Intracellular protein GBF1 displays significant associations with amyloid pathology in Alzheimer's disease.
The 1 match
- [1] § METHODS › Genetic discovery ↔ bcbio/pipeline/main.py, lines 116–202 · score 0.65 · quality control, Variant calls, pruned, jointly, GEMINI, SNPEff
Paper
Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 533 lines · 27 KB · MIT · 1 match
- """Main entry point for distributed next-gen sequencing pipelines.
- Handles running the full pipeline based on instructions
- """
- from __future__ import print_function
- from collections import defaultdict
- import copy
- import os
- import sys
- import resource
- import tempfile
- import toolz as tz
- from bcbio import log, heterogeneity, hla, structural, utils
- from bcbio.cwl.inspect import initialize_watcher
- from bcbio.distributed import prun
- from bcbio.distributed.transaction import tx_tmpdir
- from bcbio.log import logger, DEFAULT_LOG_DIR
- from bcbio.ngsalign import alignprep
- from bcbio.pipeline import datadict as dd
- from bcbio.pipeline import (archive, config_utils, disambiguate, region,
- run_info, qcsummary, rnaseq)
- from bcbio.provenance import profile, system
- from bcbio.variation import (ensemble, genotype, population, validate, joint,
- peddy)
- from bcbio.chipseq import peaks, atac
- def run_main(workdir, config_file=None, fc_dir=None, run_info_yaml=None,
- parallel=None, workflow=None):
- """Run variant analysis, handling command line options.
- """
- # Set environment to standard to use periods for decimals and avoid localization
- locale_to_use = utils.get_locale()
- os.environ["LC_ALL"] = locale_to_use
- os.environ["LC"] = locale_to_use
- os.environ["LANG"] = locale_to_use
- workdir = utils.safe_makedir(os.path.abspath(workdir))
- os.chdir(workdir)
- config, config_file = config_utils.load_system_config(config_file, workdir)
- parallel = log.create_base_logger(config, parallel)
- log.setup_local_logging(config, parallel)
- logger.info(f"System YAML configuration: {os.path.abspath(config_file)}.")
- logger.info(f"Locale set to {locale_to_use}.")
- if config.get("log_dir", None) is None:
- config["log_dir"] = os.path.join(workdir, DEFAULT_LOG_DIR)
- if parallel["type"] in ["local", "clusterk"]:
- _setup_resources()
- _run_toplevel(config, config_file, workdir, parallel,
- fc_dir, run_info_yaml)
- elif parallel["type"] == "ipython":
- assert parallel["scheduler"] is not None, "IPython parallel requires a specified scheduler (-s)"
- if parallel["scheduler"] != "sge":
- assert parallel["queue"] is not None, "IPython parallel requires a specified queue (-q)"
- elif not parallel["queue"]:
- parallel["queue"] = ""
- _run_toplevel(config, config_file, workdir, parallel,
- fc_dir, run_info_yaml)
- else:
- raise ValueError("Unexpected type of parallel run: %s" % parallel["type"])
- def _setup_resources():
- """Attempt to increase resource limits up to hard limits.
- This allows us to avoid out of file handle limits where we can
- move beyond the soft limit up to the hard limit.
- """
- target_procs = 10240
- cur_proc, max_proc = resource.getrlimit(resource.RLIMIT_NPROC)
- target_proc = min(max_proc, target_procs) if max_proc > 0 else target_procs
- resource.setrlimit(resource.RLIMIT_NPROC, (max(cur_proc, target_proc), max_proc))
- cur_hdls, max_hdls = resource.getrlimit(resource.RLIMIT_NOFILE)
- target_hdls = min(max_hdls, target_procs) if max_hdls > 0 else target_procs
- resource.setrlimit(resource.RLIMIT_NOFILE, (max(cur_hdls, target_hdls), max_hdls))
- def _run_toplevel(config, config_file, work_dir, parallel,
- fc_dir=None, run_info_yaml=None):
- """
- Run toplevel analysis, processing a set of input files.
- config_file -- Main YAML configuration file with system parameters
- fc_dir -- Directory of fastq files to process
- run_info_yaml -- YAML configuration file specifying inputs to process
- """
- dirs = run_info.setup_directories(work_dir, fc_dir, config, config_file)
- config_file = os.path.join(dirs["config"], os.path.basename(config_file))
- pipelines, config = _pair_samples_with_pipelines(run_info_yaml, config)
- system.write_info(dirs, parallel, config)
- with tx_tmpdir(config if parallel.get("type") == "local" else None) as tmpdir:
- tempfile.tempdir = tmpdir
- for pipeline, samples in pipelines.items():
- for xs in pipeline(config, run_info_yaml, parallel, dirs, samples):
- pass
- # ## Generic pipeline framework
- def _wres(parallel, progs, fresources=None, ensure_mem=None):
- """Add resource information to the parallel environment on required programs and files.
- Enables spinning up required machines and operating in non-shared filesystem
- environments.
- progs -- Third party tools used in processing
- fresources -- Required file-based resources needed. These will be transferred on non-shared
- filesystems.
- ensure_mem -- Dictionary of required minimum memory for programs used. Ensures
- enough memory gets allocated on low-core machines.
