates.wib
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phastCons46wayPrimates phastCons46wayPrimates.wig
# Create histogram to get an overview of all the data
time nice -n +19 hgWiggle -doHistogram \
-hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
- -db=hg19 pc46 > histogram.data 2>&1
+ -db=hg19 phastCons46wayPrimates > histogram.data 2>&1
# real 5m30.086s
# create plot of histogram:
@@ -5981,24 +5968,27 @@
echo "macEug1,monDom5,ornAna1,galGal3,taeGut1,anoCar1,xenTro2,tetNig2,fr2,gasAcu1,oryLat2,danRer6,petMar1" \
> placental.non-inf
gensub2 ../run.cons/ss.list single ../run.cons/template jobList
-XXX - running Wed Oct 28 13:46:45 PDT 2009
para -ram=8g create jobList
para try ... check ... push ... etc.
-# Completed: 562 of 580 jobs
-# Crashed: 18 jobs
-# CPU time in finished jobs: 33874s 564.57m 9.41h 0.39d 0.001 y
-# IO & Wait Time: 12493s 208.21m 3.47h 0.14d 0.000 y
-# Average job time: 83s 1.38m 0.02h 0.00d
-# Longest finished job: 193s 3.22m 0.05h 0.00d
-# Submission to last job: 62872s 1047.87m 17.46h 0.73d
-
- # The crashed jobs produce zero length bed files: e.g.
- # bed/chrUn_gl000246.00/chrUn_gl000246.00.1-38144.bed is empty
+# Completed: 581 of 581 jobs
+# CPU time in finished jobs: 33942s 565.69m 9.43h 0.39d 0.001 y
+# IO & Wait Time: 75536s 1258.94m 20.98h 0.87d 0.002 y
+# Average job time: 188s 3.14m 0.05h 0.00d
+# Longest finished job: 417s 6.95m 0.12h 0.00d
+# Submission to last job: 1878s 31.30m 0.52h 0.02d
# create Most Conserved track
../all/bedCat.sh > mostConserved.bed
+ cut -f1 ../../../../chrom.sizes | while read C
+do
+ ls -d bed/${C}.[0-9][0-9] 2> /dev/null | while read D
+ do
+ cat ${D}/${C}*.bed
+ done | awk 'BEGIN{ ID=1 }{printf "%s\t%d\t%d\t%s.%d\t%d\t%s\n", "'${C}'", $2, $3, "'${C}'", ID, $5, $6; ++ID}'
+done > mostConserved.bed
+ # ~ 1 minute
# load into database
ssh hgwdev
cd /hive/data/genomes/hg19/bed/multiz46way/cons/placental
@@ -6007,17 +5997,17 @@
# Loaded 4805978 elements of size 6
# real 1m15.952s
# verify coverage
featureBits hg19 phastConsElements46wayPlacental
- # 136987062 bases of 2897316137 (4.728%) in intersection
+ # 118211444 bases of 2897316137 (4.080%) in intersection
# --rho 0.3 --expected-length 45 --target-coverage 0.3
featureBits hg19 -enrichment refGene:cds phastConsElements46wayPlacental
- # refGene:cds 1.186%, phastConsElements46wayPlacental 4.728%,
- # both 0.855%, cover 72.06%, enrich 15.24x
+ # refGene:cds 1.187%, phastConsElements46wayPlacental 4.080%,
+ # both 0.861%, cover 72.59%, enrich 17.79x
featureBits hg19 -enrichment knownGene:cds phastConsElements46wayPlacental
- # knownGene:cds 1.252%, phastConsElements46wayPlacental 4.728%,
- # both 0.873%, cover 69.70%, enrich 14.74x
+ # knownGene:cds 1.252%, phastConsElements46wayPlacental 4.080%,
+ # both 0.879%, cover 70.22%, enrich 17.21x
# Create the downloads .pp files, from which the phastCons wiggle data
# is calculated
# sort by chromName, chromStart so that items are in numerical order
@@ -6068,28 +6058,24 @@
(fileName varchar(255) not null); \
insert into phastCons46wayPlacental values
("/gbdb/hg19/bbi/phastCons46wayPlacental.bw");'
-
## load table with wiggle data
- ## no longer load this data, using the bigWig file instead
-# ssh hgwdev
-# cd /hive/data/genomes/hg19/bed/multiz46way/cons/placental
-# ln -s `pwd`/phastCons46wayPlacental.wib \
-# /gbdb/hg19/multiz46way/phastCons46wayPlacental.wib
-# time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
-# phastCons46wayPlacental phastCons46wayPlacental.wig
+ ssh hgwdev
+ cd /hive/data/genomes/hg19/bed/multiz46way/cons/placental
+ ln -s `pwd`/phastCons46wayPlacental.wib \
+ /gbdb/hg19/multiz46way/phastCons46wayPlacental.wib
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phastCons46wayPlacental phastCons46wayPlacental.wig
# Instead, temporary load into a table so we can do the histogram
hgLoadWiggle hg19 pc46 phastCons46wayPlacental.wig
# Create histogram to get an overview of all the data
time nice -n +19 hgWiggle -doHistogram \
-hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
- -db=hg19 pc46 > histogram.data 2>&1
+ -db=hg19 phastCons46wayPlacental > histogram.data 2>&1
# real 8m15.623s
- hgsql -e "drop table pc46;" hg19
- rm /gbdb/hg19/wib/pc46.wib
# create plot of histogram:
cat << '_EOF_' | gnuplot > histo.png
@@ -6113,9 +6099,9 @@
display histo.png &
#########################################################################
-# phyloP conservation for 46-way (WORKING - 2009-10-21 - Hiram)
+# phyloP conservation for 46-way (DONE - 2009-10-21,2009-11-10 - Hiram)
#
# Vertebrate, Placental, Primates
#
# split SS files into 1M chunks, this business needs smaller files
@@ -6276,13 +6262,13 @@
para try ... check ... push ... etc ...
