diff --git a/pipes/WDL/workflows/augur_from_assemblies.wdl b/pipes/WDL/workflows/augur_from_assemblies.wdl index e94ee5574..08c3ab87e 100644 --- a/pipes/WDL/workflows/augur_from_assemblies.wdl +++ b/pipes/WDL/workflows/augur_from_assemblies.wdl @@ -13,6 +13,7 @@ workflow augur_from_assemblies { input { Array[File]+ assembly_fastas + Array[File]? contextual_genome_fastas Array[File]+ sample_metadata_tsvs File ref_fasta @@ -29,6 +30,10 @@ workflow augur_from_assemblies { description: "Set of assembled genomes to align and build trees. These must represent a single chromosome/segment of a genome only. Fastas may be one-sequence-per-individual or a concatenated multi-fasta (unaligned) or a mixture of the two. They may be compressed (gz, bz2, zst, lz4), uncompressed, or a mixture.", patterns: ["*.fasta", "*.fa", "*.fasta.gz", "*.fasta.zst"] } + contextual_genome_fastas: { + description: "Set of near-complete contextual genomes to include in tree build. Each fasta provided must represent a single chromosome/segment of a genome. Fastas may be one-sequence-per-individual or a concatenated multi-fasta (unaligned) or a mixture of the two. They may be compressed (gz, bz2, zst, lz4), uncompressed, or a mixture. ", + patterns: ["*.fasta", "*.fa", "*.fasta.gz", "*.fasta.zst"] + } sample_metadata_tsvs: { description: "Tab-separated metadata file that contain binning variables and values. Must contain all samples: output will be filtered to the IDs present in this file.", patterns: ["*.txt", "*.tsv"] @@ -54,7 +59,7 @@ workflow augur_from_assemblies { call utils.zcat { input: - infiles = assembly_fastas, + infiles = flatten([assembly_fastas, select_first([contextual_genome_fastas,[]])]), output_name = "all_samples_combined_assembly.fasta" } call utils.filter_sequences_by_length {