def fastqFilesExistsLocally(self):
"""Function to check if fastq file is present on disk
"""
if not hasattr(self, 'layout'):
return False
if self.layout == 'PAIRED':
if hasattr(self, 'localfastq1Path'):
if not pu.check_files_exist(self.localfastq1Path):
return False
else:
return False
if hasattr(self, 'localfastq2Path'):
if not pu.check_files_exist(self.localfastq2Path):
return False
else:
return False
return True
else:
if hasattr(self, 'localfastqPath'):
return pu.check_files_exist(self.localfastqPath)
else:
return False
def perform_qc(self,sra_object,out_dir="",out_suffix="_bbduk",objectid="NA"):
"""Run bbduk on fastq files specified by the sra_object
sra_object: SRA
An SRA object whose fastq files will be used
out_dir: str
Path to output directory
out_suffix: string
Suffix for the output sam file
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Returns the path of fastq files after QC. tuple has one item for single end files and 2 for paired.
:rtype: tuple
"""
#make out_dir
if not out_dir:
out_dir=sra_object.directory
else:
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
if sra_object.layout=='PAIRED':
fq1=sra_object.fastq_path
fq2=sra_object.fastq2_path
out_fileName1=pu.get_file_basename(fq1)+out_suffix+".fastq"
out_fileName2=pu.get_file_basename(fq2)+out_suffix+".fastq"
out_file1Path=os.path.join(out_dir,out_fileName1)
out_file2Path=os.path.join(out_dir,out_fileName2)
internal_args=()
internal_kwargs={"in":fq1,"in2":fq2,"out":out_file1Path,"out2":out_file2Path}
#run bbduk
status=self.run(*internal_args,objectid=objectid,target=[out_file1Path,out_file2Path],**internal_kwargs)
if status:
if not pu.check_files_exist(out_file1Path,out_file2Path) and not _dryrun:
return("",)
return(out_file1Path,out_file2Path)
else:
fq=sra_object.fastq_path
out_fileName=pu.get_file_basename(fq)+out_suffix+".fastq"
out_filePath=os.path.join(out_dir,out_fileName)
internal_args=()
internal_kwargs={"in":fq,"out":out_filePath}
#run bbduk
status=self.run(*internal_args,objectid=objectid,target=out_filePath,**internal_kwargs)
if status:
if not pu.check_files_exist(out_filePath) and not _dryrun:
return("",)
return(out_filePath,)
def test_samtools():
#test sam to sorted bam
sm=tools.Samtools()
sortedBam=sm.sam_sorted_bam(testVars.hisatSam,out_dir=testVars.testDir)
print("check:"+sortedBam)
st=pu.check_files_exist(sortedBam)
assert st==True, "Failed to convert sam to sorted bam"
#test merge
mergedBam=sm.merge_bam(testVars.hisatSortedBam,testVars.starSortedBam,out_dir=testVars.testDir,**{"-f":""})
st=pu.check_files_exist(mergedBam)
assert st==True, "Failed to merge bam"
def perform_quant(self,sra_object,out_suffix="",out_dir="",objectid="NA"):
"""Run kallisto quant
sra_object: SRA
SRA object contatining paths to fastq files
out_suffix: str
suffix for output file
out_dir: str
path to output directory
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Path to kallisto out directory
:rtype: string
"""
if not out_dir:
out_dir=os.path.join(sra_object.directory,"kallisto_out")
else:
#create out_dir if not exists
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
if sra_object.layout == 'PAIRED':
args=(sra_object.fastq_path,sra_object.fastq2_path)
internal_kwargs={"-o":out_dir,"-i":self.index}
else:
args=(sra_object.fastq_path,)
internal_kwargs={"-o":out_dir,"--single":"","-i":self.index}
#targets
outfile=os.path.join(out_dir,"abundance.tsv")
newfile=os.path.join(out_dir,"abundance"+out_suffix+".tsv")
#check if final files already exists
if not _force and pu.check_files_exist(newfile):
pu.print_green('Target files {} already exist.'.format(newfile))
return newfile
#call kallisto
status=self.run(*args,subcommand='quant',objectid=sra_object.srr_accession,target=outfile,**internal_kwargs)
if status:
#return rename the bam file and return path
if not _dryrun:
pe.move_file(outfile,newfile)
if not pu.check_files_exist(newfile):
return ""
return newfile
return ""
def check_index(self):
"""Check a diamond index
"""
if not hasattr(self, "index"):
return False
if pu.check_files_exist(self.index):
return True
if pu.check_files_exist(self.index + ".dmnd"):
return True
return False
def build_index(self,index_path,index_name,fasta,verbose=False,quiet=False,logs=True,objectid="NA",**kwargs):
"""Function to build kallisto index
index_path: str
path to the output directory
index_name: str
index name
verbose: bool
Print stdout and std error
quiet: bool
Print nothing
logs: bool
Log this command to pyrpipe logs
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
kwargs: dict
Options to pass to kallisto. This will override the existing options in self.passed_args_dict (only replace existing arguments and not replace all the arguments).
:return: Status of kallisto index
:rtype: bool
"""
#check input
if not pu.check_files_exist(fasta):
pu.print_boldred("{} does not exist. Exiting".format(fasta))
return False
#create out dir
if not pu.check_paths_exist(index_path):
if not pu.mkdir(index_path):
print("ERROR in building kallisto index. Failed to create index directory.")
return False
indexOut=os.path.join(index_path,index_name)
newOpts={"--":(fasta,),"-i":indexOut}
mergedOpts={**kwargs,**newOpts}
#call salmon
status=self.run_kallisto("index",verbose=verbose,quiet=quiet,logs=logs,objectid=objectid,**mergedOpts)
if status:
#check if sam file is present in the location directory of sra_object
if pu.check_files_exist(indexOut):
self.kallisto_index=indexOut
self.passedArgumentDict['-i']=self.kallisto_index
pu.print_green("kallisto_index is:"+self.kallisto_index)
return True
else:
pu.print_boldred("Failed to create kallisto index")
return False
def search_fastq(self,path):
"""Search .fastq file under a dir and create SRA object
Return True if found otherwise False
"""
#check files with names <SRR>_1.fastq and <SRR>_2.fastq
fq=os.path.join(path,self.srr_accession+'_1.fastq')
fq2=os.path.join(path,self.srr_accession+'_2.fastq')
if pu.check_files_exist(fq,fq2):
self.fastq_path=fq
self.fastq2_path=fq2
pu.print_green("Found .fastq "+self.fastq_path+" "+self.fastq2_path)
self.layout="PAIRED"
return True
#check single end file
fq=os.path.join(path,self.srr_accession+'.fastq')
if pu.check_files_exist(fq):
self.fastq_path=fq
pu.print_green("Found .fastq "+self.fastq_path)
self.layout="SINGLE"
return True
#search files under the path
#fq_files=pe.find_files(path,"*.fastq")
fq_files=pu.find_files(path,".fastq$")
if len(fq_files)<1:
return False
if len(fq_files)>2:
return False
fq_files.sort()
#case with single fastq
if len(fq_files)==1:
self.fastq_path=fq_files[0]
pu.print_green("Found .fastq "+self.fastq_path)
self.layout="SINGLE"
#case with paired fastq
if len(fq_files)==2:
self.fastq_path=fq_files[0]
self.fastq2_path=fq_files[1]
pu.print_green("Found .fastq "+self.fastq_path+" "+self.fastq2_path)
self.layout="PAIRED"
return True
def perform_quant(self,sra_object,out_suffix="",out_dir="",objectid="NA"):
"""run salmon quant
sra_object: SRA
An SRA object with valid fastq files
out_suffix: str
suffix string fout out file
out_dir: str
path to outdir
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Path to salmon out file
:rtype: string
"""
if not out_dir:
out_dir=os.path.join(sra_object.directory,"salmon_out")
else:
#create out_dir if not exists
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
if sra_object.layout == 'PAIRED':
internal_kwargs={"-o":out_dir,"-l":"A","-1":sra_object.fastq_path,"-2":sra_object.fastq2_path,"-i":self.index}
else:
internal_kwargs={"-o":out_dir,"-l":"A","-r":sra_object.fastq_path,"-i":self.index}
#targets
outfile=os.path.join(out_dir,"quant.sf")
newfile=os.path.join(out_dir,"quant"+out_suffix+".sf")
#check if final files already exists
