v1.7

B-UMMI · Aug 31, 2016 · cdc055c · cdc055c
1 parent 5d7d77e
commit cdc055c
Show file tree

Hide file tree

Showing 251 changed files with 2,152 additions and 1,142 deletions.
diff --git a/INNUca.py b/INNUca.py
@@ -9,7 +9,7 @@
 
 Copyright (C) 2016 Miguel Machado <[email protected]>
 
-Last modified: August 25, 2016
+Last modified: August 31, 2016
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -39,7 +39,7 @@
 
 
 def main():
-	version = '1.6'
+	version = '1.7'
 	args = utils.parseArguments(version)
 
 	general_start_time = time.time()
@@ -94,7 +94,7 @@ def main():
 	if not args.skipTrimmomatic:
 		programs_version_dictionary['trimmomatic-0.36.jar'] = ['-version', '==', '0.36']
 	if not args.skipSPAdes:
-		programs_version_dictionary['spades.py'] = ['--version', '>=', '3.7.1']
+		programs_version_dictionary['spades.py'] = ['--version', '>=', '3.9.0']
 	if not args.skipPilon and not args.skipSPAdes:
 		programs_version_dictionary['bowtie2'] = ['--version', '>=', '2.2.9']
 		programs_version_dictionary['samtools'] = ['--version', '==', '1.3.1']
@@ -257,7 +257,7 @@ def run_INNUca(sampleName, outdir, fastq_files, args, script_path, scheme):
 
 		# Run SPAdes
 		if not args.skipSPAdes:
-			run_successfully, pass_qc, time_taken, failing, contigs = spades.runSpades(sampleName, outdir, threads, fastq_files, args.spadesNotUseCareful, args.spadesMaxMemory, args.spadesMinCoverage, args.spadesMinContigsLength, genomeSize, args.spadesKmers, maximumReadsLength, args.spadesSaveReport, args.spadesDefaultKmers)
+			run_successfully, pass_qc, time_taken, failing, contigs = spades.runSpades(sampleName, outdir, threads, fastq_files, args.spadesNotUseCareful, args.spadesMaxMemory, args.spadesMinCoverageAssembly, args.spadesMinContigsLength, genomeSize, args.spadesKmers, maximumReadsLength, args.spadesSaveReport, args.spadesDefaultKmers, args.spadesMinCoverageContigs)
 			runs['SPAdes'] = [run_successfully, pass_qc, time_taken, failing]
 
 			if run_successfully:

diff --git a/README.md b/README.md
@@ -29,7 +29,7 @@ Dependencies
  - *FastQC* = v0.11.5
  - *Trimmomatic* = v0.36 (make sure the .jar file is executable and it is
    in your PATH)
- - *SPAdes* >= v3.7.1
+ - *SPAdes* >= v3.9.0
  - *Pilon* = v1.18
  - *Bowtie2* >= v2.2.9
  - *Samtools* = v1.3.1
@@ -55,8 +55,8 @@ Usage
                      [--trimLeading N] [--trimTrailing N] [--trimKeepFiles]
                      [--spadesNotUseCareful] [--spadesMinContigsLength N]
                      [--spadesKmers 55 77 | --spadesDefaultKmers]
-                     [--spadesMaxMemory N] [--spadesMinCoverage 10]
-                     [--spadesSaveReport]
+                     [--spadesMaxMemory N] [--spadesMinCoverageAssembly 10]
+                     [--spadesMinCoverageContigs N] [--spadesSaveReport]
                      [--pilonKeepFiles] [--pilonKeepSPAdesAssembly]
 
     INNUca - Reads Control and Assembly
@@ -144,10 +144,14 @@ Usage
                             this value (default: 200)
       --spadesMaxMemory N   The maximum amount of RAM Gb for SPAdes to use
                             (default: 25)
-      --spadesMinCoverage 10
+      --spadesMinCoverageAssembly 10
                             The minimum number of reads to consider an edge in the  
                             de Bruijn graph (or path I am not sure). Can also be
                             auto or off (default: 'off')
+      --spadesMinCoverageContigs N
+                            Minimum contigs coverage. After assembly only keep
+                            contigs with reported coverage equal or above this
+                            value (default: 5)
       --spadesSaveReport    Tells INNUca to store the number of contigs and
                             assembled nucleotides for each sample
     SPAdes k-mers options (one of the following):

diff --git a/modules/spades.py b/modules/spades.py
@@ -1,13 +1,14 @@
 import utils
 import os
+import shutil
 from functools import partial
 
