Merge pull request #41 from nextstrain/misc-tpyoes

Misc tpyoes

CHANGELOG.md

@@ -2,4 +2,6 @@
 
 We use this CHANGELOG to document breaking changes, new features, bug fixes,
 and config value changes that may affect both the usage of the workflows and
-the outputs of the workflows.
+the outputs of the workflows. See the [changelog for the ncov
+repository](https://github.com/nextstrain/ncov/blob/HEAD/docs/src/reference/change_log.md)
+for an example of formatting.

ingest/Snakefile

@@ -10,9 +10,9 @@ configfile: "defaults/config.yaml"
 
 # This is the default rule that Snakemake will run when there are no specified targets.
 # The default output of the ingest workflow is usually the curated metadata and sequences.
-# Nextstrain maintained ingest workflows will produce metadata files with the
+# Nextstrain-maintained ingest workflows will produce metadata files with the
 # standard Nextstrain fields and additional fields that are pathogen specific.
-# We recommend use these standard fields in custom ingests as well to minimize
+# We recommend using these standard fields in custom ingests as well to minimize
 # the customizations you will need for the downstream phylogenetic workflow.
 # TODO: Add link to centralized docs on standard Nextstrain metadata fields
 rule all:
@@ -21,18 +21,18 @@ rule all:
         "results/metadata.tsv",
 
 
-# Note that only PATHOGEN level customizations should be added to these
+# Note that only PATHOGEN-level customizations should be added to these
 # core steps, meaning they are custom rules necessary for all builds of the pathogen.
-# If there are build specific customizations, they should be added with the
+# If there are build-specific customizations, they should be added with the
 # custom_rules imported below to ensure that the core workflow is not complicated
-# by build specific rules.
+# by build-specific rules.
 include: "rules/fetch_from_ncbi.smk"
 include: "rules/curate.smk"
 
 
 # We are pushing to standardize ingest workflows with Nextclade runs to include
 # Nextclade outputs in our publicly hosted data. However, if a Nextclade dataset
-# does not already exist, it requires curated data as input, so we are making
+# does not already exist, creating one requires curated data as input, so we are making
 # Nextclade steps optional here.
 #
 # If Nextclade config values are included, the nextclade rules will create the
@@ -60,7 +60,7 @@ else:
 # Allow users to import custom rules provided via the config.
 # This allows users to run custom rules that can extend or override the workflow.
 # A concrete example of using custom rules is the extension of the workflow with
-# rules to support the Nextstrain automation that upload files and send internal
+# rules to support the Nextstrain automation that uploads files and sends internal
 # Slack notifications.
 # For extensions, the user will have to specify the custom rule targets when
 # running the workflow.

ingest/defaults/config.yaml

@@ -11,7 +11,7 @@ entrez_search_term: ""
 ncbi_taxon_id: ""
 
 # The list of NCBI Datasets fields to include from NCBI Datasets output
-# These need to be the mneumonics of the NCBI Datasets fields, see docs for full list of fields
+# These need to be the "mnemonics" of the NCBI Datasets fields, see docs for full list of fields
 # https://www.ncbi.nlm.nih.gov/datasets/docs/v2/reference-docs/command-line/dataformat/tsv/dataformat_tsv_virus-genome/#fields
 # Note: the "accession" field MUST be provided to match with the sequences
 ncbi_datasets_fields:

ingest/rules/fetch_from_ncbi.smk

@@ -27,7 +27,7 @@ to provide the correct parameter.
 """
 
 # This ruleorder determines which rule to use to produce the final NCBI NDJSON file.
-# The default is set to use NCBI Datasets since it does no require a custom script.
+# The default is set to use NCBI Datasets since it does not require a custom script.
 # Switch the rule order if you plan to use Entrez
 ruleorder: format_ncbi_datasets_ndjson > parse_genbank_to_ndjson
 

phylogenetic/Snakefile

@@ -1,6 +1,6 @@
 """
 This is the main phylogenetic Snakefile that orchestrates the full phylogenetic
-workflow and define its default output(s).
+workflow and defines its default output(s).
 """
 # The workflow filepaths are written relative to this Snakefile's base directory
 workdir: workflow.current_basedir
@@ -11,7 +11,7 @@ configfile: "defaults/config.yaml"
 
 # This is the default rule that Snakemake will run when there are no specified targets.
 # The default output of the phylogenetic workflow is usually the final
-# Nexstrain dataset(s) or Auspice JSON(s) that is output from `rules/export.smk`
+# Nexstrain dataset(s) or Auspice JSON(s) that are output from `rules/export.smk`
 # See Nextstrain docs on expected naming conventions of dataset files
 # https://docs.nextstrain.org/page/reference/data-formats.html
 rule all: