offtracker 2.7.10__zip → 2.10.0__zip

{offtracker-2.7.10/offtracker.egg-info → offtracker-2.10.0}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.7.10
+Version: 2.10.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu
-Author-email: runda.xu@foxmail.com
+Author-email: xrd18@tsinghua.org.cn
 Requires-Python: >=3.6.0
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
@@ -22,9 +22,10 @@ OFF-TRACKER is an end to end pipeline of Tracking-seq data analysis for detectin
 ## Dependency
 
 ```bash
-# We recommend creating a new enviroment using mamba/conda to avoid compatibility problems
+# We recommend creating a new environment 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
+# Windows systems may not be compatible with pybedtools.
+mamba create -n offtracker -c bioconda blast snakemake pybedtools chromap
 ```
 
 
@@ -58,32 +59,69 @@ 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)
-# --name: the name of the sgRNA, which will be used in the following analysis
+# --name: a user-defined name of the sgRNA, which will be used in the following analysis.
 offtracker_candidates.py -t 8 -g hg38 \
 -r /Your_Path_To_Reference/hg38_genome.fa \
 -b /Your_Path_To_Reference/hg38_genome.blastdb \
 --name 'VEGFA2' --sgrna 'GACCCCCTCCACCCCGCCTC' --pam 'NGG' \
--o /Your_Path_To_Candidates
+-o /Your_Path_To_Candidates_Folder
 
 ```
 
+
+## Quality control and adapter trimming
+
+```bash
+# Generate snakemake config file for quality control and adapter trimming.
+offtracker_qc.py -t 4 \
+-f /Your_Path_To_Input_Folder \
+--subfolder 0
+
+cd /Your_Path_To_Input_Folder/Trimmed_data
+snakemake -np # dry run to check whether everything is alright
+nohup snakemake --cores 16 1>${outdir}/sm_qc.log 2>&1 &
+
+"""
+Set “--subfolder 0” if the file structure is like: 
+| - Input_Folder
+  | - sample1_R1.fastq.gz
+  | - sample1_R2.fastq.gz
+  | - sample2_R1.fastq.gz
+  | - sample2_R2.fastq.gz
+Set “--subfolder 1” if the file structure is like:
+| - Input_Folder
+  | - Sample1_Folder
+    | - sample1_R1.fastq.gz
+    | - sample1_R2.fastq.gz
+  | - Sample2_Folder
+    | - sample2_R1.fastq.gz
+    | - sample2_R2.fastq.gz
+
+The script “offtracker_qc.py” will create a “Trimmed_data” folder under /Your_Path_To_Input_Folder. 
+If “-o /Your_Path_To_Output” is set, the output will be redirected to /Your_Path_To_Output.
+"""
+```
+
 ## Strand-specific mapping of Tracking-seq data 
 
 ```bash
-# Generate snakemake config file 
-# --subfolder: If different samples are in seperate folders, set this to 1
-# if -o is not set, the output will be in the same folder as the fastq files
+
+# Generate snakemake config file for mapping
+# Results will be generated in /Your_Path_To_Output, if -o is not set, the output will be in the same folder as the fastq files
 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 \
+-f /Your_Path_To_Trimmed_Data \
 -o /Your_Path_To_Output \ 
 --subfolder 0 
 
+# Warning: Do not contain "fastq" or "fq" in the folder name, otherwise the program may treat the folder as a fastq file
+# This problem may be fixed in the future
+
 # Run the snakemake program
 cd /Your_Path_To_Fastq
 snakemake -np # dry run
-nohup snakemake --cores 16 1>snakemake.log 2>snakemake.err &
+nohup snakemake --cores 16 1>sm_mapping.log 2>sm_mapping.err &
 
 ## about cores
 # --cores of snakemake must be larger than -t of offtracker_config.py
@@ -98,7 +136,7 @@ nohup snakemake --cores 16 1>snakemake.log 2>snakemake.err &
 ## Analyzing the genome-wide 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
+# In this part, multiple samples in the same condition can be analyzed in a single run by pattern recognition of sample names
 
 offtracker_analysis.py -g hg38 --name "VEGFA2" \
 --exp 'Cas9_VEGFA2' \
@@ -127,19 +165,18 @@ offtracker_plot.py --result Your_Offtracker_Result_CSV \
 --sgrna 'GACCCCCTCCACCCCGCCTC' --pam 'NGG'
 
 # The default output is a pdf file with Offtracker_result_{outname}.pdf
-# Change the suffix of the output file to change the format (e.g.: .png)
+# Assigning a specific output file with another suffix can change the format. e.g., "--output Offtracker_plot.png" will generate a png file.
 # The orange dash line indicates the empirical threshold of Track score = 2
 # Empirically, the off-target sites with Track score < 2 are less likely to be real off-target sites.
 ```
 
 
-## Note1
+## Note1, when not using hg38 or mm10
 
-The default setting only includes chr1-chr22, chrX, chrY, and chrM. Please make sure the reference genome contains "chr" at the beginning. 
+The default setting only includes chr1-chr22, chrX, chrY, and chrM. (only suitable for human and mouse) \
+If you are using reference genomes without "chr" at the beginning, or want to analyze all chromosomes or other species, you can set "--ignore_chr" when running offtracker_config.py to skip chromosome filter.
 
-Currently, this software is only ready-to-use for mm10 and hg38. For any other genome, e.g., hg19, please add genome size file named "hg19.chrom.sizes" to .\offtracker\mapping and instal manually. Besides, add "--blacklist none" or "--blacklist Your_Blacklist" (e.g., ENCODE blacklist) when running offtracker_config.py, because we only provide blacklists for mm10 and hg38.
-
-If you have a requirement for species other than human/mouse, please post an issue.
+Currently, this software is only ready-to-use for mm10 and hg38. For any other genome, e.g., hg19, please add a genome size file named "hg19.chrom.sizes" to .\offtracker\utility. Besides, add "--blacklist none" or "--blacklist Your_Blacklist" (e.g., ENCODE blacklist) when running offtracker_config.py, because we only include blacklists for mm10 and hg38.
 
 ## Note2
 
@@ -172,6 +209,7 @@ These files can be visualized in genome browser like IGV:
 
 ![signal](https://github.com/Lan-lab/offtracker/blob/main/example_output/signals_example.png?raw=true)
 
+The signal (coverage) for each sample is normalized to 1e7/total_reads. As only reads mapping to chr6 were extracted in the example data, the signal range is much higher than that of the whole genome samples. 
 
 ## Whole genome off-target analysis
 
@@ -183,7 +221,13 @@ After that, you can visualize the off-target sites with their genomic sequence (
 
 # Citation
 
+If you use Tracking-seq or OFF-TRACKER in your research, please cite the following paper:
+
+Zhu, M., Xu, R., Yuan, J., Wang, J. et al. Tracking-seq reveals the heterogeneity of off-target effects in CRISPR–Cas9-mediated genome editing. Nat Biotechnol (2024). https://doi.org/10.1038/s41587-024-02307-y
 
+The signal visualization of .bw file here was generated by the Integrative Genomics Viewer (IGV) software. The signal visualization in the Tracking-seq article above was generated by either IGV or pyGenomeTracks:
 
+Robinson, J., Thorvaldsdóttir, H., Winckler, W. et al. Integrative genomics viewer. Nat Biotechnol 29, 24–26 (2011). https://doi.org/10.1038/nbt.1754
 
+Lopez-Delisle L, Rabbani L, Wolff J, Bhardwaj V, Backofen R, Grüning B, Ramírez F, Manke T. pyGenomeTracks: reproducible plots for multivariate genomic data sets. Bioinformatics. 2020 Aug 3:btaa692. doi: 10.1093/bioinformatics/btaa692.
 

{offtracker-2.7.10 → offtracker-2.10.0}/README.md

@@ -1,6 +1,6 @@
-# OFF-TRACKER
+# Offtracker
 
-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).
+Offtracker 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
 
@@ -10,9 +10,10 @@ OFF-TRACKER is an end to end pipeline of Tracking-seq data analysis for detectin
 ## Dependency
 
