Skip to content

create modules part1 #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bruno-ariano wants to merge 4 commits into
base: nextflow_branch
Choose a base branch
from
Open

create modules part1 #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c4a449a
create modules part1
bruno-ariano Jan 28, 2026
257bd16
change delimiter trait export
bruno-ariano Jul 29, 2026
283cb76
ADD beta and SNP ID related to min pvalue
bruno-ariano Jul 29, 2026
10bb5cd
Merge change_delimiter_trait_export into nextflow_branch_modular.
bruno-ariano Jul 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 20 additions & 32 deletions nextflow.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,24 +45,33 @@ params {
config_profile_url = null
config_profile_name = null
}
// Execution reporting
timeline {
enabled = true
file = "${params.outdir}/pipeline_info/execution_timeline_${new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')}.html"
}

// Load nf-core custom profiles from different Institutions
try {
includeConfig "${params.custom_config_base}/nfcore_custom.config"
} catch (Exception e) {
System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
report {
enabled = true
file = "${params.outdir}/pipeline_info/execution_report_${new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')}.html"
}

trace {
enabled = true
file = "${params.outdir}/pipeline_info/execution_trace_${new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')}.txt"
}

dag {
enabled = true
file = "${params.outdir}/pipeline_info/pipeline_dag_${new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')}.html"
}
// Load nf-core custom profiles from different Institutions
includeConfig "${params.custom_config_base}/nfcore_custom.config"


// Load base.config by default
includeConfig 'conf/base.config'

// Load nf-core institutional configs (like your colleague)
try {
includeConfig "${params.custom_config_base}/nfcore_custom.config"
} catch (Exception e) {
System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
}

// Global process configuration for tdbsumstat
process {
Expand Down Expand Up @@ -145,28 +154,7 @@ profiles {
test_recompute_meta { includeConfig 'conf/test.config' }
}

// Execution reporting
def trace_timestamp = new java.util.Date().format('yyyy-MM-dd_HH-mm-ss')

timeline {
enabled = true
file = "${params.outdir}/pipeline_info/execution_timeline_${trace_timestamp}.html"
}

report {
enabled = true
file = "${params.outdir}/pipeline_info/execution_report_${trace_timestamp}.html"
}

trace {
enabled = true
file = "${params.outdir}/pipeline_info/execution_trace_${trace_timestamp}.txt"
}

dag {
enabled = true
file = "${params.outdir}/pipeline_info/pipeline_dag_${trace_timestamp}.html"
}

manifest {
name = 'TileDB-Sumstat'
Expand Down
8 changes: 6 additions & 2 deletions tdbsumstat/cli/export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,7 +249,10 @@ def query_spec(uri_path, chrom:int, trait: str = None, cell: str = None, gene: s
return_dtype=pl.Float64
).alias("ACAT_LIST"),
pl.col("N").first().alias("N"),
pl.min("P").alias("MIN_P")
pl.min("P").alias("MIN_P"),
pl.min("P").alias("MIN_BETA"),
pl.col("SNP").sort_by("P").first().alias("MIN_P_SNP"),
pl.col("BETA").sort_by("P").first().alias("MIN_P_BETA")
])
chr_gene_agg = chr_gene_agg.with_columns(
pl.col("ACAT_LIST").list.first().alias("ACAT"),
Expand All @@ -267,14 +270,15 @@ def query_spec(uri_path, chrom:int, trait: str = None, cell: str = None, gene: s
attrs=attr.split(",")
).df[:, trait_list_np , :]
else:
trait_list_pd[['cell','gene']] = trait_list_pd['TRAIT'].str.split(':', expand = True)
trait_list_pd[['cell','gene']] = trait_list_pd['TRAIT'].str.split('~', expand = True)
cells = trait_list_pd['cell'].to_list()
gene = trait_list_pd['gene'].to_list()
tiledb_iterator = A.query(
return_incomplete=True,
attrs=attr.split(",")
).df[:, cells, gene , :]


for chunk in tiledb_iterator:
chunk.to_csv(f"{out}_{batch_name}.csv", mode="a", index=False, header = False)
print(f"Saved filtered summary statistics in {out}")