if not _force and pu.check_files_exist(newfile):
pu.print_green('Target files {} already exist.'.format(newfile))
return newfile
#call salmon
status=self.run(None,subcommand='quant',objectid=sra_object.srr_accession,target=newfile,**internal_kwargs)
if status:
#return rename the bam file and return path
if not _dryrun:
pe.move_file(outfile,newfile)
if not pu.check_files_exist(newfile):
return ""
return newfile
return ""
def run_transdecoder_longorfs(self,
infasta,
out_dir=None,
verbose=False,
quiet=False,
logs=True,
objectid="NA",
**kwargs):
if not pu.check_files_exist(infasta):
pu.print_boldred("Please check input file:" + infasta)
if not out_dir:
out_dir = os.getcwd()
newOpts = {"-t": infasta, "-O": out_dir}
mergedOpts = {**newOpts, **kwargs}
#execute LongOrfs
status = self.run_transdecoder('TransDecoder.LongOrfs',
verbose=verbose,
quiet=quiet,
logs=logs,
objectid=objectid,
**mergedOpts)
if not status:
pu.print_boldred("Transdecoder failed")
return ""
return out_dir
def verify_integrity(self, target, verbose=False):
"""
Verify target file is present and is not LOCKED i.e. .Lock file is not present.
Parameters
----------
target : Str
The target file.
verbose : bool, optional
Print additional messages. The default is False.
Returns
-------
bool
Return True is target is present and not Locked.
"""
#check if lock exists
lock_files = self.get_lock_files(target)
if len(lock_files) > 0:
#remove the target and locks
if pu.check_files_exist(target):
pu.print_notification(
"Found incomplete target {}. Restarting command...".format(
target))
self.remove_locks(lock_files + [target])
else:
self.remove_locks(lock_files)
return True
def download_gtex_bams(manifest_file, outdir):
#load list of bam files
with open(manifest_file, 'r') as fi:
thisdata = json.load(fi)
flist = []
#check existing files
for d in thisdata:
f = d["file_name"]
gid = f.split('.Aligned')[0]
outfile = os.path.join(outdir, gid, f)
#if pu.check_files_exist(outfile) and pu.get_mdf(outfile)==d["md5sum"]:
if pu.check_files_exist(outfile):
print("Outfile {} exists. Skipping...".format(outfile))
#copy it back to out dir
os.rename(outfile, os.path.join(outdir, f))
flist.append(d["file_name"])
cmd = 'gen3-client download-multiple --profile={} --manifest={} --download-path={} --protocol=s3 --numparallel={} --skip-completed --no-prompt'.format(
profile, m, outdir, threads)
cdcmd = 'cd {}'.format(cwd)
sshcmd = dtn_ssh + " '{}; {}'".format(cdcmd, cmd)
out = pe.get_shell_output(sshcmd, verbose=True)
#move the files
for f in flist:
source = os.path.join(outdir, f)
gid = f.split('.Aligned')[0]
destdir = os.path.join(outdir, gid)
pu.mkdir(destdir)
dest = os.path.join(destdir, f)
#print('Moving {}-->{}'.format(source,dest))
os.rename(source, dest)
def __init__(self,kallisto_index,**kwargs):
super().__init__()
self.programName="kallisto"
self.dep_list=[self.programName]
if not pe.check_dependencies(self.dep_list):
raise Exception("ERROR: "+ self.programName+" not found.")
##kallisto index
self.validArgsIndex=['-i','--index','-k','--kmer-size','--make-unique']
##kallisto quant
self.validArgsQuant=['-i','--index','-o','--output-dir','--bias','-b','--bootstrap-samples',
'--seed','--plaintext','--fusion','--single','--fr-stranded','--rf-stranded',
'-l','--fragment-length','-s','--sd','-t','--threads','--pseudobam']
##kallisto pseudo
self.validArgsPseudo=['-i','--index','-o','--output-dir','-u','--umi','-b','--batch',
'--single','-l','--fragment-length','-s','--sd','-t','--threads','--pseudobam']
##kallisto h5dump
self.validArgsh5dump=['-o','--output-dir']
self.valid_args=pu.get_union(self.validArgsIndex,self.validArgsQuant,self.validArgsPseudo,self.validArgsh5dump)
#initialize the passed arguments
self.passedArgumentDict=kwargs
#if index is passed, update the passed arguments
if len(kallisto_index)>0 and pu.check_files_exist(kallisto_index):
print("kallisto index is: "+kallisto_index)
self.kallisto_index=kallisto_index
self.passedArgumentDict['-i']=self.kallisto_index
else:
print("No kallisto index provided. Please use build_index() now to generate an index...")
def is_paired(sra_file):
"""Function to test wheather a .sra file is paired or single.
Parameters
----------
sra_file (string) the path ro sra file
:return: True is sra is paired
:rtype: bool
"""
if not pu.check_files_exist(sra_file):
raise Exception(
"Error checking layout. {0} doesn't exist".format(sra_file))
try:
fastqdCmd = ["fastq-dump", "-X", "1", "-Z", "--split-spot", sra_file]
output = subprocess.check_output(fastqdCmd, stderr=subprocess.DEVNULL)
numLines = output.decode("utf-8").count("\n")
if (numLines == 4):
return False
elif (numLines == 8):
return True
else:
raise Exception("Unexpected output from fast-dump")
except subprocess.CalledProcessError as e:
raise Exception("Error running fastq-dump: {}".format(str(e)))
def goodbye():
logfile = os.path.join(_logs_dir, _log_name + '.log')
#if log was created
if not pu.check_files_exist(logfile):
pu.print_yellow("No logs written")
return
if _dryrun:
pu.print_yellow(
"This was a dry run. Logs were saved to {}".format(
logfile))
return
pu.print_yellow("Logs were saved to {}".format(logfile))
pu.print_yellow(
"A copy of script is saved to {} with md5 checksum {}".format(
target, _md5))
#get summary from log
envlog = logfile.replace('.log', 'ENV.log')
reports.generate_summary(logfile, envlog)
#export shell commands
out_cmds = logfile + '_commands'
reports.generateBashScript(logfile, out_cmds, None, verbose=False)
out_cmds = logfile + '_failed'
reports.generateBashScript(logfile,
out_cmds,
None,
coverage='i',
verbose=False)
#run reports/multiqc if specified
if _multiqc:
reports.generate_multiqc(directory=os.getcwd(),
tempDir='MultiQC_temp',
outDir='MultiQC_out')
def build_index(self,
in_fasta,
dbname,
out_dir=None,
threads=None,
verbose=False,
quiet=False,
logs=True,
objectid="NA",
**kwargs):
"""Build a diamond index and store its path in self
"""
#check input files
