opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Made Genetrack load only if the dependencies import

Browse Source
This commit is contained in:
Ian Schenck
2009-01-21 11:45:30 -05:00
parent 7dc603afaf
commit b8e76a8ca6
12 changed files with 502 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files
datatypes_conf.xml.sample
+15 -19
View File
@@ -26,6 +26,7 @@
<datatype extension="html" type="galaxy.datatypes.images:Html" mimetype="text/html"/>
<datatype extension="interval" type="galaxy.datatypes.interval:Interval" display_in_upload="true">
<converter file="interval_to_bed_converter.xml" target_datatype="bed"/>
<converter file="interval_to_coverage.xml" target_datatype="coverage"/>
</datatype>
<datatype extension="jpg" type="galaxy.datatypes.images:Image" mimetype="image/jpeg"/>
<datatype extension="laj" type="galaxy.datatypes.images:Laj"/>
@@ -38,7 +39,6 @@
<datatype extension="png" type="galaxy.datatypes.images:Image" mimetype="image/png"/>
<datatype extension="qual" type="galaxy.datatypes.qualityscore:QualityScore" display_in_upload="true"/>
<datatype extension="scf" type="galaxy.datatypes.images:Scf" mimetype="application/octet-stream" display_in_upload="true"/>
<datatype extension="solidqual" type="galaxy.datatypes.qualityscore:SolidQualityScore" display_in_upload="true"/>
<datatype extension="taxonomy" type="galaxy.datatypes.tabular:Taxonomy" display_in_upload="true"/>
<datatype extension="tabular" type="galaxy.datatypes.tabular:Tabular" display_in_upload="true"/>
<datatype extension="txt" type="galaxy.datatypes.data:Text" display_in_upload="true"/>
@@ -173,24 +173,20 @@
<!--
The order in which Galaxy attempts to determine data types is
important because some formats are much more loosely defined
than others. The following list should be the most rigidly
defined format first, followed by next-most rigidly defined,
and so on.
than others.
-->
<sniffer type="galaxy.datatypes.xml:BlastXml"/>
<sniffer type="galaxy.datatypes.sequence:Maf"/>
<sniffer type="galaxy.datatypes.sequence:Lav"/>
<sniffer type="galaxy.datatypes.sequence:csFasta"/>
<sniffer type="galaxy.datatypes.qualityscore:SolidQualityScore"/>
<sniffer type="galaxy.datatypes.sequence:Fasta"/>
<sniffer type="galaxy.datatypes.sequence:FastqSolexa"/>
<sniffer type="galaxy.datatypes.interval:Wiggle"/>
<sniffer type="galaxy.datatypes.images:Html"/>
<sniffer type="galaxy.datatypes.sequence:Axt"/>
<sniffer type="galaxy.datatypes.interval:Bed"/>
<sniffer type="galaxy.datatypes.interval:CustomTrack"/>
<sniffer type="galaxy.datatypes.interval:Gff"/>
<sniffer type="galaxy.datatypes.interval:Gff3"/>
<sniffer type="galaxy.datatypes.interval:Interval"/>
<sniffer order="005" type="galaxy.datatypes.xml:BlastXml"/>
<sniffer order="010" type="galaxy.datatypes.sequence:Maf"/>
<sniffer order="015" type="galaxy.datatypes.sequence:Lav"/>
<sniffer order="020" type="galaxy.datatypes.sequence:Fasta"/>
<sniffer order="025" type="galaxy.datatypes.sequence:FastqSolexa"/>
<sniffer order="030" type="galaxy.datatypes.interval:Wiggle"/>
<sniffer order="035" type="galaxy.datatypes.images:Html"/>
<sniffer order="040" type="galaxy.datatypes.sequence:Axt"/>
<sniffer order="045" type="galaxy.datatypes.interval:Bed"/>
<sniffer order="050" type="galaxy.datatypes.interval:CustomTrack"/>
<sniffer order="055" type="galaxy.datatypes.interval:Gff"/>
<sniffer order="060" type="galaxy.datatypes.interval:Gff3"/>
<sniffer order="065" type="galaxy.datatypes.interval:Interval"/>
</sniffers>
</datatypes>
lib/galaxy/datatypes/converters/interval_to_coverage.py
+80
View File
@@ -0,0 +1,80 @@
#!/usr/bin/env python
"""
Converter to generate 3 (or 4) column base-pair coverage from an interval file.
