more functional minimap2.py; added categories

.travis.yml

@@ -10,6 +10,10 @@ matrix:
       python: "2.7"
       before_install: pip install cython
       script: python setup.py build_ext
+    - language: python
+      python: "3.0"
+      before_install: pip install cython
+      script: python setup.py build_ext
     - language: python
       python: "3.5"
       before_install: pip install cython

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "14 September 2017" "minimap2-2.1.1-r364-dirty" "Bioinformatics tools"
+.TH minimap2 1 "17 September 2017" "minimap2-2.1.1-r402-dirty" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -398,6 +398,7 @@ NM	i	Total number of mismatches and gaps in the alignment
 AS	i	DP alignment score
 ms	i	DP score of the max scoring segment in the alignment
 nn	i	Number of ambiguous bases in the alignment
+ts	A	Transcript strand (splice mode only)
 cg	Z	CIGAR string (only in PAF)
 .TE
 

python/mappy.pyx

@@ -67,8 +67,11 @@ cdef class Alignment:
 		else: strand = '?'
 		if self._is_primary != 0: tp = 'tp:A:P'
 		else: tp = 'tp:A:S'
+		if self._trans_strand > 0: ts = 'ts:A:+'
+		elif self._trans_strand < 0: ts = 'ts:A:-'
+		else: ts = 'ts:A:.'
 		return "\t".join([str(self._q_st), str(self._q_en), strand, self._ctg, str(self._ctg_len), str(self._r_st), str(self._r_en),
-				str(self._blen - self._NM), str(self._blen), str(self._mapq), "NM:i:" + str(self._NM), tp, "cg:Z:" + self.cigar_str])
+				str(self._blen - self._NM), str(self._blen), str(self._mapq), tp, ts, "cg:Z:" + self.cigar_str])
 
 cdef class ThreadBuffer:
 	cdef cmappy.mm_tbuf_t *_b

python/minimap2.py

@@ -4,11 +4,28 @@ import sys, getopt
 import mappy as mp
 
 def main(argv):
-	opts, args = getopt.getopt(argv[1:], "")
+	opts, args = getopt.getopt(argv[1:], "x:n:m:k:w:r:")
 	if len(args) < 2:
-		print("Usage: minimap2.py <ref.fa>|<ref.mmi> <query.fq>")
+		print("Usage: minimap2.py [options] <ref.fa>|<ref.mmi> <query.fq>")
+		print("Options:")
+		print("  -x STR      preset: sr, map-pb, map-ont, asm5, asm10 or splice")
+		print("  -n INT      mininum number of minimizers")
+		print("  -m INT      mininum chaining score")
+		print("  -k INT      k-mer length")
+		print("  -w INT      minimizer window length")
+		print("  -r INT      band width")
 		sys.exit(1)
-	a = mp.Aligner(args[0]) # load/build index
+
+	preset, min_cnt, min_sc, k, w, bw = None, None, None, None, None, None
+	for opt, arg in opts:
+		if opt == '-x': preset = arg
+		elif opt == '-n': min_cnt = int(arg)
+		elif opt == '-m': min_chain_score = int(arg)
+		elif opt == '-r': bw = int(arg)
+		elif opt == '-k': k = int(arg)
+		elif opt == '-w': w = int(arg)
+
+	a = mp.Aligner(args[0], preset=preset, min_cnt=min_cnt, min_chain_score=min_sc, k=k, w=w, bw=bw)
 	if not a: raise Exception("ERROR: failed to load/build index file '{}'".format(args[0]))
 	for name, seq, qual in mp.fastx_read(args[1]): # read one sequence
 		for h in a.map(seq): # traverse hits

setup.py

@@ -23,14 +23,15 @@ def readme():
 
 setup(
 	name = 'mappy',
-	version = '2.2rc0',
+	version = '2.2rc1',
 	url = 'https://github.com/lh3/minimap2',
 	description = 'Minimap2 python binding',
 	long_description = readme(),
 	author = 'Heng Li',
 	author_email = 'lh3@me.com',
 	license = 'MIT',
-	keywords = ['bioinformatics', 'sequence-alignment'],
+	keywords = 'sequence-alignment',
+	scripts = ['python/minimap2.py'],
     ext_modules = [Extension('mappy',
 		sources = [module_src, 'align.c', 'bseq.c', 'chain.c', 'format.c', 'hit.c', 'index.c',
 				   'ksw2_extd2_sse.c', 'ksw2_exts2_sse.c', 'ksw2_extz2_sse.c', 'ksw2_ll_sse.c',
@@ -41,4 +42,14 @@ setup(
 		extra_compile_args = ['-msse4'], # WARNING: ancient x86_64 CPUs don't have SSE4
 		include_dirs = ['.'],
 		libraries = ['z', 'm', 'pthread'])],
+	classifiers = [
+		'Development Status :: 4 - Beta',
+		'License :: OSI Approved :: MIT License',
+		'Operating System :: POSIX',
+		'Programming Language :: C',
+		'Programming Language :: Cython',
+		'Programming Language :: Python :: 2.7',
+		'Programming Language :: Python :: 3',
+		'Intended Audience :: Science/Research',
+		'Topic :: Scientific/Engineering :: Bio-Informatics'],
 	cmdclass = cmdclass)