update

MACS3/Commands/callvar_cmd.py

@@ -1,4 +1,4 @@
-# Time-stamp: <2024-10-02 16:34:23 Tao Liu>
+# Time-stamp: <2024-10-11 10:28:07 Tao Liu>
 
 """Description: Call variants directly
 
@@ -137,11 +137,11 @@ def run(args):
 
     peakio = open(peakbedfile)
     peaks = PeakIO()
-    i = 0
+    #i = 0
     for t_peak in peakio:
         fs = t_peak.rstrip().split()
-        i += 1
-        peaks.add(fs[0].encode(), int(fs[1]), int(fs[2]), name=b"%d" % i)
+        # i += 1
+        peaks.add(fs[0].encode(), int(fs[1]), int(fs[2]))  # , name=b"%d" % i)
     peaks.sort()
 
     # chrs = peaks.get_chr_names()

MACS3/Commands/refinepeak_cmd.py

@@ -1,4 +1,4 @@
-# Time-stamp: <2024-10-02 17:01:42 Tao Liu>
+# Time-stamp: <2024-10-11 11:11:00 Tao Liu>
 
 """Description: refine peak summits
 

MACS3/IO/PeakIO.py

@@ -1,6 +1,6 @@
 # cython: language_level=3
 # cython: profile=True
-# Time-stamp: <2024-10-10 17:00:18 Tao Liu>
+# Time-stamp: <2024-10-11 11:13:11 Tao Liu>
 
 """Module for PeakIO IO classes.
 
@@ -15,7 +15,6 @@
 from itertools import groupby
 from operator import itemgetter
 import random
-import re
 import sys
 
 # ------------------------------------
@@ -75,7 +74,7 @@ def __init__(self,
                  pscore: cython.float,
                  fold_change: cython.float,
                  qscore: cython.float,
-                 name: bytes = b"NA"):
+                 name: bytes = b""):
         self.chrom = chrom
         self.start = start
         self.end = end
@@ -163,26 +162,15 @@ def __init__(self):
     @cython.ccall
     def add(self,
             chromosome: bytes,
-            start: cython.int,
-            end: cython.int,
-            summit: cython.int = 0,
-            peak_score: cython.float = 0,
-            pileup: cython.float = 0,
-            pscore: cython.float = 0,
-            fold_change: cython.float = 0,
-            qscore: cython.float = 0,
-            name: bytes = b"NA"):
-        """items:
-        start:start
-        end:end,
-        length:end-start,
-        summit:summit,
-        score:peak_score,
-        pileup:pileup,
-        pscore:pscore,
-        fc:fold_change,
-        qscore:qscore
-        """
+            start: cython.int,  # leftmost position
+            end: cython.int,    # rightmost position
+            summit: cython.int = 0,  # summit position
+            peak_score: cython.float = 0,  # score
+            pileup: cython.float = 0,      # pileup value
+            pscore: cython.float = 0,      # -log10 pvalue
+            fold_change: cython.float = 0,  # fold change
+            qscore: cython.float = 0,      # -log10 qvalue
+            name: bytes = b""):            # peak name
         if not self.peaks.has_key(chromosome):
             self.peaks[chromosome] = []
         self.peaks[chromosome].append(PeakContent(chromosome,
@@ -215,7 +203,7 @@ def get_data_from_chrom(self, chrom: bytes) -> list:
         return self.peaks[chrom]
 
     def get_chr_names(self) -> set:
-        return set(sorted(self.peaks.keys()))
+        return set(self.peaks.keys())
 
     def sort(self):
         chrs: list
@@ -342,6 +330,8 @@ def __str__(self):
         chrs: list
         n_peak: cython.int
         ret: str
+        chrom: bytes
+        peaks: list
 
         ret = ""
         chrs = list(self.peaks.keys())
@@ -448,7 +438,7 @@ def _to_summits_bed(self,
                     print_func("%s\t%d\t%d\t%s%d\t%.6g\n" % (chrom.decode(), summit_p, summit_p+1, peakprefix.decode(), n_peak, peak[score_column]))
 
     def tobed(self):
-        """Print out peaks in BED5 format.
+        """Print out (stdout) peaks in BED5 format.
 
