offtracker 2.11.3__zip → 2.12.0__zip

{offtracker-2.11.3/offtracker.egg-info → offtracker-2.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.3
+Version: 2.12.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.3 → offtracker-2.12.0}/offtracker/X_offtracker.py

@@ -1,5 +1,6 @@
 
 import pandas as pd
+import polars as pl
 import numpy as np
 import os, sys
 sys.path.append( os.path.abspath(os.path.dirname(__file__)) )
@@ -8,26 +9,65 @@ def fdr(p_vals):
     # Benjamini-Hochberg
     from scipy.stats import rankdata
     ranked_p_values = rankdata(p_vals)
-    fdr = p_vals * len(p_vals) / ranked_p_values
-    fdr[fdr > 1] = 1
-    return fdr
+    fdr_value = p_vals * len(p_vals) / ranked_p_values
+    fdr_value[fdr_value > 1] = 1
+    return fdr_value
 
-def dedup_two( df_loc, col_ID_1='ID_1', col_ID_2='ID_2'):
-    # 会根据 df_loc 的排序保留第一个 location
-    # dedup 结束后，剩下的 ID_1 + ID_2 并集可能会小于 dedup 前的并集
-    list_nondup = []
-    set_IDs = set()
-    df_IDs = df_loc[[col_ID_1,col_ID_2]]
-    for a_row in df_IDs.iterrows():
-        temp = a_row[1]
-        if (temp[col_ID_1] in set_IDs) or (temp[col_ID_2] in set_IDs):
-            # 只要有一ID出现过，即便另一ID没出现过，也不更新 set_IDs
-            list_nondup.append(False)
+
+def mark_regions_single_chr(dp, min_distance=1000):
+    unique_chr = dp['chr'].unique()
+    assert len(unique_chr) == 1
+    unique_chr = unique_chr[0]
+
+    # Initialize variables for marking regions
+    region_id = 1
+    current_start = None
+    current_end = None
+    marked_regions = []
+
+    for row in dp.iter_rows(named=True):
+        start, end = row['st'], row['ed']
+
+        if current_start is None:
+            # First region
+            current_start = start
+            current_end = end
+            marked_regions.append(f'{unique_chr}_region_{region_id}')
         else:
-            set_IDs.add(temp[col_ID_1])
-            set_IDs.add(temp[col_ID_2])
-            list_nondup.append(True)
-    return list_nondup
+            if start <= current_end + min_distance:
+                # Mark as the same region
+                marked_regions.append(f'{unique_chr}_region_{region_id}')
+            else:
+                # New region
+                region_id += 1
+                marked_regions.append(f'{unique_chr}_region_{region_id}')
+                current_start = start
+                current_end = end
+
+        current_end = max(current_end, end)
+
+    return dp.with_columns(region_index=pl.Series(marked_regions))
+
+
+
+
+
+# def dedup_two( df_loc, col_ID_1='ID_1', col_ID_2='ID_2'):
+#     # 会根据 df_loc 的排序保留第一个 location
+#     # dedup 结束后，剩下的 ID_1 + ID_2 并集可能会小于 dedup 前的并集
+#     list_nondup = []
+#     set_IDs = set()
+#     df_IDs = df_loc[[col_ID_1,col_ID_2]]
+#     for a_row in df_IDs.iterrows():
+#         temp = a_row[1]
+#         if (temp[col_ID_1] in set_IDs) or (temp[col_ID_2] in set_IDs):
+#             # 只要有一ID出现过，即便另一ID没出现过，也不更新 set_IDs
+#             list_nondup.append(False)
+#         else:
+#             set_IDs.add(temp[col_ID_1])
+#             set_IDs.add(temp[col_ID_2])
+#             list_nondup.append(True)
+#     return list_nondup
 
 def window_smooth(sr_smooth, window_size=3, times=1):
     window  = np.ones(window_size) / window_size

{offtracker-2.11.3 → offtracker-2.12.0}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.11.3"
+__version__ = "2.12.0"
 # 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
@@ -38,4 +38,6 @@ __version__ = "2.11.3"
 # 2025.06.28. v2.10.9   现在 pip 都是从 wheel 安装，不再运行 setup.py，所以增加一个 offtracker_init.py
 # 2025.06.28. v2.10.10  直接塞 script 里试试
 # 2025.06.28. v2.10.11  回滚到2.10.9外加修正
-# 2025.07.02. v2.11.3  基于 blast 的缺陷更新 candidates
+# 2025.07.02. v2.11.4   基于 blast 的缺陷更新 candidates，去除 quick mode
+# 2025.07.04. v2.11.5   offtracker_analysis 提前 skip 已有结果的样本
+# 2025.07.04. v2.12.0   新增 region_index 标记区域，用于更好的去重