usage: %prog bed_file out_file
-1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in interval file
-2, --cols2=N,N,N,N: Columns for chrom, start, end, strand in coverage file
"""
import sys
from galaxy import eggs
import pkg_resources; pkg_resources.require( "bx-python" )
from bx.intervals import io
from bx.cookbook import doc_optparse
INTERVAL_METADATA = ('chromCol',
'startCol',
'endCol',
'strandCol',)
COVERAGE_METADATA = ('chromCol',
'positionCol',
'forwardCol',
'reverseCol',)
def main( interval, coverage ):
chroms = dict()
for record in interval:
if not type( record ) is io.GenomicInterval: continue
chrom = chroms[record.chrom] = chroms.get(record.chrom, dict())
for position in xrange(record.start, record.end):
coverages = chrom[position] = chrom.get(position,[0,0])
if record.strand == "-": coverages[1] += 1
else: coverages[0] += 1
for chrom in sorted(chroms.iterkeys()):
positions = chroms[chrom]
for position in sorted(positions.iterkeys()):
coverage.write( chrom=chrom, position=position, forward=positions[position][0], reverse=positions[position][1] )
class CoverageWriter( object ):
def __init__( self, out_stream=None, chromCol=0, positionCol=1, forwardCol=2, reverseCol=3 ):
self.chromCol, self.positionCol, self.forwardCol, self.reverseCol = chromCol, positionCol, forwardCol, reverseCol
self.nfields = max( chromCol, positionCol, forwardCol, reverseCol )+1
self.out_stream = out_stream
self.nlines = 0
def write(self, chrom="chr", position=0, forward=0, reverse=0 ):
self.nlines += 1
if self.nlines % 64000: self.out_stream.flush()
outlist = [None] * self.nfields
outlist[self.chromCol] = str(chrom)
outlist[self.positionCol] = str(position)
if self.reverseCol == -1: outlist[self.forwardCol] = str(forward + reverse)
else:
outlist[self.forwardCol] = str(forward)
outlist[self.reverseCol] = str(reverse)
self.out_stream.write("%s\n" % "\t".join( outlist ))
def flush(self):
self.out_stream.flush()
if __name__ == "__main__":
options, args = doc_optparse.parse( __doc__ )
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = [int(x)-1 for x in options.cols1.split(',')]
chr_col_2, position_col_2, forward_col_2, reverse_col_2 = [int(x)-1 for x in options.cols2.split(',')]
in_fname, out_fname = args
except:
doc_optparse.exception()
coverage = CoverageWriter( out_stream = open(out_fname, "a"),
chromCol = chr_col_2, positionCol = position_col_2,
forwardCol = forward_col_2, reverseCol = reverse_col_2, )
interval = io.NiceReaderWrapper( open(in_fname, "r"),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True )
main( interval, coverage )
coverage.flush()
lib/galaxy/datatypes/converters/interval_to_coverage.xml
+18
View File
@@ -0,0 +1,18 @@
<tool id="CONVERTER_interval_to_coverage_0" name="Convert Genomic Intervals To COVERAGE">
<!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
<!-- Used on the metadata edit page. -->
<command interpreter="python">interval_to_coverage.py $input1 $output1
-1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
-2 ${output1.metadata.chromCol},${output1.metadata.positionCol},${output1.metadata.forwardCol},${output1.metadata.reverseCol}
</command>
<inputs>
<page>
<param format="interval" name="input1" type="data" label="Choose intervals"/>
</page>
</inputs>
<outputs>
<data format="coverage" name="output1"/>
</outputs>
<help>
</help>
</tool>
lib/galaxy/web/base/controller.py
+4 -1
View File
@@ -28,4 +28,7 @@ class BaseController( object ):
Root = BaseController
"""
Deprecated: `BaseController` used to be available under the name `Root`
"""
"""
class ControllerUnavailable( Exception ):
pass
lib/galaxy/web/buildapp.py
+6 -1
View File
@@ -28,13 +28,18 @@ def add_controllers( webapp, app ):
them to the webapp.