- """
- parallel = copy.deepcopy(parallel)
- parallel["progs"] = progs
- if fresources:
- parallel["fresources"] = fresources
- if ensure_mem:
- parallel["ensure_mem"] = ensure_mem
- return parallel
- def variant2pipeline(config, run_info_yaml, parallel, dirs, samples):
- ## Alignment and preparation requiring the entire input file (multicore cluster)
- # Assign GATK supplied memory if required for post-process recalibration
- align_programs = ["aligner", "samtools", "sambamba"]
- if any(tz.get_in(["algorithm", "recalibrate"], utils.to_single_data(d)) in [True, "gatk"] for d in samples):
- align_programs.append("gatk")
- with prun.start(_wres(parallel, align_programs,
- (["reference", "fasta"], ["reference", "aligner"], ["files"])),
- samples, config, dirs, "multicore",
- multiplier=alignprep.parallel_multiplier(samples)) as run_parallel:
- with profile.report("organize samples", dirs):
- samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml,
- [x[0]["description"] for x in samples]]])
- with profile.report("alignment preparation", dirs):
- samples = run_parallel("prep_align_inputs", samples)
- samples = run_parallel("disambiguate_split", [samples])
- with profile.report("alignment", dirs):
- samples = run_parallel("process_alignment", samples)
- samples = disambiguate.resolve(samples, run_parallel)
- samples = alignprep.merge_split_alignments(samples, run_parallel)
- with profile.report("callable regions", dirs):
- samples = run_parallel("prep_samples", [samples])
- samples = run_parallel("postprocess_alignment", samples)
- samples = run_parallel("combine_sample_regions", [samples])
- samples = run_parallel("calculate_sv_bins", [samples])
- samples = run_parallel("calculate_sv_coverage", samples)
- samples = run_parallel("normalize_sv_coverage", [samples])
- samples = region.clean_sample_data(samples)
- with profile.report("hla typing", dirs):
- samples = hla.run(samples, run_parallel)
- ## Variant calling on sub-regions of the input file (full cluster)
- with prun.start(_wres(parallel, ["gatk", "picard", "variantcaller"]),
- samples, config, dirs, "full",
- multiplier=region.get_max_counts(samples), max_multicore=1) as run_parallel:
- with profile.report("alignment post-processing", dirs):
- samples = region.parallel_prep_region(samples, run_parallel)
- with profile.report("variant calling", dirs):
- samples = genotype.parallel_variantcall_region(samples, run_parallel)
- with profile.report("joint squaring off/backfilling", dirs):
- samples = joint.square_off(samples, run_parallel)
- ## Finalize variants, BAMs and population databases (per-sample multicore cluster)
- with prun.start(_wres(parallel, ["gatk", "gatk-vqsr", "snpeff", "bcbio_variation",
- "gemini", "samtools", "fastqc", "sambamba",
- "bcbio-variation-recall", "qsignature",
- "svcaller", "kraken", "preseq"]),
- samples, config, dirs, "multicore2",
- multiplier=structural.parallel_multiplier(samples)) as run_parallel:
- with profile.report("variant post-processing", dirs):
- samples = run_parallel("postprocess_variants", samples)
- samples = run_parallel("split_variants_by_sample", samples)
- with profile.report("prepped BAM merging", dirs):
- samples = region.delayed_bamprep_merge(samples, run_parallel)
- with profile.report("validation", dirs):
- samples = run_parallel("compare_to_rm", samples)
- samples = genotype.combine_multiple_callers(samples)
- with profile.report("ensemble calling", dirs):
- samples = ensemble.combine_calls_parallel(samples, run_parallel)
- with profile.report("validation summary", dirs):
- samples = validate.summarize_grading(samples)
- with profile.report("structural variation", dirs):
- samples = structural.run(samples, run_parallel, "initial")
- with profile.report("structural variation", dirs):
- samples = structural.run(samples, run_parallel, "standard")
- with profile.report("structural variation ensemble", dirs):
- samples = structural.run(samples, run_parallel, "ensemble")
- with profile.report("structural variation validation", dirs):
- samples = run_parallel("validate_sv", samples)
- with profile.report("heterogeneity", dirs):
- samples = heterogeneity.run(samples, run_parallel)
- with profile.report("population database", dirs):
- samples = population.prep_db_parallel(samples, run_parallel)
- # after SV calling and SNV merging
- with profile.report("create CNV PON", dirs):
- samples = structural.create_cnv_pon(samples)
- with profile.report("peddy check", dirs):
- samples = peddy.run_peddy_parallel(samples, run_parallel)
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("archive", dirs):
- samples = archive.compress(samples, run_parallel)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- logger.info("Timing: finished")
- return samples
- def _debug_samples(i, samples):
- print("---", i, len(samples))
- for sample in (utils.to_single_data(x) for x in samples):
- print(" ", sample["description"], sample.get("region"), \
- utils.get_in(sample, ("config", "algorithm", "variantcaller")), \
- utils.get_in(sample, ("config", "algorithm", "jointcaller")), \
- utils.get_in(sample, ("metadata", "batch")), \
- [x.get("variantcaller") for x in sample.get("variants", [])], \
- sample.get("work_bam"), \
- sample.get("vrn_file"))
- def standardpipeline(config, run_info_yaml, parallel, dirs, samples):
- ## Alignment and preparation requiring the entire input file (multicore cluster)
- with prun.start(_wres(parallel, ["aligner", "samtools", "sambamba"]),
- samples, config, dirs, "multicore") as run_parallel:
- with profile.report("organize samples", dirs):
- samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml,
- [x[0]["description"] for x in samples]]])
- with profile.report("alignment", dirs):
- samples = run_parallel("process_alignment", samples)
- with profile.report("callable regions", dirs):
- samples = run_parallel("prep_samples", [samples])
- samples = run_parallel("postprocess_alignment", samples)
- samples = run_parallel("combine_sample_regions", [samples])
- samples = region.clean_sample_data(samples)
- ## Quality control
- with prun.start(_wres(parallel, ["fastqc", "qsignature", "kraken", "gatk", "samtools", "preseq"]),
- samples, config, dirs, "multicore2") as run_parallel:
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- logger.info("Timing: finished")
- return samples
- def rnaseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples)
- with prun.start(_wres(parallel, ["aligner", "picard", "samtools"],
- ensure_mem={"tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8}),
- samples, config, dirs, "alignment",
- multiplier=alignprep.parallel_multiplier(samples)) as run_parallel:
- with profile.report("alignment", dirs):
- samples = run_parallel("disambiguate_split", [samples])
- samples = run_parallel("process_alignment", samples)
- with prun.start(_wres(parallel, ["samtools", "cufflinks"]),
- samples, config, dirs, "rnaseqcount") as run_parallel:
- with profile.report("disambiguation", dirs):
- samples = disambiguate.resolve(samples, run_parallel)
- with profile.report("transcript assembly", dirs):
- samples = rnaseq.assemble_transcripts(run_parallel, samples)
- with profile.report("estimate expression (threaded)", dirs):
- samples = rnaseq.quantitate_expression_parallel(samples, run_parallel)
- with prun.start(_wres(parallel, ["dexseq", "express"]), samples, config,
- dirs, "rnaseqcount-singlethread", max_multicore=1) as run_parallel:
- with profile.report("estimate expression (single threaded)", dirs):
- samples = rnaseq.quantitate_expression_noparallel(samples, run_parallel)
- samples = rnaseq.combine_files(samples)
- with prun.start(_wres(parallel, ["gatk", "vardict"]), samples, config,
- dirs, "rnaseq-variation") as run_parallel:
- with profile.report("RNA-seq variant calling", dirs):
- samples = rnaseq.rnaseq_variant_calling(samples, run_parallel)
- with prun.start(_wres(parallel, ["samtools", "fastqc", "qualimap",
- "kraken", "gatk", "preseq"], ensure_mem={"qualimap": 4}),
- samples, config, dirs, "qc") as run_parallel:
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("create SummarizedExperiment object", dirs):
- samples = rnaseq.load_summarizedexperiment(samples)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- with profile.report("bcbioRNAseq loading", dirs):
- tools_on = dd.get_in_samples(samples, dd.get_tools_on)
- bcbiornaseq_on = tools_on and "bcbiornaseq" in tools_on
- if bcbiornaseq_on:
- if len(samples) < 3:
- logger.warn("bcbioRNASeq needs at least three samples total, skipping.")