 
 # Run Spades
-def spades(spades_folder, threads, fastq_files, notUseCareful, maxMemory, minCoverage, kmers):
+def spades(spades_folder, threads, fastq_files, notUseCareful, maxMemory, minCoverageAssembly, kmers):
 	contigs = os.path.join(spades_folder, 'contigs.fasta')
 
-	command = ['spades.py', '', '--only-assembler', '--threads', str(threads), '--memory', str(maxMemory), '--cov-cutoff', str(minCoverage), '', '-1', fastq_files[0], '-2', fastq_files[1], '-o', spades_folder]
+	command = ['spades.py', '', '--only-assembler', '--threads', str(threads), '--memory', str(maxMemory), '--cov-cutoff', str(minCoverageAssembly), '', '-1', fastq_files[0], '-2', fastq_files[1], '-o', spades_folder]
 
 	if not notUseCareful:
 		command[1] = '--careful'
@@ -22,7 +23,7 @@ def spades(spades_folder, threads, fastq_files, notUseCareful, maxMemory, minCov
 
 
 # Rename contigs and contigs.fasta file while filtering for contigs length
-def renameFilterContigs(sampleName, outdir, spadesContigs, minContigsLength):
+def renameFilterContigs(sampleName, outdir, spadesContigs, minContigsLength, minCoverageContigs):
 	newContigsFile = os.path.join(outdir, str(sampleName + '.contigs.fasta'))
 	number_contigs = 0
 	number_bases = 0
@@ -34,18 +35,20 @@ def renameFilterContigs(sampleName, outdir, spadesContigs, minContigsLength):
 	for line in contigs:
 		if line[0] == '>':
 			if contigHeader != "":
-				if len(contigSequence) >= minContigsLength:
-					writer.write(contigHeader + "\n")
+				items = contigHeader.split('_')
+				if len(contigSequence) >= minContigsLength and float(items[5]) >= minCoverageContigs:
+					writer.write(">" + sampleName + "_" + contigHeader + "\n")
 					writer.write(contigSequence + "\n")
 					number_bases = number_bases + len(contigSequence)
 					number_contigs = number_contigs + 1
 			contigHeader = ""
 			contigSequence = ""
-			contigHeader = ">" + sampleName + "_" + line[1:].splitlines()[0]
+			contigHeader = line[1:].splitlines()[0]
 		else:
 			contigSequence = contigSequence + line.splitlines()[0]
-	if len(contigSequence) >= minContigsLength:
-		writer.write(contigHeader + "\n")
+	items = contigHeader.split('_')
+	if len(contigSequence) >= minContigsLength and float(items[5]) >= minCoverageContigs:
+		writer.write(">" + sampleName + "_" + contigHeader + "\n")
 		writer.write(contigSequence + "\n")
 		number_bases = number_bases + len(contigSequence)
 		number_contigs = number_contigs + 1
@@ -68,7 +71,7 @@ def define_kmers(kmers, maximumReadsLength):
 
 # Run SPAdes procedure
 @spades_timer
-def runSpades(sampleName, outdir, threads, fastq_files, notUseCareful, maxMemory, minCoverage, minContigsLength, estimatedGenomeSizeMb, kmers, maximumReadsLength, saveReport, defaultKmers):
+def runSpades(sampleName, outdir, threads, fastq_files, notUseCareful, maxMemory, minCoverageAssembly, minContigsLength, estimatedGenomeSizeMb, kmers, maximumReadsLength, saveReport, defaultKmers, minCoverageContigs):
 	pass_qc = False
 	failing = {}
 	failing['sample'] = False
@@ -89,11 +92,12 @@ def runSpades(sampleName, outdir, threads, fastq_files, notUseCareful, maxMemory
 		else:
 			print 'SPAdes will use the following k-mers: ' + str(kmers)
 
-	run_successfully, contigs = spades(spades_folder, threads, fastq_files, notUseCareful, maxMemory, minCoverage, kmers)
+	run_successfully, contigs = spades(spades_folder, threads, fastq_files, notUseCareful, maxMemory, minCoverageAssembly, kmers)
 
 	if run_successfully:
-		print 'Filtering for contigs with at least ' + str(minContigsLength) + ' nucleotides'
-		contigsFiltered, number_contigs, number_bases = renameFilterContigs(sampleName, outdir, contigs, minContigsLength)
+		shutil.copyfile(contigs, os.path.join(outdir, 'SPAdes_original_assembly.contigs.fasta'))
+		print 'Filtering for contigs with at least ' + str(minContigsLength) + ' nucleotides and a coverage of ' + str(minCoverageContigs)
+		contigsFiltered, number_contigs, number_bases = renameFilterContigs(sampleName, outdir, contigs, minContigsLength, minCoverageContigs)
 		print str(number_bases) + ' assembled nucleotides in ' + str(number_contigs) + ' contigs'
 
 		if saveReport:

diff --git a/modules/utils.py b/modules/utils.py
@@ -51,7 +51,8 @@ def parseArguments(version):
 	spades_options.add_argument('--spadesNotUseCareful', action='store_true', help='Tells SPAdes to only perform the assembly without the --careful option')
 	spades_options.add_argument('--spadesMinContigsLength', type=int, metavar='N', help='Filter SPAdes contigs for length greater or equal than this value', required=False, default=200)
 	spades_options.add_argument('--spadesMaxMemory', type=int, metavar='N', help='The maximum amount of RAM Gb for SPAdes to use', required=False, default=25)
-	spades_options.add_argument('--spadesMinCoverage', type=spades_cov_cutoff, metavar='10', help='The minimum number of reads to consider an edge in the de Bruijn graph (or path I am not sure). Can also be auto or off', required=False, default='off')
+	spades_options.add_argument('--spadesMinCoverageAssembly', type=spades_cov_cutoff, metavar='10', help='The minimum number of reads to consider an edge in the de Bruijn graph (or path I am not sure). Can also be auto or off', required=False, default='off')
+	spades_options.add_argument('--spadesMinCoverageContigs', type=int, metavar='N', help='Minimum contigs coverage. After assembly only keep contigs with reported coverage equal or above this value', required=False, default=5)
 	spades_options.add_argument('--spadesSaveReport', action='store_true', help='Tells INNUca to store the number of contigs and assembled nucleotides for each sample')
 
 	spades_kmers_options = parser.add_mutually_exclusive_group()
@@ -98,9 +99,9 @@ def spades_cov_cutoff(argument):
 		if argument > 0:
 			return argument
 		else:
-			argparse.ArgumentParser.error('--spadesMinCoverage must be positive integer, auto or off')
+			argparse.ArgumentParser.error('--spadesMinCoverageAssembly must be positive integer, auto or off')
 	except:
-		argparse.ArgumentParser.error('--spadesMinCoverage must be positive integer, auto or off')
+		argparse.ArgumentParser.error('--spadesMinCoverageAssembly must be positive integer, auto or off')
 
 
 def runCommandPopenCommunicate(command, shell_True, timeout_sec_None):
@@ -214,7 +215,7 @@ def setPATHvariable(doNotUseProvidedSoftware, script_path):
 	if not doNotUseProvidedSoftware:
 		fastQC = os.path.join(script_folder, 'src', 'fastqc_v0.11.5')
 		trimmomatic = os.path.join(script_folder, 'src', 'Trimmomatic-0.36')
-		spades = os.path.join(script_folder, 'src', 'SPAdes-3.7.1-Linux', 'bin')
+		spades = os.path.join(script_folder, 'src', 'SPAdes-3.9.0-Linux', 'bin')
 		bowtie2 = os.path.join(script_folder, 'src', 'bowtie2-2.2.9')
 		samtools = os.path.join(script_folder, 'src', 'samtools-1.3.1', 'bin')
 		pilon = os.path.join(script_folder, 'src', 'pilon_v1.18')

diff --git a/src/SPAdes-3.7.1-Linux/bin/bwa-spades b/src/SPAdes-3.7.1-Linux/bin/bwa-spades
diff --git a/src/SPAdes-3.7.1-Linux/bin/corrector b/src/SPAdes-3.7.1-Linux/bin/corrector
diff --git a/src/SPAdes-3.7.1-Linux/bin/dipspades b/src/SPAdes-3.7.1-Linux/bin/dipspades
diff --git a/src/SPAdes-3.7.1-Linux/bin/hammer b/src/SPAdes-3.7.1-Linux/bin/hammer
diff --git a/src/SPAdes-3.7.1-Linux/bin/ionhammer b/src/SPAdes-3.7.1-Linux/bin/ionhammer
diff --git a/src/SPAdes-3.7.1-Linux/bin/scaffold_correction b/src/SPAdes-3.7.1-Linux/bin/scaffold_correction
diff --git a/src/SPAdes-3.7.1-Linux/bin/spades b/src/SPAdes-3.7.1-Linux/bin/spades
diff --git a/src/SPAdes-3.7.1-Linux/bin/spades_init.py b/src/SPAdes-3.7.1-Linux/bin/spades_init.py
diff --git a/src/SPAdes-3.7.1-Linux/share/spades/VERSION b/src/SPAdes-3.7.1-Linux/share/spades/VERSION
diff --git a/src/SPAdes-3.7.1-Linux/share/spades/configs/debruijn/distance_estimation.info.template b/src/SPAdes-3.7.1-Linux/share/spades/configs/debruijn/distance_estimation.info.template