offtracker 2.10.3__zip → 2.10.4__zip

{offtracker-2.10.3/offtracker.egg-info → offtracker-2.10.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.3
+Version: 2.10.4
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu
@@ -25,7 +25,7 @@ Offtracker is an end to end pipeline of Tracking-seq data analysis for detecting
 # 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 
 # Windows systems may not be compatible with pybedtools.
-mamba create -n offtracker -c bioconda blast snakemake pybedtools chromap
+mamba create -n offtracker -c bioconda blast snakemake pybedtools deeptools chromap
 ```
 
 

{offtracker-2.10.3 → offtracker-2.10.4}/README.md

@@ -13,7 +13,7 @@ Offtracker is an end to end pipeline of Tracking-seq data analysis for detecting
 # 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 
 # Windows systems may not be compatible with pybedtools.
-mamba create -n offtracker -c bioconda blast snakemake pybedtools chromap
+mamba create -n offtracker -c bioconda blast snakemake pybedtools deeptools chromap
 ```
 
 

{offtracker-2.10.3 → offtracker-2.10.4}/offtracker/X_offplot.py

@@ -349,131 +349,6 @@ def igv_single(location, file, fig=None, track_name='', track_name_loc='left',
     return fig, track_position
 
 
-from statsmodels.nonparametric.smoothers_lowess import lowess
-def signal_length(df_bdg_chr, chrom, cleavage_site, end='end',start='start',value='residual', 
-                  flank_max=100000, bin_size=100, window_size=3000,signal_threshold = 0.3, show_plot=False, savefig=None, save_dpi=100):
-    df_bdg_chr = df_bdg_chr[df_bdg_chr['chr']==chrom]
-    ## left
-    # 取 cleavage_site 附近的数据
-    df_bdg_chr_L = df_bdg_chr[ (df_bdg_chr[end] >= cleavage_site-flank_max) & (df_bdg_chr[end]<=cleavage_site) ].copy()
-    y_L = df_bdg_chr_L[value]
-    n_bins_L = len(y_L)
-    x_L = np.arange(n_bins_L)
-    bins=n_bins_L ## 和 right 公用
-    # 用 window_size 做临近
-    frac = window_size/(bins*bin_size)
-    lowess_smoothed_L = lowess(y_L[-bins:], x_L[-bins:], frac=frac)
-    lowess_smoothed_L = lowess(lowess_smoothed_L[:, 1], lowess_smoothed_L[:, 0], frac=frac)
-    # 得到最后一个 <signal_threshold 的 index
-    bool_L = lowess_smoothed_L[:,1]<signal_threshold
-    index_L = np.where(bool_L)[0][-1]
-    if index_L == (bins-1):
-        # 可能是单边信号，数值反向
-        lowess_smoothed_L_reverse = -lowess_smoothed_L[:,1]
-        bool_L = lowess_smoothed_L_reverse<signal_threshold
-        index_L = np.where(bool_L)[0][-1]
-    # 考虑到 smooth，所以长度 + 1
-    index_L = index_L - 1
-    signal_L = lowess_smoothed_L[index_L+1:,1]
-    length_L = (len(signal_L)*bin_size)/1000
-    max_signal_L = y_L.max()
-    y_max_L = max_signal_L*1.2
-    left_region = chrom + ':' + df_bdg_chr_L.iloc[0,1].astype(str) + '-' + df_bdg_chr_L.iloc[-1,2].astype(str)
-
-    ## right
-    # 取 cleavage_site 附近的数据
-    df_bdg_chr_R = df_bdg_chr[ (df_bdg_chr[start] <= cleavage_site+flank_max) & (df_bdg_chr[start]>=cleavage_site) ].copy()
-    y_R = df_bdg_chr_R[value]
-    n_bins_R = len(y_R)
-    x_R = np.arange(n_bins_R)
-    # 用 window_size 做临近
-    frac = window_size/(bins*bin_size)
-    lowess_smoothed_R = lowess(y_R[:bins], x_R[:bins], frac=frac)
-    lowess_smoothed_R = lowess(lowess_smoothed_R[:, 1], lowess_smoothed_R[:, 0], frac=frac)
-    # 得到第一个 >-signal_threshold 的 index
-    bool_R = lowess_smoothed_R[:,1]>-signal_threshold
-    index_R = np.where(bool_R)[0][0]
-    if index_R == 0:
-        # 可能是单边信号，数值反向
-        lowess_smoothed_R_reverse = -lowess_smoothed_R[:,1]
-        bool_R = lowess_smoothed_R_reverse>-signal_threshold
-        index_R = np.where(bool_R)[0][0]
-    # 考虑到 smooth，所以长度 + 1
-    index_R = index_R + 1
