sarscov2_nextstrain and sarscov2_lineages improvements

pipes/WDL/tasks/tasks_nextstrain.wdl

@@ -345,6 +345,35 @@ task nextstrain_build_subsample {
     }
 }
 
+task nextstrain_ncov_defaults {
+    input {
+        String   nextstrain_ncov_repo_commit = "5dbca8a45a64e39057c22163f154db981f7ed5c1"
+        String   docker = "nextstrain/base:build-20210127T135203Z"
+    }
+    command {
+        set -e
+        wget -q "https://github.com/nextstrain/ncov/archive/~{nextstrain_ncov_repo_commit}.tar.gz"
+        tar -xf "~{nextstrain_ncov_repo_commit}.tar.gz" --strip-components=1
+        cat defaults/clades.tsv defaults/subclades.tsv > clades-with-subclades.tsv
+    }
+    runtime {
+        docker: docker
+        memory: "1 GB"
+        cpu :   1
+        disks:  "local-disk 50 HDD"
+        dx_instance_type: "mem1_ssd1_v2_x2"
+    }
+    output {
+        File clades_tsv      = "clades-with-subclades.tsv"
+        File lat_longs_tsv   = "defaults/lat_longs.tsv"
+        File reference_fasta = "defaults/reference_seq.fasta"
+        File reference_gb    = "defaults/reference_seq.gb"
+        File ids_include     = "defaults/include.txt"
+        File ids_exclude     = "defaults/exclude.txt"
+        File auspice_config  = "defaults/auspice_config.json"
+    }
+}
+
 task filter_subsample_sequences {
     meta {
         description: "Filter and subsample a sequence set. See https://nextstrain-augur.readthedocs.io/en/stable/usage/cli/filter.html"

pipes/WDL/tasks/tasks_sarscov2.wdl

@@ -137,7 +137,7 @@ task pangolin_one_sample {
         grep ^lineage transposed.tsv | cut -f 2 | grep -v lineage > PANGOLIN_CLADE
     }
     runtime {
-        docker: "staphb/pangolin:2.1.10-pangolearn-2021-02-01"
+        docker: "staphb/pangolin:2.1.11-pangolearn-2021-02-01"
         memory: "3 GB"
         cpu:    2
         disks: "local-disk 50 HDD"

pipes/WDL/workflows/augur_export_only.wdl

@@ -12,6 +12,7 @@ workflow augur_export_only {
     call nextstrain.export_auspice_json
     output {
         File auspice_json = export_auspice_json.virus_json
+        File root_sequence_json = export_auspice_json.root_sequence_json
     }
 }
 

pipes/WDL/workflows/augur_from_msa.wdl

@@ -96,6 +96,11 @@ workflow augur_from_msa {
                 columns        = select_first([ancestral_traits_to_infer,[]])
         }
     }
+    call nextstrain.tip_frequencies {
+        input:
+            tree        = refine_augur_tree.tree_refined,
+            metadata    = select_first(flatten([[tsv_join.out_tsv], sample_metadata]))
+    }
     call nextstrain.ancestral_tree {
         input:
             tree        = refine_augur_tree.tree_refined,
@@ -141,5 +146,7 @@ workflow augur_from_msa {
                     translate_augur_tree.aa_muts_json,
                     assign_clades_to_nodes.node_clade_data_json])
         File  auspice_input_json  = export_auspice_json.virus_json
+        File  tip_frequencies_json = tip_frequencies.node_data_json
+        File  root_sequence_json   = export_auspice_json.root_sequence_json
     }
 }

pipes/WDL/workflows/sarscov2_nextstrain.wdl

@@ -14,13 +14,16 @@ workflow sarscov2_nextstrain {
     input {
         Array[File]+    assembly_fastas
         Array[File]+    sample_metadata_tsvs
-        File            ref_fasta
 
         String          build_name
+        File            builds_yaml
 
-        File?           clades_tsv
         Array[String]?  ancestral_traits_to_infer
 
+        File?           auspice_config
+        File?           ref_fasta
+        File?           clades_tsv
+
         Int             min_unambig_genome = 27000
     }
 
