diff --git a/COPYRIGHT b/COPYRIGHT
index c6a6a21b6a693891b7458be93fe0ae94f22fedf4..cce5466eda1755cac2b6cf9672eb4f2fa80cf37c 100644
--- a/COPYRIGHT
+++ b/COPYRIGHT
@@ -1,11 +1,11 @@
-ChIPflow - a snakemake-based workflow for the analysis of epigenomic data (ChIP-seq)
+ePeak - a snakemake-based workflow for the analysis of epigenomic data (ChIP-seq, CUT&RUN, CUT&Tag)
from the raw fastq files to the differential analysis of transcription factor binding
or histone modification marking.
Copyright © 2020 Institut Pasteur (Paris) and CNRS.
------------------------------------------------------------------
Citation:
-Daunesse M, Legendre R, Varet H, Pain A, Chica C. ChIPflow: from raw data to epigenomic dynamics
+Daunesse M, Legendre R, Varet H, Pain A, Chica C. ePeak: from replicated chromatin profiling data to epigenomic dynamics
------------------------------------------------------------------
@@ -20,7 +20,7 @@ The code includes contributions and input from:
-----------------------------------------------------------------
-ChIPflow is free software: you can redistribute it and/or modify
+ePeak is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation version 3 of the License.
diff --git a/Snakefile b/Snakefile
index a8921cfe96adf2b43a67b9bc44201cbf4f93206f..4823242687f48bdc59dd0cf59eac67c8dd485494 100755
--- a/Snakefile
+++ b/Snakefile
@@ -1,28 +1,29 @@
#########################################################################
-# ChIPflow: Standardize and reproducible ChIP-seq analysis from raw #
+# ePeak: Standardize and reproducible ChIP-seq analysis from raw #
# data to differential analysis #
# Authors: Rachel Legendre, Maelle Daunesse #
# Copyright (c) 2019-2020 Institut Pasteur (Paris) and CNRS. #
# #
-# This file is part of ChIPflow workflow. #
+# This file is part of ePeak workflow. #
# #
-# ChIPflow is free software: you can redistribute it and/or modify #
+# ePeak is free software: you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation, either version 3 of the License, or #
# (at your option) any later version. #
# #
-# ChIPflow is distributed in the hope that it will be useful, #
+# ePeak is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details . #
# #
# You should have received a copy of the GNU General Public License #
-# along with ChIPflow (LICENSE). #
+# along with ePeak (LICENSE). #
# If not, see <https://www.gnu.org/licenses/>. #
#########################################################################
+
import pandas as pd
from fnmatch import fnmatch
from re import sub, match
diff --git a/config/config.yaml b/config/config.yaml
index 5af82df8bece13dc268a1d327ff0eeb0af54a6e7..c7801288e1bb07f29e33b5ffaf7949885bafe4b3 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -1,30 +1,31 @@
#########################################################################
-# ChIPflow: Standardize and reproducible ChIP-seq analysis from raw #
+# ePeak: Standardize and reproducible ChIP-seq analysis from raw #
# data to differential analysis #
# Authors: Rachel Legendre, Maelle Daunesse #
# Copyright (c) 2019-2020 Institut Pasteur (Paris) and CNRS. #
# #
-# This file is part of ChIPflow workflow. #
+# This file is part of ePeak workflow. #
# #
-# ChIPflow is free software: you can redistribute it and/or modify #
+# ePeak is free software: you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation, either version 3 of the License, or #
# (at your option) any later version. #
# #
-# ChIPflow is distributed in the hope that it will be useful, #
+# ePeak is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details . #
# #
# You should have received a copy of the GNU General Public License #
-# along with ChIPflow (LICENSE). #
+# along with ePeak (LICENSE). #
# If not, see <https://www.gnu.org/licenses/>. #
#########################################################################
+
# ========================================================
-# ChIPflow pipeline config file
+# ePeak pipeline config file
#=========================================================
# path to the fastq directory
@@ -222,7 +223,7 @@ seacr:
#===============================================================================
compute_idr:
- do: no
+ do: yes
rank: 'signal.value'
thresh: 0.05
@@ -239,7 +240,7 @@ compute_idr:
#===============================================================================
intersectionApproach:
- do: yes
+ do: no
ia_overlap: 0.8
diff --git a/config/multiqc_config.yaml b/config/multiqc_config.yaml
index ac72410fd1d1310cb8b61d8f2d4ac7b08fdc438d..6b0c6cb830fb2d91273b620c1fe6a5f83a1b08cb 100644
--- a/config/multiqc_config.yaml
+++ b/config/multiqc_config.yaml
@@ -1,29 +1,29 @@
#########################################################################
-# ChIPflow: Standardize and reproducible ChIP-seq analysis from raw #
+# ePeak: Standardize and reproducible ChIP-seq analysis from raw #
# data to differential analysis #
# Authors: Rachel Legendre, Maelle Daunesse #
# Copyright (c) 2019-2020 Institut Pasteur (Paris) and CNRS. #
# #
-# This file is part of ChIPflow workflow. #
+# This file is part of ePeak workflow. #
# #
-# ChIPflow is free software: you can redistribute it and/or modify #
+# ePeak is free software: you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation, either version 3 of the License, or #
# (at your option) any later version. #
# #
-# ChIPflow is distributed in the hope that it will be useful, #
+# ePeak is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details . #
# #
# You should have received a copy of the GNU General Public License #
-# along with ChIPflow (LICENSE). #
+# along with ePeak (LICENSE). #
# If not, see <https://www.gnu.org/licenses/>. #
#########################################################################
