Merge pull request #8 from tjiangHIT/master

Version update

README.md

@@ -11,26 +11,25 @@ rMETL - realignment-based Mobile Element insertion detection Tool for Long read
 		|_|    |_|  \__/  |_| |______|     |_|     |______|
      
 
-	$ git clone https://github.com/hitbc/rMETL.git (git clone https://github.com/tjiangHIT/rMETL.git)
+	$ git clone https://github.com/tjiangHIT/rMETL.git (git clone https://github.com/hitbc/rMETL.git)
 	$ cd rMETL/
 	$ bash INSTALL.sh
 	$ ./rMETL.py
 
 ---	
 ### Introduction
-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.
-
+Mobile element insertion (MEI) is a major category of structure variations (SVs). The rapid development of long read sequencing technologies provides the opportunity to detect MEIs sensitively. However, the signals of MEI implied by noisy long reads are highly complex due to the repetitiveness of mobile elements as well as the high sequencing error rates. Herein, we propose the Realignment-based Mobile Element insertion detection Tool for Long read (rMETL). Benchmarking results of simulated and real datasets demonstrate that rMETL has the ability to discover MEIs sensitively as well as prevent false positives. It is suited to produce high-quality MEI callsets in many genomics studies.
 
 ---
 ### Simulated datasets
 
-The simulated datasets use for benchmarking are available at: https://drive.google.com/open?id=1ujV2C8e1PNAVhSkh9vKtjWLdG_OHcH-k
+The simulated datasets use for benchmarking are available at: [Google drive](https://drive.google.com/open?id=1ujV2C8e1PNAVhSkh9vKtjWLdG_OHcH-k)
 
 ---
 ### Memory usage
 
 The memory usage of rMETL can fit the configurations of most modern servers and workstations.
-Its peak memory footprint is about 12.18 Gigabytes (default setting), on a server with Intel Xeon CPU at 2.00 GHz, 1 Terabytes RAM running Linux Ubuntu 14.04. These reads were aligned to human reference genome hs37d5.
+Its peak memory footprint is about 7.05 Gigabytes (default setting), on a server with Intel Xeon CPU at 2.00 GHz, 1 Terabytes RAM running Linux Ubuntu 14.04. These reads were aligned to human reference genome hs37d5.
 
 ---
 ### Dependences
@@ -46,7 +45,7 @@ Its peak memory footprint is about 12.18 Gigabytes (default setting), on a serve
 ---
 ### Installation
 
-Current version of rMETL needs to be run on Linux operating system.
+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.
@@ -102,8 +101,9 @@ Strongly recommend making output directory manually at first.:blush:
 
 ---
 ### Citation
-Tao Jiang, Bo Liu, Junyi Li, Yadong Wang; rMETL: sensitive mobile element insertion detection with long read realignment, Bioinformatics, , btz106, https://doi.org/10.1093/bioinformatics/btz106
+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
 
 ---
 ### Contact
-For advising, bug reporting and requiring help, please contact [email protected] or [email protected]
+For advising, bug reporting and requiring help, please post on [Github Issue](https://github.com/tjiangHIT/rMETL/issues) or contact [email protected].

src/rMETL.py

@@ -33,9 +33,10 @@
   STAGE is one of
     detection    Inference of putative MEI loci.
     realignment  Realignment of chimeric read parts.
-    calling      Mobile Element Insertion calling.
+    calling      Mobile Element Insertion/Deletion calling.
     
   See README.md for documentation or --help for details
+  Strongly recommend making output directory manually at first.
   
   rMETL V%s
   Author: %s

src/rMETL_MEIcalling.py

@@ -32,9 +32,10 @@
 
     rMETL - realignment-based Mobile Element insertion detection Tool for Long read
 
-	rMETL MEI calling.
-
-	Optional output format: .bed or .vcf
+	Generate final MEI/MED callset in bed or vcf file.
+	
+	The output file called 'calling.bed' or 'calling.vcf'
+	stores in output directory.
 	
 	rMETL V%s
 	Author: %s
@@ -313,12 +314,12 @@ def call_vcf(args):
 def parseArgs(argv):
 	parser = argparse.ArgumentParser(prog="rMETL.py calling", description=USAGE, \
 		formatter_class=argparse.RawDescriptionHelpFormatter)
-	parser.add_argument("input", metavar="SAM", type=str, help="Input cluster.sam.")
+	parser.add_argument("input", metavar="SAM", type=str, help="Input cluster.sam on STAGE realignment.")
 	parser.add_argument("Reference", metavar="REFERENCE", type=str, \
-		help="The reference genome(fasta format).")
+		help="The reference genome in fasta format.")
 	parser.add_argument("format", metavar="[BED,VCF]", type=str, \
 		help="The format of the output file. [%(default)s]", default = "bed")
-	parser.add_argument('output', type=str, help = "Prefix of final call set.")
+	parser.add_argument('output', type=str, help = "Directory to output final callset.")
 	parser.add_argument('-hom', '--homozygous', \
 		help = "The mininum score of a genotyping reported as a homozygous.[%(default)s]", \
 		default = 0.8, type = float)
@@ -330,7 +331,7 @@ def parseArgs(argv):
 	parser.add_argument('-c', '--clipping_threshold', \
 		help = "Mininum threshold of realignment clipping.[%(default)s]", \
 		default = 0.5, type = float)
-	parser.add_argument('--sample', help = "The name of the sample that is noted.", \
+	parser.add_argument('--sample', help = "Sample description", \
 		default = "None", type = str)
 	parser.add_argument('--MEI', help = "Enables rMETL to display MEI/MED only.[%(default)s]", \
 		default = "True", type = str)
@@ -346,7 +347,7 @@ def run(argv):
     elif args.format == "vcf":
     	call_vcf(args)
     else:
-    	logging.error("The format is available.")
+    	logging.error("Invalid format.")
     	exit(1)
     logging.info("Finished in %0.2f seconds."%(time.time() - starttime))
 

src/rMETL_extraction.py

@@ -37,19 +37,19 @@
     rMETL - realignment-based Mobile Element insertion detection Tool for Long read
 