 ```bash
-# We recommend creating a new enviroment using mamba/conda to avoid compatibility problems
+# We recommend creating a new environment 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
+# Windows systems may not be compatible with pybedtools.
+mamba create -n offtracker -c bioconda blast snakemake pybedtools chromap
 ```
 
 
@@ -46,32 +47,69 @@ 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)
-# --name: the name of the sgRNA, which will be used in the following analysis
+# --name: a user-defined name of the sgRNA, which will be used in the following analysis.
 offtracker_candidates.py -t 8 -g hg38 \
 -r /Your_Path_To_Reference/hg38_genome.fa \
 -b /Your_Path_To_Reference/hg38_genome.blastdb \
 --name 'VEGFA2' --sgrna 'GACCCCCTCCACCCCGCCTC' --pam 'NGG' \
--o /Your_Path_To_Candidates
+-o /Your_Path_To_Candidates_Folder
 
 ```
 
+
+## Quality control and adapter trimming
+
+```bash
+# Generate snakemake config file for quality control and adapter trimming.
+offtracker_qc.py -t 4 \
+-f /Your_Path_To_Input_Folder \
+--subfolder 0
+
+cd /Your_Path_To_Input_Folder/Trimmed_data
+snakemake -np # dry run to check whether everything is alright
+nohup snakemake --cores 16 1>${outdir}/sm_qc.log 2>&1 &
+
+"""
+Set “--subfolder 0” if the file structure is like: 
+| - Input_Folder
+  | - sample1_R1.fastq.gz
+  | - sample1_R2.fastq.gz
+  | - sample2_R1.fastq.gz
+  | - sample2_R2.fastq.gz
+Set “--subfolder 1” if the file structure is like:
+| - Input_Folder
+  | - Sample1_Folder
+    | - sample1_R1.fastq.gz
+    | - sample1_R2.fastq.gz
+  | - Sample2_Folder
+    | - sample2_R1.fastq.gz
+    | - sample2_R2.fastq.gz
+
+The script “offtracker_qc.py” will create a “Trimmed_data” folder under /Your_Path_To_Input_Folder. 
+If “-o /Your_Path_To_Output” is set, the output will be redirected to /Your_Path_To_Output.
+"""
+```
+
 ## Strand-specific mapping of Tracking-seq data 
 
 ```bash
-# Generate snakemake config file 
-# --subfolder: If different samples are in seperate folders, set this to 1
-# if -o is not set, the output will be in the same folder as the fastq files
+
+# Generate snakemake config file for mapping
+# Results will be generated in /Your_Path_To_Output, if -o is not set, the output will be in the same folder as the fastq files
 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 \
+-f /Your_Path_To_Trimmed_Data \
 -o /Your_Path_To_Output \ 
 --subfolder 0 
 
+# Warning: Do not contain "fastq" or "fq" in the folder name, otherwise the program may treat the folder as a fastq file
+# This problem may be fixed in the future
+
 # Run the snakemake program
 cd /Your_Path_To_Fastq
 snakemake -np # dry run
-nohup snakemake --cores 16 1>snakemake.log 2>snakemake.err &
+nohup snakemake --cores 16 1>sm_mapping.log 2>sm_mapping.err &
 
 ## about cores
 # --cores of snakemake must be larger than -t of offtracker_config.py
@@ -86,7 +124,7 @@ nohup snakemake --cores 16 1>snakemake.log 2>snakemake.err &
 ## Analyzing the genome-wide 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
+# In this part, multiple samples in the same condition can be analyzed in a single run by pattern recognition of sample names
 
 offtracker_analysis.py -g hg38 --name "VEGFA2" \
 --exp 'Cas9_VEGFA2' \
@@ -115,19 +153,18 @@ offtracker_plot.py --result Your_Offtracker_Result_CSV \
 --sgrna 'GACCCCCTCCACCCCGCCTC' --pam 'NGG'
 
 # The default output is a pdf file with Offtracker_result_{outname}.pdf
-# Change the suffix of the output file to change the format (e.g.: .png)
+# Assigning a specific output file with another suffix can change the format. e.g., "--output Offtracker_plot.png" will generate a png file.
 # The orange dash line indicates the empirical threshold of Track score = 2
 # Empirically, the off-target sites with Track score < 2 are less likely to be real off-target sites.
 ```
 