- elif len(samples) > 100:
- logger.warn("Over 100 samples, skipping bcbioRNASeq.")
- else:
- run_parallel("run_bcbiornaseqload", [sample])
- logger.info("Timing: finished")
- return samples
- def fastrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples)
- ww = initialize_watcher(samples)
- with prun.start(_wres(parallel, ["samtools"]), samples, config,
- dirs, "fastrnaseq") as run_parallel:
- with profile.report("fastrnaseq", dirs):
- samples = rnaseq.fast_rnaseq(samples, run_parallel)
- ww.report("fastrnaseq", samples)
- samples = rnaseq.combine_files(samples)
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- ww.report("qcsummary", samples)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for samples in samples:
- run_parallel("upload_samples_project", [samples])
- logger.info("Timing: finished")
- return samples
- def singlecellrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples)
- with prun.start(_wres(parallel, ["samtools", "rapmap"]), samples, config,
- dirs, "singlecell-rnaseq") as run_parallel:
- with profile.report("singlecell-rnaseq", dirs):
- samples = rnaseq.singlecell_rnaseq(samples, run_parallel)
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for samples in samples:
- run_parallel("upload_samples_project", [samples])
- logger.info("Timing: finished")
- return samples
- def smallrnaseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- # causes a circular import at the top level
- from bcbio.srna.group import report as srna_report
- samples = rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples)
- with prun.start(_wres(parallel, ["aligner", "picard", "samtools"],
- ensure_mem={"bowtie": 8, "bowtie2": 8, "star": 2}),
- [samples[0]], config, dirs, "alignment") as run_parallel:
- with profile.report("prepare", dirs):
- samples = run_parallel("seqcluster_prepare", [samples])
- with profile.report("seqcluster alignment", dirs):
- samples = run_parallel("srna_alignment", [samples])
- with prun.start(_wres(parallel, ["aligner", "picard", "samtools"],
- ensure_mem={"tophat": 10, "tophat2": 10, "star": 2, "hisat2": 8}),
- samples, config, dirs, "alignment_samples",
- multiplier=alignprep.parallel_multiplier(samples)) as run_parallel:
- with profile.report("alignment", dirs):
- samples = run_parallel("process_alignment", samples)
- with prun.start(_wres(parallel, ["picard", "miraligner"]),
- samples, config, dirs, "annotation") as run_parallel:
- with profile.report("small RNA annotation", dirs):
- samples = run_parallel("srna_annotation", samples)
- with prun.start(_wres(parallel, ["seqcluster", "mirge"],
- ensure_mem={"seqcluster": 8}),
- [samples[0]], config, dirs, "cluster") as run_parallel:
- with profile.report("cluster", dirs):
- samples = run_parallel("seqcluster_cluster", [samples])
- with prun.start(_wres(parallel, ["picard", "fastqc"]),
- samples, config, dirs, "qc") as run_parallel:
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("report", dirs):
- srna_report(samples)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- return samples
- def chipseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- with prun.start(_wres(parallel, ["aligner", "picard"]),
- samples, config, dirs, "multicore",
- multiplier=alignprep.parallel_multiplier(samples)) as run_parallel:
- with profile.report("organize samples", dirs):
- samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml,
- [x[0]["description"] for x in samples]]])
- with profile.report("alignment", dirs):
- samples = run_parallel("prepare_sample", samples)
- samples = run_parallel("trim_sample", samples)
- samples = run_parallel("disambiguate_split", [samples])
- samples = run_parallel("process_alignment", samples)
- with profile.report("disambiguation", dirs):
- samples = disambiguate.resolve(samples, run_parallel)
- samples = run_parallel("clean_chipseq_alignment", samples)
- with prun.start(_wres(parallel, ["peakcaller"]),
- samples, config, dirs, "peakcalling",
- multiplier = peaks._get_multiplier(samples)) as run_parallel:
- with profile.report("peakcalling", dirs):
- samples = peaks.peakcall_prepare(samples, run_parallel)
- samples = peaks.call_consensus(samples)
- samples = run_parallel("run_chipseq_count", samples)
- samples = peaks.create_peaktable(samples)
- with prun.start(_wres(parallel, ["picard", "fastqc"]),
- samples, config, dirs, "qc") as run_parallel:
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- samples = atac.create_ataqv_report(samples)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- logger.info("Timing: finished")
- return samples
- def wgbsseqpipeline(config, run_info_yaml, parallel, dirs, samples):
- with prun.start(_wres(parallel, ["fastqc", "picard"], ensure_mem={"fastqc" : 4}),
- samples, config, dirs, "trimming") as run_parallel:
- with profile.report("organize samples", dirs):
- samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml,
- [x[0]["description"] for x in samples]]])
- samples = run_parallel("prepare_sample", samples)
- samples = run_parallel("trim_bs_sample", samples)
- with prun.start(_wres(parallel, ["aligner", "bismark", "picard", "samtools"]),
- samples, config, dirs, "multicore",
- multiplier=alignprep.parallel_multiplier(samples)) as run_parallel:
- with profile.report("alignment", dirs):
- samples = run_parallel("process_alignment", samples)
- with prun.start(_wres(parallel, ['samtools']), samples, config, dirs,
- 'deduplication') as run_parallel:
- with profile.report('deduplicate', dirs):
- samples = run_parallel('deduplicate_bismark', samples)
- with prun.start(_wres(parallel, ["caller"], ensure_mem={"caller": 5}),
- samples, config, dirs, "multicore2",
- multiplier=24) as run_parallel:
- with profile.report("cpg calling", dirs):
- samples = run_parallel("cpg_calling", samples)
- with prun.start(_wres(parallel, ["picard", "fastqc", "samtools"]),
- samples, config, dirs, "qc") as run_parallel:
- with profile.report("quality control", dirs):
- samples = qcsummary.generate_parallel(samples, run_parallel)
- with profile.report("upload", dirs):
- samples = run_parallel("upload_samples", samples)
- for sample in samples:
- run_parallel("upload_samples_project", [sample])
- logger.info("Timing: finished")
- return samples
- def rnaseq_prep_samples(config, run_info_yaml, parallel, dirs, samples):
- """
- organizes RNA-seq and small-RNAseq samples, converting from BAM if
- necessary and trimming if necessary
- """
- pipeline = dd.get_in_samples(samples, dd.get_analysis)
- trim_reads_set = any([tz.get_in(["algorithm", "trim_reads"], d) for d in dd.sample_data_iterator(samples)])
- resources = ["picard"]
- needs_trimming = (_is_smallrnaseq(pipeline) or trim_reads_set)
- if needs_trimming:
- resources.append("atropos")
- with prun.start(_wres(parallel, resources),
- samples, config, dirs, "trimming",
- max_multicore=1 if not needs_trimming else None) as run_parallel:
- with profile.report("organize samples", dirs):
- samples = run_parallel("organize_samples", [[dirs, config, run_info_yaml,
- [x[0]["description"] for x in samples]]])
- samples = run_parallel("prepare_sample", samples)
- if needs_trimming:
- with profile.report("adapter trimming", dirs):
- if _is_smallrnaseq(pipeline):
- samples = run_parallel("trim_srna_sample", samples)
- else:
- samples = run_parallel("trim_sample", samples)
- return samples
- def _get_pipeline(item):
- from bcbio.log import logger
- analysis_type = item.get("analysis", "").lower()
- if analysis_type not in SUPPORTED_PIPELINES:
- logger.error("Cannot determine which type of analysis to run, "
- "set in the run_info under details.")
