templates and tutorials

AllenInstitute · Oct 11, 2024 · 9816d87 · 9816d87
1 parent 37f2492
commit 9816d87
Show file tree

Hide file tree

Showing 6 changed files with 58 additions and 18 deletions.
diff --git a/src/sciduck/__init__.py b/src/sciduck/__init__.py
@@ -8,5 +8,5 @@
 __authors__ = ['Nelson Johansen', 'Matthew Schmitz', 'Dan Yuan']
 __credits__ = 'Allen Institute for Brain Science'
 
-from . import basic_qc as basic_qc
+from . import basic_qc as qc
 from . import plotting as pl
diff --git a/src/sciduck/templates.py b/src/sciduck/templates.py
@@ -0,0 +1,29 @@
+import numpy as np
+import pandas as pd
+from anndata import AnnData
+import warnings
+
+##
+def allen_institute_basic(adata: AnnData):
+    """
+    Adds Allen Institute basic QC standards to the AnnData object. Does not perform the filtering.
+
+    Args:
+        adata: The AnnData object where constraints will be added.
+    """
+    ## Filter cells/nuclei on UMI and gene count thresholds, showing the default values.
+    add_range_constraint(adata, column="counts", gt=2000, lt=100000)
+    add_range_constraint(adata, column="genes", gt=1000, lt=13000)
+
+    ## Filter cells/nuclei on mitochondrial gene expression, showing the default values.
+    add_range_constraint(adata, "doublet_score", lt = 0.3)
+    add_range_constraint(adata, "pct_counts_mt", lt = 3.0)
+    add_range_constraint(adata, "GEX_Reads_mapped_confidently_to_genome", gt = 0.0)
+    add_range_constraint(adata, "GEX_Reads_mapped_to_genome", gt = 0.0)
+    add_range_constraint(adata, "GEX_Reads_with_TSO", lt = 1.0)
+
+    ## Neuron / Non-Neuron QC constraints
+    add_range_constraint(adata, "genes", gt = 2000, subset = "Class", subset_values = ['Excitatory', 'Inhibitory'])
+    add_range_constraint(adata, "genes", gt = 1000, subset = "Class", subset_values = ['Astrocytes', 'Oligodendrocytes', 'Microglia', 'Endothelial', 'Pericytes'])
+
+    return adata
diff --git a/tutorials/build_annotation_table.ipynb b/tutorials/build_annotation_table.ipynb
diff --git a/tutorials/cluster_centric_qc.ipynb b/tutorials/cluster_centric_qc.ipynb
diff --git a/tutorials/entropy_qc.ipynb b/tutorials/entropy_qc.ipynb
diff --git a/tutorials/standard_workflow.ipynb b/tutorials/standard_workflow.ipynb
@@ -23,7 +23,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata = ad.read_h5ad(\"YOUR_RAW_DATA.h5ad\")"
+    "adata = ad.read_h5ad(\"/path/to/h5ad\")"
    ]
   },
   {
@@ -67,10 +67,11 @@
    "outputs": [],
    "source": [
     "## Filter cells/nuclei on UMI and gene count thresholds, showing the default values.\n",
-    "sd.basic_qc.filter_on_counts_genes(adata, \n",
-    "                                    min_counts = 2000, max_counts = 100000, \n",
-    "                                    min_genes = 1000, max_genes = 13000,\n",
-    "                                    inplace = True)\n",
+    "sd.qc.add_range_constraint(adata, column=\"counts\", gt=2000, lt=100000)\n",
+    "sd.qc.add_range_constraint(adata, column=\"genes\", gt=1000, lt=13000)\n",
+    "\n",
+    "##\n",
+    "sd.qc.apply_constraints(adata)\n",
     "adata.obs.keeper_cells.value_counts()"
    ]
   },
@@ -88,13 +89,14 @@
    "outputs": [],
    "source": [
     "## Filter cells/nuclei on mitochondrial gene expression, showing the default values.\n",
-    "adata = sd.basic_qc.filter_on_precomputed_metrics(adata, \n",
-    "                                                    doublet_score = 0.3, \n",
-    "                                                    pct_counts_mt = 3.0,\n",
-    "                                                    GEX_Reads_mapped_confidently_to_genome = 0.0, \n",
-    "                                                    GEX_Reads_mapped_to_genome = 0.0, \n",
-    "                                                    GEX_Reads_with_TSO = 1.0, \n",
-    "                                                    inplace = False)\n",
+    "sd.qc.add_range_constraint(adata, column=\"doublet_score\", lt = 0.3)\n",
+    "sd.qc.add_range_constraint(adata, column=\"pct_counts_mt\", lt = 3.0)\n",
+    "sd.qc.add_range_constraint(adata, column=\"GEX_Reads_mapped_confidently_to_genome\", gt = 0.0)\n",
+    "sd.qc.add_range_constraint(adata, column=\"GEX_Reads_mapped_to_genome\", gt = 0.0)\n",
+    "sd.qc.add_range_constraint(adata, column=\"GEX_Reads_with_TSO\", lt = 1.0)\n",
+    "\n",
+    "##\n",
+    "sd.qc.apply_constraints(adata)\n",
     "adata.obs.keeper_cells.value_counts()"
    ]
   },
@@ -111,11 +113,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata = sd.basic_qc.filter_utilizing_coarse_labels(adata, \n",
-    "                                            coarse_label_column = \"Class\", \n",
-    "                                            coarse_label_map = {'Neurons': ['Excitatory', 'Inhibitory'], \n",
-    "                                                                'Non-Neurons': ['Astrocytes', 'Oligodendrocytes', 'Microglia', 'Endothelial', 'Pericytes']}, \n",
-    "                                            coarse_label_gene_threshold = {'Neurons': 2000, 'Non-Neurons': 1000})\n",
+    "## Neuron / Non-Neuron QC constraints\n",
+    "sd.qc.add_range_constraint(adata, \n",
+    "                        column = \"genes\", \n",
+    "                        gt = 2000, \n",
+    "                        subset = \"Class\", \n",
+    "                        subset_values = ['Excitatory', 'Inhibitory'])\n",
+    "sd.qc.add_range_constraint(adata, \n",
+    "                        column = \"genes\", \n",
+    "                        gt = 1000, \n",
+    "                        subset = \"Class\", \n",
+    "                        subset_values = ['Astrocytes', 'Oligodendrocytes', 'Microglia', 'Endothelial', 'Pericytes'])\n",
+    "\n",
+    "##\n",
+    "sd.qc.apply_constraints(adata)\n",
     "adata.obs.keeper_cells.value_counts()"
    ]
   }