Skills › Knowledge Work Plugins › nextflow-development › __init__.py
__init__.py
69 lines · bio-research/skills/nextflow-development/scripts/utils/__init__.py at 2574e29
1"""
2Utility modules for nf-core pipeline deployment.
4Modules:
5 ncbi_utils: NCBI/GEO/SRA data fetching and download utilities
6 file_discovery: Find FASTQ, BAM, and CRAM files
7 sample_inference: Extract sample info, detect tumor/normal
8 validators: Validate samplesheets before writing
9"""
11# NCBI utilities for GEO/SRA data acquisition
12from .ncbi_utils import (
13 check_network_access,
14 fetch_geo_metadata,
15 fetch_sra_study_accession,
16 fetch_sra_run_info,
17 fetch_sra_run_info_detailed,
18 fetch_bioproject_from_geo,
19 fetch_ena_fastq_urls,
20 download_file,
21 fetch_pubmed_metadata,
22 format_file_size,
23 estimate_download_size,
24 group_samples_by_type,
25 format_sample_groups_table,
26)
28# File discovery utilities
29from .file_discovery import discover_files, FileInfo, count_files_by_type
31# Sample inference utilities
32from .sample_inference import (
33 extract_sample_info,
34 infer_tumor_normal_status,
35 match_read_pairs,
36 extract_replicate_number
37)
39# Validation utilities
40from .validators import validate_samplesheet, ValidationResult
42__all__ = [
43 # ncbi_utils
44 'check_network_access',
45 'fetch_geo_metadata',
46 'fetch_sra_study_accession',
47 'fetch_sra_run_info',
48 'fetch_sra_run_info_detailed',
49 'fetch_bioproject_from_geo',
50 'fetch_ena_fastq_urls',
51 'download_file',
52 'fetch_pubmed_metadata',
53 'format_file_size',
54 'estimate_download_size',
55 'group_samples_by_type',
56 'format_sample_groups_table',
57 # file_discovery
58 'discover_files',
59 'FileInfo',
60 'count_files_by_type',
61 # sample_inference
62 'extract_sample_info',
63 'infer_tumor_normal_status',
64 'match_read_pairs',
65 'extract_replicate_number',
66 # validators
67 'validate_samplesheet',
68 'ValidationResult',
69]