예제 #1
0
def _detect_rRNA(data):
    sample = dd.get_sample_name(data)
    gtf_file = dd.get_gtf_file(data)
    tidy_file = dd.get_sailfish_tidy(data)
    rrna_features = gtf.get_rRNA(gtf_file)
    transcripts = set([x[1] for x in rrna_features if x])
    if not transcripts:
        return {'rRNA': "NA", "rRNA_rate": "NA"}
    count_table = pd.read_csv(tidy_file, sep="\t")
    sample_table = count_table[count_table["sample"].isin([sample])]
    rrna_exp = map(float, sample_table[sample_table["id"].isin(transcripts)]["numreads"])
    total_exp = map(float, sample_table["numreads"])
    rrna = sum(rrna_exp)
    rrna_rate = float(rrna) / sum(total_exp)
    return {'rRNA': str(rrna), 'rRNA_rate': str(rrna_rate)}
예제 #2
0
def _detect_rRNA(data):
    sample = dd.get_sample_name(data)
    gtf_file = dd.get_gtf_file(data)
    tidy_file = dd.get_sailfish_tidy(data)
    rrna_features = gtf.get_rRNA(gtf_file)
    transcripts = set([x[1] for x in rrna_features if x])
    if not transcripts:
        return {'rRNA': "NA", "rRNA_rate": "NA"}
    count_table = pd.read_csv(tidy_file, sep="\t")
    sample_table = count_table[count_table["sample"].isin([sample])]
    rrna_exp = map(
        float, sample_table[sample_table["id"].isin(transcripts)]["numreads"])
    total_exp = map(float, sample_table["numreads"])
    rrna = sum(rrna_exp)
    rrna_rate = float(rrna) / sum(total_exp)
    return {'rRNA': str(rrna), 'rRNA_rate': str(rrna_rate)}
예제 #3
0
def _get_files_project(sample, upload_config):
    """Retrieve output files associated with an entire analysis project.
    """
    out = [{"path": sample["provenance"]["programs"]}]
    if os.path.exists(tz.get_in(["provenance", "data"], sample) or ""):
        out.append({"path": sample["provenance"]["data"]})
    for fname in ["bcbio-nextgen.log", "bcbio-nextgen-commands.log"]:
        if os.path.exists(os.path.join(log.get_log_dir(sample["config"]), fname)):
            out.append({"path": os.path.join(log.get_log_dir(sample["config"]), fname),
                        "type": "external_command_log",
                        "ext": ""})

    if "summary" in sample and sample["summary"].get("project"):
        out.append({"path": sample["summary"]["project"]})
    mixup_check = tz.get_in(["summary", "mixup_check"], sample)
    if mixup_check:
        out.append({"path": sample["summary"]["mixup_check"],
                    "type": "directory", "ext": "mixup_check"})

    report = os.path.join(dd.get_work_dir(sample), "report")
    if utils.file_exists(report):
        out.append({"path": report,
                    "type": "directory", "ext": "report"})

    multiqc = tz.get_in(["summary", "multiqc"], sample)
    if multiqc:
        out.extend(_flatten_file_with_secondary(multiqc, "multiqc"))

    if sample.get("seqcluster", None):
        out.append({"path": sample["seqcluster"],
                    "type": "directory", "ext": "seqcluster"})

    if sample.get("report", None):
        out.append({"path": os.path.dirname(sample["report"]),
                    "type": "directory", "ext": "seqclusterViz"})

    for x in sample.get("variants", []):
        if "pop_db" in x:
            out.append({"path": x["pop_db"],
                        "type": "sqlite",
                        "variantcaller": x["variantcaller"]})
    for x in sample.get("variants", []):
        if "population" in x:
            pop_db = tz.get_in(["population", "db"], x)
            if pop_db:
                out.append({"path": pop_db,
                            "type": "sqlite",
                            "variantcaller": x["variantcaller"]})
            out.extend(_get_variant_file(x, ("population", "vcf")))
    for x in sample.get("variants", []):
        if x.get("validate") and x["validate"].get("grading_summary"):
            out.append({"path": x["validate"]["grading_summary"]})
            break
    if "coverage" in sample:
        cov_db = tz.get_in(["coverage", "summary"], sample)
        if cov_db:
            out.append({"path": cov_db, "type": "sqlite", "ext": "coverage"})
        all_coverage = tz.get_in(["coverage", "all"], sample)
        if all_coverage:
            out.append({"path": all_coverage, "type": "bed", "ext": "coverage"})