#===============================================================================
-# Optimized MultiQc config file dedicated to ChIPflow workflow
+# Optimized MultiQc config file dedicated to ePeak workflow
#===============================================================================
#------------------------------------------------------------------------------
diff --git a/test/config.yaml b/test/config.yaml
index e441a6cbdf1e3848880cc6c02bf2ef3fd3d285c3..6a50d6852eb380977d7dc02fff29f82e3a5ce2a3 100644
--- a/test/config.yaml
+++ b/test/config.yaml
@@ -1,29 +1,30 @@
#########################################################################
-# ChIPflow: Standardize and reproducible ChIP-seq analysis from raw #
+# ePeak: Standardize and reproducible ChIP-seq analysis from raw #
# data to differential analysis #
# Authors: Rachel Legendre, Maelle Daunesse #
# Copyright (c) 2019-2020 Institut Pasteur (Paris) and CNRS. #
# #
-# This file is part of ChIPflow workflow. #
+# This file is part of ePeak workflow. #
# #
-# ChIPflow is free software: you can redistribute it and/or modify #
+# ePeak is free software: you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation, either version 3 of the License, or #
# (at your option) any later version. #
# #
-# ChIPflow is distributed in the hope that it will be useful, #
+# ePeak is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details . #
# #
# You should have received a copy of the GNU General Public License #
-# along with ChIPflow (LICENSE). #
+# along with ePeak (LICENSE). #
# If not, see <https://www.gnu.org/licenses/>. #
#########################################################################
+
# ========================================================
-# Config file for ChIPflow pipeline
+# Config file for ePeak pipeline
#=========================================================
# directory where fastq are stored
@@ -217,24 +218,36 @@ seacr:
threshold: 'stringent'
norm: 'norm'
-
-
-
#===============================================================================
# Compute IDR on replicates, pseudo-replicates and pooled replicates
#
# :Parameters:
#
-# - rank: Which column to use to rank peaks. Options: signal.value p.value q.value columnIndex
-# - thresh: Report statistics for peaks with a global idr below this value but return all peaks with an idr below --idr. Default: 0.05
-# - intersectionApproach: set to yes if you want to use intersection approach with narrow peaks when replicates are not closed enough
+# - do: if unchecked, this rule is ignored.
+# - rank: which column to use to rank peaks. Options: signal.value, p.value, q.value, columnIndex
+# - thresh: report statistics for peaks with a global idr below this value. Default: 0.05
#
#===============================================================================
compute_idr:
+ do: yes
rank: 'signal.value'
thresh: 0.05
- intersectionApproach: no
+
+
+#===============================================================================
+# Compute intersection approach on replicates
+#
+# :Parameters:
+#
+# - do: if set to 'yes', will compute the intersection approach and use it
+# to select reproducible peaks. (for narrow only, correspond to the default broad approach)
+# - ia_overlap: percentage of overlap between the peaks to be selected (-f parameter of bedtools intersect). Default: 0.8
+#
+#===============================================================================
+
+intersectionApproach:
+ do: no
ia_overlap: 0.8
#===============================================================================
diff --git a/workflow/rules/compute_FRiP_scores.rules b/workflow/rules/compute_FRiP_scores.rules
deleted file mode 100644
index 40666a7ec0a8c824ac83cac536f2312cf2f35c1c..0000000000000000000000000000000000000000
--- a/workflow/rules/compute_FRiP_scores.rules
+++ /dev/null
@@ -1,56 +0,0 @@
-#########################################################################
-# ePeak: Standardize and reproducible ChIP-seq analysis from raw #
-# data to differential analysis #
-# Authors: Rachel Legendre, Maelle Daunesse #
-# Copyright (c) 2019-2020 Institut Pasteur (Paris) and CNRS. #
-# #
-# This file is part of ePeak workflow. #
-# #
-# ePeak is free software: you can redistribute it and/or modify #
-# it under the terms of the GNU General Public License as published by #
-# the Free Software Foundation, either version 3 of the License, or #
-# (at your option) any later version. #
-# #
-# ePeak is distributed in the hope that it will be useful, #
-# but WITHOUT ANY WARRANTY; without even the implied warranty of #
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
-# GNU General Public License for more details . #
-# #
-# You should have received a copy of the GNU General Public License #
-# along with ePeak (LICENSE). #
-# If not, see <https://www.gnu.org/licenses/>. #
-#########################################################################
-
-
-rule compute_FRiP_scores:
- input:
- bam = compute_FRiP_scores_input
- output:
- tab = compute_FRiP_scores_output
- threads: 8
- run:
- import pysam
-
- samfile = pysam.AlignmentFile(input.bam, "rb")
-
-
- bed_files = ["peaks.bed"]
- cr = countReadsPerBin.CountReadsPerBin([bam_file1, bam_file2],
- bedFile=bed_files,
- numberOfProcessors=threads)
- reads_at_peaks = cr.run()
- print reads_at_peaks
- total = reads_at_peaks.sum(axis=0)
-
- bam1 = pysam.AlignmentFile(bam_file1)
- bam2 = pysam.AlignmentFile(bam_file2)
-
- frip1 = float(total[0]) / bam1.mapped
- frip2 = float(total[1]) / bam2.mapped
- print frip1, frip2
-
-
- with open(output.tab, 'w') as file_fp:
- file_fp.write(S)
-
-
\ No newline at end of file