 
-## Note1
+## Note1, when not using hg38 or mm10
 
-The default setting only includes chr1-chr22, chrX, chrY, and chrM. Please make sure the reference genome contains "chr" at the beginning. 
+The default setting only includes chr1-chr22, chrX, chrY, and chrM. (only suitable for human and mouse) \
+If you are using reference genomes without "chr" at the beginning, or want to analyze all chromosomes or other species, you can set "--ignore_chr" when running offtracker_config.py to skip chromosome filter.
 
-Currently, this software is only ready-to-use for mm10 and hg38. For any other genome, e.g., hg19, please add genome size file named "hg19.chrom.sizes" to .\offtracker\mapping and instal manually. Besides, add "--blacklist none" or "--blacklist Your_Blacklist" (e.g., ENCODE blacklist) when running offtracker_config.py, because we only provide blacklists for mm10 and hg38.
-
-If you have a requirement for species other than human/mouse, please post an issue.
+Currently, this software is only ready-to-use for mm10 and hg38. For any other genome, e.g., hg19, please add a genome size file named "hg19.chrom.sizes" to .\offtracker\utility. Besides, add "--blacklist none" or "--blacklist Your_Blacklist" (e.g., ENCODE blacklist) when running offtracker_config.py, because we only include blacklists for mm10 and hg38.
 
 ## Note2
 
@@ -160,6 +197,7 @@ These files can be visualized in genome browser like IGV:
 
 ![signal](https://github.com/Lan-lab/offtracker/blob/main/example_output/signals_example.png?raw=true)
 
+The signal (coverage) for each sample is normalized to 1e7/total_reads. As only reads mapping to chr6 were extracted in the example data, the signal range is much higher than that of the whole genome samples. 
 
 ## Whole genome off-target analysis
 
@@ -171,7 +209,13 @@ After that, you can visualize the off-target sites with their genomic sequence (
 
 # Citation
 
+If you use Tracking-seq or OFF-TRACKER in your research, please cite the following paper:
+
+Zhu, M., Xu, R., Yuan, J., Wang, J. et al. Tracking-seq reveals the heterogeneity of off-target effects in CRISPR–Cas9-mediated genome editing. Nat Biotechnol (2024). https://doi.org/10.1038/s41587-024-02307-y
 
+The signal visualization of .bw file here was generated by the Integrative Genomics Viewer (IGV) software. The signal visualization in the Tracking-seq article above was generated by either IGV or pyGenomeTracks:
 
+Robinson, J., Thorvaldsdóttir, H., Winckler, W. et al. Integrative genomics viewer. Nat Biotechnol 29, 24–26 (2011). https://doi.org/10.1038/nbt.1754
 
+Lopez-Delisle L, Rabbani L, Wolff J, Bhardwaj V, Backofen R, Grüning B, Ramírez F, Manke T. pyGenomeTracks: reproducible plots for multivariate genomic data sets. Bioinformatics. 2020 Aug 3:btaa692. doi: 10.1093/bioinformatics/btaa692.
 

