offtracker 2.7.7__zip → 2.7.10__zip

offtracker-2.7.7/offtracker/X_offplot.py

@@ -1,123 +0,0 @@
-import matplotlib.pyplot as plt
-import matplotlib.patches as patches
-import pandas as pd
-
-def offtable(offtargets, target_guide, 
-                         col_seq='best_target', col_score='track_score', col_mismatch='mismatch', col_loc='target_location',
-                         title=None, font='Arial', font_size=9, 
-                         box_size_x=15, box_size_y=20, box_gap=1,
-                         x_offset=15, y_offset=35, dpi=100, savefig=None):
-    # Facecolor
-    color_dict = {
-        'A': 'lightgreen',
-        'T': 'lightblue',
-        'C': 'lightcoral',
-        'G': 'lightgoldenrodyellow',
-        'N': 'lightgrey',
-        '—': 'orange',
-        '-': 'orange'
-    }
-
-    # If offtargets is a DataFrame, convert to list of dictionaries
-    if isinstance(offtargets, pd.DataFrame):
-        offtargets = offtargets.to_dict(orient='records')
-
-    # Configuration
-    # title=None
-    # font='Arial'
-    # font_size = 9
-    # box_size_x = 15 # 一个碱基图形的宽度
-    # box_size_y = 20 # 一个碱基图形的高度
-    # box_gap = 1 # 两行之间的间隔
-    # x_offset = 15
-    # y_offset = 35
-    # dpi=100
-    # col_seq='best_target'
-    # col_score='track_score'
-    # col_mismatch='mismatch'
-    # col_loc='target_location'
-    width = box_size_x * (len(target_guide) + 15)
-    height = y_offset + (len(offtargets) + 2) * (box_size_y + box_gap)
-    fig = plt.figure(figsize=(width / 100.0, height / 100.0), dpi=dpi)
-    ax = fig.add_subplot(111)
-
-    # Plot a title
-    ax.text(x_offset, 25, "Off-targets table" if title is None else f"{title}", fontsize=14, family=font)
-
-    # Plot the reference sequence
-    for i, c in enumerate(target_guide):
-        x = x_offset + i * box_size_x
-        y = y_offset
-        base_color = color_dict.get(c, 'purple') # Default to purple if base is not recognized
-        ax.add_patch(patches.Rectangle((x, y), box_size_x, box_size_y, facecolor=base_color))
-        ax.text(x + box_size_x / 2, y + box_size_y / 2, c, ha='center', va='center', family=font, fontsize=font_size)
-    # add column annotations
-    ax.text(x_offset + (len(target_guide) + 2) * box_size_x, y_offset + box_size_y / 4, 'Track\nScore', ha='center', va='center', family=font, fontsize=font_size*1.1)
-    #ax.text(x_offset + (len(target_guide) + 7) * box_size_x, y_offset + box_size_y / 2, 'Mismatch', ha='center', va='center', family=font, fontsize=font_size*1.1)
-    ax.text(x_offset + (len(target_guide) + 4) * box_size_x, y_offset + box_size_y / 2, 'Coordinates', ha='left', va='center', family=font, fontsize=font_size*1.1)
-
-    # Plot aligned sequences
-    # 目前有个bug：脱靶序列如果有 insertion，长度会不一致，而且也没想到画图怎么画，只能是默认删掉第一个碱基
-    for j, seq in enumerate(offtargets):
-        y = y_offset + (j + 1) * (box_size_y + box_gap)
-        # 长度不一致的情况
-        len_out = len(seq[col_seq]) - len(target_guide)
-        if len_out > 0:
-            if len_out > 1:
-                print(f"Warning: {seq[col_seq]} is {len_out} longer than {target_guide}")
-            # 通过比较删除开头的碱基和最后的碱基，看哪个更接近target_guide
-            delete_first = seq[col_seq][len_out:]
-            delete_last = seq[col_seq][:-len_out]
-            # 计算两个序列和target_guide的hamming distance
-            hamming_first = sum([1 for i, c in enumerate(delete_first) if c != target_guide[i]])
-            hamming_last = sum([1 for i, c in enumerate(delete_last) if c != target_guide[i]])
-            # 选择hamming distance小的那个序列
-            if hamming_first < hamming_last:
-                seq[col_seq] = delete_first
-            else:
-                seq[col_seq] = delete_last
-        elif len_out < 0:
-            print(f"Warning: {seq[col_seq]} is {-len_out} shorter than {target_guide}")
-            
-        for i, c in enumerate(seq[col_seq]):
-            # gap 的 - (minus sign) 太短了，所以替换成 — (em dash)
-            if c == '-':
-                c = '—'
-            x = x_offset + i * box_size_x
-            base_color = color_dict.get(c, 'purple') # Default to purple if base is not recognized
-            if c == target_guide[i]:
-                ax.add_patch(patches.Rectangle((x, y), box_size_x, box_size_y, facecolor='white')) # same
-            elif target_guide[i] == 'N':
-                ax.add_patch(patches.Rectangle((x, y), box_size_x, box_size_y, facecolor='white')) # N in target
-            else:
-                ax.add_patch(patches.Rectangle((x, y), box_size_x, box_size_y, facecolor=base_color))
-            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)
-        #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)
-
-    # add a vertical line to indicate the PAM
-    x_line = x_offset + (len(target_guide) - 3) * box_size_x
-    y_start = y_offset # + box_size_y / 2 
-    y_end = y_start + (len(offtargets)+1) * (box_size_y + box_gap)
-    ax.vlines(x=x_line, ymin=y_start, ymax=y_end, color='indianred', 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)
-    ax.axis('off')
-
-    # # This will make the subplot(s) expand to fill the entire figure area, with no padding on any side. 
-    # # In brief, make the plot bigger (not influence the font size)
-    plt.subplots_adjust(left=0, right=1, top=1, bottom=0)
-    if savefig is not None:
-        plt.savefig(savefig, dpi=dpi)
-    plt.show()
-    return ax
-
-
-
-
-