    if dd.get_mirna_counts(sample):
        out.append({"path": dd.get_mirna_counts(sample)})
    if dd.get_isomir_counts(sample):
        out.append({"path": dd.get_isomir_counts(sample)})
    if dd.get_novel_mirna_counts(sample):
        out.append({"path": dd.get_novel_mirna_counts(sample)})
    if dd.get_novel_isomir_counts(sample):
        out.append({"path": dd.get_novel_isomir_counts(sample)})
    if dd.get_combined_counts(sample):
        out.append({"path": dd.get_combined_counts(sample)})
    if dd.get_annotated_combined_counts(sample):
        out.append({"path": dd.get_annotated_combined_counts(sample)})
    if dd.get_combined_fpkm(sample):
        out.append({"path": dd.get_combined_fpkm(sample)})
    if dd.get_combined_fpkm_isoform(sample):
        out.append({"path": dd.get_combined_fpkm_isoform(sample)})
    if dd.get_transcript_assembler(sample):
        out.append({"path": dd.get_merged_gtf(sample)})
    if dd.get_dexseq_counts(sample):
        out.append({"path": dd.get_dexseq_counts(sample)})
    if dd.get_express_counts(sample):
        out.append({"path": dd.get_express_counts(sample)})
    if dd.get_express_fpkm(sample):
        out.append({"path": dd.get_express_fpkm(sample)})
    if dd.get_express_tpm(sample):
        out.append({"path": dd.get_express_tpm(sample)})
    if dd.get_isoform_to_gene(sample):
        out.append({"path": dd.get_isoform_to_gene(sample)})
    if dd.get_square_vcf(sample):
        out.append({"path": dd.get_square_vcf(sample)})
    if dd.get_sailfish_tidy(sample):
        out.append({"path": dd.get_sailfish_tidy(sample)})
    if dd.get_sailfish_transcript_tpm(sample):
        out.append({"path": dd.get_sailfish_transcript_tpm(sample)})
    if dd.get_sailfish_gene_tpm(sample):
        out.append({"path": dd.get_sailfish_gene_tpm(sample)})
    if dd.get_tx2gene(sample):
        out.append({"path": dd.get_tx2gene(sample)})
    return _add_meta(out, config=upload_config)
예제 #4
0
def _get_files_project(sample, upload_config):
    """Retrieve output files associated with an entire analysis project.
    """
    out = [{"path": sample["provenance"]["programs"]}]
    if os.path.exists(tz.get_in(["provenance", "data"], sample) or ""):
        out.append({"path": sample["provenance"]["data"]})
    for fname in ["bcbio-nextgen.log", "bcbio-nextgen-commands.log"]:
        if os.path.exists(os.path.join(log.get_log_dir(sample["config"]), fname)):
            out.append({"path": os.path.join(log.get_log_dir(sample["config"]), fname),
                        "type": "external_command_log",
                        "ext": ""})

    if "summary" in sample and sample["summary"].get("project"):
        out.append({"path": sample["summary"]["project"]})
    mixup_check = tz.get_in(["summary", "mixup_check"], sample)
    if mixup_check:
        out.append({"path": sample["summary"]["mixup_check"],
                    "type": "directory", "ext": "mixup_check"})

    report = os.path.join(dd.get_work_dir(sample), "report")
    if utils.file_exists(report):
        out.append({"path": report,
                    "type": "directory", "ext": "report"})

    multiqc = tz.get_in(["summary", "multiqc"], sample)
    if multiqc:
        out.extend(_flatten_file_with_secondary(multiqc, "multiqc"))

    if sample.get("seqcluster", {}):
        out.append({"path": sample["seqcluster"].get("out_dir"),
                    "type": "directory", "ext": "seqcluster"})