if not pu.check_files_exist(in_fasta):
pu.print_boldred(
"Input fasta: {} not found...\n diamond makedb failed".format(
in_fasta))
return False
#create out_dir
if not out_dir:
out_dir = os.getcwd()
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
#check if index already exists
index_path = os.path.join(out_dir, dbname)
self.index = index_path
if self.check_index():
pu.print_green("Diamond index: {} exists, using it...".format(
self.index))
self.index = index_path
return True
if not threads:
threads = self.threads
newOpts = {
"--in": in_fasta,
"-d": index_path,
"--threads": str(threads)
}
#add input files to kwargs, overwrite newOpts with kwargs
mergedOpts = {**newOpts, **kwargs}
#call run_diamond
status = self.run_diamond("makedb",
verbose=verbose,
quiet=quiet,
logs=logs,
objectid=objectid,
**mergedOpts)
if status:
self.index = index_path
return True
return False
def test_stringtie():
bam = testVars.hisatSortedBam
gtf = testVars.gtf
stie = assembly.Stringtie()
result = stie.perform_assembly(bam,
out_dir=testVars.testDir,
objectid="test")
assert pu.check_files_exist(result) == True, "Failed stringtie"
def test_mikado():
gtfdir = testVars.mikadofiles
out_dir = testVars.testDir + "/mikadoout"
mk = tools.Mikado()
listfile = mk.createMikadoGTFlist("mikadolist", out_dir, gtfdir)
st = pu.check_files_exist(listfile)
assert st == True, "Mikado list failed"
def test_cufflinks():
bam = testVars.hisatSortedBam
gtf = testVars.gtf
cl = assembly.Cufflinks(reference_gtf=gtf)
result = cl.perform_assembly(bam,
out_dir=testVars.testDir,
objectid="test")
assert pu.check_files_exist(result) == True, "Failed stringtie"
def test_cufflinks():
bam = testVars.hisatSortedBam
gtf = testVars.gtf
cl = assembly.Cufflinks()
result = cl.perform_assembly(bam,
out_dir=testVars.testDir,
objectid="test")
print('RES:', result)
assert pu.check_files_exist(result) == True, "Failed cufflinks"
def checkEnvLog(logFile):
#check all logs exist
logFileDir=pu.get_file_directory(logFile)
basename=pu.get_file_basename(logFile)
envLog=os.path.join(logFileDir,basename+"ENV.log")
if not pu.check_files_exist(logFile,envLog):
print("Please check missing log files. Exiting.")
sys.exit(1)
return envLog
def deleteFileFromDisk(filePath):
"""Delete a given file from disk
Returns true if file is deleted or doesn't exist
"""
if pu.check_files_exist(filePath):
rm_Cmd = ['rm', filePath]
rv = getReturnStatus(rm_Cmd)
return rv
#if file doesn't exist return true
return True
def __init__(self, file):
self.__params = None
self.__kwargs = None
if not pu.check_files_exist(file):
return
#read yaml
with open(file) as f:
#self.__params=yaml.full_load(f)
self.__params = yaml.load(f, Loader=yaml.SafeLoader)
self.parse_params()
def perform_alignment(self,
sra_object,
out_suffix="_bowtie2",
out_dir="",
objectid="NA"):
"""Function to perform alignment using sra_object.
Parameters
----------
sra_object SRA object
An object of type SRA. The path to fastq files will be obtained from this object.
out_suffix: string
Suffix for the output sam file
out_dir: string
Directory to save the results. Default value is sra_object.directory
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Returns the sorted bam file path after converting sam to bam and sorting it
:rtype: string
"""
if not out_dir:
out_dir = sra_object.directory
else:
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
#create path to output sam file
outSamFile = os.path.join(
out_dir, sra_object.srr_accession + out_suffix + ".sam")
#outBamFile=os.path.join(out_dir,sra_object.srr_accession+out_suffix+"_sorted.bam")
#find layout and fq file paths
if sra_object.layout == 'PAIRED':
internal_kwargs = {
"-1": sra_object.fastq_path,
"-2": sra_object.fastq2_path,
"-S": outSamFile
}
else:
internal_kwargs = {"-U": sra_object.fastq_path, "-S": outSamFile}
status = self.run(None,
objectid=sra_object.srr_accession,
target=outSamFile,
**internal_kwargs)
if status:
if not pu.check_files_exist(outSamFile) and not _dryrun:
return ""
#convert to bam before returning; returns outBamFile
return tools.Samtools().sam_sorted_bam(outSamFile)
return ""
def run_transdecoder_predict(self,
infasta,
longorfs_dir,
out_dir=None,
verbose=False,
quiet=False,
logs=True,
objectid="NA",
**kwargs):
if not pu.check_files_exist(infasta):
pu.print_boldred("Please check input file:" + infasta)
if not pu.check_paths_exist(longorfs_dir):
pu.print_boldred("Path {} doesn't exist".format(longorfs_dir))
move_flag = True
if not out_dir:
out_dir = os.getcwd()
move_flag = False
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
newOpts = {"-t": infasta, "-O": longorfs_dir}
mergedOpts = {**newOpts, **kwargs}
#execute Predict
status = self.run_transdecoder('TransDecoder.Predict',
verbose=verbose,
quiet=quiet,
logs=logs,
objectid=objectid,
**mergedOpts)
if not status:
pu.print_boldred("Transdecoder failed")
return ""
#move output files to outdir
if move_flag:
outfile_prefix = pu.get_filename(infasta) + ".transdecoder"
pe.move_file(outfile_prefix + ".bed",
os.path.join(out_dir, outfile_prefix + ".bed"),
verbose)
pe.move_file(outfile_prefix + ".cds",
os.path.join(out_dir, outfile_prefix + ".cds"),
verbose)
pe.move_file(outfile_prefix + ".gff3",
os.path.join(out_dir, outfile_prefix + ".gff3"),
verbose)
pe.move_file(outfile_prefix + ".pep",
os.path.join(out_dir, outfile_prefix + ".pep"),
verbose)
return out_dir
def __init__(self, *args, index=None, genome=None, threads=None, **kwargs):
"""
init Hisat2 object
Parameters
----------
*args : tuple
Positional arguements
index : Str, optional
Path to Hisat index. If index is not present it will generate an index using the genome. Index can be supplied via the hisat2.yaml file too. The default is None.
genome : Str, optional
Path to the reference genome. This will be used to build an index if index is not present The default is None.
threads : int, optional
Threads to use for hisat2. This will override the global --threads parameter supplied to pyrpipe. The default is None.
**kwargs : dict
keyword arguments
Raises
------
ValueError
Raises ValueError if hisat index is not found and genome is not present to generate an index.
Returns
-------
None.
"""
super().__init__(*args, **kwargs)
self._command = 'hisat2'
self._deps = [self._command, 'samtools']
self.index = index
self.genome = genome
self._param_yaml = 'hisat2.yaml'
self._valid_args = valid_args._args_HISAT2
#resolve threads to use
self.resolve_parameter("-p", threads, _threads, '_threads')
#resolve index to use
self.resolve_parameter("-x", index, index, 'index')
#check index
if not self.check_index():
if not (pu.check_files_exist(self.genome)):
pu.print_boldred(
"Hisat2 index '{}' not found; New index could not be created as genome file '{}' not found."
.format(self.index, self.genome))
raise ValueError(
"Please provide a valid Hisat2 index, or a valid fasta file to generate the index"
)
else:
#call build index to generate index
self.build_index(self.index, self.genome)
def perform_assembly(self,
bam_file,
out_dir=None,
out_suffix="_stringtie",
objectid="NA"):
"""Function to run stringtie using a bam file.
