diff --git a/nextclade/defaults/nextclade-dataset/CHANGELOG.md b/nextclade/defaults/nextclade-dataset/CHANGELOG.md index 3b67234..eb62595 100644 --- a/nextclade/defaults/nextclade-dataset/CHANGELOG.md +++ b/nextclade/defaults/nextclade-dataset/CHANGELOG.md @@ -1,3 +1,3 @@ ## Unreleased -Initial release of yellow fever virus dataset. +Initial release of yellow fever virus (prM-E region only) dataset. diff --git a/nextclade/defaults/nextclade-dataset/README.md b/nextclade/defaults/nextclade-dataset/README.md index 10bb176..1a22958 100644 --- a/nextclade/defaults/nextclade-dataset/README.md +++ b/nextclade/defaults/nextclade-dataset/README.md @@ -1,4 +1,4 @@ -# Yellow fever virus dataset +# Yellow fever virus (prM-E region only) dataset | Key | Value | | ----------------- | -----------------------------------------------------------------| @@ -36,7 +36,7 @@ following genotypes as described in the aforementioned two papers: (N.b., the reference sequence used in this data set is actually 672nt long, from bases 641-1312 of the genome reference. The 2 extra bases -make the reference an complete open reading frame.) +make the reference a complete open reading frame.) This dataset can be used to assign genotypes to any sequence that includes at least 500 bp of the prM-E region, including whole genome diff --git a/nextclade/defaults/nextclade-dataset/pathogen.json b/nextclade/defaults/nextclade-dataset/pathogen.json index 92213e6..b1d1212 100644 --- a/nextclade/defaults/nextclade-dataset/pathogen.json +++ b/nextclade/defaults/nextclade-dataset/pathogen.json @@ -15,8 +15,7 @@ }, "schemaVersion": "3.0.0", "alignmentParams": { - "minSeedCover": 0.01, - "minLength": 500 + "minSeedCover": 0.01 }, "qc": { "missingData": { @@ -36,8 +35,8 @@ }, "privateMutations": { "enabled": true, - "cutoff": 8, - "typical": 2, + "cutoff": 12, + "typical": 4, "weightLabeledSubstitutions": 1, "weightReversionSubstitutions": 1, "weightUnlabeledSubstitutions": 1