offtracker-2.7.7/offtracker/_version.py

@@ -1,27 +0,0 @@
-__version__ = "2.7.7"
-# 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
-# 2023.10.28. v2.1.0 修复bug，增加计算信号长度的功能
-# 2023.10.28. v2.2.0 修复bug，改变计算信号长度的算法
-# 2023.10.29. v2.3.0 增加 overall signal 计算
-# 2023.11.01. v2.3.1 增加 signal_only 选项
-# 2023.11.02. v2.3.2 修改 sample signal 和 group mean 的计算顺序
-# 2023.11.04. v2.3.3 修复 overall score 标准化时排序错误的问题
-# 2023.11.05. v2.3.4 修复判断单边溢出信号时的列名选取错误
-# 2023.11.13. v2.3.5 微调 track score
-# 2023.12.05. v2.3.6 candidates 增加 cleavage site，修正 alignment 有 deletion 会错位的 bug
-# 2023.12.05. v2.3.7 用 cleavage site 代替 midpoint # 还没改完
-# 2023.12.07. v2.3.8 df_score 增加 df_exp, df_ctr 各自列。修复没 df_ctr 时的 bug。track score 用 proximal
-# 2023.12.09. v2.4.0 为了兼顾 proximal 和 overall，当 normalized overall signal 高于 2 时，增加 overall signal 的加分
-# 2023.12.09. v2.5.0 尝试新的加权位置
-# 2023.12.10. v2.6.0 加入 trackseq v4 的计算分支，即考虑 Region 内的 positive_pct，避免短而尖锐的信号
-# 2023.12.10. v2.6.1 有些非特异信号数值很大，如果在 control 组是大负数，可能导致减 control 后假高信号，因此给负数一个 clip
-# 2023.12.30. v2.7.0 增加 X_offplot 模块，用于绘图
-# 2023.12.31. v2.7.1 control 的负数值 clip 由 -5 改为 -1，进一步减少假阳性。另外不加 overall 了
-# 2024.01.01. v2.7.2 权重改为 proximal + pct = 1 + 1. 防信号外溢假阳性标准由<0改为<=0
-# 2024.01.02. v2.7.3 flank regions 默认值改为 1000 2000 3000 5000。之前 control 的负数值 clip 相当于直接在 final score，现在改为每个单独 clip 后重新算 score，默认值为 CtrClip=-0.5
-# 2024.01.03. v2.7.4 更新了 blacklist.bed
-# 2024.01.04. v2.7.5 更新了 hg38 blacklist.bed
-# 2024.01.12. v2.7.6 修复小bug，输出 fdr 改为 <0.05。
-# 2024.01.23. v2.7.7 Snakefile_offtracker: add --fixedStep to bigwigCompare for not merging neighbouring bins with equal values.

offtracker-2.7.7/offtracker.egg-info/PKG-INFO

@@ -1,146 +0,0 @@
-Metadata-Version: 2.1
-Name: offtracker
-Version: 2.7.7
-Summary: Track-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 Track-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 Track-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 Track-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 Track-seq result.
-