    if sample.get("report", None):
        out.append({"path": os.path.dirname(sample["report"]),
                    "type": "directory", "ext": "seqclusterViz"})

    for x in sample.get("variants", []):
        if "pop_db" in x:
            out.append({"path": x["pop_db"],
                        "type": "sqlite",
                        "variantcaller": x["variantcaller"]})
    for x in sample.get("variants", []):
        if "population" in x:
            pop_db = tz.get_in(["population", "db"], x)
            if pop_db:
                out.append({"path": pop_db,
                            "type": "sqlite",
                            "variantcaller": x["variantcaller"]})
            suffix = "-annotated-decomposed" if tz.get_in(("population", "decomposed"), x) else "-annotated"
            out.extend([_add_batch(x, sample)
                        for x in _get_variant_file(x, ("population", "vcf"), suffix=suffix)])
    for x in sample.get("variants", []):
        if x.get("validate") and x["validate"].get("grading_summary"):
            out.append({"path": x["validate"]["grading_summary"]})
            break
    if "coverage" in sample:
        cov_db = tz.get_in(["coverage", "summary"], sample)
        if cov_db:
            out.append({"path": cov_db, "type": "sqlite", "ext": "coverage"})
        all_coverage = tz.get_in(["coverage", "all"], sample)
        if all_coverage:
            out.append({"path": all_coverage, "type": "bed", "ext": "coverage"})

    if dd.get_mirna_counts(sample):
        out.append({"path": dd.get_mirna_counts(sample)})
    if dd.get_isomir_counts(sample):
        out.append({"path": dd.get_isomir_counts(sample)})
    if dd.get_novel_mirna_counts(sample):
        out.append({"path": dd.get_novel_mirna_counts(sample)})
    if dd.get_novel_isomir_counts(sample):
        out.append({"path": dd.get_novel_isomir_counts(sample)})
    if dd.get_combined_counts(sample):
        count_file = dd.get_combined_counts(sample)
        if sample["analysis"].lower() == "scrna-seq":
            out.append({"path": count_file,
                    "type": "mtx"})
            out.append({"path": count_file + ".rownames",
                    "type": "rownames"})
            out.append({"path": count_file + ".colnames",
                    "type": "colnames"})
        else:
            out.append({"path": dd.get_combined_counts(sample)})
    if dd.get_annotated_combined_counts(sample):
        out.append({"path": dd.get_annotated_combined_counts(sample)})
    if dd.get_combined_fpkm(sample):
        out.append({"path": dd.get_combined_fpkm(sample)})
    if dd.get_combined_fpkm_isoform(sample):
        out.append({"path": dd.get_combined_fpkm_isoform(sample)})
    if dd.get_transcript_assembler(sample):
        out.append({"path": dd.get_merged_gtf(sample)})
    if dd.get_dexseq_counts(sample):
        out.append({"path": dd.get_dexseq_counts(sample)})
    if dd.get_express_counts(sample):
        out.append({"path": dd.get_express_counts(sample)})
    if dd.get_express_fpkm(sample):
        out.append({"path": dd.get_express_fpkm(sample)})
    if dd.get_express_tpm(sample):
        out.append({"path": dd.get_express_tpm(sample)})
    if dd.get_isoform_to_gene(sample):
        out.append({"path": dd.get_isoform_to_gene(sample)})
    if dd.get_square_vcf(sample):
        out.append({"path": dd.get_square_vcf(sample)})
    if dd.get_sailfish_tidy(sample):
        out.append({"path": dd.get_sailfish_tidy(sample)})
    if dd.get_sailfish_transcript_tpm(sample):
        out.append({"path": dd.get_sailfish_transcript_tpm(sample)})
    if dd.get_sailfish_gene_tpm(sample):
        out.append({"path": dd.get_sailfish_gene_tpm(sample)})
    if dd.get_tx2gene(sample):
        out.append({"path": dd.get_tx2gene(sample)})
    if dd.get_spikein_counts(sample):
        out.append({"path": dd.get_spikein_counts(sample)})
    return _add_meta(out, config=upload_config)
예제 #5
0
def _get_files_project(sample, upload_config):
    """Retrieve output files associated with an entire analysis project.
    """
    out = [{"path": sample["provenance"]["programs"]}]
    for fname in ["bcbio-nextgen.log", "bcbio-nextgen-commands.log"]:
        if os.path.exists(os.path.join(log.get_log_dir(sample["config"]), fname)):
            out.append({"path": os.path.join(log.get_log_dir(sample["config"]), fname),
                        "type": "external_command_log",
                        "ext": ""})

