Update GHA and precommit

.github/workflows/build-docker.yaml

@@ -13,7 +13,7 @@ on:
 env:
   GH_REGISTRY: ghcr.io
   GH_REGISTRY_USER: alexslemonade
-  AWS_REGISTRY: 997241705947.dkr.ecr.us-east-1.amazonaws.com
+  AWS_REGISTRY: ${{ secrets.AWS_ACCOUNT_ID }}.dkr.ecr.us-east-1.amazonaws.com
   AWS_PREFIX: ghcr_io
 
 jobs:
@@ -49,7 +49,7 @@ jobs:
         if: ${{ github.event_name == 'push' }}
         uses: aws-actions/configure-aws-credentials@v4
         with:
-          role-to-assume: arn:aws:iam::997241705947:role/gha-ecr-access-role
+          role-to-assume: arn:aws:iam::${{ secrets.AWS_ACCOUNT_ID }}:role/gha-ecr-access-role
           role-session-name: githubActionSession
           aws-region: us-east-1
 
@@ -136,7 +136,7 @@ jobs:
         uses: aws-actions/configure-aws-credentials@v4
         if: ${{ github.event_name == 'push' }}
         with:
-          role-to-assume: arn:aws:iam::997241705947:role/gha-ecr-access-role
+          role-to-assume: arn:aws:iam::${{ secrets.AWS_ACCOUNT_ID }}:role/gha-ecr-access-role
           role-session-name: githubActionSession-${{ matrix.image_name }}
           aws-region: us-east-1
 

.pre-commit-config.yaml

@@ -1,61 +1,35 @@
 # All available hooks: https://pre-commit.com/hooks.html
 # R specific hooks: https://github.com/lorenzwalthert/precommit
 repos:
+  - repo: https://github.com/posit-dev/air-pre-commit
+    # Air version
+    rev: 0.9.0
+    hooks:
+      # Run the formatter
+      - id: air-format
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.45.0
+    hooks:
+      - id: typos
   - repo: https://github.com/lorenzwalthert/precommit
-    rev: v0.4.3
+    rev: v0.4.3.9021
     hooks:
-      - id: style-files
-        args: [--style_pkg=styler, --style_fun=tidyverse_style]
       # codemeta must be above use-tidy-description when both are used
       # -   id: codemeta-description-updated
       - id: use-tidy-description
-      - id: spell-check
-        exclude: >
-          (?x)^(
-          .*\.[rR]|
-          .*\.feather|
-          .*\.jpeg|
-          .*\.pdf|
-          .*\.png|
-          .*\.py|
-          .*\.RData|
-          .*\.rds|
-          .*\.Rds|
-          .*\.Rproj|
-          .*\.sh|
-          (.*/|)\.gitattributes|
-          (.*/|)\.gitignore|
-          (.*/|)\.gitlab-ci\.yml|
-          (.*/|)\.lintr|
-          (.*/|)\.pre-commit-.*|
-          (.*/|)\.Rbuildignore|
-          (.*/|)\.Renviron|
-          (.*/|)\.Rprofile|
-          (.*/|)\.travis\.yml|
-          (.*/|)appveyor\.yml|
-          (.*/|)DESCRIPTION|
-          (.*/|)NAMESPACE|
-          (.*/|)pixi\.toml|
-          (.*/|)pixi\.lock|
-          (.*/|)renv/settings\.dcf|
-          (.*/|)renv.*\.lock|
-          (.*/|)requirements.*\.in|
-          (.*/|)requirements.*\.txt|
-          (.*/|).*Dockerfile|
-          (.*/|)WORDLIST|
-          \.github/workflows/.*|
-          data/.*|
-          )$
       - id: lintr
       - id: parsable-R
       - id: no-browser-statement
       - id: no-debug-statement
       - id: deps-in-desc
         exclude: docker/.*|renv/.*
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
       - id: check-added-large-files
         args: ["--maxkb=200"]
       - id: end-of-file-fixer
         exclude: '\.Rd'
+ci:
+  autofix_prs: true # set to false if we don't want fixes automatically applied by ci
+  autoupdate_schedule: quarterly

