Replaced String with Symbol in DataOptions

Required Roger-luo/Configurations.jl#82 fixed

Manifest.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.10.4"
 manifest_format = "2.0"
-project_hash = "2dd7c363e927c99e3e00bdc1071c09b6a60dab07"
+project_hash = "141f134cca0e625801b6251fbde9284db6f7c28a"
 
 [[deps.AbstractFFTs]]
 deps = ["LinearAlgebra"]
@@ -1205,6 +1205,11 @@ git-tree-sha1 = "8489905bcdbcfac64d1daa51ca07c0d8f0283821"
 uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
 version = "2.8.1"
 
+[[deps.Pipe]]
+git-tree-sha1 = "6842804e7867b115ca9de748a0cf6b364523c16d"
+uuid = "b98c9c47-44ae-5843-9183-064241ee97a0"
+version = "1.3.0"
+
 [[deps.Pixman_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "LLVMOpenMP_jll", "Libdl"]
 git-tree-sha1 = "35621f10a7531bc8fa58f74610b1bfb70a3cfc6b"

Project.toml

@@ -36,6 +36,7 @@ MAT = "23992714-dd62-5051-b70f-ba57cb901cac"
 Makie = "ee78f7c6-11fb-53f2-987a-cfe4a2b5a57a"
 MultivariateStats = "6f286f6a-111f-5878-ab1e-185364afe411"
 NearestNeighbors = "b8a86587-4115-5ab1-83bc-aa920d37bbce"
+Pipe = "b98c9c47-44ae-5843-9183-064241ee97a0"
 Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
 ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
@@ -56,8 +57,8 @@ Colors = "~0.12"
 Comonicon = "~1.0"
 Compat = "3.46 - 4.15"
 Configurations = "~0.17"
-Deneb = "~0.3"
 DataFrames = "1.4 - 1.7"
+Deneb = "~0.3"
 Distances = "~0.10"
 Distributions = "~0.25"
 FastRandPCA = "^0.2.1"

src/cli/main.jl

@@ -50,8 +50,8 @@ Run cell segmentation
 @cast function run(
         coordinates::String, prior_segmentation::String="";
         config::RunOptions=RunOptions(),
-        x_column::String=config.data.x, y_column::String=config.data.y, z_column::String=config.data.z,
-        gene_column::String=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
+        x_column::Symbol=config.data.x, y_column::Symbol=config.data.y, z_column::Symbol=config.data.z,
+        gene_column::Symbol=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
 
         scale::Float64=config.segmentation.scale, scale_std::String=config.segmentation.scale_std,
         n_clusters::Int=config.segmentation.n_clusters,

src/cli/preview.jl

@@ -22,8 +22,8 @@ Plot an html with the dataset preview.
 @cast function preview(
         coordinates::String;
         config::RunOptions=RunOptions(),
-        x_column::String=config.data.x, y_column::String=config.data.y, z_column::String=config.data.z,
-        gene_column::String=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
+        x_column::Symbol=config.data.x, y_column::Symbol=config.data.y, z_column::Symbol=config.data.z,
+        gene_column::Symbol=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
         output::String="preview.html"
     )
     # Parse options

src/cli/segfree.jl

@@ -27,8 +27,8 @@ Extract Neighborhood Composition Vectors (NCVs) from a dataset
         config::RunOptions=RunOptions(),
         k_neighbors::Int=0,
         # ncvs_to_save::Int=0, # TODO: uncomment and use it in the code
-        x_column::String=config.data.x, y_column::String=config.data.y, z_column::String=config.data.z,
-        gene_column::String=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
+        x_column::Symbol=config.data.x, y_column::Symbol=config.data.y, z_column::Symbol=config.data.z,
+        gene_column::Symbol=config.data.gene, min_molecules_per_cell::Int=config.data.min_molecules_per_cell,
         output::String="ncvs.loom"
     )
     opts = config.data;

src/data_loading/cli_wrappers.jl

@@ -178,11 +178,9 @@ using ..Utils: DataOptions
 function load_df(coordinates::String, data_opts::DataOptions; kwargs...)
     exclude_genes = split_string_list(data_opts.exclude_genes)
 
-    # TODO: fix Symbol when Configurations are fixed. Also replace this whole call with `to_dict(data_opts)...`
     df_spatial, gene_names = load_df(
-        coordinates; x_col=Symbol(data_opts.x), y_col=Symbol(data_opts.y), z_col=Symbol(data_opts.z), gene_col=Symbol(data_opts.gene),
-        min_molecules_per_gene=data_opts.min_molecules_per_gene, exclude_genes=exclude_genes,
-        drop_z=data_opts.force_2d, kwargs...
+        coordinates; x_col=data_opts.x, y_col=data_opts.y, z_col=data_opts.z, gene_col=data_opts.gene,
+        drop_z=data_opts.force_2d, data_opts.min_molecules_per_gene, exclude_genes, kwargs...
     )
 
     @info "Loaded $(size(df_spatial, 1)) transcripts, $(length(gene_names)) genes."

src/utils/options.jl

@@ -1,10 +1,10 @@
 using Configurations
 
 @option mutable struct DataOptions # --config.data.*
-    x::String = "x" # Name of the x column in the input data. Default: "x"
-    y::String = "y" # Name of the y column in the input data. Default: "y"
-    z::String = "z" # Name of the y column in the input data. Default: "z"
-    gene::String = "gene" # Name of gene column in the input data. Default: "gene"
+    x::Symbol = :x # Name of the x column in the input data. Default: "x"
+    y::Symbol = :y # Name of the y column in the input data. Default: "y"
+    z::Symbol = :z # Name of the y column in the input data. Default: "z"
+    gene::Symbol = :gene # Name of gene column in the input data. Default: "gene"
     force_2d::Bool = false # Ignores z-column in the data if it is provided
     min_molecules_per_gene::Int = 1 # Minimal number of molecules per gene. Default: 1
     exclude_genes::String = "" # Comma-separated list of genes or regular expressions to ignore during segmentation. Example: 'Blank*,MALAT1'