Ejemplo n.º 1
0
def get_fastqc_process_starter():
    '''
    Get the FastQC process starter path in the local computer.
    '''

    # assign the FastQC process starter path
    fastqc_process_starter = '{0}/{1}-process-starter.sh'.format(
        xlib.get_temp_dir(), xlib.get_fastqc_code())

    # return the FastQC starter path
    return fastqc_process_starter
Ejemplo n.º 2
0
def get_fastqc_config_file():
    '''
    Get the FastQC config file path.
    '''

    # assign the FastQC config file path
    fastqc_config_file = '{0}/{1}-config.txt'.format(xlib.get_config_dir(),
                                                     xlib.get_fastqc_code())

    # return the FastQC config file path
    return fastqc_config_file
Ejemplo n.º 3
0
def run_fastqc_process(cluster_name, log, function=None):
    '''
    Run a FastQC process.
    '''

    # initialize the control variable
    OK = True

    # get the FastQC option dictionary
    fastqc_option_dict = xlib.get_option_dict(get_fastqc_config_file())

    # get the experiment identification
    experiment_id = fastqc_option_dict['identification']['experiment_id']

    # warn that the log window must not be closed
    if not isinstance(log, xlib.DevStdOut):
        log.write(
            'This process might take several minutes. Do not close this window, please wait!\n'
        )

    # validate the FastQC config file
    log.write('{0}\n'.format(xlib.get_separator()))
    log.write('Validating the {0} config file ...\n'.format(
        xlib.get_fastqc_name()))
    (OK, error_list) = validate_fastqc_config_file(strict=True)
    if OK:
        log.write('The config file is OK.\n')
    else:
        log.write('*** ERROR: The config file is not valid.\n')
        log.write('Please correct this file or recreate the config files.\n')

    # create the SSH client connection
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Connecting the SSH client ...\n')
        (OK, error_list, ssh_client) = xssh.create_ssh_client_connection(
            cluster_name, 'master')
        if OK:
            log.write('The SSH client is connected.\n')
        else:
            for error in error_list:
                log.write('{0}\n'.format(error))

    # create the SSH transport connection
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Connecting the SSH transport ...\n')
        (OK, error_list, ssh_transport) = xssh.create_ssh_transport_connection(
            cluster_name, 'master')
        if OK:
            log.write('The SSH transport is connected.\n')
        else:
            for error in error_list:
                log.write('{0}\n'.format(error))

    # create the SFTP client
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Connecting the SFTP client ...\n')
        sftp_client = xssh.create_sftp_client(ssh_transport)
        log.write('The SFTP client is connected.\n')

    # warn that the requirements are being verified
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Verifying process requirements ...\n')

    # verify the master is running
    if OK:
        (master_state_code,
         master_state_name) = xec2.get_node_state(cluster_name, 'master')
        if master_state_code != 16:
            log.write(
                '*** ERROR: The cluster {0} is not running. Its state is {1} ({2}).\n'
                .format(cluster_name, master_state_code, master_state_name))
            OK = False

    # verify the FastQC is set up
    if OK:
        (OK, error_list, is_setup) = xbioinfoapp.is_setup_bioconda_package(
            xlib.get_fastqc_bioconda_code(), cluster_name, True, ssh_client)
        if OK:
            if not is_setup:
                log.write('*** ERROR: {0} is not setup.\n'.format(
                    xlib.get_fastqc_name()))
                OK = False
        else:
            log.write(
                '*** ERROR: The verification of {0} setup could not be performed.\n'
                .format(xlib.get_fastqc_name()))

    # warn that the requirements are OK
    if OK:
        log.write('Process requirements are OK.\n')

    # determine the run directory in the cluster
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Determining the run directory in the cluster ...\n')
        current_run_dir = xlib.get_cluster_current_run_dir(
            experiment_id, xlib.get_fastqc_code())
        command = 'mkdir --parents {0}'.format(current_run_dir)
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write('The directory path is {0}.\n'.format(current_run_dir))
        else:
            log.write('*** ERROR: Wrong command ---> {0}\n'.format(command))

    # build the FastQC process script
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Building the process script {0} ...\n'.format(
            get_fastqc_process_script()))
        (OK, error_list) = build_fastqc_process_script(cluster_name,
                                                       current_run_dir)
        if OK:
            log.write('The file is built.\n')
        if not OK:
            log.write('*** ERROR: The file could not be built.\n')

    # upload the FastQC process script to the cluster
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write(
            'Uploading the process script {0} to the directory {1} of the master ...\n'
            .format(get_fastqc_process_script(), current_run_dir))
        cluster_path = '{0}/{1}'.format(
            current_run_dir, os.path.basename(get_fastqc_process_script()))
        (OK, error_list) = xssh.put_file(sftp_client,
                                         get_fastqc_process_script(),
                                         cluster_path)
        if OK:
            log.write('The file is uploaded.\n')
        else:
            for error in error_list:
                log.write('{0}\n'.format(error))

