Python Lims.get_projects方法代码示例

# 需要导入模块: from genologics.lims import Lims [as 别名]
# 或者: from genologics.lims.Lims import get_projects [as 别名]
def generate_output(project_id, dest_plate_list, best_sample_struct,total_lanes, req_lanes, lane_maps, rounded_ratios, 
                    target_clusters, clusters_per_lane, extra_lanes, lane_volume, pool_excess, final_pool_sizes, volume_ratios, desired_ratios):
    """"Gathers the container id and well name for all samples in project"""
    timestamp = datetime.fromtimestamp(time()).strftime('%Y-%m-%d_%H:%M')
    
    #Cred to Denis for providing a base epp
    location = dict()
    lims = Lims(BASEURI, USERNAME, PASSWORD)
    allProjects = lims.get_projects()
    for proj in allProjects:
        if proj.id == project_id:
            projName = proj.name 
            break
    
    #Sets up source id    
    #All normalization processes for project
    norms=['Library Normalization (MiSeq) 4.0', 'Library Normalization (Illumina SBS) 4.0','Library Normalization (HiSeq X) 1.0']
    pros=lims.get_processes(type=norms, projectname=projName)
    #For all processes
    for p in pros:
        #For all artifacts in process
        for o in p.all_outputs():
            #If artifact is analyte type and has project name in sample
            if o.type=="Analyte" and project_id in o.name:
                location[o.name.split()[0]] = list()
                location[o.name.split()[0]].append(o.location[0].id)
                location[o.name.split()[0]].append(o.location[1])
    
    #Continue coding from here
    generate_summary(projName, best_sample_struct, timestamp, project_id, dest_plate_list, total_lanes, req_lanes, 
                     lane_maps, rounded_ratios, target_clusters, clusters_per_lane, extra_lanes, volume_ratios, desired_ratios, lane_volume, pool_excess)
    generate_csv(projName, timestamp, location, dest_plate_list, total_lanes, best_sample_struct, rounded_ratios, lane_volume, pool_excess, final_pool_sizes)
    generate_dumpfile(projName, timestamp, location, dest_plate_list, total_lanes, best_sample_struct, rounded_ratios, lane_volume, pool_excess, final_pool_sizes)

# 需要导入模块: from genologics.lims import Lims [as 别名]
# 或者: from genologics.lims.Lims import get_projects [as 别名]
class ProjectReport:

    def __init__(self, project_name):
        self.project_name = project_name
        self.project_source = os.path.join(cfg.query('sample','delivery_source'), project_name)
        self.project_delivery = os.path.join(cfg.query('sample','delivery_dest'), project_name)
        self.lims=Lims(**cfg.get('clarity'))
        self.params = {'project_name':project_name}
        self.results = {}
        self.fill_sample_names_from_lims()
        self.samples_delivered = self.read_metrics_csv(os.path.join(self.project_delivery, 'summary_metrics.csv'))
        self.get_sample_param()
        self.fill_project_information_from_lims()

    def fill_project_information_from_lims(self):
        project = self.lims.get_projects(name=self.project_name)[0]
        self.project_info = {}
        self.project_info['project_name']=['Project name:',self.project_name]
        self.project_info['project_title']=['Project title:', project.udf.get('Project Title', '')]
        self.project_info['enquiry'] = ['Enquiry no:', project.udf.get('Enquiry Number', '')]
        self.project_info['quote'] = ['Quote no:', project.udf.get('Quote No.', '')]
        self.project_info['researcher'] = ['Researcher:','%s %s (%s)'%(project.researcher.first_name,
                                                                       project.researcher.last_name,
                                                                       project.researcher.email)]
        self.project_order = ['project_name', 'project_title', 'enquiry', 'quote', 'researcher']


    def fill_sample_names_from_lims(self):
        samples = self.lims.get_samples(projectname=self.project_name)
        self.samples = [s.name for s in samples]
        self.modified_samples = [re.sub(r'[: ]','_', s.name) for s in samples]


    def get_library_workflow_from_sample(self, sample_name):
        samples = self.lims.get_samples(projectname=self.project_name, name=sample_name)
        if len(samples) == 1:
            return samples[0].udf.get('Prep Workflow')
        else:
            app_logger.error('%s samples found for sample name %s'%sample_name)

    def get_species_from_sample(self, sample_name):
        samples = self.lims.get_samples(projectname=self.project_name, name=sample_name)
        if len(samples) == 1:
            s = samples[0].udf.get('Species')
            return species_alias.get(s, s)
        else:
            app_logger.error('%s samples found for sample name %s'%sample_name)

    def parse_program_csv(self, program_csv):
        all_programs = {}
        if os.path.exists(program_csv):
            with open(program_csv) as open_prog:
                for row in csv.reader(open_prog):
                    all_programs[row[0]]=row[1]
        #TODO: change the hardcoded version of bcl2fastq
        all_programs['bcl2fastq'] = '2.17.1.14'
        for p in ['bcl2fastq','bcbio', 'bwa', 'gatk', 'samblaster']:
            if p in all_programs:
                self.params[p + '_version']=all_programs.get(p)
        

