Exemple #1
0
def report(params):
    """ circos_report to markdown file and html file

    Args: report input dict, key is `yaml`, value is yaml file path::

            "xx": path of xx.

    Returns:
        dict : key is `yaml`,value is yaml file path
    """
    # handle input
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin))

    yamlfile = "circos_report.json"
    paramstr = json.dumps(indict)
    cmd1 = "echo '%s' > %s " % (paramstr, yamlfile)
    tag1 = "make sure the existed yaml file"
    log.run("tag1", cmd1, i=None, o=[yamlfile])

    templ = get_template("circos_report")
    out = "circos_report.md"
    cmd = "%s -t %s -j %s -o %s -y" % (render, templ, yamlfile, out)
    log.run("render circos_report template", cmd)

    cmd = "%s %s" % (md2html, out)
    log.run("md2html circos_report ", cmd)
    outdict = {}
    outdict["circos_report"] = out
    yamlout = yamladd(yamlin, outdict)
    yamlout["circos_report_outdir"] = os.getcwd()
    return yamlout
Exemple #2
0
def report(params):
    """ enrichreport to markdown file and html file

    Args: report input dict, key is `yaml`, value is yaml file path::

            "xx": path of xx.

    Returns:
        dict : key is `yaml`,value is yaml file path
    """
    # handle input
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin))

    enrichreportl = get_template("enrichreport")
    out = "enrichreport.md"
    cmd = "%s -t %s -j %s -o %s -y" % (render, enrichreportl, yamlin, out)
    log.run("render enrichreport template", cmd)

    cmd = "%s %s" % (md2html, out)
    log.run("md2html enrichreport ", cmd, o=["html.tgz"])
    outdict = {}
    outdict["enrichreport"] = out
    yamlout = yamladd(yamlin, outdict)
    yamlout["enrichreport_outdir"] = os.getcwd()
    return yamlout
def main_multi(params):
    '''params is an input dict including the following keys

    Args:
        params (dict) : key is `yaml`, value is a yaml file::

            plotinfo: 
                    {
                        karytotype : karytotype file of circos
                        chrom_unit : the basic number of unit(numeric)
                        species : data file including unit of all chromosomes used for bedtools
                    }, 
            circos_report_template : the report template 
            cnvinp : the output of calling cnv 
            snvinp : the output of calling snv
            svinp : the output of calling sv
            circos_multi_tmp : the template of snv&cnv&sv's conf

    Returns:
        params (dict) : key is `yaml`, value is a yaml file::

            plotinfo :
                {
                    karytotype : karytotype file of circos
                    chrom_unit : the basic number of unit(numeric)
                    species : data file including unit of all chromosomes used for bedtools
                    snp_min :  the min value of snp file
                    snp_max : the max value of snp file
                    indel_min : the min value of indel file
                    indel_max : the max value of indel file
                    cnv_min : the min value of the cnv file
                    cnv_max : the max value of the cnv file
                    outfile : the output name of circos file
                    snp_out : the file are used for the snp input of circos png
                    indel_out : the file are used for the indel input of circos png
                    cnv_out : the file are used as the cnv input of circos' png 
                    sv_out : the file are used as the sv input of circos' png
                }
            outconf : name of the circos conf file
            circos_multi_tmp : the template of snv&cnv&sv's conf
            circos_report_template : the report template
            snp :  the snp file after separated from annotated file
            indel : the indel file after separated from annotated file
            snvinp : the output of calling snv
            cnvinp : the output of calling cnv
            svinp : the output of calling sv
    '''
    # handle input ...
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin).read())

    cycle_param = parse_param(indict)
    circos_res = data_cycle(cycle_param)

    # handle output ...
    outdict = {}
    outdict["circos_res"] = circos_res
    outdict["circos_text"] = "circos图由里到外依次为sv,cnv,snp和indel的结果"
    yamlout = yamladd(yamlin, outdict)
    return yamlout
Exemple #4
0
def arrange(params):
    """ circos_report arrange output files

    Args:
        params: indict , key is `yaml`, value in yaml file::

            circos_res:
                {
                    patient1: saved circos' info of the patient
                        {
                            conf: the conf file of the specific patient
                            png: the png file of the specific patient
                        }    
                }

    Returns:
        dict : key is `yaml`, value is the path of yaml file

    """