- sys.exit(1)
- else:
- return SUPPORTED_PIPELINES[analysis_type]
- def _pair_samples_with_pipelines(run_info_yaml, config):
- """Map samples defined in input file to pipelines to run.
- """
- samples = config_utils.load_config(run_info_yaml)
- if isinstance(samples, dict):
- resources = samples.pop("resources")
- samples = samples["details"]
- else:
- resources = {}
- ready_samples = []
- for sample in samples:
- if "files" in sample:
- del sample["files"]
- # add any resources to this item to recalculate global configuration
- usample = copy.deepcopy(sample)
- usample.pop("algorithm", None)
- if "resources" not in usample:
- usample["resources"] = {}
- for prog, pkvs in resources.items():
- if prog not in usample["resources"]:
- usample["resources"][prog] = {}
- if pkvs is not None:
- for key, val in pkvs.items():
- usample["resources"][prog][key] = val
- config = config_utils.update_w_custom(config, usample)
- sample["resources"] = {}
- ready_samples.append(sample)
- paired = [(x, _get_pipeline(x)) for x in ready_samples]
- d = defaultdict(list)
- for x in paired:
- d[x[1]].append([x[0]])
- return d, config
- SUPPORTED_PIPELINES = {"variant2": variant2pipeline,
- "snp calling": variant2pipeline,
- "variant": variant2pipeline,
- "standard": standardpipeline,
- "minimal": standardpipeline,
- "rna-seq": rnaseqpipeline,
- "smallrna-seq": smallrnaseqpipeline,
- "chip-seq": chipseqpipeline,
- "wgbs-seq": wgbsseqpipeline,
- "fastrna-seq": fastrnaseqpipeline,
- "scrna-seq": singlecellrnaseqpipeline}
- def _is_smallrnaseq(pipeline):
- return pipeline.lower() == "smallrna-seq"
main.py at commit 594339f, under MIT · at the source
Overview
- Genetics and Aging Research Unit McCance Center for Brain Health MassGeneral Institute for Neurodegenerative Disease Department of Neurology Massachusetts General Hospital and Harvard Medical School Charlestown Massachusetts USA
- Department of Ophthalmology and Visual Science Yale School of Medicine New Haven Connecticut USA
- Athinoula A. Martinos Center for Biomedical Imaging Department of Radiology Massachusetts General Hospital and Harvard Medical School Charlestown Massachusetts USA
- Department of Pathology Yale School of Medicine New Haven Connecticut USA
- The Broad Institute MIT and Harvard Cambridge Massachusetts USA
Abstract
The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.
Repository
Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.
chapmanb/bcbio-nextgen
594339fd1a9694c8f8ed61084e2bd5740cfd59b0, 24 August 2024Availability: 1 check, the latest on 28 September 2026: the link answers
- 28 September 2026: the link answers
318 files
- bcbio/
__init__.py — Python, 2 lines - bcbio/
bam/ — Python, 635 lines__init__.py - bcbio/
bam/ — Python, 374 linescallable.py - bcbio/
bam/ — Python, 66 linescounts.py - bcbio/
bam/ — Python, 148 linescoverage.py - bcbio/
bam/ — Python, 67 linescram.py - bcbio/
bam/ — Python, 42 linesfasta.py - bcbio/
bam/ — Python, 317 linesfastq.py - bcbio/
bam/ — Python, 121 linesreadstats.py - bcbio/
bam/ — Python, 26 linesref.py - bcbio/
bam/ — Python, 82 linesskewer.py - bcbio/
bam/ — Python, 267 linestrim.py - bcbio/
bed/ — Python, 70 lines__init__.py - bcbio/
broad/ — Python, 598 lines__init__.py - bcbio/
broad/ — Python, 502 linesmetrics.py - bcbio/
broad/ — Python, 310 linespicardrun.py - bcbio/
chipseq/ — Python, 212 lines__init__.py - bcbio/
chipseq/ — Python, 45 linesantibodies.py - bcbio/
chipseq/ — Python, 301 linesatac.py - bcbio/
chipseq/ — Python, 111 linesmacs2.py - bcbio/
chipseq/ — Python, 376 linespeaks.py - bcbio/
cwl/ — Python, 2 lines__init__.py - bcbio/
cwl/ — Python, 903 linescreate.py - bcbio/
cwl/ — Python, 266 linescwlutils.py - bcbio/
cwl/ — Python, 683 linesdefs.py - bcbio/
cwl/ — Python, 550 lineshpc.py - bcbio/
cwl/ — Python, 101 linesinspect.py - bcbio/
cwl/ — Python, 12 linesmain.py - bcbio/
cwl/ — Python, 369 linestool.py - bcbio/
cwl/ — Python, 495 linesworkflow.py - bcbio/
distributed/ — Python, 2 lines__init__.py - bcbio/
distributed/ — Python, 29 linesclargs.py - bcbio/
distributed/ — Python, 34 linesclusterk.py - bcbio/
distributed/ — Python, 141 linesipython.py - bcbio/
distributed/ — Python, 617 linesipythontasks.py - bcbio/
distributed/ — Python, 89 linesmulti.py - bcbio/
distributed/ — Python, 482 linesmultitasks.py - bcbio/
distributed/ — Python, 712 linesobjectstore.py - bcbio/
distributed/ — Python, 69 linesprun.py - bcbio/
distributed/ — Python, 234 linesresources.py - bcbio/
distributed/ — Python, 649 linesrunfn.py - bcbio/
distributed/ — Python, 143 linessplit.py - bcbio/
distributed/ — Python, 159 linestransaction.py - bcbio/