Parameters
----------
bam_file: string
path to the bam file
out_dir: string
Path to out file
out_suffix: string
Suffix for the output gtf file
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Returns the path to output GTF file
:rtype: string
"""
#create path to output file
fname = pu.get_file_basename(bam_file)
if not out_dir:
out_dir = pu.get_file_directory(bam_file)
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
out_gtf_file = os.path.join(out_dir, fname + out_suffix + ".gtf")
#Add output file name and input bam
internal_args = (bam_file, )
internal_kwargs = {"-o": out_gtf_file}
#add positional args
internal_kwargs['--'] = internal_args
#call stringtie
status = self.run(None,
objectid=objectid,
target=out_gtf_file,
**internal_kwargs)
if status:
#check if sam file is present in the location directory of sraOb
if not pu.check_files_exist(out_gtf_file) and not _dryrun:
return ""
return out_gtf_file
return ""
def init_object(self,srr_accession,directory,fastq,fastq2,sra):
#if fastq are provided
if fastq and fastq2:
self.layout="PAIRED"
self.directory=pu.get_file_directory(fastq)
if not pu.check_files_exist(fastq,fastq2) and not _dryrun:
pu.print_boldred("ERROR: File not found")
raise ValueError("Please check fastq files {} {}".format(fastq,fastq2))
return True
#if only one fastq (single)
if fastq:
self.layout="SINGLE"
self.directory=pu.get_file_directory(fastq)
if not pu.check_files_exist(fastq) and not _dryrun:
pu.print_boldred("ERROR: File not found")
raise ValueError("Please check fastq files {}".format(fastq))
return True
#init from srr_accession and directory
return self.init_from_accession(srr_accession,directory)
def test_diamond():
dm = tools.Diamond(index="", mode='sensitive')
dm.build_index(testVars.uniprot,
"diamondDB",
out_dir=testVars.testDir + "/dout")
dm.run_align(testVars.cdna,
"diamond_out",
command="blastx",
out_fmt=6,
fmt_string="qseqid sseqid evalue pident",
out_dir=testVars.testDir + "/dout")
st = pu.check_files_exist(testVars.testDir + "/dout/diamond_out")
assert st == True, "Diamond failed"
def build_index(self,index_path,index_name,fasta,verbose=False,quiet=False,logs=True,objectid="NA",**kwargs):
"""
build salmon index and store the path to index in self
index_path: str
path to the output directory
index_name: str
index name
verbose: bool
Print stdout and std error
quiet: bool
Print nothing
logs: bool
Log this command to pyrpipe logs
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
kwargs: dict
Options to pass to salmon. This will override the existing options
:return: status of salmon index
:rtype: bool
"""
#check input
if not pu.check_files_exist(fasta):
pu.print_boldred("{} does not exist. Exiting".format(fasta))
return False
#create out dir
if not pu.check_paths_exist(index_path):
if not pu.mkdir(index_path):
print("ERROR in building hisat2 index. Failed to create index directory.")
return False
indexOut=os.path.join(index_path,index_name)
newOpts={"-t":fasta,"-i":indexOut}
mergedOpts={**kwargs,**newOpts}
#call salmon
status=self.run_salmon("index",verbose=verbose,quiet=quiet,logs=logs,objectid=objectid,**mergedOpts)
if status:
#check if sam file is present in the location directory of sra_object
#if check_files_exist(os.path.join(indexOut,"versionInfo.json")): #not sure if this is reliable
if pu.check_paths_exist(indexOut):
self.salmon_index=indexOut
self.passedArgumentDict['-i']=self.salmon_index
pu.print_green("salmon index is:"+self.salmon_index)
return True
pu.print_boldred("Failed to create salmon index")
return False
def fastq_exists(self):
"""Function to check if fastq file is present on disk
"""
if not hasattr(self,'layout'):
return False
if self.layout=='PAIRED':
if hasattr(self,'fastq_path'):
if not self.fastq_path:
#if None
return False
if not pu.check_files_exist(self.fastq_path):
return False
else:
return False
if hasattr(self,'fastq2_path'):
if not self.fastq2_path:
#if None
return False
if not pu.check_files_exist(self.fastq2_path):
return False
else:
return False
return True
else:
if hasattr(self,'fastq_path'):
if not self.fastq_path:
#if None
return False
return pu.check_files_exist(self.fastq_path)
else:
return False