"""
from galaxy.web.base.controller import BaseController
from galaxy.web.base.controller import ControllerUnavailable
import galaxy.web.controllers
controller_dir = galaxy.web.controllers.__path__[0]
for fname in os.listdir( controller_dir ):
if not( fname.startswith( "_" ) ) and fname.endswith( ".py" ):
name = fname[:-3]
module_name = "galaxy.web.controllers." + name
module = __import__( module_name )
try:
module = __import__( module_name )
except ControllerUnavailable, exc:
log.debug("%s could not be loaded: %s" % (module_name, str(exc)))
continue
for comp in module_name.split( "." )[1:]:
module = getattr( module, comp )
# Look for a controller inside the modules
lib/galaxy/web/controllers/genetrack.py
+141 -19
View File
@@ -1,22 +1,127 @@
import time, glob, os
from itertools import cycle
import pkg_resources
pkg_resources.require("GeneTrack")
import atlas
from atlas import sql
from atlas import util as atlas_utils
from atlas.web import formlib
from mako import exceptions
from mako.template import Template
from mako.lookup import TemplateLookup
from galaxy.web.base.controller import *
try:
import pkg_resources
pkg_resources.require("GeneTrack")
import atlas
from atlas import sql
from atlas import hdf
from atlas import util as atlas_utils
from atlas.web import formlib, feature_query, feature_filter
from atlas.web import label_cache as atlas_label_cache
from atlas.plotting.const import *
from atlas.plotting.tracks import prefab
from atlas.plotting.tracks import chart
from atlas.plotting import tracks
except Exception, exc:
raise ControllerUnavailable("GeneTrack could not import a required dependency: %s" % str(exc))
pkg_resources.require( "Paste" )
import paste.httpexceptions
# Database helpers
SHOW_LABEL_LIMIT = 10000
color = cycle( [LIGHT, WHITE] )
def list_labels(session):
"""
Returns a list of labels that will be plotted in order.
"""
labels = sql.Label
query = session.query(labels).order_by("-id")
return query
def open_databases( conf ):
"""
A helper function that returns handles to the hdf and sql databases
"""
db = hdf.hdf_open( conf.HDF_DATABASE, mode='r' )
session = sql.get_session( conf.SQL_URI )
return db, session
def hdf_query(db, name, param, autosize=False ):
"""
Schema specific hdf query.
Note that returns data as columns not rows.
"""
if not hdf.has_node(db=db, name=name):
atlas.warn( 'missing label %s' % name )
return [], [], [], []
data = hdf.GroupData( db=db, name=name)
istart, iend = data.get_indices(label=param.chrom, start=param.start, stop=param.end)
table = data.get_table(label=param.chrom)
if autosize:
# attempts to reduce the number of points
size = len( table.cols.ix[istart:iend] )
step = max( [1, size/1200] )
else:
step = 1
ix = table.cols.ix[istart:iend:step].tolist()
wx = table.cols.wx[istart:iend:step].tolist()
cx = table.cols.cx[istart:iend:step].tolist()
ax = table.cols.ax[istart:iend:step].tolist()
return ix, wx, cx, ax
# Chart helpers
def build_tracks( param, conf, data_label, fit_label, pred_label, strand, show=False ):
"""
Builds tracks
"""
# gets all the labels for a fast lookup
label_cache = atlas_label_cache( conf )
# get database handles for hdf and sql
db, session = open_databases( conf )
# fetching x and y coordinates for bar and fit (line) for
# each strand plus (p), minus (m), all (a)
bix, bpy, bmy, bay = hdf_query( db=db, name=data_label, param=param )