para time
# Completed: 3186 of 3186 jobs
-# CPU time in finished jobs: 2272522s 37875.36m 631.26h 26.30d 0.072 y
-# IO & Wait Time: 27479s 457.99m 7.63h 0.32d 0.001 y
-# Average job time: 722s 12.03m 0.20h 0.01d
-# Longest finished job: 1106s 18.43m 0.31h 0.01d
-# Submission to last job: 12603s 210.05m 3.50h 0.15d
+# CPU time in finished jobs: 1306874s 21781.23m 363.02h 15.13d 0.041 y
+# IO & Wait Time: 105488s 1758.14m 29.30h 1.22d 0.003 y
+# Average job time: 443s 7.39m 0.12h 0.01d
+# Longest finished job: 678s 11.30m 0.19h 0.01d
+# Submission to last job: 7789s 129.82m 2.16h 0.09d
ssh hgwdev
cd /cluster/data/hg18/bed/multiz46way/consPhyloP/run.phyloP/all
find ./wigFix -type f \
@@ -6292,16 +6278,67 @@
| wigEncode stdin phyloP46way.wig phyloP46way.wib > wigEncode.log 2>&1 &
# Converted stdin, upper limit 6.39, lower limit -13.27
cat wigFile.list | xargs cat \
| wigToBigWig stdin ../../../../chrom.sizes phyloP46way.bw
- # loading bigWig table:
+ # if you wanted to use the bigWig file, loading bigWig table:
ln -s `pwd`/phyloP46way.bw /gbdb/hg19/bbi
hgsql hg19 -e 'drop table if exists phyloP46wayAll; \
create table phyloP46wayAll \
(fileName varchar(255) not null); \
insert into phyloP46wayAll values
("/gbdb/hg19/bbi/phyloP46way.bw");'
+ # loading the wiggle table:
+ ln -s `pwd`/phyloP46way.wib /gbdb/hg19/multiz46way
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phyloP46wayAll phyloP46way.wig
+
+ # create download files:
+ cat << '_EOF_' > mkDown.csh
+#!/bin/csh -fe
+foreach F (`cat wigFile.list`)
+ set C = $F:h:t:r
+ cat $F >> downloads/${C}.wigFix
+end
+'_EOF_'
+ # << happy emacs
+ chmod +x ./mkDown.csh
+ mkdir downloads
+ time ./mkDown.csh
+ # real 16m19.683s
+
+ time gzip downloads/chr*.wigFix
+ # real 47m11.017s
+
+ # Create histogram to get an overview of all the data
+ time nice -n +19 hgWiggle -doHistogram \
+ -hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
+ -db=hg19 phyloP46wayAll > histogram.data 2>&1
+ # real 8m15.623s
+
+ # create plot of histogram:
+
+ cat << '_EOF_' | gnuplot > histo.png
+set terminal png small color x000000 xffffff xc000ff x66ff66 xffff00 x00ffff
+set size 1.4, 0.8
+set key left box
+set grid noxtics
+set grid ytics
+set title " Human Hg19 Histogram phyloP46wayAll track"
+set xlabel " phyloP46wayAll score"
+set ylabel " Relative Frequency"
+set y2label " Cumulative Relative Frequency (CRF)"
+set y2range [0:1]
+set y2tics
+set yrange [0:0.02]
+
+plot "histogram.data" using 2:5 title " RelFreq" with impulses, \
+ "histogram.data" using 2:7 axes x1y2 title " CRF" with lines
+'_EOF_'
+ # << happy emacs
+
+ display histo.png &
+
###################### Running the primates #######################
mkdir /hive/data/genomes/hg19/bed/multiz46way/consPhyloP/primates
cd /hive/data/genomes/hg19/bed/multiz46way/consPhyloP/primates
rm -fr wigFix
@@ -6328,16 +6365,57 @@
> wigEncode.log 2>&1 &
# Converted stdin, upper limit 0.65, lower limit -9.12
cat wigFile.list | xargs cat \
| wigToBigWig stdin ../../../../chrom.sizes phyloP46wayPrimates.bw
- # loading bigWig table:
+ # if you wanted to use the bigWig file, loading bigWig table:
ln -s `pwd`/phyloP46wayPrimates.bw /gbdb/hg19/bbi
hgsql hg19 -e 'drop table if exists phyloP46wayPrimates; \
create table phyloP46wayPrimates \
(fileName varchar(255) not null); \
insert into phyloP46wayPrimates values
("/gbdb/hg19/bbi/phyloP46wayPrimates.bw");'
+ # loading the wiggle table:
