Test for #243

sample_data/Snakefile

@@ -38,7 +38,8 @@ configfile: "configuration.yaml"
 
 rule complete:
     input: "compare.stats", "compare_subloci.stats", "compare_input.stats", "check.ok",
-         "check_metrics.ok", "daijin_test/mikado.yaml", "g11.ok", "refmap_check.ok"
+         "check_metrics.ok", "daijin_test/mikado.yaml", "g11.ok", "refmap_check.ok",
+         "external.ok"
     output: touch("finished.ok")
 
 
@@ -128,7 +129,6 @@ rule compare_subloci:
     message: """mikado compare -r {input[reference]} -p {input[prediction]} -o compare_subloci -l {log}"""
     shell: """mikado compare -r {input[reference]} -p {input[prediction]} -o compare_subloci -l {log}"""
 
-
 rule check_refmap:
     input:
         refmap=rules.compare_input.output.refmap
@@ -177,6 +177,85 @@ rule check_pick:
       open(output[0], "wt")
 
 
+rule test_external_kal_index:
+    input:
+      fasta=rules.daijin.output.prep_fasta
+    output:
+      index=os.path.join("Daijin", "5-mikado", "mikado_prepared.idx")
+    conda: "kallisto.yaml"
+    threads: 1
+    shell: "kallisto index -i {output.index} {input.fasta}"
+
+rule test_external_kal_quant:
+    input:
+      index=rules.test_external_kal_index.output.index,
+      r1="ERR588038.R1.fq.gz",
+      r2="ERR588038.R2.fq.gz"
+    output:
+      kal_tsv=os.path.join("Daijin", "5-mikado", "kallisto", "abundance.tsv"),
+      data=os.path.join("Daijin", "5-mikado", "data.txt")
+    params:
+      folder=os.path.join("Daijin", "5-mikado", "kallisto")
+    conda: "kallisto.yaml"
+    threads: 2
+    shell: """kallisto quant -t {threads} -o {params.folder} -i {input.index} {input.r1} {input.r2} && \
+cut -f 1,5 {output.kal_tsv} | sed 's/target_id/tid/' > {output.data}"""
+
+
+rule test_external_kal_serialise:
+    input:
+      db=rules.daijin.output.db,
+      data=rules.test_external_kal_quant.output.data,
+    output:
+      db=os.path.join("Daijin", "5-mikado", "mikado_external.db"),
+      check=touch(os.path.join("Daijin", "5-mikado", "mikado_external.check.ok"))
+    params:
+      db="mikado_external.db"
+    threads: 2
+    log: os.path.join("Daijin", "5-mikado", "mikado_serialise_external.log")
+    shell: """
+    mikado serialise --xml=Daijin/5-mikado/blast/xmls --blast_targets=Daijin/5-mikado/blast/index/blastdb-proteins.fa \
+    --start-method=spawn --transcripts=Daijin/5-mikado/mikado_prepared.fasta \
+    --genome_fai=Daijin/5-mikado/chr5.fas.gz.fai --json-conf=configuration.yaml \
+    --external {input.data} -nsa --force \
+    --orfs=Daijin/5-mikado/transdecoder/transcripts.fasta.transdecoder.bed \
+    -od Daijin/5-mikado --procs={threads} -l {log} {params.db};
+    if [[ $(sqlite3 {output.db} "select count(*) > 0 from external") != 1 ]]; then exit 1; else exit 0; fi"""
+
+
+rule test_external_kal_pick:
+    input:
+      db=rules.test_external_kal_serialise.output.db,
+      gtf=rules.daijin.output.prep,
+      scoring="plant_external.yaml"
+    output:
+      loci=os.path.join("Daijin", "5-mikado", "pick", "external", "mikado-permissive.loci.gff3"),
+      scores=os.path.join("Daijin", "5-mikado", "pick", "external", "mikado-permissive.loci.scores.tsv"),
+      subscores=os.path.join("Daijin", "5-mikado", "pick", "external", "mikado.subloci.scores.tsv")
+    params:
+      outdir=os.path.join("Daijin", "5-mikado", "pick", "external"),
+      loci_out="mikado-permissive.loci.gff3"
+    log: os.path.join("Daijin", "5-mikado", "pick", "external", "mikado-permissive.log")
+    threads: 2
+    shell: """mikado pick --scoring-file {input.scoring} --source Mikado_permissive \
+    --mode=permissive --procs=2 --start-method=spawn \
+    --json-conf=configuration.yaml -od {params.outdir} \
+     -l {log} --loci-out {params.loci_out} -lv INFO -db {input.db} {input.gtf}"""
+
+rule check_external_pick:
+    input:
+      scores=rules.test_external_kal_pick.output.scores,
+      subscores=rules.test_external_kal_pick.output.subscores,
+    output: touch("external.ok")
+    run:
+        import pandas as pd
+        scores = pd.read_csv(input["scores"], delimiter="\t")
+        assert "external.tpm" in scores.columns
+        assert scores["external.tpm"].max() > 0
+        scores = pd.read_csv(input["subscores"], delimiter="\t")
+        assert "external.tpm" in scores.columns
+        assert scores["external.tpm"].max() > 0
+
 rule test_g11_prodigal:
     input:
       transcripts=rules.daijin.output.prep_fasta