fix, fpy, fmy, fay = hdf_query( db=db, name=fit_label, param=param )
# close the hdf database
db.close()
# get all features within the range
all = feature_query( session=session, param=param )
# draws the barchart and the nucleosome chart below it
if strand == 'composite':
bar = prefab.composite_bartrack( fix=fix, fay=fay, bix=bix, bay=bay, param=param)
else:
bar = prefab.twostrand_bartrack( fix=fix, fmy=fmy, fpy=fpy, bix=bix, bmy=bmy, bpy=bpy, param=param)
charts = list()
charts.append( bar )
return charts
def feature_chart(param=None, session=None, label=None, label_dict={}):
# draw the ORF tracks
all = feature_filter(feature_query(session=session, param=param), name=label, kdict=label_dict)
if len(all) == 0: return []
opts = track_options(
xscale=param.xscale, w=param.width, fgColor=PURPLE,
show_labels=param.show_labels, ylabel=str(label),
bgColor=color.next()
)
return [
tracks.split_tracks(features=all, options=opts, split=param.show_labels, track_type='vector')
]
def consolidate_charts( charts, param ):
# create the multiplot
opt = chart_options( w=param.width )
multi = chart.MultiChart(options=opt, charts=charts)
return multi
# SETUP Track Builders
from mod454.trackbuilder import build_tracks
import functools
def twostrand_tracks( param=None, conf=None ):
return build_tracks( data_label=conf.LABEL, fit_label=conf.FIT_LABEL, pred_label=conf.PRED_LABEL, param=param, conf=conf, strand='twostrand')
@@ -96,6 +201,7 @@ class WebRoot(BaseController):
"""
Main request handler
"""
color = cycle( [LIGHT, WHITE] )
data = trans.app.model.HistoryDatasetAssociation.get( dataset_id )
if not data:
raise paste.httpexceptions.HTTPRequestRangeNotSatisfiable( "Invalid reference dataset id: %s." % str( dataset_id ) )
@@ -108,10 +214,15 @@ class WebRoot(BaseController):
FIT_LABEL = "%s-SIGMA-%d" % (data.metadata.label, 20),
PRED_LABEL = "PRED-%s-SIGMA-%d" % (data.metadata.label, 20),
)
from atlas import hdf
db = hdf.hdf_open( conf.HDF_DATABASE, mode='r' )
conf.CHROM_FIELDS = [(x,x) for x in hdf.GroupData(db=db, name=conf.LABEL).labels]
db.close()
session = sql.get_session( conf.SQL_URI )
if os.path.exists( conf.HDF_DATABASE ):
db = hdf.hdf_open( conf.HDF_DATABASE, mode='r' )
conf.CHROM_FIELDS = [(x,x) for x in hdf.GroupData(db=db, name=conf.LABEL).labels]
db.close()
else:
query = session.execute(sql.select([sql.feature_table.c.chrom]).distinct())
conf.CHROM_FIELDS = [(x.chrom,x.chrom) for x in query]
# generate a new form based on the configuration
form = formlib.main_form( conf )
@@ -147,14 +258,25 @@ class WebRoot(BaseController):
# get the template and the function used to generate the tracks
tmpl_name, track_maker = conf.PLOT_MAPPER[param.plot]
if track_maker is not None:
# generate the name that the image will be stored at
fname, fpath = atlas_utils.make_tempfile( dir=conf.IMAGE_DIR, suffix='.png')
param.fname = fname
charts = []
# generate the track
track_chart = track_maker( param=param, conf=conf )
track_chart.save(fname=fpath)
fname, fpath = atlas_utils.make_tempfile( dir=conf.IMAGE_DIR, suffix='.png')
param.fname = fname
# set the scale of the plot
param.xscale = [ param.start, param.end ]
# when visualizing on wide scales labels are not useful
param.show_labels = ( param.end - param.start ) <= SHOW_LABEL_LIMIT
if track_maker is not None and os.path.exists( conf.HDF_DATABASE ):
# generate the fit track
charts = track_maker( param=param, conf=conf )
