Add chuck-size parameter to cylinter config. (#181)

cylinter/cylinter_config 1.29.23 PM.yml

@@ -0,0 +1,344 @@
+# GENERAL PROGRAM CONFIGURATIONS
+
+inDir: /Users/<username>/Desktop/cylinter_demo
+# Path to CyLinter input directory containing multi-channel
+# image files (TIF or OME-TIF), segmentation outlines (OME-TIF),
+# segmentation masks (TIF), and corresponding single-cell feature tables (CSV)
+
+outDir: /Users/<username>/Desktop/cylinter_demo/output
+# CyLinter output directory. Path is created if it does not exist.
+
+sampleMetadata:
+  "1": ["1", "Normal kidney cortex", "NKC", "CANCER-FALSE", 1]
+  "15": ["15", "Glioblastoma", "GBM", "CANCER-TRUE", 1]
+  "18": ["18", "Mesothelioma", "MTO", "CANCER-TRUE", 1]
+  "68": ["68", "Tonsil", "TSL", "CANCER-FALSE", 3]
+# Sample metadata dictionary: keys = file names; values = list of strings.
+# First elements: sample names (str)
+# Second elements: descriptive text of experimental condition (str)
+# Third elements: abbreviation of experimental condition (str)
+# Fourth elements: comma-delimited string of arbitrary binary declarations
+# for computing t-statistics between two groups of samples (str dytpe)
+# Fifth elements: replicate number specifying biological or
+# technical replicates (int)
+
+samplesToExclude: []
+# (list of strs) Sample names to exclude from analysis specified
+# according to the first elements of sampleMetadata configuration.
+
+counterstainChannel: "DNA1"
+# (str) Name of marker in markers.csv file for use in visualizing nuclear counterstain
+
+markersToExclude: ["Rabbit IgG", "Goat IgG", "Mouse IgG", "CD56", "CD13",
+                   "pAUR", "CCNE", "CDKN2A", "PCNA_1", "CDKN1B_2",
+                   "CD63", "CD32", "CCNA2", "CDKN1C", "PCNA_1",
+                   "CDKN1B_1", "CCND1", "cPARP", "pCREB",
+                   "CCNB1", "PCNA_2", "CDK2"
+                   ]
+# (list of strs) Immunomarkers to exclude from analysis
+# Does not include nuclear dyes. They are needed for the
+# cycleCorrelation module to remove cell dropout.
+
+###############################################################################
+# MODULE-SPECIFIC CONFIGURATIONS
+
+# selectROIs-------------------------------------------------------------------
+delintMode: True
+# (bool) Whether to drop (True; negative selection) or
+# retain (False; positive selection) cells selected by ROIs.
+
+showAbChannels: True
+# (bool) Whether to show all immunomarker channels (True) when Napari
+# is open (may be memory limiting) or show cycle 1 DNA only (False).
+
+samplesForROISelection: ["1", "15", "18", "68"]
+# (list of strs) Sample names for ROI selection specified
+# according to the first elements of sampleMetadata configuration.
+
+autoArtifactDetection: True
+# (bool) Whether to display tools for automated artifact detection in Napari window
+
+artifactDetectionMethod: "classical"
+# (str) Algorithm used for automated artifact detection (current option: "classical").
+# Multi-layer perceptron method ("MLP") currently under development.
+
+
+# intensityFilter-------------------------------------------------------------------
+numBinsIntensity: 50
+# (int) Number of bins for DNA intensity histograms.
+
+
+# areaFilter-------------------------------------------------------------------
+numBinsArea: 50
+# (int) Number of bins for DNA area histograms.
+
+
+# cycleCorrelation-------------------------------------------------------------------
+numBinsCorrelation: 50
+# (int) Number of bins for DNA1/DNAn histograms.
+
+
+# pruneOutliers-------------------------------------------------------------------
+hexbins: False
+# (bool) Whether to use hexbins (True) or scatter plots (False) to plot
+# single-cell signal intensities. Scatter plots allow for higher resolution,
+# but may require longer rendering times.
+
+hexbinGridSize: 20
+# (int) Hexbin grid size when hexins=True.
+# Higher values increase bin resolution.
+
+
+# metaQC (optional)-------------------------------------------------------------------
+metaQC: False
+# (bool) Whether to perform data reclassification based on
+# unsupervised clustering results of combinations of clean and
+# noisy (previously-redacted) data.
+
+embeddingAlgorithmQC: "UMAP"
+# (str) Embedding algorithm used for clustering (options: "TSNE" or "UMAP").
+
+channelExclusionsClusteringQC: []
+# (list of strs) Immunomarkers to exclude from clustering.
