From 266604aac8bd13e84b817bc768eff7d637eb9783 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Mon, 14 Oct 2024 12:35:46 -0700 Subject: [PATCH 1/4] export: Restore `--description` MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Restore use of the `--description` option for `augur export v2`, which was lost during the major refactoring of the workflow in Allows for build specific descriptions, similar to the `auspice_config` based on array_builds.smk.¹ If a build specific description is not provided, then defaults to the workflow's `config/description.md`. ¹ --- workflow/snakemake_rules/export.smk | 2 ++ 1 file changed, 2 insertions(+) diff --git a/workflow/snakemake_rules/export.smk b/workflow/snakemake_rules/export.smk index b9088382..08337bfc 100644 --- a/workflow/snakemake_rules/export.smk +++ b/workflow/snakemake_rules/export.smk @@ -65,6 +65,7 @@ rule export: metadata = build_dir + "/{build_name}/metadata.tsv", node_data = _get_node_data_by_wildcards, auspice_config = lambda w: config['builds'][w.build_name]['auspice_config'], + description = lambda w: config['builds'][w.build_name].get("description", "config/description.md"), lat_longs = config.get('lat-longs', "config/lat_longs.tsv"), output: auspice_json = "auspice/{build_name}_{segment}.json" @@ -82,6 +83,7 @@ rule export: --include-root-sequence-inline \ --lat-longs {input.lat_longs} \ --auspice-config {input.auspice_config} \ + --description {input.description} \ --output {output.auspice_json} 2>&1 | tee {log} """ From 61bc2eca09011d43ee3b7d3adeddaeeb37bd9a5e Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Mon, 14 Oct 2024 12:24:55 -0700 Subject: [PATCH 2/4] config/description.md: Update GISRS URLs --- config/description.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/config/description.md b/config/description.md index ce93cf07..2df95d33 100644 --- a/config/description.md +++ b/config/description.md @@ -1,6 +1,6 @@ **Forecasts:** For H3N2 only, the frequency panel shows projections of currently circulating strain frequencies one year into the future in one month intervals. Frequency projections are calculated from a previously trained fitness model based on the current frequency and estimated fitness of each strain as described in [Huddleston et al (2020, eLife)](https://elifesciences.org/articles/60067). We estimate strain fitness by a combination of antigenic novelty and mutational load. Antigenic novelty (available as the coloring "HI antigenic novelty") is based on inferred measurements of antigenic advance from hemaggluttination inhibition (HI) assays. Mutational load (available as the coloring "Mutational load") is the number of amino acid mutations each strain carries at putative non-epitope sites relative to its most recent ancestor from the previous season. -We thank the [GISAID Initiative](https://gisaid.org) and the [GISRS Network](http://www.who.int/influenza/gisrs_laboratory/en/) for critical surveillance efforts and open data sharing. Titer data used in antigenic analyses was generated by the [Influenza Division at the US Centers for Disease Control and Prevention](https://www.cdc.gov/flu/), the [Worldwide Influenza Centre at the Francis Crick Institute](http://www.crick.ac.uk/research/worldwide-influenza-centre), the [Victorian Infectious Diseases Reference Laboratory at the Australian Peter Doherty Institute for Infection and Immunity](http://www.vidrl.org.au/) and the [Influenza Virus Research Center at the Japan National Institute of Infectious Diseases](https://www.niid.go.jp/niid/en/flu-e.html). We gratefully acknowledge the authors, originating and submitting laboratories of sequences from the GISAID EpiFlu Database on which this research is based. An attribution table is available by clicking on "Download Data" at the bottom of the page and then clicking on "Strain Metadata" in the resulting dialog box. +We thank the [GISAID Initiative](https://gisaid.org) and the [GISRS Network](https://www.who.int/initiatives/global-influenza-surveillance-and-response-system) for critical surveillance efforts and open data sharing. Titer data used in antigenic analyses was generated by the [Influenza Division at the US Centers for Disease Control and Prevention](https://www.cdc.gov/flu/), the [Worldwide Influenza Centre at the Francis Crick Institute](http://www.crick.ac.uk/research/worldwide-influenza-centre), the [Victorian Infectious Diseases Reference Laboratory at the Australian Peter Doherty Institute for Infection and Immunity](http://www.vidrl.org.au/) and the [Influenza Virus Research Center at the Japan National Institute of Infectious Diseases](https://www.niid.go.jp/niid/en/flu-e.html). We gratefully acknowledge the authors, originating and submitting laboratories of sequences from the GISAID EpiFlu Database on which this research is based. An attribution table is available by clicking on "Download Data" at the bottom of the page and then clicking on "Strain Metadata" in the resulting dialog box. Special thanks to Jackie Katz, Dave Wentworth, Becky Kondor, Vivien Dugan, Xiyan Xu, Elizabeth Neuhaus, Sujatha Seenu, John McCauley, Rod Daniels, Vicki Gregory, Kanta Subbarao, Ian Barr, Aeron Hurt, Takato Odagiri, Shinji Watanabe, Tomoko Kuwahara, Michael Lässig, Marta Łuksza, Richard Reeve, Colin Russell, Sebastian Maurer-Stroh and Peter Bogner for feedback and advice. This analysis represents an updated frontend to the Nextflu informatic pipeline, originally