for label in list_labels( session ):
charts.extend( feature_chart(param=param, session=session, label=label.name, label_dict={label.name:label.id}) )
track_chart = consolidate_charts( charts, param )
track_chart.save(fname=fpath)
return trans.fill_template_mako(tmpl_name, conf=conf, form=form, param=param, dataset_id=dataset_id)
scripts/paster.py
-1
View File
@@ -12,7 +12,6 @@ assert sys.version_info[:2] >= ( 2, 4 )
new_path = [ os.path.join( os.getcwd(), "lib" ) ]
new_path.extend( sys.path[1:] ) # remove scripts/ from the path
sys.path = new_path
print sys.path
from galaxy import eggs
import pkg_resources
templates/genetrack/base.html
+29
View File
@@ -0,0 +1,29 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
<title>${self.title()}</title>
<link rel="stylesheet" href="${h.url_for('/static/genetrack/genetrack.css')}" type="text/css" media="screen">
<script type="text/javascript" src="${h.url_for('/static/genetrack/genetrack.js')}">var dummy1=0;</script>
</head>
<%def name="title()">
Title
</%def>
<%def name="footer()">
<div align="center" id="footer">
<a href="/">Home</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="${h.url_for(controller='genetrack',action='search',dataset_id=dataset_id)}">Search</a>
</div>
<div align="center" id="tag">
Powered by <a href="http://genetrack.googlecode.com">GeneTrack</a> |
<a href="http://atlas.bx.psu.edu/">Penn State Genome Cartography (2008)</a>
</div>
</%def>
<body>
${self.body()}
${self.footer()}
</body>
</html>
templates/genetrack/index.html
+75
View File
@@ -0,0 +1,75 @@
## index.html
<%inherit file="base.html"/>
<%def name="title()">
Index
</%def>
<h1 align="center">${conf.TITLE}</h1>
<form action="" method="get">
<table align="center" cellpadding="2" cellspacing="1" width="100%">
% if form.errors():
<tr class="error"><td align="center">
% for ekey, evalue in form.errors().items():
<b>ERROR:</b> &nbsp;&nbsp; ${ekey}: &nbsp;&nbsp; ${evalue}<br>
% endfor
</td></tr>
% endif
<tr class="grey">
<td colspan="4" align="center">
<a href="javascript:toggle('options')">More</a><img src="/static/images/thumbtack_icon.png" align="absmiddle" border="0">
Chromosome: ${form.chrom.tag()}&nbsp;&nbsp;
Feature: ${form.feature.tag()}&nbsp;&nbsp;
Width: ${form.zoom.tag()}&nbsp;&nbsp;
Plot: ${form.plot.tag()}&nbsp;&nbsp;
<input type="submit" name="submit" value="Display!">
<div id="options" style="display:none" class="selected">
<table cellpadding="3">
<tr>
<td>
<!-- Nucleosome:${form.nuc_track.tag()} &nbsp;&nbsp;
ORF:${form.orf_track.tag()} &nbsp;&nbsp;
-->
Fit threshold: ${form.min_fit.tag()} &nbsp;&nbsp;
Image width: ${form.img_size.tag()} &nbsp;&nbsp;
</td>
</tr>
</table>
</div>
</td>
</tr>
<tr>
<td align="center">
<input type="submit" name="move_left" value="<< Move Left">
&nbsp;&nbsp;&nbsp;
<input type="submit" name="zoom_out" value="Shrink -">
&nbsp;&nbsp;&nbsp;
<input type="submit" name="zoom_in" value="Magnify +">
&nbsp;&nbsp;&nbsp;
<input type="submit" name="move_right" value="Move Right >>">
</td>
</tr>
<tr>
<td align="center">
<img src="${h.url_for('/static/genetrack/plots/' + param.fname)}" align="center" border="0">
</td>
</tr>
<tr>
<td align="center">
<!-- <a href='/search'>Search</a> -->
</td>
</tr>
</table>
<input type="hidden" id="dataset_id" name="dataset_id" value="${dataset_id}" />
</form>
templates/genetrack/search.html
+55
View File
@@ -0,0 +1,55 @@
## search.html
<%!
