offtracker 2.7.8__zip → 2.10.0__zip

offtracker-2.7.8/offtracker/mapping/Snakefile_offtracker

@@ -1,245 +0,0 @@
-# 2023.08.11. adding a option for not normalizing the bw file
-# 2024.01.23. add --fixedStep to bigwigCompare for not merging neighbouring bins with equal values.
-
-configfile: "config.yaml"
-
-_threads = config["thread"]
-BinSize = str(config["binsize"])
-normalize = config["normalize"]
-output_dir = config["output_dir"]
-nametype = config["nametype"]
-suffix = config["suffix"]
-name1 = nametype.replace('2','1') + '.' + suffix
-name2 = nametype + '.' + suffix
-
-import os
-
-if normalize == "True":
-    rule all:
-        input:
-            expand( os.path.join(output_dir,"{sample}.fw.bed"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.rv.bed"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.fw.scaled.bw"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.rv.scaled.bw"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}." + BinSize + ".add.bdg"),sample=config["sample"] ),
-elif normalize == "False":
-    rule all:
-        input:
-            expand( os.path.join(output_dir,"{sample}.fw.bed"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.rv.bed"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.fw.raw.bw"), sample=config["sample"] ),
-            expand( os.path.join(output_dir,"{sample}.rv.raw.bw"), sample=config["sample"] ),
-else:
-    raise ValueError('Please provide "True" or "False" for "--normalize" when running offtracker_config.py')
-
-
-rule chromap:
-    input:
-        R1= lambda w: config["sample"][w.sample] + name1,
-        R2= lambda w: config["sample"][w.sample] + name2
-    threads:
-        _threads
-    params:
-        index=config["index"],
-        fasta=config["fasta"]
-    output:
-        temp(os.path.join(output_dir,"{sample}.chromapx.bed"))
-    shell:
-        """
-        chromap -l 3000 --low-mem --BED --remove-pcr-duplicates \
-        --min-read-length 10 --allocate-multi-mappings \
-        -x {params.index} -r {params.fasta} -t {threads} -1 {input.R1} -2 {input.R2} -o {output}
-        """
-
-if config["blacklist"] != 'none':
-    rule remove_blacklist:
-        input:
-            os.path.join(output_dir,"{sample}.chromapx.bed")
-        threads:
-            _threads
-        params:
-            blacklist=config["blacklist"]
-        output:
-            temp(os.path.join(output_dir,"{sample}.filtered.bed"))
-        shell:
-            "bedtools intersect -a {input} -b {params.blacklist} -v > {output}"
-
-    rule bed2fr:
-        input:
-            os.path.join(output_dir,"{sample}.filtered.bed")
-        threads:
-            _threads
-        params:
-            dir_script=config["script_folder"]
-        output:
-            fw=os.path.join(output_dir,"{sample}.fw.bed"),
-            rv=os.path.join(output_dir,"{sample}.rv.bed")
-        shell:
-            "python {params.dir_script}/1.1_bed2fr_v4.5.py -b {input}"
-else:
-    rule bed2fr:
-        input:
-            os.path.join(output_dir,"{sample}.chromapx.bed")
-        threads:
-            _threads
-        params:
-            dir_script=config["script_folder"]
-        output:
-            fw=os.path.join(output_dir,"{sample}.fw.bed"),
-            rv=os.path.join(output_dir,"{sample}.rv.bed")
-        shell:
-            "python {params.dir_script}/1.1_bed2fr_v4.5.py -b {input}"    
-
-rule bed2bdg_fw:
-    input:
-        os.path.join(output_dir,"{sample}.fw.bed")
-    threads:
-        _threads
-    params:
-        gl=config["genomelen"]
-    output:
-        temp(os.path.join(output_dir,"{sample}.fw.bdg"))
-    shell:
-        "bedtools genomecov -bg -i {input} -g {params.gl} > {output}"
-
-rule bed2bdg_rv:
-    input:
-        os.path.join(output_dir,"{sample}.rv.bed")
-    threads:
-        _threads
-    params:
-        gl=config["genomelen"]
-    output:
-        temp(os.path.join(output_dir,"{sample}.rv.bdg"))
-    shell:
-        "bedtools genomecov -bg -i {input} -g {params.gl} > {output}"
-
-rule bdg_sort_fw:
-    input:
-        fw=os.path.join(output_dir,"{sample}.fw.bdg")