    # set run permision to the FastQC process script in the cluster
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Setting on the run permision of {0}/{1} ...\n'.format(
            current_run_dir, os.path.basename(get_fastqc_process_script())))
        command = 'chmod u+x {0}/{1}'.format(
            current_run_dir, os.path.basename(get_fastqc_process_script()))
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write('The run permision is set.\n')
        else:
            log.write('*** ERROR: Wrong command ---> {0}\n'.format(command))

    # build the FastQC process starter
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Building the process starter {0} ...\n'.format(
            get_fastqc_process_starter()))
        (OK, error_list) = build_fastqc_process_starter(current_run_dir)
        if OK:
            log.write('The file is built.\n')
        if not OK:
            log.write('***ERROR: The file could not be built.\n')

    # upload the FastQC process starter to the cluster
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write(
            'Uploading the process starter {0} to the directory {1} of the master ...\n'
            .format(get_fastqc_process_starter(), current_run_dir))
        cluster_path = '{0}/{1}'.format(
            current_run_dir, os.path.basename(get_fastqc_process_starter()))
        (OK, error_list) = xssh.put_file(sftp_client,
                                         get_fastqc_process_starter(),
                                         cluster_path)
        if OK:
            log.write('The file is uploaded.\n')
        else:
            for error in error_list:
                log.write('{0}\n'.format(error))

    # set run permision to the FastQC process starter in the cluster
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Setting on the run permision of {0}/{1} ...\n'.format(
            current_run_dir, os.path.basename(get_fastqc_process_starter())))
        command = 'chmod u+x {0}/{1}'.format(
            current_run_dir, os.path.basename(get_fastqc_process_starter()))
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write('The run permision is set.\n')
        else:
            log.write('*** ERROR: Wrong command ---> {0}\n'.format(command))

    # submit the FastQC process
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Submitting the process script {0}/{1} ...\n'.format(
            current_run_dir, os.path.basename(get_fastqc_process_starter())))
        sge_env = xcluster.get_sge_env()
        command = '{0}; qsub -V -b n -cwd {1}/{2}'.format(
            sge_env, current_run_dir,
            os.path.basename(get_fastqc_process_starter()))
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            for line in stdout:
                log.write('{0}\n'.format(line))
        else:
            log.write('*** ERROR: Wrong command ---> {0}\n'.format(command))

    # close the SSH transport connection
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Closing the SSH transport connection ...\n')
        xssh.close_ssh_transport_connection(ssh_transport)
        log.write('The connection is closed.\n')

    # close the SSH client connection
    if OK:
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('Closing the SSH client connection ...\n')
        xssh.close_ssh_client_connection(ssh_client)
        log.write('The connection is closed.\n')

    # warn that the log window can be closed
    if not isinstance(log, xlib.DevStdOut):
        log.write('{0}\n'.format(xlib.get_separator()))
        log.write('You can close this window now.\n')

    # execute final function
    if function is not None:
        function()

    # return the control variable
    return OK
Ejemplo n.º 4
0
def get_result_dataset_dict(cluster_name, experiment_id, status, passed_connection, ssh_client):
    '''
    Get a dictionary with the result datasets of an experiment in the cluster.
    '''

    # initialize the control variable and the error list
    OK = True
    error_list = []

    # get the result directory in the cluster
    cluster_result_dir = xlib.get_cluster_result_dir()

    # initialize the dictionary of the result datasets
    result_dataset_dict = {}

    # create the SSH client connection
    if not passed_connection:
        (OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')

    # verify the result directory is created
    if OK:
        command = '[ -d {0} ] && echo RC=0 || echo RC=1'.format(cluster_result_dir)
        (OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
        if stdout[len(stdout) - 1] != 'RC=0':
            error_list.append('*** ERROR: There is not any volume mounted in the result directory.\n')
            error_list.append('You must link a volume in the mounting point {0} for the template {1}.\n'.format(cluster_result_dir, cluster_name))
            OK = False

    # get the dictionary of the result datasets
    if OK:
        if status == 'uncompressed':
            command = 'cd  {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
        elif status == 'compressed':
            command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^d > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
        (OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            if status == 'uncompressed':
                input_pattern = '{0}-(.+)-(.+)'
                output_pattern = '{0} ({1} {2})'
            elif status == 'compressed':
                input_pattern = '{0}-(.+)-(.+).tar.gz'
                output_pattern = '{0} ({1} {2}) [compressed]'
            for line in stdout:
                line = line.rstrip('\n')
                if line != 'lost+found':
                    result_dataset_id = line
                    if result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_cd_hit_est_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_cd_hit_est_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_fastqc_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_fastqc_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_gzip_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_gzip_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_insilico_read_normalization_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_insilico_read_normalization_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_quast_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_quast_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_ref_eval_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_ref_eval_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_rnaquast_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_rnaquast_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_rsem_eval_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_rsem_eval_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_soapdenovotrans_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_soapdenovotrans_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_star_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_star_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_transabyss_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_transabyss_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_transcript_filter_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_transcript_filter_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_transcriptome_blastx_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_transcriptome_blastx_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_transrate_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_transrate_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_trimmomatic_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_trimmomatic_name(), date, time)
                    elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
                        mo = re.match(input_pattern.format(xlib.get_trinity_code()), result_dataset_id)
                        date = mo.group(1)
                        time = mo.group(2)
                        result_dataset_name = output_pattern.format(xlib.get_trinity_name(), date, time)
                    else:
                        result_dataset_name = result_dataset_id
                    result_dataset_dict[result_dataset_id] = {'result_dataset_id': result_dataset_id, 'result_dataset_name': result_dataset_name}

