import random from sklearn import manifold from sklearn.metrics import euclidean_distances from sklearn.preprocessing import scale as sklearn_scale from sklearn.decomposition import PCA as sklearnPCA from rpy2.robjects import r as R import rpy2.robjects.pandas2ri as py2ri from CGATReport.ResultBlock import ResultBlocks, ResultBlock import seaborn from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P import CGATPipelines.PipelineTracks as PipelineTracks from CGATReport.Utils import PARAMS DATABASE = PARAMS.get("readqc_backend", PARAMS.get("sql_backend", "sqlite:///./csvdb")) class RnaseqqcTracker(TrackerSQL): """Define convenience tracks for plots""" def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs) class SampleOverlap(RnaseqqcTracker): table = "sailfish_transcripts" def __call__(self, *args):
import itertools import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P import CGATPipelines.Pipeline as Pipeline import CGATPipelines.PipelineTracks as PipelineTracks ################################################################### ################################################################### # parameterization EXPORTDIR = P.get('calling_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('calling_datadir', P.get('datadir', '.')) DATABASE = P.get('calling_backend', P.get('report_sql_backend', 'sqlite:///./csvdb')) ################################################################### # cf. pipeline_chipseq.py # This should be automatically gleaned from pipeline_chipseq.py ################################################################### PARAMS_PIPELINE = Pipeline.peekParameters(".", "pipeline_chipseq.py") Sample = PipelineTracks.Sample3 suffixes = ["export.txt.gz", "sra", "fastq.gz", "fastq.1.gz", "csfasta.gz"]
import itertools import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P import CGATPipelines.Pipeline as Pipeline import CGATPipelines.PipelineTracks as PipelineTracks ################################################################### ################################################################### # parameterization EXPORTDIR = P.get('calling_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('calling_datadir', P.get('datadir', '.')) DATABASE = P.get('calling_backend', P.get('report_sql_backend', 'sqlite:///./csvdb')) ################################################################### # cf. pipeline_chipseq.py # This should be automatically gleaned from pipeline_chipseq.py ################################################################### PARAMS_PIPELINE = Pipeline.peekParameters(".", "pipeline_chipseq.py") Sample = PipelineTracks.Sample3 suffixes = ["export.txt.gz", "sra", "fastq.gz", "fastq.1.gz", "csfasta.gz"] TRACKS = sum( itertools.chain([ PipelineTracks.Tracks(Sample).loadFromDirectory([ x for x in glob.glob("%s/*.%s" % (DATADIR, s)) if "input" not in x ], "%s/(\S+).%s" % (DATADIR, s)) for s in suffixes
import pandas as pd import numpy as np import sqlite3 from CGATReport.Tracker import SingleTableTrackerRows from CGATReport.Tracker import SingleTableTrackerHistogram from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from IsoformReport import * ############################################################################### # parse params ############################################################################### DATABASE = P.get('', P.get('sql_backend', 'sqlite:///./csvdb')) ANNOTATIONS_DATABASE = P.get('annotations_database') ############################################################################### # trackers ############################################################################### class SleuthResults(IsoformTracker): pattern = "(.*)_DEresults$" direction = "" where = "WHERE p_value NOT NULL" def __call__(self, track, slice=None): quantifier = track.split("_")[-2]
from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P PIPELINE_DB = P.get("capturec_database", P.get("database_name", None)) class CaptureCTracker(TrackerSQL): def __init__(self, *args, **kwags): if PIPELINE_DB is not None: self.backend = PIPELINE_DB TrackerSQL.__init__(self, *args, **kwargs)
from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P EXPORTDIR = P.get('motifs_exportdir', P.get('report_exportdir', "export")) DATADIR = P.get('motifs_datadir', P.get('report_datadir', ".")) DATABASE = P.get('motifs_backend', P.get('report_backend', "sqlite:///./csvdb")) class IntervalTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs)