{offtracker-2.7.10 → offtracker-2.10.0}/offtracker/X_offplot.py

@@ -12,6 +12,7 @@ dict_rc = {
 rcParams.update(dict_rc)
 
 # 2024.06.03. offtable 添加 threshold 分界线，默认为 None，常用的是 2
+
 def offtable(offtargets, target_guide,  length_pam = 3, 
                          col_seq='best_target', col_score='track_score', col_mismatch='mismatch', col_loc='target_location',
                          title=None, font='Arial', font_size=9, 
@@ -28,12 +29,15 @@ def offtable(offtargets, target_guide,  length_pam = 3,
         '-': 'orange'
     }
 
+
+
     # If offtargets is a DataFrame, convert to list of dictionaries
     if isinstance(offtargets, pd.DataFrame):
         if threshold is not None:
             n_positive = sum(offtargets[col_score]>=threshold)
         offtargets = offtargets.to_dict(orient='records')
 
+
     # Configuration
     # title=None
     # font='Arial'
@@ -106,10 +110,16 @@ def offtable(offtargets, target_guide,  length_pam = 3,
             ax.text(x + box_size_x / 2, y + box_size_y / 2, "." if c == target_guide[i] else c, ha='center', va='center', family=font, fontsize=font_size, weight='bold')
 
         # Annotations for score, mismatches, and location coordinates
-        ax.text(x_offset + (len(target_guide) + 2) * box_size_x, y + box_size_y / 2, round(seq[col_score],2), ha='center', va='center', family=font, fontsize=font_size)
+        # 2025.06.05. 如果有负数的，用红色显示
+        if seq[col_score]>0:
+            text_color = 'black'
+        else:
+            text_color = 'red'
+        ax.text(x_offset + (len(target_guide) + 2) * box_size_x, y + box_size_y / 2, round(seq[col_score],2), ha='center', va='center', family=font, fontsize=font_size, color=text_color)
         #ax.text(x_offset + (len(target_guide) + 7) * box_size_x, y + box_size_y / 2, "Target" if seq[col_mismatch] == 0 else seq[col_mismatch], ha='center', va='center', family=font, fontsize=font_size, color='red' if seq[col_mismatch] == 0 else 'black')
-        ax.text(x_offset + (len(target_guide) + 4) * box_size_x, y + box_size_y / 2, seq[col_loc], ha='left', va='center', family=font, fontsize=font_size)
+        ax.text(x_offset + (len(target_guide) + 4) * box_size_x, y + box_size_y / 2, seq[col_loc], ha='left', va='center', family=font, fontsize=font_size, color=text_color)
 
+        
     # add a vertical line to indicate the PAM
     x_line = x_offset + (len(target_guide) - length_pam) * box_size_x
     y_start = y_offset # + box_size_y / 2 
@@ -123,6 +133,7 @@ def offtable(offtargets, target_guide,  length_pam = 3,
         thresh_y = y_offset + (n_positive+1) * (box_size_y + box_gap) - box_gap*0.5
         ax.hlines(y=thresh_y, xmin=thresh_x_start, xmax=thresh_x_end, color='orange', linestyle='--')
 
+
     # Styling and save
     ax.set_xlim(0, width*1.1) # location 的文字太长了，所以要加长一点
     ax.set_ylim(height, 0)

{offtracker-2.7.10 → offtracker-2.10.0}/offtracker/X_sequence.py

@@ -3,6 +3,7 @@ import math
 import pandas as pd
 from itertools import product
 import numpy as np
+import os, glob
 
 ambiguous_nt = {'A': ['A'],
                 'T': ['T'],
@@ -19,7 +20,7 @@ ambiguous_nt = {'A': ['A'],
                 'H': ['A', 'C', 'T'],
                 'D': ['A', 'G', 'T'],
                 'B': ['C', 'G', 'T'],
-                'N': ['A', 'T', 'C', 'G']}
+                'N': ['A', 'C', 'G', 'T']}
 
 def is_seq_valid(sequence, extra=True, ambiguous_nt=ambiguous_nt):
     if extra:
@@ -43,12 +44,24 @@ def possible_seq(sequence):
         raise KeyError(f'Unvalid character \'{valid_check}\' in sequence')
     return sequences
 