    # close the SSH client connection
    if OK and not passed_connection:
        xssh.close_ssh_client_connection(ssh_client)

    # return the control variable, error list and dictionary of the result datasets
    return (OK, error_list, result_dataset_dict)
Ejemplo n.º 5
0
def form_list_cluster_experiment_processes():
    '''
    List the processes of an experiment in the cluster.
    '''

    # initialize the control variable
    OK = True

    # print the header
    clib.clear_screen()
    clib.print_headers_with_environment('Logs - List experiment processes in the cluster')

    # get the cluster name
    print(xlib.get_separator())
    if xec2.get_running_cluster_list(volume_creator_included=False) != []:
        cluster_name = cinputs.input_cluster_name(volume_creator_included=False, help=True)
    else:
        print('WARNING: There is not any running cluster.')
        OK = False

    # create the SSH client connection
    if OK:
        (OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
        for error in error_list:
            log.write('{0}\n'.format(error))

    # get experiment identification
    if OK:
        experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
        if experiment_id == '':
            print('WARNING: The cluster {0} has not experiment data.'.format(cluster_name))
            OK = False

    # get the result dataset list of the experiment
    if OK:
        command = 'cd  {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), experiment_id)
        (OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            result_dataset_id_list = []
            for line in stdout:
                line = line.rstrip('\n')
                if line != 'lost+found':
                    result_dataset_id_list.append(line)

    # print the result dataset identification list of the experiment
    if OK:
        print(xlib.get_separator())
        if result_dataset_id_list == []:
            print('*** WARNING: There is not any result dataset of the experiment {0}.'.format(experiment_id))
        else:
            result_dataset_id_list.sort()
            # set data width
            result_dataset_width = 25
            bioinfo_app_width = 25
            # set line template
            line_template = '{0:' + str(result_dataset_width) + '}   {1:' + str(bioinfo_app_width) + '}'
            # print header
            print(line_template.format('Result dataset', 'Bioinfo app / Utility'))
            print(line_template.format('=' * result_dataset_width, '=' * bioinfo_app_width))
            # print detail lines
            for result_dataset_id in result_dataset_id_list:
                if result_dataset_id.startswith(xlib.get_bedtools_code()+'-'):
                    bioinfo_app_name = xlib.get_bedtools_name()
                elif result_dataset_id.startswith(xlib.get_blastplus_code()+'-'):
                    bioinfo_app_name = xlib.get_blastplus_name()
                elif result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
                    bioinfo_app_name = xlib.get_bowtie2_name()
                elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
                    bioinfo_app_name = xlib.get_busco_name()
                elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
                    bioinfo_app_name = xlib.get_cd_hit_est_name()
                elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
                    bioinfo_app_name = xlib.get_cd_hit_est_name()
                elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
                    bioinfo_app_name = xlib.get_detonate_name()
                elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
                    bioinfo_app_name = xlib.get_emboss_name()
                elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
                    bioinfo_app_name = xlib.get_fastqc_name()
                elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
                    bioinfo_app_name = xlib.get_gmap_name()
                elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code()+'-'):
                    bioinfo_app_name = xlib.get_gmap_gsnap_name()
                elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
                    bioinfo_app_name = xlib.get_gzip_name()
                elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
                    bioinfo_app_name = xlib.get_insilico_read_normalization_name()
                elif result_dataset_id.startswith(xlib.get_miniconda3_code()+'-'):
                    bioinfo_app_name = xlib.get_miniconda3_name()
                elif result_dataset_id.startswith(xlib.get_ngshelper_code()+'-'):
                    bioinfo_app_name = xlib.get_ngshelper_name()
                elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
                    bioinfo_app_name = xlib.get_quast_name()
                elif result_dataset_id.startswith(xlib.get_r_code()+'-'):
                    bioinfo_app_name = xlib.get_r_name()
                elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
                    bioinfo_app_name = xlib.get_ref_eval_name()
                elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
                    bioinfo_app_name = xlib.get_rnaquast_name()
                elif result_dataset_id.startswith(xlib.get_rsem_code()+'-'):
                    bioinfo_app_name = xlib.get_rsem_name()
                elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
                    bioinfo_app_name = xlib.get_rsem_eval_name()
                elif result_dataset_id.startswith(xlib.get_samtools_code()+'-'):
                    bioinfo_app_name = xlib.get_samtools_name()
                elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
                    bioinfo_app_name = xlib.get_soapdenovotrans_name()
                elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
                    bioinfo_app_name = xlib.get_star_name()
                elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
                    bioinfo_app_name = xlib.get_transabyss_name()
                elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
                    bioinfo_app_name = xlib.get_transcript_filter_name()
                elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
                    bioinfo_app_name = xlib.get_transcriptome_blastx_name()
                elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
                    bioinfo_app_name = xlib.get_transrate_name()
                elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
                    bioinfo_app_name = xlib.get_trimmomatic_name()
                elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
                    bioinfo_app_name = xlib.get_trinity_name()
                else:
                    bioinfo_app_name = 'xxx'
                print(line_template.format(result_dataset_id, bioinfo_app_name))