-    threads:
-        _threads
-    output:
-        temp(os.path.join(output_dir,"{sample}.fw.sorted.bdg"))
-    shell:
-        "bedtools sort -i {input.fw} > {output}"
-
-rule bdg_sort_rv:
-    input:
-        rv=os.path.join(output_dir,"{sample}.rv.bdg")
-    threads:
-        _threads
-    output:
-        temp(os.path.join(output_dir,"{sample}.rv.sorted.bdg"))
-    shell:
-        "bedtools sort -i {input.rv} > {output}"
-
-if normalize == "True":
-    rule bdg_normalize_fw:
-        input:
-            bdg=os.path.join(output_dir,"{sample}.fw.sorted.bdg"),
-            bed=os.path.join(output_dir,"{sample}.fw.bed")
-        threads:
-            _threads
-        params:
-            dir_script=config["script_folder"]
-        output:
-            temp(os.path.join(output_dir,"{sample}.fw.scaled.bdg"))
-        shell:
-            "python {params.dir_script}/1.3_bdg_normalize_v4.0.py --bdg {input.bdg} --bed {input.bed}"
-    
-    rule bdg_normalize_rv:
-        input:
-            bdg=os.path.join(output_dir,"{sample}.rv.sorted.bdg"),
-            bed=os.path.join(output_dir,"{sample}.rv.bed")
-        threads:
-            _threads
-        params:
-            dir_script=config["script_folder"]
-        output:
-            temp(os.path.join(output_dir,"{sample}.rv.scaled.bdg"))
-        shell:
-            "python {params.dir_script}/1.3_bdg_normalize_v4.0.py --bdg {input.bdg} --bed {input.bed}"
-    
-    rule bdg2bw_fw:
-        input:
-            os.path.join(output_dir,"{sample}.fw.scaled.bdg")
-        threads:
-            _threads
-        params:
-            gl=config["genomelen"],
-            dir_script=config["script_folder"]
-        output:
-            os.path.join(output_dir,"{sample}.fw.scaled.bw")
-        shell:
-            "{params.dir_script}/bedGraphToBigWig {input} {params.gl} {output}"
-    
-    rule bdg2bw_rv:
-        input:
-            os.path.join(output_dir,"{sample}.rv.scaled.bdg")
-        threads:
-            _threads
-        params:
-            gl=config["genomelen"],
-            dir_script=config["script_folder"]
-        output:
-            os.path.join(output_dir,"{sample}.rv.scaled.bw")
-        shell:
-            "{params.dir_script}/bedGraphToBigWig {input} {params.gl} {output}"
-    
-    rule bwAdd:
-        input:
-            fw=os.path.join(output_dir,"{sample}.fw.scaled.bw"),
-            rv=os.path.join(output_dir,"{sample}.rv.scaled.bw")
-        threads:
-            _threads
-        output:
-            os.path.join(output_dir,"{sample}." + BinSize + ".add.bdg")
-        shell:
-            """
-            bigwigCompare --binSize {BinSize} -p {threads} --verbose -o {output} \
-            --outFileFormat bedgraph --fixedStep \
-            --bigwig1 {input.fw} \
-            --bigwig2 {input.rv} \
-            --operation add 
-            """
-else:
-    rule bdg_reverse_rv:
-        input:
-            os.path.join(output_dir,"{sample}.rv.sorted.bdg")
-        threads:
-            _threads
-        output:
-            temp(os.path.join(output_dir,"{sample}.rv.sorted_r.bdg"))
-        shell:
-            "awk -F '\t' -v OFS='\t' '{{$4=-$4; print}}' {input} > {output}"
-    
-    rule bdg2bw_fw:
-        input:
-            os.path.join(output_dir,"{sample}.fw.sorted.bdg")
-        threads:
-            _threads
-        params:
-            gl=config["genomelen"],
-            dir_script=config["script_folder"]
-        output:
-            os.path.join(output_dir,"{sample}.fw.raw.bw")
-        shell:
-            "{params.dir_script}/bedGraphToBigWig {input} {params.gl} {output}"
-    
-    rule bdg2bw_rv:
-        input:
-            os.path.join(output_dir,"{sample}.rv.sorted_r.bdg")
-        threads:
-            _threads
-        params:
-            gl=config["genomelen"],
-            dir_script=config["script_folder"]
-        output:
-            os.path.join(output_dir,"{sample}.rv.raw.bw")
-        shell:
-            "{params.dir_script}/bedGraphToBigWig {input} {params.gl} {output}"
-
-
-
-