    # handle input
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin).read())
    pngs = data_cycle(indict)

    # process cmd
    log.move(pngs, "report/circos")

    #handle out
    outdict = {}
    outdict["circos_pngs"] = pngs
    yamlout = yamladd(yamlin, outdict)
    return yamlout
Exemple #5
0
def arrange(arr_dict, yamlfile):

    func_pdfs_report = files_report(arr_dict['func_pdfs'])
    go_dot_pdfs_report = files_report(arr_dict['go_dot_pdfs'])
    go_net_pdfs_report = files_report(arr_dict['go_net_pdfs'])
    kegg_pdfs_report = files_report(arr_dict['kegg_pdfs'])

    func_xls_report = transfor(arr_dict['func_csvs'])
    go_xls_report = transfor(arr_dict['go_csvs'])
    go_xls_all = transfor(arr_dict['go_csvs_all'])
    kegg_xls_report = transfor(arr_dict['kegg_csvs'])
    kegg_xls_all = transfor(arr_dict['kegg_csvs_all'])

    if len(kegg_pdfs_report) == 0:
        kegg_pdf_report = ''
    else:
        kegg_pdf_report = kegg_pdfs_report[0]

    out_dict = {"func_pdfs_report": func_pdfs_report, "go_dot_pdfs_report": go_dot_pdfs_report, "go_net_pdfs_report": go_net_pdfs_report, \
                "kegg_pdf_report": kegg_pdf_report, "func_xls_report": func_xls_report, "go_xls_report": go_xls_report, "kegg_xls_report": kegg_xls_report}

    # report paramters
    #
    res = yamladd(yamlfile, out_dict)

    return res
Exemple #6
0
def arrange(ymlfile):
    """ {{projName}} arrange output files use log.run

    """

    # handle input
    indict = yaml.load(open(ymlfile).read())

    # process cmd and user log.move to arrange files to report
    pass

    # handle output

    #handle out
    outdict = {}
    yamladd(ymlfile, outdict)
    return ymlfile
Exemple #7
0
def main_cnv(params):
    '''params is an input dict including the following keys

    Args:
        params (dict) : key is `yaml`, value is a yaml file::

            plotinfo: 
                    {
                        karytotype : karytotype file of circos
                        chrom_unit : the basic number of unit(numeric)
                        species : data file including unit of all chromosomes used for bedtools
                    }, 
            circos_report_template : the report template 
            cnvinp : the output of calling cnv 
            circos_cnv_tmp : the template of cnv's conf

    Returns:
        params (dict) : key is `yaml`, value is a yaml file::

            plotinfo :
                {
                    karytotype : karytotype file of circos
                    chrom_unit : the basic number of unit(numeric)
                    species : data file including unit of all chromosomes used for bedtools
                    cnv_min : the min value of the cnv file
                    cnv_max : the max value of the cnv file
                    outfile : the output name of circos file
                    cnv_out : the file are used as the cnv input of circos' png 
                }
            outconf : name of the circos conf file
            circos_cnv_tmp : the template of cnv's conf
            circos_report_template : the report template
            cnvinp : the output of calling cnv
    '''
    # handle input ...
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin).read())

    cycle_param = parse_param(indict)
    circos_res = data_cycle(cycle_param)

    # handle output ...
    outdict = {}
    outdict["circos_res"] = circos_res
    outdict["circos_text"] = "circos图为cnv的结果"
    yamlout = yamladd(yamlin, outdict)
    return yamlout
Exemple #8
0
def circmd(params):
    '''params is an input dict which includes the following keys

    Args:
        params (dict) : key is `yaml`, value is a yaml file::

            'outconf:': the name of the circos conf file

    Returns:
        str : out yaml file
    '''

    # handle input ...
    yamlin = params["yaml"]
    indict = yaml.load(open(yamlin).read())
    data_cycle(indict)

    # handle output ...
    outdict = {}
    yamlout = yamladd(yamlin, outdict)
    return yamlout
Exemple #9
0
def report(ymlfile):
    """ {{projName}} to markdown file and html file

    """
    # handle input
    indict = yaml.load(open(ymlfile))

    render_yml = "{{projName}}_render.yml"
    cmd = "echo '%s' > %s" % (json.dumps(indict),render_yml)
    log.run("get {{projName}} args to render",cmd)

    templ = get_template("{{projName}}")
    out = "{{projName}}.md"
    cmd = "%s -t %s -j %s -o %s -y" % (render,templ,render_yml,out)
    log.run("render {{projName}} template",cmd,docker="jbioi/report",singularity="report.img")
    
    cmd = "%s %s" % (md2html,out)
    log.run("md2html {{projName}} ",cmd,docker="jbioi/report",singularity="report.img")
    outdict = {}
    outdict["{{projName}}"] = out
    yamlout = yamladd(yamlin,outdict)
    yamlout["{{projName}}_outdir"] = os.getcwd()
    return ymlfile
Exemple #10
0
def enrich(parms):
    '''Gene GO functional annotation, GO enrichment and KEGG enrichment