dragen/ — Python, 1 line__init__.py - bcbio/
dragen/ — Python, 86 linesdragen.py - bcbio/
galaxy/ — Python, 2 lines__init__.py - bcbio/
galaxy/ — Python, 82 linesapi.py - bcbio/
galaxy/ — Python, 88 linesloc.py - bcbio/
galaxy/ — Python, 189 linesnglims.py - bcbio/
graph/ — Python, 3 lines__init__.py - bcbio/
graph/ — Python, 312 linescollectl.py - bcbio/
graph/ — Python, 455 linesgraph.py - bcbio/
heterogeneity/ — Python, 146 lines__init__.py - bcbio/
heterogeneity/ — Python, 501 linesbubbletree.py - bcbio/
heterogeneity/ — Python, 95 lineschromhacks.py - bcbio/
heterogeneity/ — Python, 434 linesloh.py - bcbio/
heterogeneity/ — Python, 265 linesphylowgs.py - bcbio/
heterogeneity/ — Python, 221 linestheta.py - bcbio/
hla/ — Python, 32 lines__init__.py - bcbio/
hla/ — Python, 89 linesbwakit.py - bcbio/
hla/ — Python, 564 linesgroups.py - bcbio/
hla/ — Python, 148 linesoptitype.py - bcbio/
hmmer/ — Python, 2 lines__init__.py - bcbio/
hmmer/ — Python, 96 linessearch.py - bcbio/
illumina/ — Python, 2 lines__init__.py - bcbio/
illumina/ — Python, 51 linesdemultiplex.py - bcbio/
illumina/ — Python, 81 linesflowcell.py - bcbio/
illumina/ — Python, 176 linesmachine.py - bcbio/
illumina/ — Python, 133 linessamplesheet.py - bcbio/
illumina/ — Python, 46 linestransfer.py - bcbio/
install.py — Python, 824 lines - bcbio/
log/ — Python, 165 lines__init__.py - bcbio/
log/ — Python, 134 lineslogbook_zmqpush.py - bcbio/
ngsalign/ — Python, 2 lines__init__.py - bcbio/
ngsalign/ — Python, 726 linesalignprep.py - bcbio/
ngsalign/ — Python, 39 linesbbmap.py - bcbio/
ngsalign/ — Python, 157 linesbismark.py - bcbio/
ngsalign/ — Python, 74 linesbowtie.py - bcbio/
ngsalign/ — Python, 152 linesbowtie2.py - bcbio/
ngsalign/ — Python, 52 linesbsmap.py - bcbio/
ngsalign/ — Python, 359 linesbwa.py - bcbio/
ngsalign/ — Python, 146 lineshisat2.py - bcbio/
ngsalign/ — Python, 51 linesminimap2.py - bcbio/
ngsalign/ — Python, 92 linesmosaik.py - bcbio/
ngsalign/ — Python, 148 linesnovoalign.py - bcbio/
ngsalign/ — Python, 337 linespostalign.py - bcbio/
ngsalign/ — Python, 100 linesrtg.py - bcbio/
ngsalign/ — Python, 86 linessnap.py - bcbio/
ngsalign/ — Python, 333 linesstar.py - bcbio/
ngsalign/ — Python, 370 linestophat.py - bcbio/
picard/ — Python, 2 lines__init__.py - bcbio/
picard/ — Python, 2 linesmetrics.py - bcbio/
picard/ — Python, 2 linesutils.py - bcbio/
pipeline/ — Python, 14 lines__init__.py - bcbio/
pipeline/ — Python, 173 linesalignment.py - bcbio/
pipeline/ — Python, 31 linesarchive.py - bcbio/
pipeline/ — Python, 161 linescleanbam.py - bcbio/
pipeline/ — Python, 492 linesconfig_utils.py - bcbio/
pipeline/ — Python, 434 linesdatadict.py - bcbio/
pipeline/ — Python, 167 linesdisambiguate/ __init__.py - bcbio/
pipeline/ — Python, 352 linesdisambiguate/ run.py - bcbio/
pipeline/ — Python, 140 linesfastq.py - bcbio/
pipeline/ — Python, 285 linesgenome.py - bcbio/
pipeline/ — Python, 533 lines, 1 matchmain.py - bcbio/
pipeline/ — Python, 131 linesmerge.py - bcbio/
pipeline/ — Python, 411 linesqcsummary.py - bcbio/
pipeline/ — Python, 189 linesregion.py - bcbio/
pipeline/ — Python, 608 linesrnaseq.py - bcbio/
pipeline/ — Python, 1,165 linesrun_info.py - bcbio/
pipeline/ — Python, 427 linessample.py - bcbio/
pipeline/ — Python, 302 linesshared.py - bcbio/
pipeline/ — Python, 135 linessra.py - bcbio/
pipeline/ — Python, 37 linestools.py - bcbio/
pipeline/ — Python, 171 linesvariation.py - bcbio/
provenance/ — Python, 2 lines__init__.py - bcbio/
provenance/ — Python, 39 linesdata.py - bcbio/
provenance/ — Python, 77 linesdiagnostics.py - bcbio/
provenance/ — Python, 157 linesdo.py - bcbio/
provenance/ — Python, 12 linesprofile.py - bcbio/
provenance/ — Python, 289 linesprograms.py - bcbio/
provenance/ — Python, 224 linessystem.py - bcbio/
provenance/ — Python, 97 linesversioncheck.py - bcbio/
qc/ — Python, 2 lines__init__.py - bcbio/
qc/ — Python, 6 linesatac.py - bcbio/
qc/ — Python, 21 linesatropos.py - bcbio/
qc/ — Python, 84 lineschipseq.py - bcbio/
qc/ — Python, 113 linescontamination.py - bcbio/
qc/ — Python, 118 linescoverage.py - bcbio/
qc/ — Python, 27 linesdamage.py - bcbio/
qc/ — Python, 135 linesfastqc.py - bcbio/
qc/ — Python, 95 lineskraken.py - bcbio/
qc/ — Python, 616 linesmultiqc.py - bcbio/
qc/ — Python, 40 linespicard.py - bcbio/
qc/ — Python, 152 linespreseq.py - bcbio/
qc/ — Python, 194 linesqsignature.py - bcbio/
qc/ — Python, 399 linesqualimap.py - bcbio/
qc/ — Python, 82 linessamtools.py - bcbio/
qc/ — Python, 72 linessrna.py - bcbio/
qc/ — Python, 76 linesumi.py - bcbio/
qc/ — Python, 154 linesvariant.py - bcbio/
qc/ — Python, 107 linesviral.py - bcbio/
