README.md

@@ -1,20 +1,17 @@
-# rMETL: 
-rMETL - realignment-based Mobile Element insertion detection Tool for Long read
-
----
-### Getting Start
 		        __        __   ______   _________   _
 		 _ __  |  \      /  | |  ____| |___   ___| | |
 		| ^__| |   \    /   | | |___       | |     | |
 		| |    | |\ \  / /| | |  ___|      | |     | |
 		| |    | | \ \/ / | | | |____      | |     | |____
 		|_|    |_|  \__/  |_| |______|     |_|     |______|
      
-
-	$ git clone https://github.com/tjiangHIT/rMETL.git (git clone https://github.com/hitbc/rMETL.git)
-	$ cd rMETL/
-	$ bash INSTALL.sh
-	$ ./rMETL.py
+	rMETL - realignment-based Mobile Element insertion detection Tool for Long read
+
+[![PyPI version](https://badge.fury.io/py/rMETL.svg)](https://badge.fury.io/py/rMETL)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/rmetl/badges/version.svg)](https://anaconda.org/bioconda/rmetl)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/rmetl/badges/license.svg)](https://anaconda.org/bioconda/rmetl)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/rmetl/badges/platforms.svg)](https://anaconda.org/bioconda/rmetl)
+[![Anaconda-Server Badge](https://anaconda.org/bioconda/rmetl/badges/latest_release_date.svg)](https://anaconda.org/bioconda/rmetl)
 
 ---	
 ### Introduction
@@ -45,10 +42,18 @@ Its peak memory footprint is about 7.05 Gigabytes (default setting), on a server
 ---
 ### Installation
 
+	#install via pip
+	$ pip install rMETL
+
+	#install via conda
+	$ conda install -c bioconda rmetl
+
+	#install from github
+	$ git clone https://github.com/tjiangHIT/rMETL.git (git clone https://github.com/hitbc/rMETL.git)
+	$ cd rMETL/
+	$ pip install .
+
 Current version of rMETL has been tested on 64bit Linux operating system.
-The source code is written in python, and can be directly download from: https://github.com/hitbc/rMETL 
-A mirror is also in: https://github.com/tjiangHIT/rMETL
-The INSTALL.sh is attached. Use the bash command for generating the executable file.
 
 ---
 ### Synopsis
@@ -102,7 +107,7 @@ Strongly recommend making output directory manually at first.:blush:
 ---
 ### Citation
 If you use rMETL, please cite:
-> Tao Jiang *et al*; rMETL: sensitive mobile element insertion detection with long read realignment, *Bioinformatics*, , btz106, https://doi.org/10.1093/bioinformatics/btz106
+> Tao Jiang *et al*; rMETL: sensitive mobile element insertion detection with long read realignment, *Bioinformatics*, Volume 35, Issue 18, 15 September 2019, Pages 3484–3486, https://doi.org/10.1093/bioinformatics/btz106
 
 ---
 ### Contact

setup.py

@@ -2,27 +2,29 @@
 
 from setuptools import setup, find_packages
 
-LONG_DESCRIPTION = '''Mobile element insertion (MEI) is a major category of structure variations (SVs). 
-The rapid development of long read sequencing provides the opportunity to sensitively discover MEIs. 
-However, the signals of MEIs implied by noisy long reads are highly complex, due to the repetitiveness 
-of mobile elements as well as the serious sequencing errors. Herein, we propose Realignment-based 
-Mobile Element insertion detection Tool for Long read (rMETL). rMETL takes advantage of 
-its novel chimeric read re-alignment approach to well handle complex MEI signals. 
-Benchmarking results on simulated and real datasets demonstrated that rMETL has the ability 
-to more sensitivity discover MEIs as well as prevent false positives. 
+LONG_DESCRIPTION = '''Mobile element insertion (MEI) is a major category of structure variations (SVs). \
+The rapid development of long read sequencing provides the opportunity to sensitively discover MEIs. \
+However, the signals of MEIs implied by noisy long reads are highly complex, due to the repetitiveness \
+of mobile elements as well as the serious sequencing errors. Herein, we propose Realignment-based \
+Mobile Element insertion detection Tool for Long read (rMETL). rMETL takes advantage of \
+its novel chimeric read re-alignment approach to well handle complex MEI signals. \
+Benchmarking results on simulated and real datasets demonstrated that rMETL has the ability \
+to more sensitivity discover MEIs as well as prevent false positives. \
 It is suited to produce high quality MEI callsets in many genomics studies.'''
 