offtracker-2.7.8/offtracker.egg-info/PKG-INFO

@@ -1,146 +0,0 @@
-Metadata-Version: 2.1
-Name: offtracker
-Version: 2.7.8
-Summary: Tracking-seq data analysis
-Home-page: https://github.com/Lan-lab/offtracker
-Author: Runda Xu
-Author-email: runda.xu@foxmail.com
-Requires-Python: >=3.6.0
-Description-Content-Type: text/markdown
-License-File: LICENSE.txt
-
-
-OFF-TRACKER
-=======================
-
-OFF-TRACKER is an end to end pipeline of Tracking-seq data analysis for detecting off-target sites of any genome editing tools that generate double-strand breaks (DSBs) or single-strand breaks (SSBs).
-
-System requirements
------
-* Linux/Unix 
-* Python >= 3.6
-
-Dependency
------
-
-```bash
-# We recommend creating a new enviroment using mamba/conda to avoid compatibility problems
-# If you don't use mamba, just replace the code with conda 
-mamba create -n offtracker -c bioconda blast snakemake pybedtools
-```
-
-
-Installation 
------
-
-```bash
-# activate the environment
-conda activate offtracker
-
-# Direct installation with pip
-pip install offtracker
-
-# (Alternative) Download the offtracker from github
-git clone https://github.com/Lan-lab/offtracker.git 
-cd offtracker
-pip install .
-```
-
-
-Before analyzing samples
------
-
-```bash
-# Build blast index (only need once for each genome)
-makeblastdb -input_type fasta -title hg38 -dbtype nucl -parse_seqids \
--in /Your_Path_To_Reference/hg38_genome.fa \
--out /Your_Path_To_Reference/hg38_genome.blastdb \
--logfile /Your_Path_To_Reference/hg38_genome.blastdb.log
-
-# Build chromap index (only need once for each genome)
-chromap -i -r /Your_Path_To_Reference/hg38_genome.fa \
--o /Your_Path_To_Reference/hg38_genome.chromap.index
-
-# Generate candidate regions by sgRNA sequence (need once for each genome and sgRNA)
-offtracker_candidates.py -t 8 -g hg38 \
--r /Your_Path_To_Reference/hg38_genome.fa \
--b /Your_Path_To_Reference/hg38_genome.blastdb \
---name 'HEK4' --sgrna 'GGCACTGCGGCTGGAGGTGG' --pam 'NGG' \
--o /Your_Path_To_Candidates
-
-```
-
-Strand-specific mapping of Tracking-seq data 
------
-
-```bash
-# Generate snakemake config file 
-offtracker_config.py -t 8 -g hg38 --blacklist hg38 \
--r /Your_Path_To_Reference/hg38_genome.fa \
--i /Your_Path_To_Reference/hg38_genome.chromap.index \
--f /Your_Path_To_Fastq \
--o /Your_Path_To_Output \ 
---subfolder 0 
-
-# --subfolder: If different samples are in seperate folders, set this to 1
-# -o: Default is outputting to /Your_Path_To_Fastq
-
-# Run the snakemake program
-cd /Your_Path_To_Fastq
-snakemake -np # dry run
-nohup snakemake --cores 16 1>snakemake.log 2>snakemake.err &
-
-## about cores
-# --cores of snakemake must be larger than -t of offtracker_config.py
-# parallel number = cores/t
-
-## about output
-# This part will generate "*.fw.scaled.bw" and ".rv.scaled.bw" for IGV visualization
-# "*.fw.bed" and "*.rv.bed" are used in the next part.
-```
-
-
-Analyzing the off-target sites
------
-
-```bash
-# In this part, multiple samples in the same condition can be analyzed in a single run by pattern recogonization of sample names
-
-offtracker_analysis.py -g hg38 --name "HEK4" \
---exp 'Cas9_HEK4.*293' \
---control 'control' \
---outname 'Cas9_HEK4_293' \
--f /Your_Path_To_Output \
---seqfolder /Your_Path_To_Candidates
-
-# --name: the same as that in offtracker_candidates.py
-# --exp/--control: add one or multiple patterns of file name in regex
-
-
-# This step will generate Trackseq_result_{outname}.csv
-# Intermediate files are saved in ./temp folder, which can be deleted 
-# Keeping the intermediate files can make the analysis faster if involving previously analyzed samples (e.g. using the same control samples for different analyses)
-```
-
-
-Note1
---------------
-The default setting only includes chr1-chr22, chrX, chrY, and chrM.
-
-Please make sure the reference genome contains "chr" at the beginning. 
-
-If you have requirement for other chromosomes or species other than human/mouse, please post an issue.
-
-Note2
---------------
-Currently, this software is only ready-to-use for mm10 and hg38. 
-
-For any other genome, say hg19, please add genome size file named "hg19.chrom.sizes" to .\offtracker\mapping before install.
-
-Besides, add "--blacklist none" or "--blacklist Your_Blacklist" when running offtracker_config.py
-
-Note3
---------------
-The FDR in the Tracking-seq result is not rigorous to the real off-target probability.
-It is strongly recommended to observe the "fw.scaled.bw" and "rv.scaled.bw" using IGV to check each target location from the Tracking-seq result.
-

offtracker-2.7.8/offtracker.egg-info/SOURCES.txt

@@ -1,25 +0,0 @@
-LICENSE.txt
-MANIFEST.in
-README.md
-setup.py
-offtracker/X_offplot.py
-offtracker/X_offtracker.py
-offtracker/X_sequence.py
-offtracker/__init__.py
-offtracker/_version.py
-offtracker.egg-info/PKG-INFO
-offtracker.egg-info/SOURCES.txt
-offtracker.egg-info/dependency_links.txt
-offtracker.egg-info/requires.txt
-offtracker.egg-info/top_level.txt
-offtracker/mapping/1.1_bed2fr_v4.5.py
-offtracker/mapping/1.3_bdg_normalize_v4.0.py
-offtracker/mapping/Snakefile_offtracker
-offtracker/mapping/bedGraphToBigWig
-offtracker/mapping/hg38.chrom.sizes
-offtracker/mapping/mm10.chrom.sizes
-offtracker/mapping/offtracker_blacklist_hg38.merged.bed
-offtracker/mapping/offtracker_blacklist_mm10.merged.bed
-scripts/offtracker_analysis.py
-scripts/offtracker_candidates.py
-scripts/offtracker_config.py