v0.1.2 (#36)

* update

* check for no reads passing filters

* Fix odd too many files open error in bigtools by not reading from stdin

* bump version

---------

Co-authored-by: Mitchell R. Vollger <mvollger@gmai.com>

Author: mrvollger

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to this project will be documented in this file.
 
+## v0.1.2
+
+- fix #34
+- fix #33
+- Update to pull test data from a new s3 bucket
+
 ## v0.1.1
 
 Added more informative error messages if an FDR distribution cannot be made or there is not enough coverage.

pixi.toml

@@ -4,56 +4,58 @@ channels = ["conda-forge", "bioconda"]
 description = "Add a short description here"
 name = "FIRE"
 platforms = ["osx-64", "linux-64"]
-version = "0.1.1"
+version = "0.1.2"
 
 [tasks]
 fmt = "ruff format . && taplo format pixi.toml && snakefmt workflow/"
 test-data = { cmd = [
-  "cd",
-  "$INIT_CWD",
-  "&&",
-  "mkdir",
-  "-p",
-  "fire-test-data",
-  "&&",
-  "aws",
-  "s3",
-  "--no-sign-request",
-  "sync",
-  "s3://stergachis-public1/FIRE/test-data",
-  "fire-test-data/",
+    "cd",
+    "$INIT_CWD",
+    "&&",
+    "mkdir",
+    "-p",
+    "fire-test-data",
+    "&&",
+    "aws",
+    "s3",
+    "--no-sign-request",
+    "sync",
+    "--endpoint-url",
+    "https://s3.kopah.orci.washington.edu",
+    "s3://stergachis/public/FIRE/test-data",
+    "fire-test-data/",
 ] }
 test = { cmd = [
-  "cd",
-  "$INIT_CWD/fire-test-data",
-  "&&",
-  "snakemake",
-  "-s",
-  "$PIXI_PROJECT_ROOT/workflow/Snakefile",
-  "--configfile",
-  "test.yaml",
-  "-k",
-], depends_on = [
-  "test-data",
+    "cd",
+    "$INIT_CWD/fire-test-data",
+    "&&",
+    "snakemake",
+    "-s",
+    "$PIXI_PROJECT_ROOT/workflow/Snakefile",
+    "--configfile",
+    "test.yaml",
+    "-k",
+], depends-on = [
+    "test-data",
 ], clean-env = true }
 
 fire = { cmd = [
-  "cd",
-  "$INIT_CWD",
-  "&&",
-  "snakemake",
-  "-s",
-  "$PIXI_PROJECT_ROOT/workflow/Snakefile",
+    "cd",
+    "$INIT_CWD",
+    "&&",
+    "snakemake",
+    "-s",
+    "$PIXI_PROJECT_ROOT/workflow/Snakefile",
 ] }
 slurm = { cmd = [
-  "cd",
-  "$INIT_CWD",
-  "&&",
-  "snakemake",
-  "-s",
-  "$PIXI_PROJECT_ROOT/workflow/Snakefile",
-  "--profile",
-  "$PIXI_PROJECT_ROOT/profiles/slurm-executor",
+    "cd",
+    "$INIT_CWD",
+    "&&",
+    "snakemake",
+    "-s",
+    "$PIXI_PROJECT_ROOT/workflow/Snakefile",
+    "--profile",
+    "$PIXI_PROJECT_ROOT/profiles/slurm-executor",
 ] }
 
 [dependencies]
@@ -62,7 +64,7 @@ snakemake = "==8.21"
 snakemake-executor-plugin-slurm = ">=0.11.2"
 snakefmt = "*"
 ruff = "*"
-awscli = "2.22"
+awscli = "2.22.*"
 taplo = "*"
 
 [pypi-dependencies]

workflow/rules/apply-model.smk

@@ -36,6 +36,13 @@ rule fire:
                 --output-fmt-option embed_ref=1 \
                 --input-fmt-option required_fields=0x1bff \
                 --write-index -o {output.cram}
+
+        # check if the cram file has zero reads 
+        reads_in_header=$(samtools view {output.cram} | head | wc -l || true)
+        if [ $reads_in_header -eq 0 ]; then
+            printf "\nNo reads passed filters exiting...\n\nPlease review https://fiberseq.github.io/quick-start.html to make sure the input BAM has been correctly processed.\n\n"
+            exit 1
+        fi
         """
 
 

workflow/rules/coverages.smk

@@ -151,6 +151,7 @@ rule unreliable_coverage_regions:
     output:
         bed="results/{sm}/additional-outputs-{v}/coverage/unreliable-coverage-regions.bed.gz",
         bed_tbi="results/{sm}/additional-outputs-{v}/coverage/unreliable-coverage-regions.bed.gz.tbi",
+        tmp=temp("temp/{sm}/additional-outputs-{v}/unreliable-coverage-regions.bed"),
         bb="results/{sm}/trackHub-{v}/bb/unreliable-coverage-regions.bb",
     threads: 4
     params:
@@ -171,10 +172,11 @@ rule unreliable_coverage_regions:
         > {output.bed}
 
         # bigbed
-        bgzip -cd {output.bed} -@ {threads} \
-            | bigtools bedtobigbed \
+        # for some reason bigtools gives a too many files open error when reading from stdin
+        bedtools merge -i {output.bed} > {output.tmp}
+        bigtools bedtobigbed \
                 -s start -a {params.bed3_as} \
-                - {input.fai} {output.bb}
+                {output.tmp} {input.fai} {output.bb}
 
         # index 
         tabix -f -p bed {output.bed}