 setup(
     name = "rMETL",
-    version = "1.0.2",
+    version = "1.0.4",
     description = "realignment-based Mobile Element insertion detection Tool for Long read",
     author = "Jiang Tao",
     author_email = "tjiang@hit.edu.cn",
     url = "https://github.com/tjiangHIT/rMETL",
-    license = "MIT Licence",
-    packages = find_packages('src'),
-    package_dir = {'': 'src'},
+    license = "MIT",
+    packages = find_packages("src"),
+    package_dir = {"": "src"},
+    data_files = [("", ["LICENSE"])],
+    scripts=['src/rMETL/rMETL'],
     long_description = LONG_DESCRIPTION,
     zip_safe = False,
     install_requires = ['pysam', 'Biopython', 'Cigar']
-)
+)

src/rMETL.py → src/rMETL/rMETL

@@ -2,19 +2,17 @@
 
 ''' 
  * All rights Reserved, Designed By HIT-Bioinformatics   
- * @Title:  process.py
- * @Package: argparse
  * @Description: Control the rMETL pipeline
  * @author: Jiang Tao (tjiang@hit.edu.cn)
  * @date: Apr 24 2018
- * @version V1.0.2   
+ * @version V1.0.4   
 '''
 
 import argparse
-import rMETL_extraction
-import rMETL_realign
-import rMETL_MEIcalling
-from rMETL_version import __version__, __author__, __contact__
+import rMETL.rMETL_extraction as rMETL_extraction
+import rMETL.rMETL_realign as rMETL_realign
+import rMETL.rMETL_MEIcalling as rMETL_MEIcalling
+from rMETL.rMETL_version import __version__, __author__, __contact__
 
 STAGES = {'detection': rMETL_extraction.run, \
           'realignment': rMETL_realign.run, \
@@ -44,7 +42,7 @@
 '''%(__version__, __author__, __contact__)
 
 def parseArgs():
-	parser = argparse.ArgumentParser(prog='rMETL.py', description=USAGE, \
+	parser = argparse.ArgumentParser(prog='rMETL', description=USAGE, \
     formatter_class=argparse.RawDescriptionHelpFormatter)
 	parser.add_argument('stage', metavar='STAGE', choices=STAGES.keys(), \
     type=str, help='Stage to execute')
@@ -54,4 +52,4 @@ def parseArgs():
 	STAGES[args.stage](args.options)
 
 if __name__ == '__main__':
-	parseArgs()
+	parseArgs()

src/rMETL_MEIcalling.py → src/rMETL/rMETL_MEIcalling.py

@@ -2,12 +2,10 @@
 
 ''' 
  * All rights Reserved, Designed By HIT-Bioinformatics   
- * @Title:  call_TE.py
- * @Package: argparse, sys, logging, pysam, Bio
  * @Description: Establish the ME callset
  * @author: Jiang Tao (tjiang@hit.edu.cn)
  * @date: Apr 24 2018
- * @version V1.0.2  
+ * @version V1.0.4  
 '''
 
 import argparse
@@ -17,10 +15,10 @@
 import cigar
 
 from collections import Counter
-from rMETL_version import __version__, __author__, __contact__
-from rMETL_genotype import simple_call_genotype
-from rMETL_cmdRunner import setupLogging
-from rMETL_utils import load_ref
+from rMETL.rMETL_version import __version__, __author__, __contact__
+from rMETL.rMETL_genotype import simple_call_genotype
+from rMETL.rMETL_cmdRunner import setupLogging
+from rMETL.rMETL_utils import load_ref
 
 USAGE="""\
            _  ___  _   _____   _______   _
@@ -312,7 +310,7 @@ def call_vcf(args):
 # 
 # ************************MAIN_FUNCTION*******************************
 def parseArgs(argv):
-	parser = argparse.ArgumentParser(prog="rMETL.py calling", description=USAGE, \
+	parser = argparse.ArgumentParser(prog="rMETL calling", description=USAGE, \
 		formatter_class=argparse.RawDescriptionHelpFormatter)
 	parser.add_argument("input", metavar="SAM", type=str, help="Input cluster.sam on STAGE realignment.")
 	parser.add_argument("Reference", metavar="REFERENCE", type=str, \