sample_data/kallisto.yaml

@@ -0,0 +1,5 @@
+channels:
+  - bioconda
+  - conda-forge
+dependencies:
+  - kallisto

sample_data/plant_external.yaml

@@ -0,0 +1,77 @@
+  # Scoring file suitable for any species with intron sizes similar to plants
+requirements:
+  expression: [(combined_cds_fraction.ncrna or combined_cds_fraction.coding), and, ((exon_num.multi and  (cdna_length.multi, or,  combined_cds_length.multi) and max_intron_length, and, min_intron_length and proportion_verified_introns_inlocus ) or (exon_num.mono and (combined_cds_length.mono or cdna_length.mono))) ]
+  parameters:
+    combined_cds_fraction.ncrna: {operator: eq, value: 0}
+    combined_cds_fraction.coding: {operator: gt, value: 0.30}
+    cdna_length.mono: {operator: gt, value: 400}
+    cdna_length.multi: {operator: ge, value: 300}
+    combined_cds_length.mono: {operator: gt, value: 225}
+    combined_cds_length.multi: {operator: gt, value: 150}
+    exon_num.mono: {operator: eq, value: 1}
+    exon_num.multi: {operator: gt, value: 1}
+    max_intron_length: {operator: le, value: 20000}
+    min_intron_length: {operator: ge, value: 5}
+    proportion_verified_introns_inlocus: {operator: gt, value: 0}
+as_requirements:
+  expression: [cdna_length and three_utr_length and five_utr_length and utr_length and suspicious_splicing]
+  parameters:
+    cdna_length: {operator: ge, value: 300}
+    utr_length: {operator: le, value: 2500}
+    five_utr_length: {operator: le, value: 2500}
+    three_utr_length: {operator: le, value: 2500}
+    suspicious_splicing: {operator: ne, value: true}
+    max_intron_length: {operator: le, value: 10000}
+not_fragmentary:
+ expression: [((exon_num.multi and (cdna_length.multi or combined_cds_length.multi)), or, (exon_num.mono and combined_cds_length.mono))]
+ parameters:
+   is_complete: {operator: eq, value: true}
+   exon_num.multi: {operator: gt, value: 1}
+   cdna_length.multi: {operator: ge, value: 400}
+   combined_cds_length.multi: {operator: gt, value: 200}
+   exon_num.mono: {operator: eq, value: 1}
+   combined_cds_length.mono: {operator: gt, value: 600}
+scoring:
+  blast_score: {rescaling: max}
+  cdna_length: {rescaling: max}
+  cds_not_maximal: {rescaling: min}
+  cds_not_maximal_fraction: {rescaling: min}
+  exon_num: {
+    rescaling: max,
+    filter: {
+    operator: ge,
+    value: 3}
+  }
+  five_utr_length:
+    filter: {operator: le, value: 2500}
+    rescaling: target
+    value: 200
+  five_utr_num:
+    filter: {operator: lt, value: 4}
+    rescaling: target
+    value: 2
+  end_distance_from_junction:
+    filter: {operator: lt, value: 55}
+    rescaling: min
+  highest_cds_exon_number: {rescaling: max}
+  intron_fraction: {rescaling: max}
+  is_complete: {rescaling: target, value: true}
+  number_internal_orfs: {rescaling: target, value: 1}
+  non_verified_introns_num: {rescaling: min}
+  proportion_verified_introns_inlocus: {rescaling: max}
+  retained_fraction: {rescaling: min}
+  retained_intron_num: {rescaling: min}
+  selected_cds_fraction: {rescaling: target, value: 0.8}
+  selected_cds_intron_fraction: {rescaling: max}
+  selected_cds_length: {rescaling: max}
+  selected_cds_num: {rescaling: max}
+  three_utr_length:
+    filter: {operator: le, value: 2500}
+    rescaling: target
+    value: 400
+  three_utr_num:
+    filter: {operator: lt, value: 3}
+    rescaling: target
+    value: 1
+  combined_cds_locus_fraction: {rescaling: max}
+  external.tpm: {rescaling: max}