offtracker 2.10.11__zip → 2.11.0__zip

{offtracker-2.10.11/offtracker.egg-info → offtracker-2.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.11
+Version: 2.11.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.10.11 → offtracker-2.11.0}/offtracker/X_offplot.py

@@ -5,10 +5,21 @@ import matplotlib.pyplot as plt
 import matplotlib.patches as patches
 from matplotlib import rcParams
 # 和用 plt.rcParams or matplotlib.rcParams 是一样的
-dict_rc = {
-    'pdf.fonttype': 42,
-    'font.family': ['Arial']
-}
+import sys
+if sys.platform[:3] == 'win':
+    dict_rc = {
+        'pdf.fonttype': 42,
+        'font.family': ['Arial']
+    }
+elif sys.platform[:5] == 'linux':
+    dict_rc = {
+        'pdf.fonttype': 42,
+        'font.family': ['Arial']
+    }
+else:
+    dict_rc = {
+        'pdf.fonttype': 42,
+    }
 rcParams.update(dict_rc)
 
 # 2024.06.03. offtable 添加 threshold 分界线，默认为 None，常用的是 2

{offtracker-2.10.11 → offtracker-2.11.0}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.10.11"
+__version__ = "2.11.0"
 # 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
@@ -37,4 +37,5 @@ __version__ = "2.10.11"
 # 2025.06.27. v2.10.8   将 chmod 放在了 setup.py 里
 # 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
+# 2025.06.28. v2.10.11  回滚到2.10.9外加修正
+# 2025.07.02. v2.11.0  基于 blast 的缺陷更新 candidates

{offtracker-2.10.11 → offtracker-2.11.0/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.11
+Version: 2.11.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.10.11 → offtracker-2.11.0}/offtracker.egg-info/requires.txt

@@ -1,4 +1,5 @@
 pandas
+polars>=1.19.0
 numpy
 biopython<=1.85
 pybedtools

{offtracker-2.10.11 → offtracker-2.11.0}/scripts/offtracker_candidates.py

@@ -20,6 +20,7 @@ script_folder= os.path.join(script_dir, 'utility')
 
 import argparse
 import pandas as pd
+import polars as pl
 import pybedtools
 import multiprocessing as mp
 from Bio.Blast.Applications import NcbiblastnCommandline 
@@ -89,18 +90,20 @@ def main():
     #########
     # BLAST #
     #########
+    # 2025.07.02 基于 blast 的缺陷更新
+
     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=10000,outfmt=6, num_threads=n_threads,
-                                                gapopen=4, gapextend=2, reward=2, word_size=5, dust='no', soft_masking=False)
+                                                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=10000,outfmt=6, num_threads=n_threads,
-                                                gapopen=4, gapextend=2, reward=2, word_size=4, dust='no', soft_masking=False)   
+                                                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)   
         print(f'BLAST for candidate off-target sites of {sgRNA_name}.')
         blastx_cline()
         print(f'BLAST finished.')
@@ -109,33 +112,39 @@ def main():
     # Output bed #
     ##############
     