-    signal_R = lowess_smoothed_R[:index_R,1]
-    length_R = (len(signal_R)*bin_size)/1000
-    min_signal_R = y_R.min()
-    y_mim_R = min_signal_R*1.2
-    right_region = chrom + ':' + df_bdg_chr_R.iloc[0,1].astype(str) + '-' + df_bdg_chr_R.iloc[-1,2].astype(str)
-
-    if show_plot:
-        fig = plt.figure(figsize=(10, 3))
-        ax1 = fig.add_axes([0.0, 0.1, 0.5, 0.8])
-        ax2 = fig.add_axes([0.5, 0.1, 0.5, 0.8])
-
-        # plot left
-        ax1.plot(range(bins), y_L[-bins:], label='Original')
-        ax1.plot(range(bins), lowess_smoothed_L[-bins:, 1], label='LOWESS', color='red')
-        ax1.plot([0,bins],[0,0],label='zero',color='black')
-        ax1.plot([0,bins],[signal_threshold,signal_threshold],label='threshold_left',color='orange')
-        ax1.plot([0,bins],[-signal_threshold,-signal_threshold],label='threshold_right',color='orange')
-        ax1.plot([index_L+1,index_L+1],[y_mim_R,y_max_L],label='length cutoff',color='orange')
-        ax1.set_ylim(y_mim_R,y_max_L)
-        ax1.set_xlim(-1,bins+1)
-        ax1.set_xlabel('distance to cleavage site (kb)')
-        ax1.set_title(left_region)
-
-        # add xticks
-        xtick_gap = 10000/bin_size # 10kb
-        n_xticks = int(np.ceil(bins/xtick_gap))
-        xticks = np.arange(0,n_xticks+1)*xtick_gap
-        xticks_label = np.arange(0,n_xticks+1)*10
-        xticks_label = np.flip(xticks_label)
-        # add length cutoff into xticks
-        # # 不加到xticks，可能会和原来的重合，改用text
-        # xticks = np.append(xticks, index_L+1)
-        # xticks_label = np.append(xticks_label, length_L)
-        ax1.text(index_L-3, 3, f'{length_L:g} kb', ha='right', va='top')
-        ax1.set_xticks(xticks)
-        _ = ax1.set_xticklabels([f'{x:g}' for x in xticks_label])
-        ax1.set_ylabel('signal difference\n(coverage per 10M reads)')
-
-        # plot right
-        ax2.plot(range(bins), y_R[:bins], label='Original')
-        ax2.plot(range(bins), lowess_smoothed_R[:bins, 1], label='LOWESS', color='red')
-        ax2.plot([0,bins],[0,0],label='zero',color='black')
-        ax2.plot([0,bins],[signal_threshold,signal_threshold],label='threshold_left',color='orange')
-        ax2.plot([0,bins],[-signal_threshold,-signal_threshold],label='threshold_right',color='orange')
-        ax2.plot([index_R,index_R],[y_mim_R,y_max_L],label='length cutoff',color='orange')
-        ax2.set_ylim(y_mim_R,y_max_L)
-        ax2.set_xlim(-1,bins+1)
-        ax2.set_xlabel('distance to cleavage site (kb)')
-        ax2.set_title(right_region)
-
-        # add xticks
-        xtick_gap = 10000/bin_size # 10kb
-        n_xticks = int(np.ceil(bins/xtick_gap))
-        xticks = np.arange(0,n_xticks+1)*xtick_gap
-        xticks_label = np.arange(0,n_xticks+1)*10
-        # add length cutoff into xticks
-        # # 不加到xticks，可能会和原来的重合，改用text
-        # xticks = np.append(xticks, index_R)
-        # xticks_label = np.append(xticks_label, length_R)
-        ax2.text(index_R+4, -3, f'{length_R:g} kb', ha='left', va='bottom')
-        ax2.set_xticks(xticks)
-        _ = ax2.set_xticklabels([f'{x:g}' for x in xticks_label])
-        
-        # 左右两个图紧贴
-        ax2.set_yticks([])
-        ax2.set_yticklabels([])
-        ax2.set_ylabel('')
-        if savefig is not None:
-            plt.savefig(savefig, dpi=save_dpi, bbox_inches='tight')
-        #fig.tight_layout()
-        plt.show()
-    return length_L, length_R, lowess_smoothed_L, lowess_smoothed_R, y_L, y_R
-
-
 def tracking_plot(signal_L, signal_R, bin_size=100, bins=None, 
                   figsize=(10, 3), title='',
                   show_plot=True, fig=None, ax1=None, ax2=None,

