📌 v0.2.2 release

gao-lab · Oct 26, 2023 · 5d3c59b · 5d3c59b
1 parent fba97cf
commit 5d3c59b
Show file tree

Hide file tree

Showing 15 changed files with 1,645 additions and 184 deletions.
diff --git a/.gitignore b/.gitignore
@@ -25,6 +25,7 @@
 *.gz
 *.whl
 *.html
+*.DS_Store
 
 # folder
 **/conda/

diff --git a/benchmark/analysis/aggr_datasets.ipynb b/benchmark/analysis/aggr_datasets.ipynb
diff --git a/benchmark/analysis/celltype_region_analysis.ipynb b/benchmark/analysis/celltype_region_analysis.ipynb
diff --git a/benchmark/analysis/check_MERFISH.ipynb b/benchmark/analysis/check_MERFISH.ipynb
diff --git a/benchmark/analysis/hetero.ipynb b/benchmark/analysis/hetero.ipynb
diff --git a/benchmark/analysis/plot_confusion_matrix.ipynb b/benchmark/analysis/plot_confusion_matrix.ipynb
diff --git a/benchmark/analysis/plot_keypoints.ipynb b/benchmark/analysis/plot_keypoints.ipynb
diff --git a/benchmark/config/config.yaml b/benchmark/config/config.yaml
@@ -1,13 +1,13 @@
 #-------------------------------- Global ----------------------------------#
 timeout: 24h
 timehold: 200h
-seed: 8
+seed: 1
 sample: 0
 fix_sample: True
 
 use:
- # - benchmark
- - perturb
+ - benchmark
+ # - perturb
  # - split_data
  # - build_3d
 

diff --git a/benchmark/profiles/impetus/impetus.yaml b/benchmark/profiles/impetus/impetus.yaml
@@ -3,7 +3,7 @@ __default__:
  output: ".slurm/{rule}.out"
  error: ".slurm/{rule}.err"
  account: gglab
- partition: cpu2
+ partition: fat2
  n_node: 1
  n_task: 1
  n_cpu: "{threads}"

diff --git a/benchmark/workflow/notebooks/data_split.ipynb b/benchmark/workflow/notebooks/data_split.ipynb
@@ -95,7 +95,7 @@
  "name": "python",
  "nbconvert_exporter": "python",
  "pygments_lexer": "ipython3",
- "version": "3.8.13"
+ "version": "3.8.17"
  },
  "orig_nbformat": 4,
  "vscode": {

diff --git a/benchmark/workflow/notebooks/emb2metrics.ipynb b/benchmark/workflow/notebooks/emb2metrics.ipynb
@@ -15,7 +15,9 @@
  "import pandas as pd\n",
  "import scanpy as sc\n",
  "import scipy.sparse as sp\n",
- "from sklearn.metrics import f1_score\n",
+ "import matplotlib.pyplot as plt\n",
+ "from sklearn.metrics import f1_score, confusion_matrix, ConfusionMatrixDisplay\n",
+ "\n",
  "\n",
  "from scSLAT.model import spatial_match\n",
  "from scSLAT.metrics import global_score, euclidean_dis, rotation_angle\n",
@@ -108,6 +110,16 @@
  " spot_size = 5"
  ]
  },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "out_dir = Path(os.path.dirname(metric_file))\n",
+ "sc.settings.figdir = out_dir"
+ ]
+ },
  {
  "cell_type": "markdown",
  "metadata": {},
@@ -190,7 +202,7 @@
  "cell_type": "markdown",
  "metadata": {},
  "source": [
- "## Ground truth (perturb)"
+ "## Confusion Matrix"
  ]
  },
  {
@@ -199,18 +211,55 @@
  "metadata": {},
  "outputs": [],
  "source": [
- "if 'perturb' in matching_file:\n",
- " match_ratio = (matching[0] == matching[1]).sum() / len(matching[0])\n",
- "else:\n",
- " match_ratio = -1"
+ "celltype_label = adata2.obs[biology_meta].unique().tolist()\n",
+ "region_label = adata2.obs[topology_meta].unique().tolist()\n",
+ "celltype_region_label = adata2.obs['celltype_region'].unique().tolist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.figure(figsize=(len(celltype_region_label) / 2, len(celltype_region_label) /2))\n",
+ "cm = confusion_matrix(adata2.obs['celltype_region'], adata2.obs['target_celltype_region'], labels=celltype_region_label)\n",
+ "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=celltype_region_label)\n",
+ "disp.plot(cmap='Reds', xticks_rotation='vertical', ax=plt.gca())\n",
+ "plt.savefig(out_dir / 'joint_confusing_matrix.png', dpi=300, bbox_inches='tight')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.figure(figsize=(len(celltype_label) / 2, len(celltype_label) /2))\n",
+ "cm = confusion_matrix(adata2.obs[biology_meta], adata2.obs['target_celltype'], labels=celltype_label)\n",
+ "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=celltype_label)\n",
+ "disp.plot(cmap='Reds', xticks_rotation='vertical', ax=plt.gca())\n",
+ "plt.savefig(out_dir / 'celltype_confusing_matrix.png', dpi=300, bbox_inches='tight')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.figure(figsize=(len(region_label) / 2, len(region_label) /2))\n",
+ "cm = confusion_matrix(adata2.obs[topology_meta], adata2.obs['target_region'], labels=region_label)\n",
+ "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=region_label)\n",
+ "disp.plot(cmap='Reds', xticks_rotation='vertical', ax=plt.gca())\n",
+ "plt.savefig(out_dir / 'region_confusing_matrix.png', dpi=300, bbox_inches='tight')"
  ]
  },
  {
- "attachments": {},
  "cell_type": "markdown",
  "metadata": {},
  "source": [
- "# Save"
+ "## Ground truth (perturb)"
  ]
  },
  {
@@ -219,8 +268,18 @@
  "metadata": {},
  "outputs": [],
  "source": [
- "out_dir = Path(os.path.dirname(metric_file))\n",
- "sc.settings.figdir = out_dir"
+ "if 'perturb' in matching_file:\n",
+ " match_ratio = (matching[0] == matching[1]).sum() / len(matching[0])\n",
+ "else:\n",
+ " match_ratio = -1"
+ ]
+ },
+ {
+ "attachments": {},
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Save"
  ]
  },
  {