rnaseq/ — Python, 2 lines__init__.py - bcbio/
rnaseq/ — Python, 72 linesannotate_gtf.py - bcbio/
rnaseq/ — Python, 65 linesarriba.py - bcbio/
rnaseq/ — Python, 191 linesbcbiornaseq.py - bcbio/
rnaseq/ — Python, 83 linescount.py - bcbio/
rnaseq/ — Python, 152 linescpat.py - bcbio/
rnaseq/ — Python, 266 linescufflinks.py - bcbio/
rnaseq/ — Python, 106 linesdexseq.py - bcbio/
rnaseq/ — Python, 174 linesericscript.py - bcbio/
rnaseq/ — Python, 97 linesexpress.py - bcbio/
rnaseq/ — Python, 183 linesfeatureCounts.py - bcbio/
rnaseq/ — Python, 444 linesgtf.py - bcbio/
rnaseq/ — Python, 198 lineskallisto.py - bcbio/
rnaseq/ — Python, 189 linesoncofuse.py - bcbio/
rnaseq/ — Python, 124 linespizzly.py - bcbio/
rnaseq/ — Python, 66 linesqc.py - bcbio/
rnaseq/ — Python, 102 linesrapmap.py - bcbio/
rnaseq/ — Python, 61 linesrsem.py - bcbio/
rnaseq/ — Python, 213 linessailfish.py - bcbio/
rnaseq/ — Python, 268 linessalmon.py - bcbio/
rnaseq/ — Python, 77 linessinglecellexperiment.py - bcbio/
rnaseq/ — Python, 115 linesspikein.py - bcbio/
rnaseq/ — Python, 121 linesstringtie.py - bcbio/
rnaseq/ — Python, 522 linesumi.py - bcbio/
rnaseq/ — Python, 207 linesvariation.py - bcbio/
scripts/ — R, 67 linesR/ bcbio2se.R - bcbio/
scripts/ — R, 262 linesR/ se2qc.Rmd - bcbio/
server/ — Python, 2 lines__init__.py - bcbio/
server/ — Python, 132 linesbackground.py - bcbio/
server/ — Python, 41 linesmain.py - bcbio/
server/ — Python, 87 linesrun.py - bcbio/
setpath.py — Python, 89 lines - bcbio/
srna/ — Python, 4 lines__init__.py - bcbio/
srna/ — Python, 221 linesgroup.py - bcbio/
srna/ — Python, 105 linesmirdeep.py - bcbio/
srna/ — Python, 80 linesmirge.py - bcbio/
srna/ — Python, 4 linesqc.py - bcbio/
srna/ — Python, 337 linessample.py - bcbio/
srna/ — Python, 88 linesumis.py - bcbio/
structural/ — Python, 395 lines__init__.py - bcbio/
structural/ — Python, 101 linesannotate.py - bcbio/
structural/ — Python, 130 linesbattenberg.py - bcbio/
structural/ — Python, 226 linescn_mops.py - bcbio/
structural/ — Python, 768 linescnvkit.py - bcbio/
structural/ — Python, 94 linesconvert.py - bcbio/
structural/ — Python, 188 linesdelly.py - bcbio/
structural/ — Python, 336 linesgatkcnv.py - bcbio/
structural/ — Python, 113 linesgridss.py - bcbio/
structural/ — Python, 162 lineshydra.py - bcbio/
structural/ — Python, 232 lineslumpy.py - bcbio/
structural/ — Python, 180 linesmanta.py - bcbio/
structural/ — Python, 59 linesmetasv.py - bcbio/
structural/ — Python, 155 linespindel.py - bcbio/
structural/ — Python, 116 linesplot.py - bcbio/
structural/ — Python, 217 linesprioritize.py - bcbio/
structural/ — Python, 446 linespurecn.py - bcbio/
structural/ — Python, 337 linespurple.py - bcbio/
structural/ — Python, 503 linesregions.py - bcbio/
structural/ — Python, 37 linesscramble.py - bcbio/
structural/ — Python, 394 linesseq2c.py - bcbio/
structural/ — Python, 331 linesshared.py - bcbio/
structural/ — Python, 257 linestitancna.py - bcbio/
structural/ — Python, 402 linesvalidate.py - bcbio/
structural/ — Python, 87 lineswham.py - bcbio/
upload/ — Python, 963 lines__init__.py - bcbio/
upload/ — Python, 87 linesfilesystem.py - bcbio/
upload/ — Python, 188 linesgalaxy.py - bcbio/
upload/ — Python, 49 linesirods.py - bcbio/
upload/ — Python, 98 liness3.py - bcbio/
upload/ — Python, 17 linesshared.py - bcbio/
utils.py — Python, 1,050 lines - bcbio/
variation/ — Python, 2 lines__init__.py - bcbio/
variation/ — Python, 174 linesannotation.py - bcbio/
variation/ — Python, 132 linesbamprep.py - bcbio/
variation/ — Python, 266 linesbedutils.py - bcbio/
variation/ — Python, 332 linescortex.py - bcbio/
variation/ — Python, 278 linescoverage.py - bcbio/
variation/ — Python, 94 linesdamage.py - bcbio/
variation/ — Python, 78 linesdeepvariant.py - bcbio/
variation/ — Python, 451 lineseffects.py - bcbio/
variation/ — Python, 265 linesensemble.py - bcbio/
variation/ — Python, 372 linesfreebayes.py - bcbio/
variation/ — Python, 268 linesgatk.py - bcbio/
variation/ — Python, 309 linesgatkfilter.py - bcbio/
variation/ — Python, 187 linesgatkjoint.py - bcbio/
variation/ — Python, 486 linesgenotype.py - bcbio/
variation/ — Python, 262 linesgermline.py - bcbio/
variation/ — Python, 237 linesjoint.py - bcbio/
variation/ — Python, 271 linesmulti.py - bcbio/
variation/ — Python, 245 linesmutect.py - bcbio/
variation/ — Python, 270 linesmutect2.py - bcbio/
variation/ — Python, 173 linesnaming.py - bcbio/
variation/ — Python, 130 linesnormalize.py - bcbio/
variation/ — Python, 161 linesoctopus.py - bcbio/
variation/ — Python, 159 linespeddy.py - bcbio/
variation/ — Python, 73 linespisces.py - bcbio/
variation/ — Python, 72 linesplatypus.py - bcbio/