{offtracker-2.10.3 → offtracker-2.10.4}/offtracker/X_offtracker.py

@@ -308,32 +308,3 @@ def target_signal_chunk(df_bdg_chr, df_alignment_chr, flank_max=100000, smooth_t
     return df_result
 
 
-
-
-# 2024.01.22. 额外写一个 signal length 算法，增加基于 pos_pct 而非 smooth 后的 overall_signal 的 length，叫 singal_length
-def signal_length(df_bdg_chr, chrom, cleavage_site, end='end',start='start',value='residual', 
-                  flank_max=100000, binsize=100):
-    # 输入数据必须是同一条染色体内的
-    # Left
-    df_bdg_chr_L = df_bdg_chr[ (df_bdg_chr[end] >= cleavage_site-flank_max) & (df_bdg_chr[end]<=cleavage_site) ].copy()
-    
-    # pos and neg
-    df_bdg_chr_L_flank_pos = df_bdg_chr_L_flank[df_bdg_chr_L_flank[value] > 0]
-    df_bdg_chr_L_flank_neg = df_bdg_chr_L_flank[df_bdg_chr_L_flank[value] <= 0]
-    n_pos_left = len(df_bdg_chr_L_flank_pos)
-    n_neg_left = len(df_bdg_chr_L_flank_neg)
-    # avoid zero
-    if n_pos_left == 0:
-        pos_pct_left = 0
-    else:
-        pos_pct_left = n_pos_left/(n_pos_left+n_neg_left)    
-    
-    
-    df_bdg_chr_R = df_bdg_chr[ (df_bdg_chr[start] <= cleavage_site+flank_max) & (df_bdg_chr[start]>=cleavage_site) ].copy()
-    # list_signal_residual_L 数值和之前类似
-    list_signal_pct_L = []
-    list_pct_score_L = []
-    list_signal_residual_L = []
-    
-
-    return list_return

{offtracker-2.10.3 → offtracker-2.10.4}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.10.3"
+__version__ = "2.10.4"
 # 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
@@ -33,4 +33,4 @@ __version__ = "2.10.3"
 # 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。
-# 2025.06.17. v2.10.3   修复翻新代码结构导致的bug
+# 2025.06.17. v2.10.4   修复翻新代码结构导致的bug