    def parse_project_summary_yaml(self, summary_yaml):
        with open(summary_yaml, 'r') as open_file:
            full_yaml = yaml.safe_load(open_file)
        sample_yaml=full_yaml['samples'][0]
        path_to_bcbio = os.path.basename(os.path.dirname(sample_yaml['dirs']['galaxy']))
        self.params['bcbio_version'] = path_to_bcbio.split('/')[-2]
        if sample_yaml['genome_build'] == 'hg38':
            self.params['genome_version'] = 'GRCh38 (with alt, decoy and HLA sequences)'

    def read_metrics_csv(self, metrics_csv):
        samples_to_info={}
        with open(metrics_csv) as open_metrics:
            reader = csv.DictReader(open_metrics, delimiter='\t', quoting=csv.QUOTE_NONE)
            for row in reader:
                samples_to_info[row['Sample Id']] = row
        return samples_to_info

    def get_sample_param(self):
        self.fill_sample_names_from_lims()
        project_size = 0
        library_workflows=set()
        species = set()
        for sample in self.samples:
            library_workflow = self.get_library_workflow_from_sample(sample)
            library_workflows.add(library_workflow)
            species.add(self.get_species_from_sample(sample))
        if len(library_workflows) == 1 :
            self.library_workflow = library_workflows.pop()
        else:
            app_logger.error('More than one workfkow used in project %s: %s'%(self.project_name, ', '.join(library_workflows)))

        if len(species) == 1 :
            self.species = species.pop()
        else:
            app_logger.error('More than one species used in project %s: %s'%(self.project_name, ', '.join(species)))


        if self.library_workflow in ['TruSeq Nano DNA Sample Prep', None] :
            self.template = 'truseq_nano_template'
#.........这里部分代码省略.........

# 需要导入模块: from genologics.lims import Lims [as 别名]
# 或者: from genologics.lims.Lims import get_projects [as 别名]
def generate_output(project, destid, total_lanes, req_lanes, lane_maps, acc_ratios):
    #Gathers the container id and well name for all samples in project
    #Cred to Denis for providing a base epp
    location = dict()
    lims = Lims(BASEURI, USERNAME, PASSWORD)
    allProjects = lims.get_projects()
    for proj in allProjects:
        if proj.id == project:
            projName = proj.name 
            break

    #All normalization processes for project
    norms=['Library Normalization (MiSeq) 4.0', 'Library Normalization (Illumina SBS) 4.0','Library Normalization (HiSeq X) 1.0']
    pros=lims.get_processes(type=norms, projectname=projName)
    #For all processes
    for p in pros:
        #For all artifacts in process
        for o in p.all_outputs():
            #If artifact is analyte type and has project name in sample
            if o.type=="Analyte" and project in o.name:
                location[o.name.split()[0]] = list()
                location[o.name.split()[0]].append(o.location[0].id)
                location[o.name.split()[0]].append(o.location[1])
                
    #PRINT section
    #Print stats including duplicates
    timestamp = datetime.fromtimestamp(time()).strftime('%Y-%m-%d_%H:%M')
    sumName = projName,  "_summary_", timestamp,".txt"
    sumName = ''.join(sumName)
    with open(sumName, "w") as summary:
        if sum(req_lanes.values()) != 0:
            OPT = sum(total_lanes)/sum(req_lanes.values())
        else: 
            OPT = 0
        output = "Ideal lanes (same schema): ", str(sum(req_lanes.values())) , ", Total lanes: ", str(sum(total_lanes)), ", OPT: ", str(round(OPT,3)),'\n'
        output = ''.join(output)
        summary.write( output )
        output = "Unique pools: ", str(len(total_lanes)), ", Average pool duplication: ", str(sum(total_lanes)/float(len(total_lanes))) ,'\n'
        output = ''.join(output)
        summary.write( output )
        
        bin = 0
        for index in xrange(1, len(lane_maps)+1):
            bin  += 1
            summary.write('\n')
            output = "Wells ", str(bin) , '-' , str(bin+int(total_lanes[index-1])-1),':','\n'
            output = ''.join(output)
            summary.write( output )
            bin += int(total_lanes[index-1]-1)
            for counter in xrange(1, len(lane_maps[index])):
                output = str(lane_maps[index][counter]),' ', str(acc_ratios[index][counter]), "%",'\n'
                output = ''.join(output)
                summary.write( output )

    
    #Creates csv   
    name = projName,"_repool_",timestamp,".csv"
    name = ''.join(name)
    wells = ['Empty','A','B','C','D','E','F','G','H']
    #Index 0 is number, index 1 is Letter
    wellIndex = [1, 1]
    destNo = 0
    
    with open(name, 'w') as csvfile:
        writer = csv.writer(csvfile)
        for index in xrange(1, len(lane_maps)+1):
            for dupes in xrange(1, int(total_lanes[index-1])+1):
                if lane_maps[index] == 0:
                    raise Exception('Error: Project not logged in x_flowcells database!')
                
                for counter in xrange(1, len(lane_maps[index])):
                    #<source plate ID>,<source well>,<volume>,<destination plate ID>,<destination well>
                    #Destination well 200 microL, minimum pipette 2 microL; acc_ratios multiplied by 2.
                    sample = lane_maps[index][counter]
                    position = wells[wellIndex[1]],':',str(wellIndex[0])
                    position = ''.join(position)
                    try:
                        output = location[sample][0],location[sample][1],str(int(acc_ratios[index][counter]*2)),str(destid[destNo]),position
                    except KeyError:
                        print "Error: Samples incorrectly parsed into database, thus causing sample name conflicts!"
                    if not acc_ratios[index][counter] == 0:
                        writer.writerow(output)
                #Increment wellsindex
                if not acc_ratios[index][counter] == 0:
                    if not wellIndex[1] >= 8:
                        wellIndex[1] += 1
                    else:
                        wellIndex[1] = 1
                        if not wellIndex[0] >= 8:
                            wellIndex[0] += 1
                        else:
                            wellIndex[0] = 1
                            destNo += 1
                            try:
                                destid[destNo]
                            except IndexError:
                                print "Critical error; not enough destination plates provided"

# 需要导入模块: from genologics.lims import Lims [as 别名]
# 或者: from genologics.lims.Lims import get_projects [as 别名]
def namesetter(PID):

    lims = Lims(BASEURI, USERNAME, PASSWORD)
    lims.check_version()
    #Find LIMS entry with same PID
    allProjects = lims.get_projects()
    for proj in allProjects:
        if proj.id == PID:
            limsproject = proj.name
            break
    #Error handling
    if not 'limsproject' in locals():
        print "{} not available in LIMS.".format(PID)
        return None
    
    #Enter project summary process
    stepname=['Project Summary 1.3']
    process=lims.get_processes(type=stepname, projectname=limsproject)
    #Error handling
    if process == []:
        print "{} for {} is not available in LIMS.".format(stepname, limsproject)
        return None

    loop = True
    while loop:
        if "Bioinfo responsible" in process[0].udf:
            response = process[0].udf["Bioinfo responsible"]
        else:
            response = "Unassigned"
        print "Existing Bioinfo responsible for project {} aka {} is: {}".format(limsproject, PID, response.encode('utf-8'))
        
        #Checks for valid name
        in_responsibles = False
        config_responsibles =Udfconfig(lims, id="1128")
        while not in_responsibles:
            newname = raw_input("Enter name of new Bioinfo responsible: ")
            for names in config_responsibles.presets:
                if newname in names:
                    in_responsibles = True
                    newname = names
            if not in_responsibles:
                print "Subset {} not found in accepted Bioinfo responsible list.".format(newname)
            else:
                print "Suggested name is {}".format(newname)
        
        confirmation = raw_input("Project {} aka {} will have {} as new Bioinfo responsible, is this correct (Y/N)? ".format(limsproject, PID, newname))
        if confirmation == 'Y' or confirmation == 'y':
            try:
                newname.decode('ascii')
                process[0].udf["Bioinfo responsible"] = unicode(newname)
                process[0].put()
                print "Project {} aka {} assigned to {}".format(limsproject, PID, newname)
                return None
            except UnicodeDecodeError:
                #Weird solution due to put function
                process[0].udf["Bioinfo responsible"] = response
                print "ERROR: You tried to use a special character, didn't you? Don't do that. New standards and stuff..."
        elif confirmation == 'N' or confirmation == 'n':
            loop = False
        else:
            print "Invalid answer."

# 需要导入模块: from genologics.lims import Lims [as 别名]
# 或者: from genologics.lims.Lims import get_projects [as 别名]
"""

import codecs

from genologics.lims import Lims

# Login parameters for connecting to a LIMS instance.
# NOTE: Modify according to your setup.
from genologics.site_cloud import BASEURI, USERNAME, PASSWORD

# Create the LIMS interface instance, and check the connection and version.
lims = Lims(BASEURI, USERNAME, PASSWORD)
lims.check_version()

# Get the list of all projects.
projects = lims.get_projects()
print len(projects), 'projects in total'

# Get the list of all projects opened since May 30th 2012.
day = '2012-05-30'
projects = lims.get_projects(open_date=day)
print len(projects), 'projects opened since', day

# Get the project with the specified LIMS id, and print some info.
project = lims.get_project('KRA61')
print project, project.name, project.open_date

print 'UDFs:'
for key, value in project.udf.items():
    if isinstance(value, unicode):
        value = codecs.encode(value, 'UTF-8')