+# 包含 degenerate base pairs
+def get_base_score(base1, base2, exact_score=2, partial_match=2, mismatch_score=0.01):
+    base1 = ambiguous_nt[base1]
+    base2 = ambiguous_nt[base2]
+    if base1 == base2:
+        return exact_score
+    if list(np.union1d(base1,base2)) == base1 or list(np.union1d(base1,base2)) == base2:
+        # 其中一个是子集，注意顺序不一致会导致不等，所以必须排好序
+        return partial_match
+    return mismatch_score
+
+
 def complement(seq):
-    complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'N': 'N', '-':'-',
+    dict_complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'N': 'N', '-':'-',
                   'M': 'K', 'R': 'Y', 'W': 'W', 'S': 'S', 'Y': 'R', 'K':'M',
                   'V': 'B', 'H': 'D', 'D': 'H', 'B': 'V'} 
     bases = list(seq) 
-    letters = [complement[base] for base in bases] 
+    letters = [dict_complement[base] for base in bases] 
     return ''.join(letters)
 
 def reverse(seq):
@@ -100,14 +113,107 @@ def add_ID(df, chr_col=0, midpoint='cleavage_site'):#, midpoint='midpoint'):
 	df.loc[point_tail>=500,'ID_2'] = df[chr_col_name] + ':' + (point_head+1).astype(str)
 	return df
 