{offtracker-2.10.3 → offtracker-2.10.4/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.3
+Version: 2.10.4
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu
@@ -25,7 +25,7 @@ Offtracker is an end to end pipeline of Tracking-seq data analysis for detecting
 # 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 
 # Windows systems may not be compatible with pybedtools.
-mamba create -n offtracker -c bioconda blast snakemake pybedtools chromap
+mamba create -n offtracker -c bioconda blast snakemake pybedtools deeptools chromap
 ```
 
 

{offtracker-2.10.3 → offtracker-2.10.4}/scripts/offtracker_analysis.py

@@ -26,7 +26,7 @@ def main():
     parser.add_argument('--name'         , type=str, required=True,    help='custom name of the sgRNA' )
     parser.add_argument('--exp'          , type=str, default='all',    nargs='+', help='A substring mark in the name of experimental samples. The default is to use all samples other than control' )
     parser.add_argument('--control'      , type=str, default='none',   nargs='+', help='A substring mark in the name of control samples. The default is no control. "others" for all samples other than --exp.' )
-    parser.add_argument('--fdr'          , type=int, default=0.05,     help='FDR threshold for the final result. Default is 0.05.')
+    parser.add_argument('--fdr'          , type=int, default=0.01,     help='FDR threshold for the final result. Default is 0.01.')
     parser.add_argument('--score'        , type=int, default=2,        help='Track score threshold for the final result. Default is 2.')
     parser.add_argument('--smooth'       , type=int, default=1,        help='Smooth strength for the signal.')
     parser.add_argument('--window'       , type=int, default=3,        help='Window size for smoothing the signal.')
@@ -93,7 +93,7 @@ def main():
     all_sample_files = []
     for a_folder in folders:    
         bdg_files = pd.Series(glob.glob(os.path.join( a_folder, '*.add.bdg' ))).sort_values().reset_index(drop=True)
-        sample_names = bdg_files.apply(os.path.basename).str.extract('(.*)\.\d+\.add\.bdg',expand=False)
+        sample_names = bdg_files.apply(os.path.basename).str.extract(r'(.*)\.\d+\.add\.bdg',expand=False)
         all_sample_names.extend( sample_names )
         all_sample_files.extend( bdg_files )
     all_sample_files = pd.Series(all_sample_files)
@@ -209,7 +209,7 @@ def main():
         df_score =  pd.read_csv(output, index_col=0)
     else:
         signal_files = pd.Series(glob.glob( os.path.join(outdir, 'temp', f'*{sgRNA_name}.signal.csv') ))
-        signal_names = signal_files.apply(os.path.basename).str.extract(f'(.*)\.{sgRNA_name}\.signal\.csv',expand=False)
+        signal_names = signal_files.apply(os.path.basename).str.extract(rf'(.*)\.{sgRNA_name}\.signal\.csv',expand=False)
 
         # 读取并合并 samples
         list_df_exp_samples = []
@@ -287,7 +287,7 @@ def main():
         # 整理表格
         mean_seq_score = round(df_score['best_seq_score'].mean(),3)
         df_score['norm_best_seq_score'] = np.power(df_score['best_seq_score']/mean_seq_score, seq_score_power)        
-        df_score['final_score_1'] = df_score[f'proximal_signal']*df_score['norm_best_seq_score']
+        df_score['final_score_1'] = df_score['proximal_signal']*df_score['norm_best_seq_score']
         df_score['final_score_2'] = df_score['pct_score']*df_score['norm_best_seq_score']
         #df_score['final_score_2'] = df_score[f'overall_signal']*df_score['norm_best_seq_score']
         df_score['raw_score'] = df_score['final_score_1'] + df_score['final_score_2']
@@ -303,10 +303,10 @@ def main():
         score_bkg = df_result['raw_score'][n_outliers:-n_outliers]
         mean_score_bkg = score_bkg.mean()
         std_score_bkg = score_bkg.std()
-        df_result['track_score'] = (df_result[f'raw_score'] - mean_score_bkg) / std_score_bkg
-        df_result['track_score'] = df_result[f'track_score']*target_std + 1
+        df_result['track_score'] = (df_result['raw_score'] - mean_score_bkg) / std_score_bkg
+        df_result['track_score'] = df_result['track_score']*target_std + 1
         df_result = df_result.sort_values(by='track_score', ascending=False)
-        df_result['log2_track_score'] = np.log2(df_result[f'track_score'].clip(lower=0.5))   
+        df_result['log2_track_score'] = np.log2(df_result['track_score'].clip(lower=0.5))   
 
         # 单边信号周围有更高分的，去掉
         # v2.1 后 cols_L, cols_R 要手动
@@ -345,7 +345,7 @@ def main():
         mu, std = norm.fit(score_for_fitting) 
         print('mean_score:{:.3f};std:{:.3f}'.format(mu,std))
         # pv and fdr
-        df_result['pv'] = df_result[f'log2_track_score'].apply( lambda x: norm.sf(x,loc=mu,scale=std) )
+        df_result['pv'] = df_result['log2_track_score'].apply( lambda x: norm.sf(x,loc=mu,scale=std) )
         df_result['pv'] = df_result['pv'].clip(lower=1e-320)
         df_result['fdr'] = offtracker.fdr(df_result['pv'])
         df_result['rank'] = range(1,len(df_result)+1)
@@ -354,7 +354,7 @@ def main():
         bool_fdr = df_result['fdr']<=fdr_thresh
         bool_score = df_result['track_score']>=score_thresh
         # 2025.06.05. BE可能会形成单边信号，导致 track_score 为负数，也保留
-        bool_neg_score = df_result['track_score']<0
+        bool_neg_score = df_result['track_score']<-0.5
         df_output = df_result[bool_fdr|bool_score|bool_neg_score].copy()
         if pattern_ctr != 'none':
             df_output = df_output[['target_location', 'best_strand','best_target','deletion','insertion','mismatch',

{offtracker-2.10.3 → offtracker-2.10.4}/scripts/offtracker_config.py

@@ -13,6 +13,7 @@ import offtracker
 import offtracker.X_sequence as xseq
 script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
 utility_dir = os.path.join(script_dir, 'utility')
+os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
 
 ###
 parser = argparse.ArgumentParser()