R/add_cell_mito_qc.R

@@ -28,7 +28,7 @@ add_cell_mito_qc <- function(sce, mito, miQC = FALSE, ...) {
     stop("sce must be a SingleCellExperiment object")
   }
 
-  # check that mito is not empty, otherwise resulting colData will be innacurate
+  # check that mito is not empty, otherwise resulting colData will be inaccurate
   if (length(mito) == 0) {
     stop("Mitochondrial gene list not used, cannot calculate mitochondrial metrics.")
   }
@@ -50,7 +50,6 @@ add_cell_mito_qc <- function(sce, mito, miQC = FALSE, ...) {
     ...
   )
 
-
   if (miQC) {
     sce <- add_miQC(sce)
   }

R/processing_pcs.R

@@ -22,7 +22,7 @@ filter_pcs <- function(pcs, batches, rename_pcs = TRUE) {
 
   # Check dimensions after filtering
   if (nrow(pcs) != length(batches)) {
-    stop("Incompatable PC and batch information dimensions after removing NAs.")
+    stop("Incompatible PC and batch information dimensions after removing NAs.")
   }
 
   # rename PCs to batches if specified
@@ -34,7 +34,6 @@ filter_pcs <- function(pcs, batches, rename_pcs = TRUE) {
 }
 
 
-
 #' Downsample PCs for use in integration metric calculations
 #'
 #' @param pcs The PCs to downsample, these PCs should contain batch labels as rownames
@@ -55,10 +54,7 @@ downsample_pcs <- function(pcs, frac_cells, min_cells = 50) {
   }
 
   # Determines rows to sample
-  downsampled_indices <- sample(1:num_cells,
-    frac_cells * num_cells,
-    replace = FALSE
-  )
+  downsampled_indices <- sample(1:num_cells, frac_cells * num_cells, replace = FALSE)
 
   # Extract PCs for downsample
   downsampled_pcs <- pcs[downsampled_indices, , drop = FALSE]

R/sim_sce.R

@@ -21,7 +21,7 @@ sim_sce <- function(n_genes = 200, n_cells = 100, n_empty = 1000, n_groups = 3)
     stop("n_genes must be a positive number.")
   }
   if (n_cells < 1) {
-    stop("n_cells must be a postive number.")
+    stop("n_cells must be a positive number.")
   }
   # enforce some minimums
   n_empty <- max(n_empty, 0)

air.toml

@@ -0,0 +1,6 @@
+[format]
+line-width = 100
+indent-width = 2
+indent-style = "space"
+line-ending = "lf"
+skip = ["stopifnot"]

docker/make-requirements.sh

@@ -2,7 +2,7 @@
 set -euo pipefail
 # This script is used to generate or update requirements/lock files for R and Python packages
 # Requires that the `pip-tools` python package is installed.
-# Before running, make sure that the renv.lock file and installed libaries are
+# Before running, make sure that the renv.lock file and installed libraries are
 # consistent with renv::snapshot() or renv::restore()
 
 # To upgrade packages, set the `UPGRADE_PY` environment variable as follows:

tests/testthat/test-add_sample_metadata.R

@@ -9,36 +9,29 @@ sample_metadata_df <- data.frame(
 )
 
 test_that("`add_sample_metadata` works as expected", {
-  updated_sce <- add_sample_metadata(sce,
-    metadata_df = sample_metadata_df
-  )
+  updated_sce <- add_sample_metadata(sce, metadata_df = sample_metadata_df)
 
   expect_equal(
     metadata(updated_sce)$sample_metadata,
     sample_metadata_df
   )
 })
 
-test_that("`add_sample_metadata` fails as exepected", {
+test_that("`add_sample_metadata` fails as expected", {
   # missing sce
   expect_error(add_sample_metadata(
     sce = "not an sce",
     metadata_df = sample_metadata_df
   ))
 
   # incorrect format for metadata_df
-  expect_error(add_sample_metadata(sce,
-    metadata_df = "not a data frame"
-  ))
-
+  expect_error(add_sample_metadata(sce, metadata_df = "not a data frame"))
 