    Args:
        parms (dict) : which has the following keys::
            
            {
                yaml : a yaml file including parms for gene enrich analysis
            }

    Returns:
        dict : ``{"yaml": yamlfile for arrange and report}``
    '''

    yaml_file = parms["yaml"]
    fp = open(yaml_file)
    enrich_dict = yaml.load(fp.read())
    fp.close()

    files = enrich_dict['enrichFiles']
    func_pdfs, func_csvs, func_xls = [], [], []
    go_dot_pdfs, go_net_pdfs, go_csvs, go_csvs_all, go_xls, go_xls_all = [], [], [], [], [], []
    kegg_pdfs, kegg_csvs, kegg_csvs_all, kegg_xls, kegg_xls_all = [], [], [], [], []
    id_files = []

    for prefix, enrichFile in files.items():
        # check file
        #
        with open(enrichFile, 'r') as f:
            head = f.readline().split('\t')
            try:
                gidx = head.index("Gene")
            except ValueError:
                print("\n\nInput file: {} need the head include 'Gene'.\n\n".
                      format(enrichFile))

        # functation annotation
        #
        cmd = "%s %s %s" % (funcAnnoGO, enrichFile, prefix)
        log.run('func annotation', cmd, i=[enrichFile])

        # GO enrich analysis
        #
        cmd = "%s %s %s" % (enrichGO, enrichFile, prefix)
        log.run('GO enrich analysis', cmd)

        # KEGG enrich analysis
        #
        cmd = "%s %s %s" % (enrichKEGG, enrichFile, prefix)
        log.run('KEGG enrich analysis', cmd)

        for item in ['CC', 'BP', 'MF']:
            func_pdfs.append('{prefix}.go.{item}.bar.func.pdf'.format(
                prefix=prefix, item=item))
            func_csvs.append('{prefix}.go.{item}.func.csv'.format(
                prefix=prefix, item=item))
            func_xls.append('{prefix}.go.{item}.func.xls'.format(prefix=prefix,
                                                                 item=item))

            go_dot_pdfs.append('{prefix}.go.{item}.dot.enrich.pdf'.format(
                prefix=prefix, item=item))

            go_net_pdfs.append('{prefix}.go.{item}.net.enrich.pdf'.format(
                prefix=prefix, item=item))

            go_csvs.append('{prefix}.go.{item}.enrich.csv'.format(
                prefix=prefix, item=item))
            go_csvs_all.append('{prefix}.go.{item}.enrich.all.csv'.format(
                prefix=prefix, item=item))
            go_xls.append('{prefix}.go.{item}.enrich.xls'.format(prefix=prefix,
                                                                 item=item))
            go_xls_all.append('{prefix}.go.{item}.enrich.all.xls'.format(
                prefix=prefix, item=item))

        id_files.append("{}.gene_id.csv".format(prefix))
        kegg_pdfs.append('{}.KEGG.enrich.pdf'.format(prefix))
        kegg_csvs.append('{}.KEGG.enrich.csv'.format(prefix))
        kegg_csvs_all.append('{}.KEGG.enrich.all.csv'.format(prefix))
        kegg_xls.append('{}.KEGG.enrich.xls'.format(prefix))
        kegg_xls_all.append('{}.KEGG.enrich.all.xls'.format(prefix))

    out_dict = {'func_pdfs':func_pdfs, 'go_dot_pdfs':go_dot_pdfs, 'go_net_pdfs': go_net_pdfs, 'kegg_pdfs':kegg_pdfs, \
            'func_csvs': func_csvs, 'func_xls': func_xls, 'go_csvs': go_csvs, 'go_xls': go_xls, 'go_csvs_all': go_csvs_all, 'go_xls_all': go_xls_all, 'kegg_csvs': kegg_csvs , \
            'kegg_csvs_all': kegg_csvs_all, 'kegg_xls': kegg_xls, 'kegg_xls_all': kegg_xls_all}

    res = yamladd(yaml_file, out_dict)

    # csv2xls
    #
    cmd = "{csv2xls} {yamlfile}".format(csv2xls=csv2xls, yamlfile=yaml_file)
    log.run('csv2xls', cmd)

    return res