+
+samplesToRemoveClusteringQC: []
+# (list of strs) Samples to exclude from clustering.
+
+fracForEmbeddingQC: 1.0
+# (float) Fraction of cells to be embedded (range: 0.0-1.0)
+# Limits the amount of data passed to downstream modules.
+
+dimensionEmbeddingQC: 2
+# (int) Dimension of the embedding (fixed to 2 in current version).
+
+topMarkersQC: "clusters"
+# (str) Normalization axis ("channels" or "clusters") used to define
+# highest expressed markers per cluster.
+
+colormapAnnotationQC: "Sample"
+# (str) Metadata annotation to colormap the embedding: Sample or Condition.
+
+metricQC: "euclidean"
+# (str) Distance metric for computing embedding.
+# Choose from valid metrics used by scipy.spatial.distance.pdist:
+# "braycurtis", "canberra", "chebyshev", "cityblock", "correlation", "cosine",
+# "dice", "euclidean", "hamming", "jaccard", "jensenshannon", "kulsinski",
+# "mahalanobis", "matching", "minkowski", "rogerstanimoto", "russellrao",
+# "seuclidean", "sokalmichener", "sokalsneath", "sqeuclidean", "yule".
+
+# --------------------------------------
+# tSNE-specific configurations:
+# https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html
+perplexityQC: 50.0
+# (float) Related to the number of nearest neighbors used in other
+# manifold learning algorithms. Larger datasets usually require
+# larger perplexity. Different values can result in significantly
+# different results.
+
+earlyExaggerationQC: 12.0
+# (float) For larger values, the space between natural clusters
+# will be larger in the embedded space.
+
+learningRateTSNEQC: 200.0
+# (float) tSNE learning rate (typically between 10.0 and 1000.0).
+
+randomStateQC: 5
+# (int) Determines the random number generator for reproducible results
+# across multiple function calls.
+
+# --------------------------------------
+# UMAP-specific configurations:
+# https://umap-learn.readthedocs.io/en/latest/api.html
+nNeighborsQC: 6
+# (int) The size of local neighborhood (in terms of number of
+# neighboring sample points) used for manifold approximation.
+# Larger values result in more global views of the manifold,
+# while smaller values result in more local data being preserved.
+# In general values should be in the range 2 to 100.
+
+learningRateUMAPQC: 1.0
+# (float) The initial learning rate for the embedding optimization.
+
+minDistQC: 0.1
+# (float) The effective minimum distance between embedded points.
+# Smaller values will result in a more clustered/clumped
+# embedding where nearby points on the manifold are drawn
+# closer together, while larger values will result on a more
+# even dispersal of points. The value should be set relative
+# to the spread value, which determines the scale at which
+# embedded points will be spread out.
+
+repulsionStrengthQC: 5.0
+# (float) Weighting applied to negative samples in low dimensional
+# embedding optimization. Values higher than one will
+# result in greater weight being given to negative samples.
+
+
+# PCA-------------------------------------------------------------------
+channelExclusionsPCA: []
+# (strs) Immunomarkers to exclude from PCA analysis.
+
+samplesToRemovePCA: []
+# (list of strs) Samples to exclude from PCA analysis.
+
+dimensionPCA: 2
+# (int) Number of PCs to compute.
+
+pointSize: 90.0
+# (float) scatter point size for sample scores plot.
+
+labelPoints: True
+# (bool) Annotate scatter points with condition abbreviations
+# from sampleMetadata configuration.
+
+distanceCutoff: 0.15
+# (float) Maximum distance between data points in PCA scores plot to
+# be annotated with a common label. Useful for increasing visual clarity
+# of PCA plots containing many data points. Applicable when
+# labelPoints is True.
+
+conditionsToSilhouette: []
+# (list of strs) List of abbreviated condition names whose corresponding
+#scores plot points will be greyed out, left unannotated, and sent to the back
+# of the plot (zorder). Useful for increasing visual clarity of PCA
+# plots containing many data points.
+
+
+# gating (optional)-------------------------------------------------------------------
+gating: True
+# (bool) Whether to perform SYLARAS-style gating on single-cell data.
+# Cell Syst. 2020 Sep 23;11(3):272-285.e9 PMID: 32898474
+
+channelExclusionsGating: []
+# (list of strs) Immunomarkers to exclude from gating.
+
+samplesToRemoveGating: []
+# (list of strs) Samples to exclude from gating.
+
+vectorThreshold: 100
+# (int) vizualize Boolean vectors with cell counts >= vectorThreshold
+
+classes:
+  Tumor: 
+    definition: [+pan-CK, +KI67]
+    subsets: []
+# (dict) Boolean immunophenotype signatures.