+ ln -s `pwd`/phyloP46wayPrimates.wib /gbdb/hg19/multiz46way
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phyloP46wayPrimates phyloP46wayPrimates.wig
+
+ # create download files:
+ mkdir downloads
+ time ../all/mkDown.csh
+ # real 18m44.186s
+ time gzip downloads/chr*.wigFix
+ # real 32m11.461s
+
+ # Create histogram to get an overview of all the data
+ time nice -n +19 hgWiggle -doHistogram \
+ -hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
+ -db=hg19 phyloP46wayPrimates > histogram.data 2>&1
+ # real 8m15.623s
+
+ # create plot of histogram:
+
+ cat << '_EOF_' | gnuplot > histo.png
+set terminal png small color x000000 xffffff xc000ff x66ff66 xffff00 x00ffff
+set size 1.4, 0.8
+set key left box
+set grid noxtics
+set grid ytics
+set title " Human Hg19 Histogram phyloP46wayPrimates track"
+set xlabel " phyloP46wayPrimates score"
+set ylabel " Relative Frequency"
+set y2label " Cumulative Relative Frequency (CRF)"
+set y2range [0:1]
+set y2tics
+set yrange [0:0.02]
+
+plot "histogram.data" using 2:5 title " RelFreq" with impulses, \
+ "histogram.data" using 2:7 axes x1y2 title " CRF" with lines
+'_EOF_'
+ # << happy emacs
+
+ display histo.png &
+
###################### Running the placentals #######################
mkdir /hive/data/genomes/hg19/bed/multiz46way/consPhyloP/placentals
cd /hive/data/genomes/hg19/bed/multiz46way/consPhyloP/placentals
rm -fr wigFix
@@ -6348,8 +6426,9 @@
para try ... check ... push ... etc ...
para time
# Completed: 3186 of 3186 jobs
# CPU time in finished jobs: 1582989s 26383.14m 439.72h 18.32d 0.050 y
+rY.phyloP46way.placental.wigFix.gz
# IO & Wait Time: 25577s 426.29m 7.10h 0.30d 0.001 y
# Average job time: 505s 8.41m 0.14h 0.01d
# Longest finished job: 768s 12.80m 0.21h 0.01d
# Submission to last job: 12967s 216.12m 3.60h 0.15d
@@ -6372,8 +6451,50 @@
(fileName varchar(255) not null); \
insert into phyloP46wayPlacental values
("/gbdb/hg19/bbi/phyloP46wayPlacental.bw");'
+ # loading the wiggle table:
+ ln -s `pwd`/phyloP46wayPlacental.wib /gbdb/hg19/multiz46way
+ time hgLoadWiggle
+ time nice -n +19 hgLoadWiggle -pathPrefix=/gbdb/hg19/multiz46way hg19 \
+ phyloP46wayPlacental phyloP46wayPlacental.wig
+
+ # create download files:
+ mkdir downloads
+ time ../all/mkDown.csh
+ # real 18m52.778s
+ time gzip downloads/chr*.wigFix
+ # real 46m55.550s
+
+ # Create histogram to get an overview of all the data
+ time nice -n +19 hgWiggle -doHistogram \
+ -hBinSize=0.001 -hBinCount=1000 -hMinVal=0.0 -verbose=2 \
+ -db=hg19 phyloP46wayPlacental > histogram.data 2>&1
+ # real 8m15.623s
+
+ # create plot of histogram:
+
+ cat << '_EOF_' | gnuplot > histo.png
+set terminal png small color x000000 xffffff xc000ff x66ff66 xffff00 x00ffff
+set size 1.4, 0.8
+set key left box
+set grid noxtics
+set grid ytics
+set title " Human Hg19 Histogram phyloP46wayPlacental track"
+set xlabel " phyloP46wayPlacental score"
+set ylabel " Relative Frequency"
+set y2label " Cumulative Relative Frequency (CRF)"
+set y2range [0:1]
+set y2tics
+set yrange [0:0.02]
+
+plot "histogram.data" using 2:5 title " RelFreq" with impulses, \
+ "histogram.data" using 2:7 axes x1y2 title " CRF" with lines
+'_EOF_'
+ # << happy emacs
+
+ display histo.png &
+
#########################################################################
# LASTZ Zebrafish DanRer6 (DONE - 2009-07-08,10 - Hiram)
mkdir /hive/data/genomes/hg19/bed/lastzDanRer6.2009-07-08
cd /hive/data/genomes/hg19/bed/lastzDanRer6.2009-07-08