 
-	Map reads using NGMLR and Samtools to produce .bam file.
+	Support reads aligned with Ngmlr and sorted with Samtools
 
-	If input is a .fastq, or .fasta, we do the initial mapping
-	for you all at once.
+	If input is a fastq or fasta format file, rMETL generates
+	alignments with Ngmlr at first;
 
-	If input is a .sam, we convert and sort it to be a bam, 
-	and then make an index for it.  
+	If input is a sam format file, rMETL converts and sorts it
+	to be a bam format file;
 
-	If your input is a .bam, we extract the ME signatures and
-	collect the sub-sequence of them.
+	If your input is a bam format file with index, rMETL extracts
+	the ME signatures and collects the sub-sequence of them.
 
-	The output is a .fasta file contains potentials non-reference
-	ME clusters.
+	The output is a fasta format file called 'potential.fa' 
+	contains potentials non-reference ME clusters.
 
 	rMETL V%s
 	Author: %s
@@ -428,7 +428,7 @@ def single_pipe(out_path, chr, bam_path, low_bandary, evidence_read, SV_size):
 	'''
 	samfile = pysam.AlignmentFile(bam_path)
 	CLIP_note = dict()
-	logging.info("Resolving the chromsome %s."%(chr))
+	logging.info("Resolving chromsome %s."%(chr))
 	if chr not in CLIP_note:
 		CLIP_note[chr] = dict()
 	cluster_pos_INS = list()
@@ -455,7 +455,7 @@ def single_pipe(out_path, chr, bam_path, low_bandary, evidence_read, SV_size):
 			SV_size, low_bandary)
 		del cluster_pos_DEL
 		gc.collect()
-	logging.info("%d MEI signal locuses in the chromsome %s."%(len(Cluster_INS)+\
+	logging.info("%d MEI/MED signal loci in the chromsome %s."%(len(Cluster_INS)+\
 		len(Cluster_DEL), chr))
 	combine_result(add_genotype(Cluster_INS, samfile, low_bandary), \
 		add_genotype(Cluster_DEL, samfile, low_bandary), out_path, chr)
@@ -528,12 +528,12 @@ def parseArgs(argv):
 	parser = argparse.ArgumentParser(prog="rMETL.py detection", \
 		description=USAGE, formatter_class=argparse.RawDescriptionHelpFormatter)
 	parser.add_argument("input", metavar="[SAM,BAM,FASTA,FASTQ]", type=str, \
-		help="Input [Mapped/Unmapped] reads.")
+		help="Input reads with/without alignment.")
 	parser.add_argument("Reference", metavar="REFERENCE", type=str, \
-		help="The reference genome (fasta format).")
+		help="The reference genome in fasta format.")
 	parser.add_argument('temp_dir', type=str, \
 		help = "Temporary directory to use for distributed jobs.")
-	parser.add_argument('output', type=str, \
+	parser.add_argument('output_dir', type=str, \
 		help = "Directory to output potential ME loci.")
 	parser.add_argument('-s', '--min_support',\
 	 help = "Mininum number of reads that support a ME.[%(default)s]", \
@@ -542,7 +542,7 @@ def parseArgs(argv):
 		help = "Mininum length of ME to be reported.[%(default)s]", \
 		default = 50, type = int)
 	parser.add_argument('-d', '--min_distance', \
-		help = "Mininum distance of two ME clusters to be intergrated.[%(default)s]", \
+		help = "Mininum distance of two ME signatures to be intergrated.[%(default)s]", \
 		default = 20, type = int)
 	parser.add_argument('-t', '--threads', \
 		help = "Number of threads to use.[%(default)s]", default = 8, \

src/rMETL_realign.py

@@ -34,7 +34,7 @@
 	TE refs: Alu concensus
 		 L1 concensus
 		 SVA concensus
-	The output of this script is a .sam file.
+	The output is a sam format file called 'cluster.sam'.
 
 	rMETL V%s
 	Author: %s
@@ -69,9 +69,9 @@ def call_ngmlr(inFile, ref, presets, nproc, outFile, SUBREAD_LENGTH, SUBREAD_COR
 def parseArgs(argv):
 	parser = argparse.ArgumentParser(prog="rMETL.py realignment", description=USAGE, \
 		formatter_class=argparse.RawDescriptionHelpFormatter)
-	parser.add_argument("input", metavar="FASTA", type=str, help="Input potential_ME.fa.")
-	parser.add_argument("ME_Ref", type=str, help="The reference genome(fasta format).")
-	parser.add_argument('output', type=str, help = "Prefix of potential ME classification.")
+	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.")
+	parser.add_argument('output', type=str, help = "Directory to output realignments.")
 	parser.add_argument('-t', '--threads', help = "Number of threads to use.[%(default)s]", \
 		default = 8, type = int)
 	parser.add_argument('-x', '--presets', \

src/rMETL_version.py

@@ -1,5 +1,5 @@
 # * @author: Jiang Tao ([email protected])
 
-__version__ = '1.0.2'
+__version__ = '1.0.3'
 __author__ = 'Jiang Tao'
 __contact__ = '[email protected]'