offtracker 2.11.2__zip → 2.11.5__zip

{offtracker-2.11.2/offtracker.egg-info → offtracker-2.11.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.2
+Version: 2.11.5
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.2 → offtracker-2.11.5}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.11.2"
+__version__ = "2.11.5"
 # 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 +38,5 @@ __version__ = "2.11.2"
 # 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. v2.11.2  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

{offtracker-2.11.2 → offtracker-2.11.5/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.2
+Version: 2.11.5
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.2 → offtracker-2.11.5}/scripts/offtracker_analysis.py

@@ -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}')
@@ -353,33 +359,30 @@ 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-2.11.2 → offtracker-2.11.5}/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
@@ -95,15 +95,9 @@ 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,
+        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=6, dust='no', soft_masking=False)
-        else:
-            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)   
+                                                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}.')
         blastx_cline()
         print(f'BLAST finished.')
@@ -312,6 +306,10 @@ def main():
     # df_candidate['midpoint'] = ((df_candidate['ed'] + df_candidate['st'])/2).astype(int)
     df_candidate = xseq.add_ID(df_candidate, midpoint='cleavage_site')
 
+    # 2025.07.02 为了削弱 blast 缺陷增加了候选位点数量，这里过滤一下减少计算
+    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)
     print(f'Output df_candidate_{sgRNA_name}.csv')
     os.remove(temp_bed)