+
+
+def detect_fastq(folder, n_subfolder, NGS_type='paired-end'):
+    """
+    搜索 folder 的 n级子目录下的所有 fastq/fastq.gz/fq/fq.gz 文件
+    paired-end 模式 : 识别 2.fq/2.fastq 为 paired-end 的 R2 文件，并验证对应 R1 文件
+    single-end 模式 : 所有 fastq/fastq.gz/fq/fq.gz 文件都视为 single-end 文件
+    
+    不建议 2. 和 fq/fastq 之间有其他字符，如 2.trimmed.fq.gz，因为中间字符不确定，使用通配符容易误判文件名其他的2.
+    样本名不要带点，建议用_分割特征，同特征内分割不要用_可以用-，如 sample_day-hour_type_batch_rep_1.fq.gz
+
+    Input
+    ----------
+    folder : 根目录
+    n_subfolder : n级子目录
+
+    Parameter
+    ----------
+    NGS_type : 'paired-end' or 'single-end'
+    
+    Output
+    ----------
+    sample_names : 识别的样品名
+    files_R1 : R1文件的完整路径
+    files_R2 : R2文件的完整路径
+
+    """
+    # import os, sys, glob
+    # import pandas as pd
+    if NGS_type == 'paired-end':
+        print('paired-end mode')
+        files_R2 = []
+        # 支持四种文件扩展名
+        # 个人习惯包含绝对路径
+        for fastq in ['*2.fq','*2.fastq','*2.fq.gz','*2.fastq.gz']:
+            fq_files = glob.glob( os.path.join(folder, n_subfolder*'*/', fastq ) )
+            print(f'{len(fq_files)} {fastq[2:]} samples detected')
+            files_R2.extend( fq_files )
+        #
+        if len(files_R2) > 0:
+            files_R2 = pd.Series(files_R2).sort_values().reset_index(drop=True)
+            # 拆分文件名
+            suffix = files_R2.str.extract('(\.fastq.*|\.fq.*)',expand=False)
+            prefix = files_R2.str.extract('(.*)(?:.fq|.fastq)',expand=False)
+            # 将 prefix 进一步拆分为 sample_dir （真样品名） 和 nametype （某种统一后缀），支持五种样本名后缀
+            nametype = []
+            sample_dir = []
+            for a_prefix in prefix:
+                for a_type in ['_trimmed_2', '_2_val_2','_R2_val_2','_R2','_2']:
+                    len_type = len(a_type)
+                    if a_prefix[-len_type:] == a_type:
+                        nametype.append(a_type)
+                        sample_dir.append(a_prefix[:-len_type])
+                        break
+            assert len(nametype) == len(files_R2), 'The file name pattern is invaild!'
+            nametype = pd.Series(nametype)
+            sample_dir = pd.Series(sample_dir)
+            # 根据 R2 文件，检查 R1 文件是否存在
+            files_R1 = sample_dir + nametype.str.replace('2','1') + suffix
+            for i in range(len(files_R1)):
+                assert os.path.exists(files_R1[i]), f'{files_R1[i]} not found!'
+            sample_names = sample_dir.apply(os.path.basename)
+        else:
+            print('No paired-end samples detected!')
+            sample_names = 'no sample'
+            files_R1 = []
+
+    elif NGS_type == 'single-end':
+        print('single-end mode')
+        files_R1 = []
+        files_R2 = [] # 占位
+        # 支持四种文件扩展名
+        # 个人习惯包含绝对路径
+        for fastq in ['*.fq','*.fastq','*.fq.gz','*.fastq.gz']:
+            fq_files = glob.glob( os.path.join(folder, n_subfolder*'*/', fastq ) )
+            print(f'{len(fq_files)} {fastq[1:]} samples detected')
+            files_R1.extend( fq_files )
+        files_R1 = pd.Series(files_R1).sort_values()
+        #
+        if len(files_R1) > 0:
+            # 拆分文件名
+            suffix = files_R1.str.extract('(\.fastq.*|\.fq.*)',expand=False)
+            prefix = files_R1.str.extract('(.*)(?:.fq|.fastq)',expand=False)
+            # 单端模式下，所有前缀都视为样品名
+            sample_names = prefix.apply(os.path.basename)
+        else:
+            print('No single-end samples detected!')
+            sample_names = 'no sample'
+            files_R1 = []
+
+    return sample_names, files_R1, files_R2
+
+
 def sgRNA_alignment(a_key, sgRNA, seq, frag_len, DNA_matrix=None, mismatch_score = 0.01, return_align=False):
     from Bio import pairwise2
     import numpy as np
     if DNA_matrix is None:
-        DNA_matrix = {('A','A'): 2, ('A','T'):0.01, ('A','C'):0.01, ('A','G'):0.01, ('A','N'):0.01,
-                    ('T','T'): 2, ('T','A'):0.01, ('T','C'):0.01, ('T','G'):0.01, ('T','N'):0.01,
-                    ('G','G'): 2, ('G','A'):0.01, ('G','C'):0.01, ('G','T'):0.01, ('G','N'):0.01,
-                    ('C','C'): 2, ('C','A'):0.01, ('C','G'):0.01, ('C','T'):0.01, ('C','N'):0.01,
+        DNA_matrix = {('A','A'): 2, ('A','T'):0.01, ('A','C'):0.01, ('A','G'):0.01, ('A','N'):2,
+                    ('T','T'): 2, ('T','A'):0.01, ('T','C'):0.01, ('T','G'):0.01, ('T','N'):2,
+                    ('G','G'): 2, ('G','A'):0.01, ('G','C'):0.01, ('G','T'):0.01, ('G','N'):2,
+                    ('C','C'): 2, ('C','A'):0.01, ('C','G'):0.01, ('C','T'):0.01, ('C','N'):2,
                     ('N','N'): 2, ('N','C'):2, ('N','A'): 2, ('N','G'): 2, ('N','T'): 2}        
     # a_key 是 pybedtools 得到的位置 chrA:X-Y 而 X 数字会往左多1bp
     alignments = pairwise2.align.localds( sgRNA, seq, DNA_matrix, -2, -2, penalize_extend_when_opening=False)