variation/ — Python, 95 linesploidy.py - bcbio/
variation/ — Python, 425 linespopulation.py - bcbio/
variation/ — Python, 205 linesprioritize.py - bcbio/
variation/ — Python, 233 linesqsnp.py - bcbio/
variation/ — Python, 99 linesrealign.py - bcbio/
variation/ — Python, 182 linesrecalibrate.py - bcbio/
variation/ — Python, 111 linessamtools.py - bcbio/
variation/ — Python, 201 linesscalpel.py - bcbio/
variation/ — Python, 185 linessentieon.py - bcbio/
variation/ — Python, 44 linessmcounter2.py - bcbio/
variation/ — Python, 37 linessplit.py - bcbio/
variation/ — Python, 401 linesstrelka2.py - bcbio/
variation/ — Python, 746 linesvalidate.py - bcbio/
variation/ — Python, 388 linesvalidateplot.py - bcbio/
variation/ — Python, 392 linesvardict.py - bcbio/
variation/ — Python, 327 linesvarscan.py - bcbio/
variation/ — Python, 192 linesvcfanno.py - bcbio/
variation/ — Python, 738 linesvcfutils.py - bcbio/
variation/ — Python, 232 linesvfilter.py - bcbio/
wgbsseq/ — Python, 1 line__init__.py - bcbio/
wgbsseq/ — Python, 87 linesalign.py - bcbio/
wgbsseq/ — Python, 262 linescpg_caller.py - bcbio/
wgbsseq/ — Python, 48 linesdeduplication.py - bcbio/
wgbsseq/ — Python, 12 lineskits.py - bcbio/
wgbsseq/ — Python, 82 linestrimming.py - bcbio/
workflow/ — Python, 12 lines__init__.py - bcbio/
workflow/ — Python, 73 linesstormseq.py - bcbio/
workflow/ — Python, 606 linestemplate.py - bcbio/
workflow/ — Python, 79 linesxprize.py - config/
examples/ — Shell, 23 linesHCC2218-sv-getdata.sh - config/
examples/ — Shell, 22 linesNA12878-exome-methodcmp- getdata.sh - config/
examples/ — Shell, 19 linesNA12878-hg38-validate-ge tdata.sh - config/
examples/ — Shell, 25 linesNA12878-sv-getdata.sh - config/
examples/ — Shell, 10 linesNA12878-trio-wgs-validat e-getdata.sh - config/
examples/ — Shell, 32 linesNA12878.validate.sh - config/
examples/ — Shell, 35 linesNA24385-10x-getdata.sh - config/
examples/ — Shell, 13 linesarchived/ NA12878-trio-sv-getdata. sh - config/
examples/ — Shell, 28 linescancer-dream-syn3-getdat a.sh - config/
examples/ — Shell, 30 linescancer-giab-na12878-na24 385-getdata.sh - config/
examples/ — Shell, 23 linesgiab-validate-setup.sh - config/
examples/ — Shell, 23 linesrnaseq-seqc-getdata.sh - config/
teaching/ — Shell, 17 linescancer-syn3-chr6-prep.sh - docs/
conf.py — Python, 82 lines - scripts/
bcbio_fastq_umi_prep.py — Python, 278 lines - scripts/
bcbio_nextgen.py — Python, 245 lines - scripts/
bcbio_nextgen_install.py — Python, 306 lines - scripts/
bcbio_prepare_samples.py — Python, 196 lines - scripts/
bcbio_setup_genome.py — Python, 366 lines - scripts/
cwl/ — Python, 114 linesarvados_bcbio_runtimes.p y - scripts/
cwltool2wdl.py — Python, 328 lines - scripts/
vagrant.sh — Shell, 16 lines - setup.py — Python, 28 lines
- tests/
__init__.py — Python, 1 line - tests/
bcbio_vm/ — Python, 91 linestest_docker.py - tests/
conftest.py — Python, 170 lines - tests/
integration/ — Python, 1 line__init__.py - tests/
integration/ — Python, 1 linernaseq/ __init__.py - tests/
integration/ — Python, 137 linesrnaseq/ test_ericscript.py - tests/
integration/ — Python, 40 linestest_S3_pipelines.py - tests/
integration/ — Python, 42 linestest_SequencingDump.py - tests/
integration/ — Python, 223 linestest_automated_analysis. py - tests/
integration/ — Python, 139 linestest_pipeline.py - tests/
run_tests.sh — Shell, 33 lines - tests/
scripts/ — Shell, 2 linesgoofys_logs.sh - tests/
scripts/ — Shell, 33 linesmount.sh - tests/
unit/ — Python, 1 line__init__.py - tests/
unit/ — Python, 39 linesconftest.py - tests/
unit/ — Python, 246 linesdata.py - tests/
unit/ — Python, 1 linedistributed/ __init__.py - tests/
unit/ — Python, 237 linesdistributed/ test_transaction.py - tests/
unit/ — Python, 1 linepipeline/ __init__.py - tests/
unit/ — Python, 14 linespipeline/ test_datadict.py - tests/
unit/ — Python, 41 linespipeline/ test_rnaseq.py - tests/
unit/ — Python, 1 linernaseq/ __init__.py - tests/
unit/ — Python, 61 linesrnaseq/ test_ericscript.py - tests/
unit/ — Python, 13 linestest_alignprep.py - tests/
unit/ — Python, 1 lineupload/ __init__.py - tests/
unit/ — Python, 35 linesupload/ test_upload.py - LICENSE.txt — License, 20 lines
- README.md — Text, 84 lines
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 316 scripts, each with its path and the digest of its content;
- 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
No dataset and no data link were found in the paper.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 28 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 17 authors, 6 keywords, 13 MeSH terms, 7 funders, 80 references.