    # close the SSH client connection
    if OK:
        xssh.close_ssh_client_connection(ssh_client)

    # show continuation message 
    print(xlib.get_separator())
    input('Press [Intro] to continue ...')
Ejemplo n.º 6
0
def run_fastqc_process(cluster_name, log, function=None):
    '''
    Run a FastQC process.
    '''

    # initialize the control variable
    OK = True

    # get the FastQC option dictionary
    fastqc_option_dict = xlib.get_option_dict(get_fastqc_config_file())

    # get the experiment identification
    experiment_id = fastqc_option_dict['identification']['experiment_id']

    # warn that the log window does not have to be closed
    if not isinstance(log, xlib.DevStdOut):
        log.write(
            'This process might take several minutes. Do not close this window, please wait!\n'
        )

    # check the FastQC config file
    log.write(f'{xlib.get_separator()}\n')
    log.write(f'Checking the {xlib.get_fastqc_name()} config file ...\n')
    (OK, error_list) = check_fastqc_config_file(strict=True)
    if OK:
        log.write('The file is OK.\n')
    else:
        log.write('*** ERROR: The config file is not valid.\n')
        log.write('Please correct this file or recreate the config files.\n')

    # create the SSH client connection
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Connecting the SSH client ...\n')
        (OK, error_list,
         ssh_client) = xssh.create_ssh_client_connection(cluster_name)
        if OK:
            log.write('The SSH client is connected.\n')
        else:
            for error in error_list:
                log.write(f'{error}\n')

    # create the SSH transport connection
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Connecting the SSH transport ...\n')
        (OK, error_list,
         ssh_transport) = xssh.create_ssh_transport_connection(cluster_name)
        if OK:
            log.write('The SSH transport is connected.\n')
        else:
            for error in error_list:
                log.write(f'{error}\n')

    # create the SFTP client
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Connecting the SFTP client ...\n')
        sftp_client = xssh.create_sftp_client(ssh_transport)
        log.write('The SFTP client is connected.\n')

    # warn that the requirements are being verified
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Checking process requirements ...\n')

    # check the master is running
    if OK:
        (master_state_code,
         master_state_name) = xec2.get_node_state(cluster_name)
        if master_state_code != 16:
            log.write(
                f'*** ERROR: The cluster {cluster_name} is not running. Its state is {master_state_code} ({master_state_name}).\n'
            )
            OK = False

    # check the FastQC is installed
    if OK:
        (OK, error_list,
         is_installed) = xbioinfoapp.is_installed_anaconda_package(
             xlib.get_fastqc_anaconda_code(), cluster_name, True, ssh_client)
        if OK:
            if not is_installed:
                log.write(
                    f'*** ERROR: {xlib.get_fastqc_name()} is not installed.\n')
                OK = False
        else:
            log.write(
                f'*** ERROR: The verification of {xlib.get_fastqc_name()} installation could not be performed.\n'
            )

    # warn that the requirements are OK
    if OK:
        log.write('Process requirements are OK.\n')

    # determine the run directory in the cluster
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Determining the run directory in the cluster ...\n')
        current_run_dir = xlib.get_cluster_current_run_dir(
            experiment_id, xlib.get_fastqc_code())
        command = f'mkdir --parents {current_run_dir}'
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write(f'The directory path is {current_run_dir}.\n')
        else:
            log.write(f'*** ERROR: Wrong command ---> {command}\n')

    # build the FastQC process script
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Building the process script {get_fastqc_process_script()} ...\n')
        (OK, error_list) = build_fastqc_process_script(cluster_name,
                                                       current_run_dir)
        if OK:
            log.write('The file is built.\n')
        if not OK:
            log.write('*** ERROR: The file could not be built.\n')

    # upload the FastQC process script to the cluster
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Uploading the process script {get_fastqc_process_script()} to the directory {current_run_dir} ...\n'
        )
        cluster_path = f'{current_run_dir}/{os.path.basename(get_fastqc_process_script())}'
        (OK, error_list) = xssh.put_file(sftp_client,
                                         get_fastqc_process_script(),
                                         cluster_path)
        if OK:
            log.write('The file is uploaded.\n')
        else:
            for error in error_list:
                log.write(f'{error}\n')

    # set run permision to the FastQC process script in the cluster
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Setting on the run permision of {current_run_dir}/{os.path.basename(get_fastqc_process_script())} ...\n'
        )
        command = f'chmod u+x {current_run_dir}/{os.path.basename(get_fastqc_process_script())}'
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write('The run permision is set.\n')
        else:
            log.write(f'*** ERROR: Wrong command ---> {command}\n')

    # build the FastQC process starter
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Building the process starter {get_fastqc_process_starter()} ...\n'
        )
        (OK, error_list) = build_fastqc_process_starter(current_run_dir)
        if OK:
            log.write('The file is built.\n')
        if not OK:
            log.write('***ERROR: The file could not be built.\n')

    # upload the FastQC process starter to the cluster
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Uploading the process starter {get_fastqc_process_starter()} to the directory {current_run_dir} ...\n'
        )
        cluster_path = f'{current_run_dir}/{os.path.basename(get_fastqc_process_starter())}'
        (OK, error_list) = xssh.put_file(sftp_client,
                                         get_fastqc_process_starter(),
                                         cluster_path)
        if OK:
            log.write('The file is uploaded.\n')
        else:
            for error in error_list:
                log.write(f'{error}\n')

    # set run permision to the FastQC process starter in the cluster
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Setting on the run permision of {current_run_dir}/{os.path.basename(get_fastqc_process_starter())} ...\n'
        )
        command = f'chmod u+x {current_run_dir}/{os.path.basename(get_fastqc_process_starter())}'
        (OK, stdout,
         stderr) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            log.write('The run permision is set.\n')
        else:
            log.write(f'*** ERROR: Wrong command ---> {command}\n')

    # submit the FastQC process
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write(
            f'Submitting the process script {current_run_dir}/{os.path.basename(get_fastqc_process_starter())} ...\n'
        )
        OK = xssh.submit_script(cluster_name, ssh_client, current_run_dir,
                                os.path.basename(get_fastqc_process_starter()),
                                log)

    # close the SSH transport connection
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Closing the SSH transport connection ...\n')
        xssh.close_ssh_transport_connection(ssh_transport)
        log.write('The connection is closed.\n')

    # close the SSH client connection
    if OK:
        log.write(f'{xlib.get_separator()}\n')
        log.write('Closing the SSH client connection ...\n')
        xssh.close_ssh_client_connection(ssh_client)
        log.write('The connection is closed.\n')

    # warn that the log window can be closed
    if not isinstance(log, xlib.DevStdOut):
        log.write(f'{xlib.get_separator()}\n')
        log.write('You can close this window now.\n')

    # execute final function
    if function is not None:
        function()

    # return the control variable
    return OK
Ejemplo n.º 7
0
    def execute(self, event=None):
        '''
        Execute the list the result logs in the cluster.
        '''

        # validate inputs
        OK = self.validate_inputs()
        if not OK:
            message = 'Some input values are not OK.'
            tkinter.messagebox.showerror('{0} - {1}'.format(xlib.get_project_name(), self.head), message)