from itertools import cycle
colors = cycle( [ 'even', 'odd' ] )
%>
<%inherit file="base.html"/>
<%def name="title()">
Search
</%def>
<h1 align="center">Search</h1>
<div align="center">
<form action="search" method="get">
Search terms <input type="text" name="word" value="${param.word}">
<input type="hidden" name="dataset_id" id="dataset_id" value="${dataset_id}" />
<input type="submit" name="submit" value="Search!">
</form>
</div>
% if param.word:
% if len(query)>0:
<h4 align="center">Showing the best ${len(query)} matches</h4>
<table align="center" class="data_table" cellpadding="6" cellspacing="0">
<tr align="center">
<th width="25%">Name</td>
<th width="25%">Chromosome</td>
<th width="25%">Start:End</td>
<th width="25%">Type</td>
</tr>
% for color, row in zip(colors, query):
${makerow(color, row)}
% endfor
</table>
% else:
<h4 align="center">No results found</h4>
% endif
%endif
<br>
<%def name="makerow(color, row)">
<tr class="${color}" align="center">
<td><a href="${h.url_for(controller='genetrack', action='index', chrom=row.chrom, feature=row.start, dataset_id=dataset_id)}">${row.name}</a></td>
<td>${row.chrom}</td>
<td>${row.start}:${row.end}</td>
<td>${row.label.name}</td>
</tr>
</%def>
</form>
tools/visualization/genetrack.py
+67 -17
View File
@@ -14,15 +14,19 @@ import pkg_resources
pkg_resources.require("GeneTrack")
pkg_resources.require("bx-python")
from atlas import commands
from bx.cookbook import doc_optparse
import os
import commands as oscommands
from atlas import commands
from atlas import sql
from bx.cookbook import doc_optparse
from bx.intervals import io
import os
import tempfile
from functools import partial
SIGMA = 20
WIDTH = 5 * SIGMA
EXCLUSION_ZONE = 147
EXCLUSION_ZONE = 147
def main(label, fit, feats, data_dir, output):
os.mkdir(data_dir)
@@ -31,14 +35,14 @@ def main(label, fit, feats, data_dir, output):
CLOBBER = True,
DATA_SIZE = 3*10**6,
MINIMUM_PEAK_SIZE = 0.1,
LOADER_ENABLED = True,
FITTER_ENABLED = True,
PREDICTOR_ENABLED = True,
EXPORTER_ENABLED = True,
LOADER_ENABLED = False,
FITTER_ENABLED = False,
PREDICTOR_ENABLED = False,
EXPORTER_ENABLED = False,
LOADER = loader,
FITTER = fitter,
PREDICTOR = predictor,
EXPORTER = exporter,
EXPORTER = partial( commands.exporter, formatter=commands.bed_formatter),
HDF_DATABASE = os.path.join( data_dir, "data.hdf" ),
SQL_URI = "sqlite:///%s" % os.path.join( data_dir, "features.sqlite" ),
SIGMA = SIGMA,
@@ -51,12 +55,23 @@ def main(label, fit, feats, data_dir, output):
RIGHT_SHIFT = EXCLUSION_ZONE / 2,
EXPORT_LABELS = [ "PRED-%s-SIGMA-%d" % ( label,SIGMA ) ],
EXPORT_DIR = os.path.join( data_dir ),
DATA_FILE=fit[1],
DATA_FILE=fit and fit[1] or None,
fit=fit,
feats=feats,
)
if fit:
# Turn on fit processing.
conf.LOADER_ENABLED = True,
conf.FITTER_ENABLED = True,
conf.PREDICTOR_ENABLED = True,
conf.EXPORTER_ENABLED = True,
for feat in feats:
load_feature_files(conf, feats)
commands.execute(conf)
outname = "%s.%s.txt" % (conf.__name__, conf.EXPORT_LABELS[0] )
if os.path.exists( os.path.join(data_dir, outname) ):
os.rename( os.path.join(data_dir, outname), output)
# mod454 seems to be a module without a package. The necessary funcitons are
# stubbed out here until I'm sure of their final home. INS
@@ -97,8 +112,40 @@ def predictor( conf ):
from mod454.predictor import predictor as mod454_predictor
return mod454_predictor( conf )
def exporter( conf ):
return commands.bed_exporter(conf)
def load_feature_files( conf, feats):
"""
Loads features from file names
"""
engine = sql.get_engine( conf.SQL_URI )
sql.drop_indices(engine)
conn = engine.connect()
for label, fname, col_spec in feats:
label_id = sql.make_label(engine, name=label, clobber=False)
reader = io.NiceReaderWrapper( open(fname,"r"),
chrom_col=col_spec.chromCol,
start_col=col_spec.startCol,
end_col=col_spec.endCol,
strand_col=col_spec.strandCol,
fix_strand=False )
values = list()
for interval in reader:
print interval
if not type( interval ) is io.GenomicInterval: continue
row = {'label_id':label_id,
'name':col_spec.nameCol == -1 and "%s-%s" % (str(interval.start), str(interval.end)) or interval.fields[col_spec.nameCol],
'altname':"",
'chrom':interval.chrom,
'start':interval.start,
'end':interval.end,
'strand':interval.strand,
'value':0,
'freetext':""}
values.append(row)
insert = sql.feature_table.insert()
conn.execute( insert, values)
conn.close()
sql.create_indices(engine)
class Bunch( object ):
def __init__(self, **kwargs):
@@ -115,9 +162,12 @@ if __name__ == "__main__":
options, args = doc_optparse.parse( __doc__ )
try:
label = options.label
fit_name, fit_meta = options.fits.split(':')[0], [int(x)-1 for x in options.fits.split(':')[1:]]
fit_meta = Bunch(chromCol=fit_meta[0], positionCol=fit_meta[1], forwardCol=fit_meta[2], reverseCol=fit_meta[3])
fit = ( label, fit_name, fit_meta, )
if options.fits:
fit_name, fit_meta = options.fits.split(':')[0], [int(x)-1 for x in options.fits.split(':')[1:]]
fit_meta = Bunch(chromCol=fit_meta[0], positionCol=fit_meta[1], forwardCol=fit_meta[2], reverseCol=fit_meta[3])
fit = ( label, fit_name, fit_meta, )
else:
fit = []
# split apart the string into nested lists, preserves order
if options.feats:
feats = [ (
@@ -127,7 +177,7 @@ if __name__ == "__main__":
strandCol=int(strandCol)-1, nameCol=int(nameCol)-1),
)
for feat_label, fname, chromCol, startCol, endCol, strandCol, nameCol
in ( feat.split(':') for feat in options.feats.split(',') )]
in ( feat.split(':') for feat in options.feats.split(',') if len(feat) > 0 )]
else:
feats = []
data_dir = options.data
tools/visualization/genetrack.xml
+12 -3
View File
@@ -8,7 +8,10 @@
<command interpreter="python">
genetrack.py -l $data_label
-1 ${fit_data}:${fit_data.metadata.chromCol}:${fit_data.metadata.positionCol}:${fit_data.metadata.forwardCol}:${fit_data.metadata.reverseCol}
#if not str($fit_data) == "None"
-1
${fit_data}:${fit_data.metadata.chromCol}:${fit_data.metadata.positionCol}:${fit_data.metadata.forwardCol}:${fit_data.metadata.reverseCol}
#end if
#if $feature_data
-2
#end if
@@ -23,7 +26,7 @@
<param name="data_label" type="text" label="Track Label" size="50">
<validator type="regex" message="Please name the track with only alphanumeric characters.">[a-zA-Z0-9]{0,25}</validator>
</param>
<param name="fit_data" type="data" format="coverage" label="Coverage Dataset" />
<param name="fit_data" type="data" format="coverage" label="Coverage Dataset" optional="true" />
<repeat name="feature_data" title="Features">
<param name="input" type="data" format="interval" label="Dataset" />
<param name="name" type="text" label="Feature Type (mRNA, ESTs, ORFs, etc.)" size="25">
@@ -36,7 +39,13 @@
<data format="genetrack" name="genetrack" />
<data format="bed" name="bed_out" />
</outputs>
<requirements>
<requirement type="python-module">tables</requirement>
<requirement type="python-module">atlas</requirement>
<requirement type="python-module">pychartdir</requirement>
<requirement type="python-module">numpy</requirement>
</requirements>
<help>
This tool takes the input Fit Data and creates a peak and curve plot showing
the reads and fitness on each basepair. Features can be plotted below as tracks.