    if "summary" in sample and sample["summary"].get("project"):
        out.append({"path": sample["summary"]["project"]})
    mixup_check = tz.get_in(["summary", "mixup_check"], sample)
    if mixup_check:
        out.append({"path": sample["summary"]["mixup_check"],
                    "type": "directory", "ext": "mixup_check"})

    report = os.path.join(dd.get_work_dir(sample), "report")
    if utils.file_exists(report):
        out.append({"path": report,
            "type": "directory", "ext": "report"})

    if sample.get("seqcluster", None):
        out.append({"path": sample["seqcluster"],
                    "type": "directory", "ext": "seqcluster"})

    for x in sample.get("variants", []):
        if "pop_db" in x:
            out.append({"path": x["pop_db"],
                        "type": "sqlite",
                        "variantcaller": x["variantcaller"]})
    for x in sample.get("variants", []):
        if "population" in x:
            pop_db = tz.get_in(["population", "db"], x)
            if pop_db:
                out.append({"path": pop_db,
                            "type": "sqlite",
                            "variantcaller": x["variantcaller"]})
            out.extend(_get_variant_file(x, ("population", "vcf")))
    for x in sample.get("variants", []):
        if x.get("validate") and x["validate"].get("grading_summary"):
            out.append({"path": x["validate"]["grading_summary"]})
            break
    if "coverage" in sample:
        cov_db = tz.get_in(["coverage", "summary"], sample)
        if cov_db:
            out.append({"path": cov_db, "type": "sqlite", "ext": "coverage"})
        all_coverage = tz.get_in(["coverage", "all"], sample)
        if all_coverage:
            out.append({"path": all_coverage, "type": "bed", "ext": "coverage"})

    if dd.get_mirna_counts(sample):
        out.append({"path": dd.get_mirna_counts(sample)})
    if dd.get_isomir_counts(sample):
        out.append({"path": dd.get_isomir_counts(sample)})
    if dd.get_combined_counts(sample):
        out.append({"path": dd.get_combined_counts(sample)})
    if dd.get_annotated_combined_counts(sample):
        out.append({"path": dd.get_annotated_combined_counts(sample)})
    if dd.get_combined_fpkm(sample):
        out.append({"path": dd.get_combined_fpkm(sample)})
    if dd.get_combined_fpkm_isoform(sample):
        out.append({"path": dd.get_combined_fpkm_isoform(sample)})
    if dd.get_assembled_gtf(sample):
        out.append({"path": dd.get_assembled_gtf(sample)})
    if dd.get_dexseq_counts(sample):
        out.append({"path": dd.get_dexseq_counts(sample)})
    if dd.get_express_counts(sample):
        out.append({"path": dd.get_express_counts(sample)})
    if dd.get_express_fpkm(sample):
        out.append({"path": dd.get_express_fpkm(sample)})
    if dd.get_express_tpm(sample):
        out.append({"path": dd.get_express_tpm(sample)})
    if dd.get_isoform_to_gene(sample):
        out.append({"path": dd.get_isoform_to_gene(sample)})
    if dd.get_square_vcf(sample):
        out.append({"path": dd.get_square_vcf(sample)})
    if dd.get_sailfish_tidy(sample):
        out.append({"path": dd.get_sailfish_tidy(sample)})
    if dd.get_sailfish_transcript_tpm(sample):
        out.append({"path": dd.get_sailfish_transcript_tpm(sample)})
    if dd.get_sailfish_gene_tpm(sample):
        out.append({"path": dd.get_sailfish_gene_tpm(sample)})
    return _add_meta(out, config=upload_config)