src/rMETL_extraction.py → src/rMETL/rMETL_extraction.py

@@ -2,12 +2,10 @@
 
 ''' 
  * All rights Reserved, Designed By HIT-Bioinformatics   
- * @Title:  extract_simple.py
- * @Package: argparse, pysam, sys, Bio, os, logging
  * @Description: Parse the ME signatures from alignments
  * @author: Jiang Tao (tjiang@hit.edu.cn)
  * @date: Apr 24 2018
- * @version V1.0.2     
+ * @version V1.0.4     
 '''
 
 import pysam
@@ -20,11 +18,11 @@
 import gc
 
 from multiprocessing import Pool
-from rMETL_version import __version__, __author__, __contact__
-from rMETL_concensus import construct_concensus_info
-from rMETL_genotype import add_genotype
-from rMETL_utils import load_ref, check_bai, call_ngmlr, call_samtools
-from rMETL_cmdRunner import setupLogging, exe
+from rMETL.rMETL_version import __version__, __author__, __contact__
+from rMETL.rMETL_concensus import construct_concensus_info
+from rMETL.rMETL_genotype import add_genotype
+from rMETL.rMETL_utils import load_ref, check_bai, call_ngmlr, call_samtools
+from rMETL.rMETL_cmdRunner import setupLogging, exe
 
 USAGE="""\
            _  ___  _   _____   _______   _
@@ -497,7 +495,8 @@ def load_sam_multi_processes(args):
 	analysis_pools.join()
 	samfile.close()
 
-	output_p = args.output if args.output.endswith('/') else "%s/"%(args.output)
+	output_p = args.output_dir if args.output_dir.endswith('/') else \
+	"%s/"%(args.output_dir)
 	if not os.path.exists(output_p):
 		os.mkdir(output_p)
 	merge_cmd = ("cat %ssignatures/* > %spotential_ME.fa"%(temporary_dir, output_p))
@@ -525,7 +524,7 @@ def load_sam_multi_processes(args):
 # 
 # ************************MAIN_FUNCTION*******************************
 def parseArgs(argv):
-	parser = argparse.ArgumentParser(prog="rMETL.py detection", \
+	parser = argparse.ArgumentParser(prog="rMETL detection", \
 		description=USAGE, formatter_class=argparse.RawDescriptionHelpFormatter)
 	parser.add_argument("input", metavar="[SAM,BAM,FASTA,FASTQ]", type=str, \
 		help="Input reads with/without alignment.")

src/rMETL_realign.py → src/rMETL/rMETL_realign.py

@@ -2,21 +2,19 @@
 
 ''' 
  * All rights Reserved, Designed By HIT-Bioinformatics   
- * @Title:  Map.py
- * @Package: argparse, sys, logging
  * @Description: Classify the ME types
   * @author: Jiang Tao (tjiang@hit.edu.cn)
  * @date: Apr 24 2018
- * @version V1.0.2
+ * @version V1.0.4
 '''
 
 import argparse
 import logging
 import sys
 import time
 
-from rMETL_version import __version__, __author__, __contact__
-from rMETL_cmdRunner import setupLogging, exe
+from rMETL.rMETL_version import __version__, __author__, __contact__
+from rMETL.rMETL_cmdRunner import setupLogging, exe
 
 USAGE="""\
            _  ___  _   _____   _______   _
@@ -67,7 +65,7 @@ def call_ngmlr(inFile, ref, presets, nproc, outFile, SUBREAD_LENGTH, SUBREAD_COR
 # 
 # ************************MAIN_FUNCTION*******************************
 def parseArgs(argv):
-	parser = argparse.ArgumentParser(prog="rMETL.py realignment", description=USAGE, \
+	parser = argparse.ArgumentParser(prog="rMETL realignment", description=USAGE, \
 		formatter_class=argparse.RawDescriptionHelpFormatter)
 	parser.add_argument("input", metavar="FASTA", type=str, help="Input potential_ME.fa on STAGE detection.")
 	parser.add_argument("ME_Ref", type=str, help="The transposable element concensus in fasta format.")

src/rMETL_utils.py → src/rMETL/rMETL_utils.py

@@ -4,7 +4,7 @@
 import logging
 import os
 from Bio import SeqIO
-from rMETL_cmdRunner import exe
+from rMETL.rMETL_cmdRunner import exe
 
 def load_ref(ref_g):
 	logging.info("Loading reference genome...")

src/rMETL_version.py → src/rMETL/rMETL_version.py

@@ -1,5 +1,5 @@
 # * @author: Jiang Tao (tjiang@hit.edu.cn)
 
-__version__ = '1.0.3'
+__version__ = '1.0.4'
 __author__ = 'Jiang Tao'
 __contact__ = 'tjiang@hit.edu.cn'