{offtracker-2.11.3 → offtracker-2.12.0/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.3
+Version: 2.12.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.3 → offtracker-2.12.0}/scripts/offtracker_analysis.py

@@ -82,7 +82,7 @@ def main():
         df_candidate.index = df_candidate['target_location']
         df_candidate_brief = df_candidate[['chr','st','ed','best_strand','best_target','best_seq_score',
                                  'deletion', 'insertion','mismatch', 'GG', 
-                                 'target_location', 'cleavage_site', 'ID_1','ID_2']]
+                                 'target_location', 'cleavage_site', 'ID_1','ID_2', 'region_index']] # 2025.07.06 添加 region_index
         df_candidate_sub = df_candidate[['chr','cleavage_site']]
     except FileNotFoundError:
         return 'Please run offtracker_candidates.py first and provide the correct directory with --seqfolder'
@@ -192,7 +192,8 @@ def main():
 
     if args.signal_only:
         return 'signal_only is on, stop here.'
-    
+
+
     ####################
     ## group analysis ##
     ####################
@@ -204,6 +205,11 @@ def main():
     else:
         outname = args.outname
 
+    # skip finished
+    output = f'Offtracker_result_{outname}.csv'
+    if (os.path.isfile(output))&(not args.overwrite):
+        return 'skip {output} as the result exists!'
+
     output = f'./temp/df_score_{outname}.csv'
     if (os.path.isfile(output))&(not args.overwrite):
         print(f'skip {output}')
@@ -294,9 +300,12 @@ def main():
         df_score['raw_score'] = df_score['final_score_1'] + df_score['final_score_2']
         df_score = df_score.sort_values('raw_score', ascending=False)    
 
-        # local dedup
-        list_nondup = offtracker.dedup_two(df_score,'ID_1','ID_2')
-        df_result = df_score[list_nondup].copy()
+        # # local dedup
+        # list_nondup = offtracker.dedup_two(df_score,'ID_1','ID_2')
+        # df_result = df_score[list_nondup].copy()
+
+        # 2025.07.06 更新去重方式
+        df_result = df_score.drop_duplicates(subset=['region_index'], keep='first')
 
         # 标准化分布      
         target_std=0.15
@@ -353,33 +362,30 @@ def main():
         df_result.to_csv(output)
 
     output = f'Offtracker_result_{outname}.csv'
-    if (os.path.isfile(output))&(not args.overwrite):
-        print(f'skip {output} as the result exists')
+    # 2024.06.03. 以防 fdr<=fdr_thresh 滤掉了 track_score>=2 的位点
+    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']< -1
+    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',
+                            'exp_L_length', 'exp_R_length','ctr_L_length','ctr_R_length','L_length','R_length','signal_length',
+                            'norm_best_seq_score','track_score', 'log2_track_score','fdr','rank']]
+        df_output.columns = ['target_location', 'strand', 'target', 'deletion', 'insertion', 'mismatch', 
+                            'exp_L_length', 'exp_R_length','ctr_L_length','ctr_R_length','L_length','R_length','signal_length',
+                            'seq_score', 'track_score', 'log2_track_score','FDR', 'rank']
     else:
-        # 2024.06.03. 以防 fdr<=fdr_thresh 滤掉了 track_score>=2 的位点
-        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']< -1
-        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',
-                                'exp_L_length', 'exp_R_length','ctr_L_length','ctr_R_length','L_length','R_length','signal_length',
-                                'norm_best_seq_score','track_score', 'log2_track_score','fdr','rank']]
-            df_output.columns = ['target_location', 'strand', 'target', 'deletion', 'insertion', 'mismatch', 
-                                'exp_L_length', 'exp_R_length','ctr_L_length','ctr_R_length','L_length','R_length','signal_length',
-                                'seq_score', 'track_score', 'log2_track_score','FDR', 'rank']
-        else:
-            df_output = df_output[['target_location', 'best_strand','best_target','deletion','insertion','mismatch',
-                                'L_length', 'R_length','signal_length',
-                                'norm_best_seq_score','track_score', 'log2_track_score','fdr','rank']]
-            df_output.columns = ['target_location', 'strand', 'target', 'deletion', 'insertion', 'mismatch', 
-                                'L_length', 'R_length','signal_length',
-                                'seq_score', 'track_score', 'log2_track_score','FDR', 'rank']
-        df_output.to_csv(f'Offtracker_result_{outname}.csv', index=False)
-
-        if args.clean:
-            shutil.rmtree('./temp')
+        df_output = df_output[['target_location', 'best_strand','best_target','deletion','insertion','mismatch',
+                            'L_length', 'R_length','signal_length',
+                            'norm_best_seq_score','track_score', 'log2_track_score','fdr','rank']]
+        df_output.columns = ['target_location', 'strand', 'target', 'deletion', 'insertion', 'mismatch', 
+                            'L_length', 'R_length','signal_length',
+                            'seq_score', 'track_score', 'log2_track_score','FDR', 'rank']
+    df_output.to_csv(f'Offtracker_result_{outname}.csv', index=False)
+
+    if args.clean:
+        shutil.rmtree('./temp')
 