-    blast_regions = pd.read_csv(dir_sgRNA_blast, sep='\t',header=None)
+    # 2025.07.02 基于 blast 的缺陷更新
+    len_sgRNA = len(sgRNA_seq)
+    blast_regions = pl.read_csv(dir_sgRNA_blast, separator='\t',has_header=False)
     blast_regions.columns = ['query acc.','chr','% identity','alignment length','mismatches','gap opens','q. start','q. end','st','ed','evalue','bit score']
-    blast_regions = blast_regions[blast_regions.evalue<10000]
-    
-    # reverse strand 
-    blast_regions['reverse'] = (blast_regions['st']>blast_regions['ed']).astype(int)
-    blast_regions_f = blast_regions[blast_regions.reverse==0].copy()
-    blast_regions_r = blast_regions[blast_regions.reverse==1].copy()
-    temp = blast_regions_r['st'].copy()
-    blast_regions_r['st'] = blast_regions_r['ed']
-    blast_regions_r['ed'] = temp
-    blast_regions = pd.concat([blast_regions_f, blast_regions_r])
-    # sort and add location
-    blast_regions = blast_regions.sort_values('evalue').reset_index(drop=True)
-    blast_regions['location']=blast_regions['chr'].str[:] + ':' + blast_regions['st'].astype(str).str[:] + '-' + blast_regions['ed'].astype(str).str[:]
-    blast_regions = blast_regions.drop_duplicates(subset='location').copy()
-    
-    # alignment length 筛选
-    len_sgRNA=len(sgRNA_seq)
-    min_len = len_sgRNA-8
-    blast_regions = blast_regions[blast_regions['alignment length']>=min_len].copy().reset_index(drop=True)
-    blast_regions = blast_regions.reindex(columns = ['chr', 'st', 'ed' , 'query acc.', '% identity', 'alignment length', 'mismatches',
-        'gap opens', 'q. start', 'q. end', 'evalue', 'bit score', 'reverse', 'location'] )
-    
+
+    # reverse strand
+    blast_regions = blast_regions.with_columns((pl.col('st') > pl.col('ed')).cast(pl.Int8).alias('reverse'))
+    blast_regions_f = blast_regions.filter(pl.col('reverse') == 0)
+    blast_regions_r = blast_regions.filter(pl.col('reverse') == 1)
+    blast_regions_r = blast_regions_r.with_columns([
+        pl.col('ed').alias('st'),
+        pl.col('st').alias('ed')
+    ])
+    blast_regions = pl.concat([blast_regions_f, blast_regions_r])
+
+    # add location 
+    blast_regions = blast_regions.with_column(
+        (pl.col('chr') + ':' + pl.col('st').cast(str) + '-' + pl.col('ed').cast(str)).alias('location')
+    )
+    # filter, sort, dedup
+    blast_regions = blast_regions.with_columns(mis=(len_sgRNA - 1 - pl.col('q. end')+pl.col('q. start')+pl.col('mismatches')+pl.col('gap opens')).cast(pl.Int8))
+    blast_regions = blast_regions.with_columns(mis2=(len_sgRNA - pl.col('alignment length')*pl.col('% identity')/100).round().cast(pl.Int8))
+    blast_regions = blast_regions.filter((pl.col('mis')<8)|(pl.col('mis2')<8))
+    blast_regions = blast_regions.sort('mis').unique('location',keep='first', maintain_order=True)
+    blast_regions = blast_regions.select([
+        'chr', 'st', 'ed', 'query acc.', '% identity', 'alignment length', 'mismatches',
+        'gap opens', 'q. start', 'q. end', 'evalue', 'bit score', 'reverse', 'location', 'mis', 'mis2'
+    ])
+
     # 输出 bed 用于后续 alignment score 计算
-    blast_regions_bed = blast_regions[['chr','st','ed']]
-    xseq.write_bed(blast_regions_bed, dir_sgRNA_bed)
+    blast_regions_bed = blast_regions.select(['chr', 'st', 'ed'])
+    blast_regions_bed.write_csv(dir_sgRNA_bed, separator='\t', has_header=False)
+
     # 对 bed 进行排序但不合并
     a = pybedtools.BedTool(dir_sgRNA_bed)
     a.sort(g=dir_chrom_sizes).saveas( dir_sgRNA_bed )
@@ -155,10 +164,10 @@ def main():
     bed_short = xseq.X_readbed(dir_sgRNA_bed)
     bed_short = bed_short[bed_short['chr'].isin(common_chr)].copy()
     bed_short['midpoint'] = ((bed_short['st'] + bed_short['ed'])/2).astype(int)
-    bed_short['st'] = bed_short['midpoint'] - half_width 
+    bed_short['st'] = bed_short['midpoint'] - half_width
     bed_short['ed'] = bed_short['midpoint'] + half_width
     bed_short.loc[bed_short['st']<0,'st']=0
-    bed_short = bed_short.drop_duplicates()        
+    bed_short = bed_short.drop_duplicates()
 
     #########
     # 根据 bed_f 位点 ed 前后 half_width 取基因组序列

{offtracker-2.10.11 → offtracker-2.11.0}/setup.py

@@ -26,7 +26,7 @@ with open(os.path.join(here, package_folder, '_version.py'),'r',encoding='utf-8'
 
 # requirements
 REQUIRED = [
-   'pandas', 'numpy', 'biopython<=1.85', 'pybedtools', 'pyyaml', 
+   'pandas', 'polars>=1.19.0', 'numpy', 'biopython<=1.85', 'pybedtools', 'pyyaml', 
 ]
 ## pybedtools may be not supported in Windows