        # get the run dictionary of the experiment
        if OK:
            # -- command = 'ls {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
            command = 'cd  {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
            (OK, stdout, stderr) = xssh.execute_cluster_command(self.ssh_client, command)
            if OK:
                result_dataset_dict = {}
                for line in stdout:
                    line = line.rstrip('\n')
                    if line != 'lost+found':
                        result_dataset_id = line
                        try:
                            pattern = r'^(.+)\-(.+)\-(.+)$'
                            mo = re.search(pattern, result_dataset_id)
                            bioinfo_app_code = mo.group(1).strip()
                            yymmdd = mo.group(2)
                            hhmmss = mo.group(3)
                            date = '20{0}-{1}-{2}'.format(yymmdd[:2], yymmdd[2:4], yymmdd[4:])
                            time = '{0}:{1}:{2}'.format(hhmmss[:2], hhmmss[2:4], hhmmss[4:])
                        except:
                            bioinfo_app_code = 'xxx'
                            date = '0000-00-00'
                            time = '00:00:00'
                        if result_dataset_id.startswith(xlib.get_bedtools_code()+'-'):
                            bioinfo_app_name = xlib.get_bedtools_name()
                        elif result_dataset_id.startswith(xlib.get_blastplus_code()+'-'):
                            bioinfo_app_name = xlib.get_blastplus_name()
                        elif result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
                            bioinfo_app_name = xlib.get_bowtie2_name()
                        elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
                            bioinfo_app_name = xlib.get_busco_name()
                        elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
                            bioinfo_app_name = xlib.get_cd_hit_name()
                        elif result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
                            bioinfo_app_name = xlib.get_cd_hit_est_name()
                        elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
                            bioinfo_app_name = xlib.get_detonate_name()
                        elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
                            bioinfo_app_name = xlib.get_emboss_name()
                        elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
                            bioinfo_app_name = xlib.get_fastqc_name()
                        elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
                            bioinfo_app_name = xlib.get_gmap_name()
                        elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code()+'-'):
                            bioinfo_app_name = xlib.get_gmap_gsnap_name()
                        elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
                            bioinfo_app_name = xlib.get_gzip_name()
                        elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
                            bioinfo_app_name = xlib.get_insilico_read_normalization_name()
                        elif result_dataset_id.startswith(xlib.get_miniconda3_code()+'-'):
                            bioinfo_app_name = xlib.get_miniconda3_name()
                        elif result_dataset_id.startswith(xlib.get_ngshelper_code()+'-'):
                            bioinfo_app_name = xlib.get_ngshelper_name()
                        elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
                            bioinfo_app_name = xlib.get_quast_name()
                        elif result_dataset_id.startswith(xlib.get_r_code()+'-'):
                            bioinfo_app_name = xlib.get_r_name()
                        elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
                            bioinfo_app_name = xlib.get_ref_eval_name()
                        elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
                            bioinfo_app_name = xlib.get_rnaquast_name()
                        elif result_dataset_id.startswith(xlib.get_rsem_code()+'-'):
                            bioinfo_app_name = xlib.get_rsem_name()
                        elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
                            bioinfo_app_name = xlib.get_rsem_eval_name()
                        elif result_dataset_id.startswith(xlib.get_samtools_code()+'-'):
                            bioinfo_app_name = xlib.get_samtools_name()
                        elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
                            bioinfo_app_name = xlib.get_soapdenovotrans_name()
                        elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
                            bioinfo_app_name = xlib.get_star_name()
                        elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
                            bioinfo_app_name = xlib.get_transabyss_name()
                        elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
                            bioinfo_app_name = xlib.get_transcript_filter_name()
                        elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
                            bioinfo_app_name = xlib.get_transcriptome_blastx_name()
                        elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
                            bioinfo_app_name = xlib.get_transrate_name()
                        elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
                            bioinfo_app_name = xlib.get_trimmomatic_name()
                        elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
                            bioinfo_app_name = xlib.get_trinity_name()
                        else:
                            bioinfo_app_name = 'xxx'
                        result_dataset_dict[result_dataset_id] = {'experiment_id': self.wrapper_experiment_id.get(), 'result_dataset_id': result_dataset_id, 'bioinfo_app': bioinfo_app_name, 'date': date, 'time': time}

        # verify if there are any nodes running
        if OK:
            if result_dataset_dict == {}:
                message = 'There is not any run.'
                tkinter.messagebox.showwarning('{0} - {1}'.format(xlib.get_project_name(), self.head), message)

        # build the data list
        if OK:
            data_list = ['experiment_id', 'result_dataset_id', 'bioinfo_app', 'date', 'time']

        # build the data dictionary
        if OK:
            data_dict = {}
            data_dict['experiment_id']= {'text': 'Experiment id. / Process', 'width': 200, 'aligment': 'left'}
            data_dict['result_dataset_id'] = {'text': 'Result dataset', 'width': 200, 'aligment': 'left'}
            data_dict['bioinfo_app'] = {'text': 'Bioinfo app / Utility', 'width': 200, 'aligment': 'left'}
            data_dict['date'] = {'text': 'Date', 'width': 80, 'aligment': 'right'}
            data_dict['time'] = {'text': 'Time', 'width': 80, 'aligment': 'right'}

        # create the dialog Table to show the nodes running
        if OK:
            dialog_table = gdialogs.DialogTable(self, 'Experiment runs in {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get()), 400, 900, data_list, data_dict, result_dataset_dict, 'view_result_logs', [self.wrapper_cluster_name.get()])
            self.wait_window(dialog_table)

        # close the form
        if OK:
            self.close()
Ejemplo n.º 8
0
def form_list_cluster_experiment_processes():
    '''
    List the processes of an experiment in the cluster.
    '''

    # initialize the control variable
    OK = True

    # print the header
    clib.clear_screen()
    clib.print_headers_with_environment(
        'Logs - List experiment processes in the cluster')

    # get the cluster name
    print(xlib.get_separator())
    if xec2.get_running_cluster_list(only_environment_cluster=True,
                                     volume_creator_included=False) != []:
        cluster_name = cinputs.input_cluster_name(
            volume_creator_included=False, help=True)
    else:
        print('WARNING: There is not any running cluster.')
        OK = False

    # create the SSH client connection
    if OK:
        (OK, error_list,
         ssh_client) = xssh.create_ssh_client_connection(cluster_name)
        for error in error_list:
            print(error)

    # get experiment identification
    if OK:
        experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
        if experiment_id == '':
            print(
                f'WARNING: The cluster {cluster_name} does not have experiment data.'
            )
            OK = False

    # get the result dataset list of the experiment
    if OK:
        command = f'cd  {xlib.get_cluster_result_dir()}/{experiment_id}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'
        (OK, stdout, _) = xssh.execute_cluster_command(ssh_client, command)
        if OK:
            result_dataset_id_list = []
            for line in stdout:
                line = line.rstrip('\n')
                if line != 'lost+found':
                    result_dataset_id_list.append(line)

