Initial release: rarelens platform skeleton (AGPL-3.0)

End-to-end variant interpretation platform for rare genetic disease research:
SvelteKit UI, FastAPI + PostgreSQL API, Nextflow/Ensembl VEP pipeline,
LightGBM pathogenicity scoring with MLflow, K8s/ArgoCD/GCP infrastructure.
Public test data only; no clinical claims.

pipeline/modules/load_db.nf

@@ -0,0 +1,13 @@
+process LOAD_DB {
+    tag "$job_id"
+    input:
+        path tsv
+        val job_id
+        val db_url
+    output: stdout
+
+    script:
+    """
+    load_db.py --tsv $tsv --job-id $job_id --db-url '$db_url'
+    """
+}

pipeline/modules/normalise.nf

@@ -0,0 +1,11 @@
+process NORMALISE {
+    tag "$vcf.simpleName"
+    input:  path vcf
+    output: path "${vcf.simpleName}.norm.vcf.gz", emit: vcf
+
+    script:
+    """
+    bcftools norm -m -both -Oz -o ${vcf.simpleName}.norm.vcf.gz $vcf
+    bcftools index -t ${vcf.simpleName}.norm.vcf.gz
+    """
+}

pipeline/modules/vep.nf

@@ -0,0 +1,16 @@
+process VEP {
+    tag "$vcf.simpleName"
+    publishDir params.outdir, mode: 'copy'
+    input:  path vcf
+    output:
+        path "${vcf.simpleName}.vep.tsv",      emit: tsv
+        path "${vcf.simpleName}.vep_summary.html"
+
+    script:
+    """
+    vep -i $vcf -o ${vcf.simpleName}.vep.tsv --tab \\
+        --assembly ${params.assembly} --cache --dir_cache ${params.vep_cache} --offline \\
+        --everything --pick --af_gnomade --plugin CADD --plugin AlphaMissense \\
+        --stats_file ${vcf.simpleName}.vep_summary.html --fork ${task.cpus}
+    """
+}