Merge pull request #31 from poeli/master

add long-read support and update docker image to accommodate long-reads

Dockerfile

@@ -2,11 +2,11 @@ FROM continuumio/miniconda3:latest
 
 LABEL developer="Po-E Li"
 LABEL email="[email protected]"
-LABEL version="1.0.5"
+LABEL version="1.0.8"
 LABEL software="nmdc_taxa_profilers"
 LABEL tags="metagenome, bioinformatics, NMDC, taxonomy"
 
-ENV container docker
+ENV container=docker
 
 # system updates
 RUN apt-get update --allow-releaseinfo-change \
@@ -18,32 +18,29 @@ RUN conda config --add channels conda-forge \
     && conda config --add channels bioconda
 
 # install singlem
-RUN wget https://github.com/wwood/singlem/archive/refs/tags/v0.15.0.tar.gz \
-    && tar -xzf v0.15.0.tar.gz
-RUN conda env create -n singlem -f singlem-0.15.0/singlem.yml \
-    && ln -s ${PWD}/singlem-0.15.0/bin/* /opt/conda/envs/singlem/bin/
-RUN rm -f v0.15.0.tar.gz
+RUN conda create -n singlem singlem \
+    && conda clean --all -y
 
 # install gottcha2
-RUN wget https://github.com/poeli/GOTTCHA2/archive/refs/tags/2.1.8.5.tar.gz \
-    && tar -xzf 2.1.8.5.tar.gz
-RUN conda env create -n gottcha2 -f GOTTCHA2-2.1.8.5/environment.yml \
-    && cp GOTTCHA2-2.1.8.5/gottcha/scripts/*.py /usr/local/bin
-RUN rm -rf GOTTCHA2-2.1.8.5/ 2.1.8.5.tar.gz
+RUN conda create -n gottcha2 gottcha2=2.1.8.8 \
+    && conda clean --all -y
 
 # install kraken2
-RUN conda create -n kraken2 kraken2=2.1.2
+RUN conda create -n kraken2 kraken2=2.1.2 \
+    && conda clean --all -y
 
 # install centrifuge
-RUN conda create -n centrifuge centrifuge=1.0.4_beta
+RUN conda create -n centrifuge centrifuge=1.0.4_beta \
+    && conda clean --all -y
 
 # install krona
 # The "curl" 
 RUN conda install curl krona \
+    && conda clean --all -y \
     && ktUpdateTaxonomy.sh
 
 # install additional libs
-RUN conda install pandas click
+RUN conda install pandas click && conda clean --all -y
 ADD *.py /opt/conda/bin/
 
 CMD ["/bin/bash"]

ReadbasedAnalysis.wdl

@@ -15,8 +15,9 @@ workflow ReadbasedAnalysis {
         String proj
         String prefix = sub(proj, ":", "_")
         Boolean? paired = false
+        Boolean? long_read = false
         String bbtools_container = "microbiomedata/bbtools:38.96"
-        String docker = "microbiomedata/nmdc_taxa_profilers:1.0.5"
+        String docker = "microbiomedata/nmdc_taxa_profilers:1.0.8"
     }
 
     call stage {
@@ -30,6 +31,7 @@ workflow ReadbasedAnalysis {
             input: READS = stage.reads,
                    DB = db_gottcha2,
                    PREFIX = prefix,
+                   LONG_READ = long_read,
                    CPU = cpu,
                    DOCKER = docker
         }

ReadbasedAnalysisTasks.wdl

@@ -6,11 +6,11 @@ task profilerGottcha2 {
         String DB
         String PREFIX
         String? RELABD_COL = "ROLLUP_DOC"
+        Boolean? LONG_READ = false
         String DOCKER
         Int? CPU = 4
     }
     command <<<
-
         set -euo pipefail
         . /opt/conda/etc/profile.d/conda.sh
         conda activate gottcha2
@@ -20,11 +20,13 @@ task profilerGottcha2 {
                     -t ~{CPU} \
                     -o . \
                     -p ~{PREFIX} \
-                    --database ~{DB}
-
-        grep "^species" ~{PREFIX}.tsv | ktImportTaxonomy -t 3 -m 9 -o ~{PREFIX}.krona.html - || true
+                    --database ~{DB} \
+                    ~{true="-np" false="" LONG_READ}
 
+        grep "^species" ~{PREFIX}.tsv | ktImportTaxonomy -t 3 -m 9 -o ~{PREFIX}.krona.html - || true
+
         gottcha2.py --version > ~{PREFIX}.info
+        touch ~{PREFIX}.full.tsv
     >>>
     output {
         File report_tsv = "~{PREFIX}.tsv"
@@ -138,31 +140,31 @@ task profilerKraken2 {
     }
 }
 
-task generateSummaryJson {
-    input {
-        Array[Map[String, String]?] TSV_META_JSON
-        String PREFIX
-        String DOCKER
-    }
-
-    command {
-        outputTsv2json.py --meta ~{write_json(TSV_META_JSON)} > ~{PREFIX}.json
-    }
-    output {
-        File summary_json = "~{PREFIX}.json"
-    }
-    runtime {
-        docker: DOCKER
-        node: 1
-        nwpn: 1
-        memory: "45G"
-        time: "04:00:00"
-    }
-    meta {
-        author: "Po-E Li, B10, LANL"
-        email: "[email protected]"
-    }
-}
+# task generateSummaryJson {
+#    input {
+#        Array[Map[String, String]?] TSV_META_JSON
+#        String PREFIX
+#        String DOCKER
+#    }
+
+#    command {
+#        outputTsv2json.py --meta ~{write_json(TSV_META_JSON)} > ~{PREFIX}.json
+#    }
+#    output {
+#        File summary_json = "~{PREFIX}.json"
+#    }
+#    runtime {
+#        docker: DOCKER
+#        node: 1
+#        nwpn: 1
+#        memory: "45G"
+#        time: "04:00:00"
+#    }
+#    meta {
+#        author: "Po-E Li, B10, LANL"
+#        email: "[email protected]"
+#    }
+# }
 
 task stage {
     input {

ReadbasedAnalysis_inputs.json

@@ -1,6 +1,7 @@
 {
   "ReadbasedAnalysis.input_file": "https://nmdc-edge.org/projects/KUYAOFKQW2mZJFBc/output/ReadsQC/SRR7877884-int-0.1/SRR7877884-int-0.1.anqdpht.fastq.gz",
   "ReadbasedAnalysis.paired": false,
+  "ReadbasedAnalysis.long_read": false,
   "ReadbasedAnalysis.prefix": "TEST",
   "ReadbasedAnalysis.cpu": 8,
   "ReadbasedAnalysis.proj": "TEST"

options.json

@@ -1,5 +1,5 @@
 {
     "default_runtime_attributes": {
-        "docker": "microbiomedata/nmdc_taxa_profilers:1.0.5"
+        "docker": "microbiomedata/nmdc_taxa_profilers:1.0.8"
     }
 }