available at nextflu.org. @@ -8,7 +8,7 @@ Special thanks to Jackie Katz, Dave Wentworth, Becky Kondor, Vivien Dugan, Xiyan gisaid-logo - + gisrs-logo From 6219e2475739660c5b5a0f701b8d1e362b9e121b Mon Sep 17 00:00:00 2001 From: John Huddleston Date: Mon, 14 Oct 2024 12:52:16 -0700 Subject: [PATCH 3/4] Export description for nextflu-private builds --- profiles/nextflu-private/antigenic_distances.smk | 2 ++ 1 file changed, 2 insertions(+) diff --git a/profiles/nextflu-private/antigenic_distances.smk b/profiles/nextflu-private/antigenic_distances.smk index 77342ab9..449bc100 100644 --- a/profiles/nextflu-private/antigenic_distances.smk +++ b/profiles/nextflu-private/antigenic_distances.smk @@ -172,6 +172,7 @@ rule export_private: node_data = _get_node_data_by_wildcards, private_node_data = get_private_node_data, auspice_config = lambda w: config['builds'][w.build_name]['auspice_config'], + description = lambda w: config['builds'][w.build_name].get("description", "config/description.md"), lat_longs = config['lat-longs'] output: auspice_json = "auspice/{build_name}_{segment}.json" @@ -189,6 +190,7 @@ rule export_private: --include-root-sequence-inline \ --lat-longs {input.lat_longs} \ --auspice-config {input.auspice_config} \ + --description {input.description} \ --minify-json \ --output {output.auspice_json} 2>&1 | tee {log} """ From 4bf97ea72e9779c985eab6424bbe0faf5f27c5f3 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Mon, 14 Oct 2024 13:00:23 -0700 Subject: [PATCH 4/4] Update config/description.md Remove section on forecasts and refer to "Acknowledgements" option. Co-authored-by: John Huddleston --- config/description.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/config/description.md b/config/description.md index 2df95d33..cd519096 100644 --- a/config/description.md +++ b/config/description.md @@ -1,6 +1,5 @@ -**Forecasts:** For H3N2 only, the frequency panel shows projections of currently circulating strain frequencies one year into the future in one month intervals. Frequency projections are calculated from a previously trained fitness model based on the current frequency and estimated fitness of each strain as described in [Huddleston et al (2020, eLife)](https://elifesciences.org/articles/60067). We estimate strain fitness by a combination of antigenic novelty and mutational load. Antigenic novelty (available as the coloring "HI antigenic novelty") is based on inferred measurements of antigenic advance from hemaggluttination inhibition (HI) assays. Mutational load (available as the coloring "Mutational load") is the number of amino acid mutations each strain carries at putative non-epitope sites relative to its most recent ancestor from the previous season. -We thank the [GISAID Initiative](https://gisaid.org) and the [GISRS Network](https://www.who.int/initiatives/global-influenza-surveillance-and-response-system) for critical surveillance efforts and open data sharing. Titer data used in antigenic analyses was generated by the [Influenza Division at the US Centers for Disease Control and Prevention](https://www.cdc.gov/flu/), the [Worldwide Influenza Centre at the Francis Crick Institute](http://www.crick.ac.uk/research/worldwide-influenza-centre), the [Victorian Infectious Diseases Reference Laboratory at the Australian Peter Doherty Institute for Infection and Immunity](http://www.vidrl.org.au/) and the [Influenza Virus Research Center at the Japan National Institute of Infectious Diseases](https://www.niid.go.jp/niid/en/flu-e.html). We gratefully acknowledge the authors, originating and submitting laboratories of sequences from the GISAID EpiFlu Database on which this research is based. An attribution table is available by clicking on "Download Data" at the bottom of the page and then clicking on "Strain Metadata" in the resulting dialog box. +We thank the [GISAID Initiative](https://gisaid.org) and the [GISRS Network](https://www.who.int/initiatives/global-influenza-surveillance-and-response-system) for critical surveillance efforts and open data sharing. Titer data used in antigenic analyses was generated by the [Influenza Division at the US Centers for Disease Control and Prevention](https://www.cdc.gov/flu/), the [Worldwide Influenza Centre at the Francis Crick Institute](http://www.crick.ac.uk/research/worldwide-influenza-centre), the [Victorian Infectious Diseases Reference Laboratory at the Australian Peter Doherty Institute for Infection and Immunity](http://www.vidrl.org.au/) and the [Influenza Virus Research Center at the Japan National Institute of Infectious Diseases](https://www.niid.go.jp/niid/en/flu-e.html). We gratefully acknowledge the authors, originating and submitting laboratories of sequences from the GISAID EpiFlu Database on which this research is based. An attribution table is available by clicking on "Download Data" at the bottom of the page and then clicking on "Acknowledgments" in the resulting dialog box. Special thanks to Jackie Katz, Dave Wentworth, Becky Kondor, Vivien Dugan, Xiyan Xu, Elizabeth Neuhaus, Sujatha Seenu, John McCauley, Rod Daniels, Vicki Gregory, Kanta Subbarao, Ian Barr, Aeron Hurt, Takato Odagiri, Shinji Watanabe, Tomoko Kuwahara, Michael Lässig, Marta Łuksza, Richard Reeve, Colin Russell, Sebastian Maurer-Stroh and Peter Bogner for feedback and advice. This analysis represents an updated frontend to the Nextflu informatic pipeline, originally available at nextflu.org.