import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from collections import OrderedDict as odict from CGATPipelines.PipelineGeneset import mapUCSCToEnsembl # get from config file UCSC_DATABASE = P["genome"] ################################################################### ################################################################### # parameterization EXPORTDIR = P.get( 'rnaseqdiffexpression_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('rnaseqdiffexpression_datadir', P.get('datadir', '.')) DATABASE = P.get('rnaseqdiffexpression_backend', P.get( 'sql_backend', 'sqlite:///./csvdb')) DATABASE_ANNOTATIONS = P['annotations_database'] ################################################################### # cf. pipeline_rnaseq.py # This should be automatically gleaned from pipeline_rnaseq.py ################################################################### import CGATPipelines.PipelineTracks as PipelineTracks TRACKS = PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory( glob.glob("%s/*.bam" % DATADIR), "(\S+).bam")
import itertools import random from sklearn import manifold from sklearn.metrics import euclidean_distances from sklearn.preprocessing import scale as sklearn_scale from sklearn.decomposition import PCA as sklearnPCA from rpy2.robjects import r as R import rpy2.robjects.pandas2ri as py2ri from CGATReport.ResultBlock import ResultBlocks, ResultBlock import seaborn from CGATReport.Tracker import * from CGATReport.Utils import PARAMS import CGATPipelines.Pipeline as Pipeline import matplotlib.pyplot as plt DATABASE = PARAMS.get('readqc_backend', PARAMS.get('sql_backend', 'sqlite:///./csvdb')) class imagesTracker(TrackerImages): '''Convience Tracker for globbing images for gallery plot''' def __init__(self, *args, **kwargs): Tracker.__init__(self, *args, **kwargs) if "glob" not in kwargs: raise ValueError("TrackerImages requires a:glob: parameter") self.glob = kwargs["glob"] class RnaseqqcTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs)
from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P ################################################################### ################################################################### # parameterization EXPORTDIR = P.get('intervals_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('intervals_datadir', P.get('datadir', '.')) DATABASE = P.get('intervals_backend', P.get('sql_backend', 'sqlite:///./csvdb')) class IntervalTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs)
import os import sys import re import types import itertools import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from collections import OrderedDict as odict EXPORTDIR = P.get('motifs_exportdir', P.get('report_exportdir', "export")) DATADIR = P.get('motifs_datadir', P.get('report_datadir', ".")) DATABASE = P.get('motifs_backend', P.get('report_backend', "sqlite:///./csvdb")) class IntervalTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs)
from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from collections import OrderedDict as odict ################################################################### # parameterization EXPORTDIR = P.get('annotations_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('annotations_datadir', P.get('datadir', '.')) DATABASE = P.get('annotations_backend', P.get('sql_backend', 'sqlite:///./csvdb')) class AnnotationTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs) class BedSummaryIntervals(TrackerSQL): pattern = '(.*)_bedsummary' def __call__(self, track): return self.getValue( "SELECT sum(nintervals) FROM %(track)s_bedsummary") class BedSummaryIntervalsPerContig(TrackerSQL): pattern = '(.*)_bedsummary' def __call__(self, track):
import pandas as pd import numpy as np from CGATReport.Tracker import SingleTableTrackerRows from CGATReport.Tracker import SingleTableTrackerHistogram from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from IsoformReport import * ############################################################################### # parse params ############################################################################### DATABASE = P.get('', P.get('sql_backend', 'sqlite:///./csvdb')) ############################################################################### # trackers ############################################################################### class SleuthResults(IsoformTracker): pattern = "(.*)_DEresults$" direction = "" where = "" def __call__(self, track, slice=None): statement = ''' SELECT A.gene_name, A.gene_id, A.transcript_id, A.transcript_biotype, A.control_mean AS expression, A.fold, A.l2fold AS log2_fold,