@@ -49,6 +52,7 @@ workflow sarscov2_nextstrain {
         }
     }
 
+    call nextstrain.nextstrain_ncov_defaults
 
     #### mafft_and_snp
 
@@ -65,7 +69,7 @@ workflow sarscov2_nextstrain {
     call nextstrain.mafft_one_chr as mafft {
         input:
             sequences = filter_sequences_by_length.filtered_fasta,
-            ref_fasta = ref_fasta,
+            ref_fasta = select_first([ref_fasta, nextstrain_ncov_defaults.reference_fasta]),
             basename  = "all_samples_aligned.fasta"
     }
     call nextstrain.snp_sites {
@@ -94,7 +98,8 @@ workflow sarscov2_nextstrain {
         input:
             alignment_msa_fasta = mafft.aligned_sequences,
             sample_metadata_tsv = derived_cols.derived_metadata,
-            build_name = build_name
+            build_name = build_name,
+            builds_yaml = builds_yaml
     }
     call nextstrain.fasta_to_ids {
         input:
@@ -104,9 +109,13 @@ workflow sarscov2_nextstrain {
 
     #### augur_from_msa
 
+    call nextstrain.augur_mask_sites {
+        input:
+            sequences = subsample.subsampled_msa
+    }
     call nextstrain.draft_augur_tree {
         input:
-            msa_or_vcf = subsample.subsampled_msa
+            msa_or_vcf = augur_mask_sites.masked_sequences
     }
 
     call nextstrain.refine_augur_tree {
@@ -142,28 +151,29 @@ workflow sarscov2_nextstrain {
     call nextstrain.translate_augur_tree {
         input:
             tree        = refine_augur_tree.tree_refined,
-            nt_muts     = ancestral_tree.nt_muts_json
+            nt_muts     = ancestral_tree.nt_muts_json,
+            genbank_gb  = nextstrain_ncov_defaults.reference_gb
     }
-    if(defined(clades_tsv)) {
-        call nextstrain.assign_clades_to_nodes {
-            input:
-                tree_nwk     = refine_augur_tree.tree_refined,
-                nt_muts_json = ancestral_tree.nt_muts_json,
-                aa_muts_json = translate_augur_tree.aa_muts_json,
-                ref_fasta    = ref_fasta,
-                clades_tsv   = select_first([clades_tsv])
-        }
+    call nextstrain.assign_clades_to_nodes {
+        input:
+            tree_nwk     = refine_augur_tree.tree_refined,
+            nt_muts_json = ancestral_tree.nt_muts_json,
+            aa_muts_json = translate_augur_tree.aa_muts_json,
+            ref_fasta    = select_first([ref_fasta, nextstrain_ncov_defaults.reference_fasta]),
+            clades_tsv   = select_first([clades_tsv, nextstrain_ncov_defaults.clades_tsv])
     }
     call nextstrain.export_auspice_json {
         input:
             tree            = refine_augur_tree.tree_refined,
             sample_metadata = derived_cols.derived_metadata,
+            lat_longs_tsv   = nextstrain_ncov_defaults.lat_longs_tsv,
             node_data_jsons = select_all([
                                 refine_augur_tree.branch_lengths,
                                 ancestral_traits.node_data_json,
                                 ancestral_tree.nt_muts_json,
                                 translate_augur_tree.aa_muts_json,
                                 assign_clades_to_nodes.node_clade_data_json]),
+            auspice_config = select_first([auspice_config, nextstrain_ncov_defaults.auspice_config]),
             out_basename = "auspice-~{build_name}"
     }
 

requirements-modules.txt

@@ -6,5 +6,5 @@ broadinstitute/beast-beagle-cuda=1.10.5pre
 broadinstitute/ncbi-tools=2.10.7.1
 nextstrain/base=build-20210127T135203Z
 andersenlabapps/ivar=1.3
-staphb/pangolin=2.1.10-pangolearn-2021-02-01
+staphb/pangolin=2.1.11-pangolearn-2021-02-01
 neherlab/nextclade=0.12.0