Cite
This paper
Miller, S. J., Prokopenko, D., Bai, P., Mondal, P., Scott, A., Zhang, W., Gomm, A., Zhang, S., Child, D. D., Shen, N., Ward, J., Schulte, S., Lei, D., Hafler, B. P., Wang, C., Tanzi, R. E., & Zhang, C. (2026). Intracellular protein GBF1 displays significant associations with amyloid pathology in Alzheimer's disease. Alzheimer's & dementia : the journal of the Alzheimer's Association, 22(4), e71271. https://
BibTeX
@article{miller2026intra
author = {Miller, Sean J. and Prokopenko, Dmitry and Bai, Ping and Mondal, Prasenjit and Scott, Abigael and Zhang, Wei and Gomm, Ashley and Zhang, Siyi and Child, Daniel D. and Shen, Nolan and Ward, Joseph and Schulte, Scott and Lei, Dan and Hafler, Brian P. and Wang, Changning and Tanzi, Rudolph E. and Zhang, Can},
title = {{Intracellular protein GBF1 displays significant associations with amyloid pathology in Alzheimer's disease}},
journal = {Alzheimer's \& dementia : the journal of the Alzheimer's Association},
year = {2026},
month = apr,
volume = {22},
number = {4},
pages = {e71271},
publisher = {Wiley},
issn = {1552-5260},
doi = {10.1002/
url = {https://
pmid = {41988936},
pmcid = {PMC13084705}
}
RIS
TY - JOUR
AU - Miller, Sean J.
AU - Prokopenko, Dmitry
AU - Bai, Ping
AU - Mondal, Prasenjit
AU - Scott, Abigael
AU - Zhang, Wei
AU - Gomm, Ashley
AU - Zhang, Siyi
AU - Child, Daniel D.
AU - Shen, Nolan
AU - Ward, Joseph
AU - Schulte, Scott
AU - Lei, Dan
AU - Hafler, Brian P.
AU - Wang, Changning
AU - Tanzi, Rudolph E.
AU - Zhang, Can
TI - Intracellular protein GBF1 displays significant associations with amyloid pathology in Alzheimer's disease
T2 - Alzheimer's & dementia : the journal of the Alzheimer's Association
J2 - Alzheimers Dement
PY - 2026
DA - 2026/
VL - 22
IS - 4
SP - e71271
SN - 1552-5260
PB - Wiley
DO - 10.1002/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1002/
"type": "article-journal",
"title": "Intracellular protein GBF1 displays significant associations with amyloid pathology in Alzheimer's disease",
"container-title": "Alzheimer's & dementia : the journal of the Alzheimer's Association",
"author": [
{
"family": "Miller",
"given": "Sean J."
},
{
"family": "Prokopenko",
"given": "Dmitry"
},
{
"family": "Bai",
"given": "Ping"
},
{
"family": "Mondal",
"given": "Prasenjit"
},
{
"family": "Scott",
"given": "Abigael"
},
{
"family": "Zhang",
"given": "Wei"
},
{
"family": "Gomm",
"given": "Ashley"
},
{
"family": "Zhang",
"given": "Siyi"
},
{
"family": "Child",
"given": "Daniel D."
},
{
"family": "Shen",
"given": "Nolan"
},
{
"family": "Ward",
"given": "Joseph"
},
{
"family": "Schulte",
"given": "Scott"
},
{
"family": "Lei",
"given": "Dan"
},
{
"family": "Hafler",
"given": "Brian P."
},
{
"family": "Wang",
"given": "Changning"
},
{
"family": "Tanzi",
"given": "Rudolph E."
},
{
"family": "Zhang",
"given": "Can"
}
],
"container-title-short":
"volume": "22",
"issue": "4",
"page": "e71271",
"DOI": "10.1002/
"PMID": "41988936",
"PMCID": "PMC13084705",
"ISSN": "1552-5260",
"publisher": "Wiley",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
1
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1038/s41467-026-76675-1 [code]
- Long-read proteogenomic atlas of human neuronal differentiation reveals isoform diversity informing neurodevelopmental risk mechanisms.Journal: Nature communicationsIn common: pysam, Biopython, BEDTools, 9 other tools
- [2] doi:10.1038/s41592-026-03211-w [code]
- Spatial isoform sequencing at single-cell resolution reveals cell-type-specific spatial isoform variability in multiple brain cell types.Journal: Nature methodsIn common: pysam, Biopython, BEDTools, 9 other tools, mouse
- [3] doi:10.1038/s41467-026-71790-5 [code]
- Recurrent DNA break clusters drive replication-stress-induc
ed copy number variants and genome diversification. Journal: Nature communicationsIn common: BCFtools, pysam, BEDTools, 8 other tools, mouse, cellular / molecular - [4] doi:10.1038/s41586-026-10512-9 [code]
- Astrocyte glucocorticoid receptor signalling restricts neuronal plasticity.Journal: NatureIn common: pysam, Biopython, BEDTools, 8 other tools, mouse, cellular / molecular
- [5] doi:10.21203/rs.3.rs-9927928/v1 [code]
- Genome-wide and allele-resolved maps of the radial architecture of the mouse genomeJournal: Research Square (preprint)In common: BCFtools, pysam, BEDTools, 8 other tools, mouse
- [6] doi:10.1126/sciadv.aed2952 [code]
- Activation of transposable elements is linked to a region- and cell type-specific interferon response in Parkinson's disease.Journal: Science advancesIn common: pysam, Biopython, BEDTools, 8 other tools, cellular / molecular
- [7] doi:10.1038/s42003-026-10957-8 [code]
- Brain defence by the extracellular matrix protein Cochlin.Journal: Communications biologyIn common: BCFtools, Biopython, SAMtools, 8 other tools, mouse, cellular / molecular
- [8] doi:10.1038/s44318-026-00818-9 [code]
- FAM134B-mediated ER-phagy degrades APP and suppresses Alzheimer's disease pathology.Journal: The EMBO journalIn common: Biopython, BEDTools, DESeq2, 7 other tools, Alzheimer's / dementia, mouse, cellular / molecular, 1 reference
- [9] doi:10.1038/s41467-026-72598-z [code]
- Functional impact of genetic background on variable expressivity in neurodevelopmental disorders.Journal: Nature communicationsIn common: BCFtools, BEDTools, SAMtools, 8 other tools
- [10] doi:10.1038/s41467-026-73902-7 [code]
- GWAS on short tandem repeats identifies genetic mechanisms in Alzheimer's disease.Journal: Nature communicationsIn common: BCFtools, SAMtools, ggplot2, 5 other tools, Alzheimer's / dementia, cellular / molecular, 3 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 316 scripts, and 1 match between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:9ce7d235f8f60684…
Add the badge to its README
The badge links the code to this page. Copy one of these into the README of the paper's code: only you decide where it goes, and nothing is changed for you.
Markdown
[, paste the snippet at the top, then “Commit changes…” and, to review it first, “Create a new branch and start a pull request”. You open the pull request; OSCR asks for no permission.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.
Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
