offtracker 2.11.2__zip → 2.11.3__zip

{offtracker-2.11.2/offtracker.egg-info → offtracker-2.11.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.2
+Version: 2.11.3
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.2 → offtracker-2.11.3}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.11.2"
+__version__ = "2.11.3"
 # 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 +38,4 @@ __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. v2.11.3  基于 blast 的缺陷更新 candidates

{offtracker-2.11.2 → offtracker-2.11.3/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.11.2
+Version: 2.11.3
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.11.2 → offtracker-2.11.3}/scripts/offtracker_candidates.py

@@ -99,11 +99,11 @@ def main():
             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=6, dust='no', soft_masking=False)
+                                                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,
                                                 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 +312,10 @@ 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)