small fixed

chanzuckerberg · Dec 7, 2023 · a1c1f68 · a1c1f68
1 parent 43825a4
commit a1c1f68
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 4 deletions.
diff --git a/workflows/index-generation/index-generation.wdl b/workflows/index-generation/index-generation.wdl
@@ -52,6 +52,7 @@ workflow index_generation {
         call SplitFastaBySeqLengthAndSort as SplitFastaBySeqLengthAndSortNR {
             input:
             fasta = DownloadNR.nr,
+            combined_sorted_path = "combined_sorted_nr.fa",
             cpu = 64,
             docker_image_id = docker_image_id
         }
@@ -78,7 +79,8 @@ workflow index_generation {
     if (!skip_nuc_compression) {
         call SplitFastaBySeqLengthAndSort as SplitFastaBySeqLengthAndSortNT {
             input:
-            fasta = DownloadNR.nr,
+            fasta = DownloadNT.nt,
+            combined_sorted_path = "combined_sorted_nt.fa",
             cpu = 64,
             docker_image_id = docker_image_id
         }
@@ -662,6 +664,7 @@ task GenerateIndexMinimap2 {
 task SplitFastaBySeqLengthAndSort {
     input {
         File fasta
+        String combined_sorted_path
         Int cpu
         Int threads = if cpu * 0.6 < 1 then 1 else floor(cpu * 0.6)
         String docker_image_id
@@ -695,10 +698,10 @@ task SplitFastaBySeqLengthAndSort {
         # cd ..
 
         # Combine the sorted files with longest sequences at the top
-        ls -r outputs/*.fa | xargs cat > combined_sorted.fa
+        ls -r outputs/*.fa | xargs cat > ~{combined_sorted_path}
     >>>
     output {
-        File sorted = "combined_sorted.fa"
+        File sorted = combined_sorted_path
     }
     runtime {
         docker: docker_image_id

diff --git a/workflows/index-generation/ncbi-compress/src/commands.rs b/workflows/index-generation/ncbi-compress/src/commands.rs
@@ -117,7 +117,7 @@ pub mod commands {
             let input_fasta_path = path.to_str().unwrap();
             let taxid = path.file_name().unwrap().to_str().unwrap().split(".").collect::<Vec<&str>>()[0];
             let reads_count = count_fasta_reads(input_fasta_path);
-            if reads_count >= 9500000 { // back of the envelope calculation for how many 50,000 character reads we can store in 488GB of RAM 
+            if reads_count >= 3 { //9500000 { // back of the envelope calculation for how many 50,000 character reads we can store in 488GB of RAM 
                 log::info!("Breaking apart taxid {} into smaller chunks", taxid);
                 let input_taxid_dir = format!("{}/{}_split", input_taxid_dir, taxid);
                 split_fasta_into_chunks(&input_fasta_path, &input_taxid_dir, &reads_count, &3, taxid).expect("error splitting fasta into chunks");