     return 'Done!'
     

{offtracker-2.11.3 → offtracker-2.12.0}/scripts/offtracker_candidates.py

@@ -37,7 +37,7 @@ def main():
     parser.add_argument('-o','--outdir' , type=str, required=True, help='The output folder')
     parser.add_argument('-g','--genome' , type=str, default='hg38', help='File of chromosome sizes, or "hg38", "mm10" ')
     parser.add_argument('-t','--thread' , type=int, default=4,     help='Number of threads for parallel computing')
-    parser.add_argument('--quick_mode'  , action='store_true',  help='BLAST faster but less candidates.')
+    # parser.add_argument('--quick_mode'  , action='store_true',  help='Quick mode is deprecated due to blast flaw.')
 
     args = parser.parse_args()
     
@@ -57,7 +57,7 @@ def main():
         os.makedirs(dir_output)
     dir_ref_fa = args.ref
     blast_db   = args.blastdb
-    quick_mode = args.quick_mode
+    # quick_mode = args.quick_mode
     
     # parameters for alignment
     half_width = 100
@@ -95,13 +95,7 @@ def main():
     if os.path.isfile(dir_sgRNA_blast):
         print(f'{dir_sgRNA_blast} exists, skipped.')
     else:
-        if quick_mode:
-            print('Using quick mode for BLAST')
-            blastx_cline = NcbiblastnCommandline(query=dir_sgRNA_fasta, task='blastn-short',out=dir_sgRNA_blast,
-                                                db=blast_db, evalue=100000,outfmt=6, num_threads=n_threads,
-                                                gapopen=4, gapextend=2, reward=2, word_size=5, dust='no', soft_masking=False)
-        else:
-            blastx_cline = NcbiblastnCommandline(query=dir_sgRNA_fasta, task='blastn-short',out=dir_sgRNA_blast,
+        blastx_cline = NcbiblastnCommandline(query=dir_sgRNA_fasta, task='blastn-short',out=dir_sgRNA_blast,
                                                 db=blast_db, evalue=100000,outfmt=6, num_threads=n_threads,
                                                 gapopen=4, gapextend=2, reward=2, word_size=4, dust='no', soft_masking=False)   
         print(f'BLAST for candidate off-target sites of {sgRNA_name}.')
@@ -316,7 +310,18 @@ def main():
     df_candidate['mis_all'] = df_candidate[['mismatch','deletion','insertion']].sum(axis=1)
     df_candidate = df_candidate[df_candidate['mis_all']<8]
 
-    df_candidate.to_csv(dir_df_candidate)
+    # 2025.07.06 增加 region 标记用于去重
+    # 将 df_candidate 按照染色体分组
+    candidate_groups = df_candidate.groupby('chr')
+    # 定义一个空的列表，用于存储每个染色体的数据
+    list_dp = []
+    for chr_name, chr_candidate in candidate_groups:
+        dp_marked = offtracker.mark_regions_single_chr(pl.DataFrame(chr_candidate))
+        list_dp.append(dp_marked)
+    df_candidate = pl.concat(list_dp)
+
+    # 改成 pl 输出
+    df_candidate.write_csv(dir_df_candidate)
     print(f'Output df_candidate_{sgRNA_name}.csv')
     os.remove(temp_bed)