         Five columns are chromosome, peak start, peak end, peak name, and peak height.
 
@@ -462,19 +452,19 @@ def tobed(self):
         fc:fold_change,
         qscore:qvalue
         """
-        return self._to_bed(name_prefix=b"peak_", score_column="score", name=b"", description=b"")
+        return self._to_bed(name_prefix=b"%s_peak_", score_column="score", name=self.name, description=b"")
 
     def to_summits_bed(self):
-        """Print out peak summits in BED5 format.
+        """Print out (stdout) peak summits in BED5 format.
 
         Five columns are chromosome, summit start, summit end, peak name, and peak height.
 
         """
-        return self._to_summits_bed(name_prefix=b"peak_", score_column="score", name=b"", description=b"")
+        return self._to_summits_bed(name_prefix=b"%s_peak_", score_column="score", name=self.name, description=b"")
 
     # these methods are very fast, specifying types is unnecessary
     def write_to_bed(self, fhd,
-                     name_prefix: bytes = b"peak_",
+                     name_prefix: bytes = b"%s_peak_",
                      name: bytes = b"MACS",
                      description: bytes = b"%s",
                      score_column: str = "score",
@@ -538,7 +528,7 @@ def write_to_summit_bed(self, fhd,
 
     def write_to_narrowPeak(self, fhd,
                             name_prefix: bytes = b"%s_peak_",
-                            name: bytes = b"peak",
+                            name: bytes = b"MACS",
                             score_column: str = "score",
                             trackline: bool = False):
         """Print out peaks in narrowPeak format.

MACS3/Signal/FixWidthTrack.pyx

@@ -1,6 +1,6 @@
 # cython: language_level=3
 # cython: profile=True
-# Time-stamp: <2022-09-15 17:17:37 Tao Liu>
+# Time-stamp: <2024-10-11 11:11:10 Tao Liu>
 
 """Module for FWTrack classes.
 

MACS3/Signal/PairedEndTrack.py

@@ -1,6 +1,6 @@
 # cython: language_level=3
 # cython: profile=True
-# Time-stamp: <2024-10-10 17:03:45 Tao Liu>
+# Time-stamp: <2024-10-11 11:21:30 Tao Liu>
 
 """Module for filter duplicate tags from paired-end data
 
@@ -684,6 +684,7 @@ def add_frag(self,
         if chromosome not in self.__locations:
             self.__buf_size[chromosome] = self.buffer_size
             # note: ['l'] is the leftmost end, ['r'] is the rightmost end of fragment.
+            # ['c'] is the count number of this fragment
             self.__locations[chromosome] = np.zeros(shape=self.buffer_size,
                                                     dtype=[('l', 'i4'), ('r', 'i4'), ('c', 'u1')])
             self.__barcodes[chromosome] = np.zeros(shape=self.buffer_size,

test/test_ScoreTrack.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# Time-stamp: <2020-11-30 14:12:58 Tao Liu>
+# Time-stamp: <2024-10-11 10:17:53 Tao Liu>
 
 import io
 import unittest
@@ -96,11 +96,11 @@ def setUp(self):
 chrY	160	210	6.40804
 """
         # for peak calls
-        self.peak1 = """chrY	0	60	peak_1	60.4891
-chrY	160	210	peak_2	6.40804
+        self.peak1 = """chrY	0	60	MACS_peak_1	60.4891
+chrY	160	210	MACS_peak_2	6.40804
 """
-        self.summit1 = """chrY	5	6	peak_1	60.4891
-chrY	185	186	peak_2	6.40804
+        self.summit1 = """chrY	5	6	MACS_peak_1	60.4891
+chrY	185	186	MACS_peak_2	6.40804
 """
         self.xls1    ="""chr	start	end	length	abs_summit	pileup	-log10(pvalue)	fold_enrichment	-log10(qvalue)	name
 chrY	1	60	60	6	100	63.2725	9.18182	-1	MACS_peak_1