+# +marker = immunopositive , -marker = immunonegative, marker = don't care
+
+
+# clustering-------------------------------------------------------------------
+embeddingAlgorithm: "UMAP"
+# (str) Embedding algorithm to use for clustering (options: "TSNE" or "UMAP").
+
+channelExclusionsClustering: []
+# (list of strs) Immunomarkers to exclude from clustering.
+
+samplesToRemoveClustering: []
+# (list of strs) Samples to exclude from clustering.
+
+normalizeTissueCounts: True
+# (bool) Make the number of cells per tissue for clustering more similar
+# through sample-weighted random sampling.
+
+fracForEmbedding: 1.0
+# (float) Fraction of cells to be embedded (range: 0.0-1.0).
+# Limits amount of data passed to downstream modules.
+
+dimensionEmbedding: 2
+# (int) Dimension of the embedding (options: 2 or 3).
+
+topMarkers: "clusters"
+# (str) Normalization axis ("channels" or "clusters") used to define
+# highest expressed markers per cluster.
+
+colormapAnnotationClustering: "Sample"
+# (str) Metadata annotation to colormap the embedding: Sample or Condition.
+
+metric: "euclidean"
+# (str) Distance metric for computing embedding.
+# Choose from valid metrics used by scipy.spatial.distance.pdist:
+# "braycurtis", "canberra", "chebyshev", "cityblock", "correlation", "cosine",
+# "dice", "euclidean", "hamming", "jaccard", "jensenshannon", "kulsinski",
+# "mahalanobis", "matching", "minkowski", "rogerstanimoto", "russellrao",
+# "seuclidean", "sokalmichener", "sokalsneath", "sqeuclidean", "yule".
+
+# --------------------------------------
+# tSNE-specific configurations:
+# https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html
+perplexity: 50.0
+# (float) Related to the number of nearest neighbors used in other
+# manifold learning algorithms. Larger datasets usually require
+# larger perplexity. Different values can result in significantly
+# different results.
+
+earlyExaggeration: 12.0
+# (flaot) For larger values, the space between natural clusters
+# will be larger in the embedded space.
+
+learningRateTSNE: 200.0
+# (float) tSNE learning rate (typically between 10.0 and 1000.0).
+
+randomStateTSNE: 5
+# (int) Determines the random number generator for reproducible results
+# across multiple function calls.
+
+# --------------------------------------
+# UMAP-specific configurations:
+# https://umap-learn.readthedocs.io/en/latest/api.html
+nNeighbors: 6
+# (int) The size of local neighborhood (in terms of number of
+# neighboring sample points) used for manifold approximation.
+# Larger values result in more global views of the manifold,
+# while smaller values result in more local data being preserved.
+# In general values should be in the range 2 to 100.
+
+learningRateUMAP: 1.0
+# (float) The initial learning rate for the embedding optimization.
+
+minDist: 0.1
+# (float) The effective minimum distance between embedded points.
+# Smaller values will result in a more clustered/clumped
+# embedding where nearby points on the manifold are drawn
+# closer together, while larger values will result on a more
+# even dispersal of points. The value should be set relative
+# to the spread value, which determines the scale at which
+# embedded points will be spread out.
+
+repulsionStrength: 5.0
+# (float) Weighting applied to negative samples in low dimensional
+# embedding optimization. Values higher than one will
+# result in greater weight being given to negative samples.
+
+randomStateUMAP: 5
+# (int) Determines the random number generator for reproducible results
+# across multiple function calls.
+
+
+# frequencyStats-------------------------------------------------------------------
+controlGroups: ["CANCER-FALSE"]
+# (list of strs) Corresponds to control groups for each binary declaration
+# specified as the third elements of sampleMetadata values.
+
+denominatorCluster: null
+# (None type) Cluster to be used as the denominator when computing cluster
+# frequency ratios. Set to null first, change to cluster integer number
+# to normalize cluster frequencies to a particular cluster if desired.
+
+FDRCorrection: False
+# (bool) Whether to compute p-vals and false discovery rate (FDR)-corrected
+# q-vals (True) or compute uncorrected p-vals only (False).
+
+
+# curateThumbnails-------------------------------------------------------------
+numThumbnails: 25
+# (int) Number of examples per cluster to be curated.
+
+topMarkersThumbnails: "clusters"
+# (str) Normalization axis ("channels" or "clusters") used to define
+# highest expressed markers per cluster.
+
+windowSize: 30
+# (int) Number of pixels in x and y dimensions per thumbnail.
+
+segOutlines: True
+# (bool) Whether to overlay cell segmentation outlines on thumbnail images.