from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P PIPELINE_DB = P.get("capturec_database", P.get("database_name", None)) class CaptureCTracker(TrackerSQL): def __init__(self, *args, **kwargs): print PIPELINE_DB if PIPELINE_DB is not None: self.backend = "sqlite:///" + PIPELINE_DB TrackerSQL.__init__(self, *args, **kwargs)
import re from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P # get from config file UCSC_DATABASE = "hg19" EXPORTDIR = "export" ################################################################### ################################################################### ################################################################### ################################################################### # Run configuration script EXPORTDIR = P.get('exome_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('exome_datadir', P.get('datadir', '.')) DATABASE = P.get('exome_backend', P.get('sql_backend', 'sqlite:///./csvdb')) TRACKS = ['WTCHG_10997_01', 'WTCHG_10997_02'] ########################################################################### def splitLocus(locus): if ".." in locus: contig, start, end = re.match("(\S+):(\d+)\.\.(\d+)", locus).groups() elif "-" in locus: contig, start, end = re.match("(\S+):(\d+)\-(\d+)", locus).groups() return contig, int(start), int(end) def linkToUCSC(contig, start, end):
import random from sklearn import manifold from sklearn.metrics import euclidean_distances from sklearn.preprocessing import scale as sklearn_scale from sklearn.decomposition import PCA as sklearnPCA from rpy2.robjects import r as R import rpy2.robjects.pandas2ri as py2ri from CGATReport.ResultBlock import ResultBlocks, ResultBlock import seaborn from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P import CGATPipelines.PipelineTracks as PipelineTracks from CGATReport.Utils import PARAMS DATABASE = PARAMS.get('readqc_backend', PARAMS.get('sql_backend', 'sqlite:///./csvdb')) class RnaseqqcTracker(TrackerSQL): '''Define convenience tracks for plots''' def __init__(self, *args, **kwargs): TrackerSQL.__init__(self, *args, backend=DATABASE, **kwargs) class SampleOverlap(RnaseqqcTracker): table = "sailfish_transcripts" def __call__(self, *args):
import types import itertools import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from collections import OrderedDict as odict from CGATReport.ResultBlock import ResultBlock, ResultBlocks from CGATReport import Utils ################################################################### ################################################################### # parameterization EXPORTDIR = P.get('readqc_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('readqc_datadir', P.get('datadir', '.')) DATABASE = P.get('readqc_backend', P.get('sql_backend', 'sqlite:///./csvdb')) ################################################################### # cf. pipeline_rnaseq.py # This should be automatically gleaned from pipeline_rnaseq.py ################################################################### import CGATPipelines.PipelineTracks as PipelineTracks TRACKS = PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory( glob.glob("%s/*.sra" % DATADIR), "(\S+).sra") +\ PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory( glob.glob("%s/*.fastq.gz" % DATADIR), "(\S+).fastq.gz") +\ PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory( glob.glob("%s/*.fastq.1.gz" % DATADIR), "(\S+).fastq.1.gz") +\
import glob from CGATReport.Tracker import * from CGATReport.Utils import PARAMS as P from collections import OrderedDict as odict from CGATPipelines.PipelineGeneset import mapUCSCToEnsembl # get from config file UCSC_DATABASE = P["genome"] ################################################################### ################################################################### # parameterization EXPORTDIR = P.get('rnaseqdiffexpression_exportdir', P.get('exportdir', 'export')) DATADIR = P.get('rnaseqdiffexpression_datadir', P.get('datadir', '.')) DATABASE = P.get('rnaseqdiffexpression_backend', P.get('sql_backend', 'sqlite:///./csvdb')) DATABASE_ANNOTATIONS = P['annotations_database'] ################################################################### # cf. pipeline_rnaseq.py # This should be automatically gleaned from pipeline_rnaseq.py ################################################################### import CGATPipelines.PipelineTracks as PipelineTracks TRACKS = PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory( glob.glob("%s/*.bam" % DATADIR), "(\S+).bam")