   # incorrect sample id column
   incorrect_metadata <- data.frame(
     not_sample_id = "sample_id"
   )
-  expect_error(add_sample_metadata(sce,
-    metadata_df = incorrect_metadata
-  ))
+  expect_error(add_sample_metadata(sce, metadata_df = incorrect_metadata))
 
   # sample ids don't match
   metadata(sce)$sample_id <- "not a sample id"

tests/testthat/test-integrate_sces.R

@@ -12,10 +12,7 @@ rownames(colData(merged_sce)) <- new_rownames
 # Add "sample" to colData
 colData(merged_sce)$sample <- batches
 # Add in a "covariate" column for testing
-colData(merged_sce)$covariate <- sample(letters[1:4],
-  size = 300,
-  replace = TRUE
-)
+colData(merged_sce)$covariate <- sample(letters[1:4], size = 300, replace = TRUE)
 
 # add a logcounts assay for testing (numbers don't matter)
 logcounts(merged_sce) <- counts(merged_sce)
@@ -29,11 +26,9 @@ batch_column <- "sample"
 
 ################################################################################
 
-
-
 test_that("`integrate_fastmnn` works as expected", {
   suppressWarnings(
-    # warnings are supressed here b/c simulated data plays poorly enough with
+    # warnings are suppressed here b/c simulated data plays poorly enough with
     # algorithms to trigger warnings like:
     ### Warning in (function (A, nv = 5, nu = nv, maxit = 1000, work = nv + 7, reorth = TRUE,  :
     ### You're computing too large a percentage of total singular values, use a standard svd instead.
@@ -75,7 +70,6 @@ test_that("`integrate_harmony` works as expected", {
 })
 
 
-
 test_that("`integrate_harmony` fails when PCs are missing", {
   reducedDim(merged_sce, "PCA") <- NULL
   expect_error(
@@ -85,10 +79,7 @@ test_that("`integrate_harmony` fails when PCs are missing", {
 
 test_that("`integrate_harmony` fails when covariate columns are missing", {
   expect_error(
-    integrate_harmony(merged_sce,
-      batch_column,
-      covariate_cols = "not_a_column"
-    )
+    integrate_harmony(merged_sce, batch_column, covariate_cols = "not_a_column")
   )
 })
 
@@ -108,7 +99,6 @@ test_that("`integrate_harmony` fails when covariates and covariate_lambda don't
 ################################################################################
 ################################################################################
 
-
 test_that("`integrate_sces` fail as expected", {
   # bad sce
   expect_error(
@@ -122,10 +112,7 @@ test_that("`integrate_sces` fail as expected", {
 
   # missing batch column
   expect_error(
-    integrate_sces(merged_sce,
-      "fastMNN",
-      batch_column = "not_a_column"
-    )
+    integrate_sces(merged_sce, "fastMNN", batch_column = "not_a_column")
   )
 
   # insufficient batches
@@ -163,10 +150,7 @@ test_that("`integrate_sces` works as expected for return_corrected_expression=TR
   # fastmnn:
   suppressWarnings({
     # simulated-data related numerical warnings
-    integrated_sce <- integrate_sces(merged_sce,
-      "fastMNN",
-      return_corrected_expression = TRUE
-    )
+    integrated_sce <- integrate_sces(merged_sce, "fastMNN", return_corrected_expression = TRUE)
   })
 
   expect_equal(
@@ -186,23 +170,16 @@ test_that("`integrate_sces` works as expected for return_corrected_expression=TR
 })
 
 
-
-
-
 test_that("`integrate_sces` works as expected with fastmnn extra arguments", {
   expect_no_error(
     suppressWarnings({
       # simulated-data related numerical warnings
-      integrated_sce <- integrate_sces(merged_sce,
-        "fastMNN",
-        cos.norm = FALSE
-      )
+      integrated_sce <- integrate_sces(merged_sce, "fastMNN", cos.norm = FALSE)
     })
   )
 })
 
 
-
 test_that("`integrate_sces` works as expected for harmony defaults", {
   integrated_sce <- integrate_sces(
     merged_sce,