    # print the result dataset identification list of the experiment
    if OK:
        print(xlib.get_separator())
        if result_dataset_id_list == []:
            print(
                f'*** WARNING: There is not any result dataset of the experiment {experiment_id}.'
            )
        else:
            result_dataset_id_list.sort()
            # set data width
            result_dataset_width = 30
            bioinfo_app_width = 25
            # set line
            line = '{0:' + str(result_dataset_width) + '}   {1:' + str(
                bioinfo_app_width) + '}'
            # print header
            print(line.format('Result dataset', 'Bioinfo app / Utility'))
            print(
                line.format('=' * result_dataset_width,
                            '=' * bioinfo_app_width))
            # print detail lines
            for result_dataset_id in result_dataset_id_list:

                if result_dataset_id.startswith(xlib.get_bedtools_code() +
                                                '-'):
                    bioinfo_app_name = xlib.get_bedtools_name()

                elif result_dataset_id.startswith(xlib.get_blastplus_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_blastplus_name()

                elif result_dataset_id.startswith(xlib.get_bcftools_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_bcftools_name()

                elif result_dataset_id.startswith(xlib.get_bowtie2_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_bowtie2_name()

                elif result_dataset_id.startswith(xlib.get_busco_code() + '-'):
                    bioinfo_app_name = xlib.get_busco_name()

                elif result_dataset_id.startswith(xlib.get_cd_hit_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cd_hit_name()

                elif result_dataset_id.startswith(xlib.get_cd_hit_est_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cd_hit_est_name()

                elif result_dataset_id.startswith(xlib.get_cuffdiff_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cuffdiff_name()

                elif result_dataset_id.startswith(xlib.get_cufflinks_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cufflinks_name()

                elif result_dataset_id.startswith(
                        xlib.get_cufflinks_cuffmerge_code() + '-'):
                    bioinfo_app_name = xlib.get_cufflinks_cuffmerge_name()

                elif result_dataset_id.startswith(xlib.get_cuffnorm_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cuffnorm_name()

                elif result_dataset_id.startswith(xlib.get_cuffquant_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cuffquant_name()

                elif result_dataset_id.startswith(xlib.get_cutadapt_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_cutadapt_name()

                elif result_dataset_id.startswith(
                        xlib.get_ddradseq_simulation_code() + '-'):
                    bioinfo_app_name = xlib.get_ddradseq_simulation_name()

                elif result_dataset_id.startswith(
                        xlib.get_ddradseqtools_code() + '-'):
                    bioinfo_app_name = xlib.get_ddradseqtools_name()

                elif result_dataset_id.startswith(xlib.get_detonate_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_detonate_name()

                elif result_dataset_id.startswith(xlib.get_diamond_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_diamond_name()

                elif result_dataset_id.startswith(xlib.get_emboss_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_emboss_name()

                elif result_dataset_id.startswith(
                        xlib.get_entrez_direct_code() + '-'):
                    bioinfo_app_name = xlib.get_entrez_direct_name()

                elif result_dataset_id.startswith(xlib.get_express_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_express_name()

                elif result_dataset_id.startswith(xlib.get_fastqc_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_fastqc_name()

                elif result_dataset_id.startswith(xlib.get_ggtrinity_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_ggtrinity_name()

                elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_gmap_gsnap_name()

                elif result_dataset_id.startswith(xlib.get_gmap_code() + '-'):
                    bioinfo_app_name = xlib.get_gmap_name()

                elif result_dataset_id.startswith(xlib.get_gsnap_code() + '-'):
                    bioinfo_app_name = xlib.get_gsnap_name()

                elif result_dataset_id.startswith(xlib.get_gzip_code() + '-'):
                    bioinfo_app_name = xlib.get_gzip_name()

                elif result_dataset_id.startswith(xlib.get_hisat2_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_hisat2_name()

                elif result_dataset_id.startswith(xlib.get_htseq_code() + '-'):
                    bioinfo_app_name = xlib.get_htseq_name()

                elif result_dataset_id.startswith(xlib.get_htseq_count_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_htseq_count_name()

                elif result_dataset_id.startswith(
                        xlib.get_insilico_read_normalization_code() + '-'):
                    bioinfo_app_name = xlib.get_insilico_read_normalization_name(
                    )

                elif result_dataset_id.startswith(xlib.get_ipyrad_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_ipyrad_name()

                elif result_dataset_id.startswith(xlib.get_kallisto_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_kallisto_name()

                elif result_dataset_id.startswith(xlib.get_miniconda3_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_miniconda3_name()

                elif result_dataset_id.startswith(xlib.get_ngshelper_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_ngshelper_name()

                elif result_dataset_id.startswith(xlib.get_quast_code() + '-'):
                    bioinfo_app_name = xlib.get_quast_name()

                elif result_dataset_id.startswith(xlib.get_r_code() + '-'):
                    bioinfo_app_name = xlib.get_r_name()

                elif result_dataset_id.startswith(xlib.get_raddesigner_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_raddesigner_name()

                elif result_dataset_id.startswith(xlib.get_ref_eval_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_ref_eval_name()

