diff --git a/phylogenetic/defaults/auspice_config.json b/phylogenetic/defaults/auspice_config.json index a352ec5..3913356 100644 --- a/phylogenetic/defaults/auspice_config.json +++ b/phylogenetic/defaults/auspice_config.json @@ -1,5 +1,11 @@ { "title": "Washington Focused West Nile Virus Build", + "data_provenance": [ + { + "name": "GenBank", + "url": "https://www.ncbi.nlm.nih.gov/genbank/" + } + ], "colorings": [ {"key": "gt", "title": "Genotype", "type": "categorical"}, {"key": "num_date", "title": "Sampling Date", "type": "continuous"}, diff --git a/phylogenetic/defaults/auspice_config_global.json b/phylogenetic/defaults/auspice_config_global.json index 26ab194..b7b598b 100644 --- a/phylogenetic/defaults/auspice_config_global.json +++ b/phylogenetic/defaults/auspice_config_global.json @@ -1,5 +1,11 @@ { "title": "Global West Nile Virus Build", + "data_provenance": [ + { + "name": "GenBank", + "url": "https://www.ncbi.nlm.nih.gov/genbank/" + } + ], "colorings": [ {"key": "gt", "title": "Genotype", "type": "categorical"}, {"key": "num_date", "title": "Sampling Date", "type": "continuous"}, diff --git a/phylogenetic/defaults/description.md b/phylogenetic/defaults/description.md index 60e5e46..38354ea 100644 --- a/phylogenetic/defaults/description.md +++ b/phylogenetic/defaults/description.md @@ -1,3 +1,8 @@ We gratefully acknowledge the authors, originating and submitting laboratories of the genetic sequences and metadata for sharing their work. Please note that although data generators have generously shared data in an open fashion, that does not mean there should be free license to publish on this data. Data generators should be cited where possible and collaborations should be sought in some circumstances. Please try to avoid scooping someone else's work. Reach out if uncertain. Special thanks to individuals at the [Northwest Pathogen Genomics Center of Excellence](https://github.com/NW-PaGe) and [Grubaugh lab](https://grubaughlab.com/) for comments, code and suggestions. + +We curate sequence data and metadata from NCBI as starting point for our analyses. For global lineage designations, we query [pathoplexus](https://pathoplexus.org/) for lineage assignments and exclusively work with NCBI-sourced records at this time. Curated sequences and metadata are available as flat files at: + +* [data.nextstrain.org/files/workflows/WNV/sequences.fasta.zst](https://data.nextstrain.org/files/workflows/WNV/sequences.fasta.zst) +* [data.nextstrain.org/files/workflows/WNV/metadata.tsv.zst](https://data.nextstrain.org/files/workflows/WNV/metadata.tsv.zst)