diff --git a/benchmark/workflow/notebooks/run_SLAT_dpca.ipynb b/benchmark/workflow/notebooks/run_SLAT_dpca.ipynb
@@ -84,25 +84,21 @@
  " biology_meta = 'cell_type'\n",
  " topology_meta = 'layer_guess'\n",
  " alpha = 10\n",
- " LGCN_layer = 2\n",
  " spot_size = 5\n",
  "elif 'merfish' and 'hypothalamic' in adata1_file:\n",
  " biology_meta = 'Cell_class'\n",
  " topology_meta = 'region'\n",
  " alpha = 25\n",
- " LGCN_layer = 2\n",
  " spot_size = 15\n",
  "elif 'stereo' and 'embryo' in adata1_file:\n",
  " biology_meta = 'annotation'\n",
  " topology_meta = 'region'\n",
  " alpha = 3\n",
- " LGCN_layer = 1\n",
  " spot_size = 5\n",
  "elif 'brain' in adata1_file:\n",
  " biology_meta = 'layer_guess'\n",
  " topology_meta = 'layer_guess'\n",
  " alpha = 10\n",
- " LGCN_layer = 2\n",
  " spot_size = 5"
  ]
  },
@@ -154,7 +150,7 @@
  "Cal_Spatial_Net(adata1, k_cutoff=20, model='KNN')\n",
  "Cal_Spatial_Net(adata2, k_cutoff=20, model='KNN')\n",
  "edges, features = load_anndatas([adata1, adata2], feature='dpca', singular=True, dim=30)\n",
- "embd0, embd1, time1 = run_SLAT(features, edges, 6, LGCN_layer=LGCN_layer)\n",
+ "embd0, embd1, time1 = run_SLAT(features, edges, 6, LGCN_layer=3)\n",
  "run_time = str(time.time() - start)\n",
  "print('Runtime: ' + run_time)"
  ]

diff --git a/benchmark/workflow/notebooks/run_SLAT_dpca_one2many.ipynb b/benchmark/workflow/notebooks/run_SLAT_dpca_one2many.ipynb
@@ -82,25 +82,21 @@
  " biology_meta = 'cell_type'\n",
  " topology_meta = 'layer_guess'\n",
  " alpha = 10\n",
- " LGCN_layer = 2\n",
  " spot_size = 5\n",
  "elif 'merfish' and 'hypothalamic' in adata1_file:\n",
  " biology_meta = 'Cell_class'\n",
  " topology_meta = 'region'\n",
  " alpha = 25\n",
- " LGCN_layer = 2\n",
  " spot_size = 15\n",
  "elif 'stereo' and 'embryo' in adata1_file:\n",
  " biology_meta = 'annotation'\n",
  " topology_meta = 'region'\n",
  " alpha = 3\n",
- " LGCN_layer = 1\n",
  " spot_size = 5\n",
  "elif 'brain' in adata1_file:\n",
  " biology_meta = 'layer_guess'\n",
  " topology_meta = 'layer_guess'\n",
  " alpha = 10\n",
- " LGCN_layer = 2\n",
  " spot_size = 5"
  ]
  },
@@ -152,7 +148,7 @@
  "Cal_Spatial_Net(adata1, k_cutoff=20, model='KNN')\n",
  "Cal_Spatial_Net(adata2, k_cutoff=20, model='KNN')\n",
  "edges, features = load_anndatas([adata1, adata2], feature='dpca', singular=True, dim=30)\n",
- "embd0, embd1, time1 = run_SLAT(features, edges, 6, LGCN_layer=LGCN_layer)\n",
+ "embd0, embd1, time1 = run_SLAT(features, edges, 6, LGCN_layer=3)\n",
  "run_time = str(time.time() - start)\n",
  "print('Runtime: ' + run_time)"
  ]

diff --git a/pyproject.toml b/pyproject.toml
@@ -31,7 +31,7 @@ classifiers = [
 [tool.poetry.dependencies]
 python = "^3.8"
 numpy = ">1.19"
-scipy = ">1.3"
+scipy = ">1.3, <1.9"
 pandas = ">1.1, <2.0"
 matplotlib = ">3.1.2, <3.7"
 seaborn = ">0.9"

diff --git a/scSLAT/viz/multi_dataset.py b/scSLAT/viz/multi_dataset.py
@@ -462,9 +462,9 @@ class match_3D_celltype(match_3D_multi):
  highlight_cell
  color to highlight the cell
  meta
- dataframe colname of meta, such as celltype
+ dataframe col name of meta, such as celltype
  expr
- dataframe colname of gene expr
+ dataframe col name of gene expr
  subsample_size
  subsample size of matches
  reliability