feat(docs): list valid nucleotide and amino acid symbols #573

GenSpectrum · Jan 16, 2024 · 35ccf58 · 35ccf58
1 parent 9158575
commit 35ccf58
Show file tree

Hide file tree

Showing 6 changed files with 72 additions and 29 deletions.
diff --git a/lapis2-docs/astro.config.mjs b/lapis2-docs/astro.config.mjs
@@ -51,8 +51,12 @@ export default defineConfig({
                             link: '/references/open-api-definition/',
                         },
                         {
-                            label: 'Reference Genome',
-                            link: '/references/reference-genome/',
+                            label: 'Reference Genomes',
+                            link: '/references/reference-genomes/',
+                        },
+                        {
+                            label: 'Nucleotide And Amino Acid Symbols',
+                            link: '/references/nucleotide-and-amino-acid-symbols/',
                         },
                         {
                             label: 'Database Config',

diff --git a/lapis2-docs/src/content/docs/concepts/ambiguous-symbols.mdx b/lapis2-docs/src/content/docs/concepts/ambiguous-symbols.mdx
@@ -3,27 +3,8 @@ title: Ambiguous symbols
 description: Explanation how ambiguous reads are handled in the data
 ---
 
-The underlying sequence files in `.FASTA` format can contain any of the following symbols:
-
-| Symbol | Meaning           |
-| ------ | ----------------- |
-| A      | Adenine           |
-| C      | Cytosine          |
-| G      | Guanine           |
-| T      | Thymine           |
-| -      | Deletion          |
-| N      | failed read / any |
-| R      | A or G            |
-| Y      | C or T            |
-| S      | C or G            |
-| W      | A or T            |
-| K      | G or T            |
-| M      | A or C            |
-| B      | not A             |
-| D      | not C             |
-| H      | not G             |
-| V      | not T             |
-
+[The symbols page](/references/nucleotide-and-amino-acid-symbols)
+lists all symbols that the underlying sequence files in `.FASTA` format can contain.
 The ambiguous symbols arise from imperfect reads in the sequencer.
 
 While one mostly queries for the symbols `A`, `C`, `G`, `T` and `-` to look for specific features and mutations of a sequence,

diff --git a/lapis2-docs/src/content/docs/maintainer-docs/references/reference-genomes.mdx b/lapis2-docs/src/content/docs/maintainer-docs/references/reference-genomes.mdx
@@ -39,7 +39,7 @@ The file must contain a JSON object with two keys:
 
 A reference sequence is a JSON object that permits the following keys:
 
-| Key      | Type   | Required | Description                               |
-| -------- | ------ | -------- | ----------------------------------------- |
-| name     | string | true     | The name of the sequence. Must be unique. |
-| sequence | string | true     | The sequence.                             |
+| Key      | Type   | Required | Description                                                                                     |
+| -------- | ------ | -------- | ----------------------------------------------------------------------------------------------- |
+| name     | string | true     | The name of the sequence. Must be unique.                                                       |
+| sequence | string | true     | The sequence. See [here for allowed characters](/references/nucleotide-and-amino-acid-symbols). |
diff --git a/lapis2-docs/src/content/docs/references/nucleotide-and-amino-acid-symbols.mdx b/lapis2-docs/src/content/docs/references/nucleotide-and-amino-acid-symbols.mdx
@@ -0,0 +1,57 @@
+---
+title: Nucleotide And Amino Acid Symbols
+description: A reference list of valid symbols
+---
+
+This page lists valid symbols for nucleotides and amino acids.
+
+## Nucleotides
+
+| Symbol | Meaning           | Ambiguous Symbol |
+| ------ | ----------------- | ---------------- |
+| A      | Adenine           |                  |
+| C      | Cytosine          |                  |
+| G      | Guanine           |                  |
+| T      | Thymine           |                  |
+| -      | Deletion          |                  |
+| N      | failed read / any |                  |
+| R      | A or G            | ✔               |
+| Y      | C or T            | ✔               |
+| S      | C or G            | ✔               |
+| W      | A or T            | ✔               |
+| K      | G or T            | ✔               |
+| M      | A or C            | ✔               |
+| B      | not A             | ✔               |
+| D      | not C             | ✔               |
+| H      | not G             | ✔               |
+| V      | not T             | ✔               |
+
+## Amino Acids
+
+| Symbol | Meaning                     | Ambiguous Symbol |
+| ------ | --------------------------- | ---------------- |
+| -      | Deletion                    |                  |
+| A      | Alanine                     |                  |
+| C      | Cysteine                    |                  |
+| D      | Aspartic Acid               |                  |
+| E      | Glutamic Acid               |                  |
+| F      | Phenylalanine               |                  |
+| G      | Glycine                     |                  |
+| H      | Histidine                   |                  |
+| I      | Isoleucine                  |                  |
+| K      | Lysine                      |                  |
+| L      | Leucine                     |                  |
+| M      | Methionine                  |                  |
+| N      | Asparagine                  |                  |
+| P      | Proline                     |                  |
+| Q      | Glutamine                   |                  |
+| R      | Arginine                    |                  |
+| S      | Serine                      |                  |
+| T      | Threonine                   |                  |
+| V      | Valine                      |                  |
+| W      | Tryptophan                  |                  |
+| Y      | Tyrosine                    |                  |
+| \*     | Stop codon                  |                  |
+| B      | Aspartic Acid or Asparagine | ✔               |
+| Z      | Glutamine or Glutamic Acid  | ✔               |
+| X      | Alanine                     | ✔               |
diff --git a/...tent/docs/references/reference-genome.mdx → ...ent/docs/references/reference-genomes.mdx b/...tent/docs/references/reference-genome.mdx → ...ent/docs/references/reference-genomes.mdx
@@ -1,5 +1,5 @@
 ---
-title: Reference Genome
+title: Reference Genomes
 description: reference genome
 ---
 

diff --git a/lapis2-docs/tests/docs.spec.ts b/lapis2-docs/tests/docs.spec.ts
@@ -8,7 +8,8 @@ const referencesPages = [
     'Fields',
     'Filters',
     'Open API / Swagger',
-    'Reference Genome',
+    'Reference Genomes',
+    'Nucleotide And Amino Acid Symbols',
     'Database Config',
 ];