                elif result_dataset_id.startswith(xlib.get_rnaquast_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_rnaquast_name()

                elif result_dataset_id.startswith(xlib.get_rsem_code() + '-'):
                    bioinfo_app_name = xlib.get_rsem_name()

                elif result_dataset_id.startswith(xlib.get_rsem_eval_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_rsem_eval_name()

                elif result_dataset_id.startswith(xlib.get_rsitesearch_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_rsitesearch_name()

                elif result_dataset_id.startswith(xlib.get_samtools_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_samtools_name()

                elif result_dataset_id.startswith(xlib.get_soapdenovo2_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_soapdenovo2_name()

                elif result_dataset_id.startswith(
                        xlib.get_soapdenovotrans_code() + '-'):
                    bioinfo_app_name = xlib.get_soapdenovotrans_name()

                elif result_dataset_id.startswith(xlib.get_star_code() + '-'):
                    bioinfo_app_name = xlib.get_star_name()

                elif result_dataset_id.startswith(xlib.get_starcode_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_starcode_name()

                elif result_dataset_id.startswith(xlib.get_toa_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_name()

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_basic_data_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_basic_data_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_dicots_04_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_dicots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_gene_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_gene_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_go_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_go_name()

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_gymno_01_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_gymno_01_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_interpro_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_interpro_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_monocots_04_code() +
                        '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_monocots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_download_taxonomy_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_download_taxonomy_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.
                        get_toa_process_gilist_viridiplantae_nucleotide_gi_code(
                        ) + '-'):
                    bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_nucleotide_gi_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.
                        get_toa_process_gilist_viridiplantae_protein_gi_code()
                        + '-'):
                    bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_protein_gi_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_basic_data_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_basic_data_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_dicots_04_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_dicots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_gene_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_gene_name()

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_go_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_go_name()

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_gymno_01_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_gymno_01_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_interpro_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_interpro_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_load_monocots_04_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_load_monocots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_merge_annotations_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_merge_annotations_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_nr_blastplus_db_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_nr_blastplus_db_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_nr_diamond_db_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_nr_diamond_db_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_nt_blastplus_db_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_nt_blastplus_db_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_pipeline_aminoacid_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_pipeline_aminoacid_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_pipeline_nucleotide_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_pipeline_nucleotide_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_proteome_dicots_04_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_proteome_dicots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_proteome_gymno_01_code() + '-'):
                    bioinfo_app_name = xlib.get_toa_process_proteome_gymno_01_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_proteome_monocots_04_code() +
                        '-'):
                    bioinfo_app_name = xlib.get_toa_process_proteome_monocots_04_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_proteome_refseq_plant_code() +
                        '-'):
                    bioinfo_app_name = xlib.get_toa_process_proteome_refseq_plant_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_rebuild_toa_database_code() +
                        '-'):
                    bioinfo_app_name = xlib.get_get_toa_process_rebuild_toa_database_name(
                    )

                elif result_dataset_id.startswith(
                        xlib.get_toa_process_recreate_toa_database_code() +
                        '-'):
                    bioinfo_app_name = xlib.get_get_toa_process_recreate_toa_database_name(
                    )

                elif result_dataset_id.startswith(xlib.get_tophat_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_tophat_name()

                elif result_dataset_id.startswith(xlib.get_transabyss_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_transabyss_name()

                elif result_dataset_id.startswith(
                        xlib.get_transcript_filter_code() + '-'):
                    bioinfo_app_name = xlib.get_transcript_filter_name()

                elif result_dataset_id.startswith(
                        xlib.get_transcriptome_blastx_code() + '-'):
                    bioinfo_app_name = xlib.get_transcriptome_blastx_name()

                elif result_dataset_id.startswith(
                        xlib.get_transdecoder_code() + '-'):
                    bioinfo_app_name = xlib.get_transdecoder_name()

                elif result_dataset_id.startswith(xlib.get_transrate_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_transrate_name()

                elif result_dataset_id.startswith(xlib.get_trimmomatic_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_trimmomatic_name()

                elif result_dataset_id.startswith(xlib.get_trinity_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_trinity_name()

                elif result_dataset_id.startswith(
                        xlib.get_variant_calling_code() + '-'):
                    bioinfo_app_name = xlib.get_variant_calling_name()

                elif result_dataset_id.startswith(xlib.get_vcftools_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_vcftools_name()

                elif result_dataset_id.startswith(
                        xlib.get_vcftools_perl_libraries_code() + '-'):
                    bioinfo_app_name = xlib.get_vcftools_perl_libraries_name()

                elif result_dataset_id.startswith(xlib.get_vsearch_code() +
                                                  '-'):
                    bioinfo_app_name = xlib.get_vsearch_name()

                else:
                    bioinfo_app_name = 'xxx'

                print(line.format(result_dataset_id, bioinfo_app_name))

    # close the SSH client connection
    if OK:
        xssh.close_ssh_client_connection(ssh_client)

    # show continuation message
    print(xlib.get_separator())
    input('Press [Intro] to continue ...')