{offtracker-2.7.10 → offtracker-2.10.0}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.7.10"
+__version__ = "2.10.0"
 # 2023.08.11. v1.1.0	adding a option for not normalizing the bw file
 # 2023.10.26. v1.9.0	prerelease for v2.0
 # 2023.10.27. v2.0.0	大更新，还没微调
@@ -27,4 +27,10 @@ __version__ = "2.7.10"
 # 2024.01.23. v2.7.7	Snakefile_offtracker: add --fixedStep to bigwigCompare for not merging neighbouring bins with equal values.
 # 2024.02.01. v2.7.8	逐步添加 X_offplot.py 功能
 # 2024.06.02. v2.7.9	添加 offtracker_plot.py
-# 2024.06.03. v2.7.10	修复 bugs，offtable 添加 threshold = 2 的分界
+# 2024.06.03. v2.7.10	修复 bugs，offtable 添加 threshold = 2 的分界
+# 2024.06.04. v2.7.11	readme 修改
+# 2024.11.19. v2.7.12	offtracker_candidates.py 新增 --pam_location 参数指定 upstream 或 downstream，用于非 Cas9 情况
+# 2025.04.25. v2.8.0	修复了 offtracker candidates 会把小写序列转换成 N 的 bug
+# 2025.05.22. v2.9.0	翻新部分代码结构
+# 2025.06.05. v2.10.0	增加了QC模块。保留了负数score的记录，并在plot时显示为红字。增加了 "--ignore_chr" 用于跳过common chr过滤。
+

offtracker-2.10.0/offtracker/snakefile/Snakefile_QC.smk

@@ -0,0 +1,66 @@
+# 更新记录:
+# 2022.05.04. v1.0:    初步运行, fastp + multiqc
+# 2024.01.17. v2.0:    翻新结构，匹配 X_NGS 框架
+
+# 参数列表
+configfile: "config.yaml"
+
+### config['files_R1'], config['files_R2'] 为 dict型
+
+# # fastq 信息
+_files_R1 = config['files_R1'] # dict型, key 为 sample
+_files_R2 = config['files_R2'] # dict型, key 为 sample
+# # 输入输出文件夹
+# config['input_dir']
+_output_dir = config["output_dir"]
+# # 运行参数
+_thread = config['thread']
+# config['utility_dir']
+
+import os
+
+############################
+# conditional output_files #
+############################
+output_HT = expand( os.path.join(_output_dir,"{sample}_fastp.html"), sample=_files_R1)
+output_JS = expand( os.path.join(_output_dir,"{sample}_fastp.json"), sample=_files_R1)
+output_MQC = os.path.join(_output_dir,"MultiQC_Report_Raw.html")
+output_R1 = expand( os.path.join(_output_dir,"{sample}_trimmed_1.fq.gz"), sample=_files_R1) # dict 会自动迭代 keys
+output_R2 = expand( os.path.join(_output_dir,"{sample}_trimmed_2.fq.gz"), sample=_files_R1)
+
+output_files = output_HT + output_JS + [output_MQC] + output_R1 + output_R2
+
+rule all:
+    input:
+        output_files
+
+#######################
+## fastp and multiQC ##
+#######################
+rule QCtrim:
+    input:
+        R1=lambda w: _files_R1[w.sample],
+        R2=lambda w: _files_R2[w.sample]
+    threads:
+        _thread
+    output:
+        R1=os.path.join(_output_dir,"{sample}_trimmed_1.fq.gz"),
+        R2=os.path.join(_output_dir,"{sample}_trimmed_2.fq.gz"),
+        HT=os.path.join(_output_dir,"{sample}_fastp.html"),
+        JS=os.path.join(_output_dir,"{sample}_fastp.json")
+    shell:
+        """
+        fastp -i {input.R1} -I {input.R2} -o {output.R1} -O {output.R2} \
+        -h {wildcards.sample}_fastp.html -j {wildcards.sample}_fastp.json \
+        --length_required 10 --thread {threads} --detect_adapter_for_pe --disable_quality_filtering
+        """
+
+rule multiqc:
+    input:
+        expand( os.path.join(_output_dir,"{sample}_fastp.html"), sample=_files_R1 )
+    threads:
+        _thread
+    output:
+        os.path.join(_output_dir,"MultiQC_Report_Raw.html")
+    shell:
+        "multiqc {_output_dir} -n MultiQC_Report_Raw --outdir {_output_dir}"