Merge pull request #5 from openproblems-bio/metrics/spearman_corr

Metrics: Spearman Corr

Author: seohyonkim

CHANGELOG.md

@@ -7,6 +7,7 @@
 ## NEW FUNCTIONALITY
 
 * Added `spaTrack` method (PR #4).
+* Added `Spearman's correlation` metric (PR #5).
 
 ## MAJOR CHANGES
 

src/metrics/spearman_corr/config.vsh.yaml

@@ -0,0 +1,62 @@
+__merge__: ../../api/comp_metric.yaml
+
+name: spearman_corr
+
+info:
+  metrics:
+    - name: spearman_corr
+      label: Spearman's Corr
+      summary: "Computes the Spearman rank correlation coefficient between inferred and ground-truth pseudotime."
+      description: |
+        Calculates the Spearman rank correlation coefficient (rho) between predicted cell pseudotime
+        values and the true ground-truth pseudotime. Measures monotonic relationships regardless of linearity.
+      references:
+        doi:
+          - 10.1038/s41592-020-0772-5
+        bibtex: |
+          @article{Virtanen_2020,
+           author  = {Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E. and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and {van der Walt}, St{\'e}fan J. and Brett, Matthew and Wilson, Joshua and Jarrod Millman, K. and Mayorov, Nikolay and Nelson, Andrew R. J. and Jones, Eric and Kern, Robert and Larson, Eric and Carey, C. J. and Polat, {\dot{I}}lhan and Feng, Yu and Moore, Eric W. and VanderPlas, Jake and Laxalde, Denis and Perktold, Josef and Cimrman, Robert and Henriksen, Ian and Quintero, E. A. and Harris, Charles R. and Archibald, Anne M. and Ribeiro, Ant{\^o}nio H. and Pedregosa, Fabian and {van Mulbregt}, Paul and {SciPy 1.0 Contributors}},
+           title   = {Author Correction: SciPy 1.0: fundamental algorithms for scientific computing in Python},
+           journal = {Nature Methods},
+           volume  = {17},
+           number  = {3},
+           pages   = {352},
+           year    = {2020},
+           doi     = {10.1038/s41592-020-0772-5}
+           }
+      links:
+        documentation: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.spearmanr.html
+        repository: https://github.com/scipy/scipy
+      min: -1
+      max: 1
+      maximize: true
+
+resources:
+  - type: python_script
+    path: script.py
+
+engines:
+  - type: docker
+    image: python:3.11-slim
+    setup:
+      - type: apt
+        packages:
+          - procps              # required by Nextflow
+          - git                 # pip needs it to install openproblems core from git+https
+      - type: python
+        packages:
+          - anndata~=0.10.0
+          - scanpy~=1.10.0
+          - scipy
+          - pandas
+          - pyyaml
+          - requests
+          - jsonschema
+        github:
+          - "openproblems-bio/core#subdirectory=packages/python/openproblems"
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime,midmem,midcpu]

src/metrics/spearman_corr/script.py

@@ -0,0 +1,74 @@
+import anndata as ad
+import numpy as np
+import pandas as pd
+from scipy import stats
+
+## VIASH START
+# Note: this section is auto-generated by viash at runtime. To edit it, make changes
+# in config.vsh.yaml and then run `viash config inject config.vsh.yaml`.
+par = {
+    'input_solution': 'resources_test/task_spatial_trajectory_inference/cxg_mouse_pancreas_atlas/solution.h5ad',
+    'input_prediction': 'resources_test/task_spatial_trajectory_inference/cxg_mouse_pancreas_atlas/prediction.h5ad',
+    'output': 'output.h5ad',
+}
+meta = {
+  'name': 'spearman_corr'
+}
+## VIASH END
+
+
+def compute_spearman(true_values, inferred_values):
+    """Calculates Spearman rank correlation on finite overlapping values."""
+    mask = np.isfinite(true_values) & np.isfinite(inferred_values)
+    
+    if mask.sum() < 2:
+        return 0.0
+
+    rho, _ = stats.spearmanr(true_values[mask], inferred_values[mask])
+    
+    if np.isnan(rho):
+        return 0.0
+        
+    return float(rho)
+
+# read input data
+print('Reading input files', flush=True)
+input_solution = ad.read_h5ad(par['input_solution'])
+input_prediction = ad.read_h5ad(par['input_prediction'])
+
+assert (input_prediction.obs_names == input_solution.obs_names).all(), "obs_names not the same in prediction and solution inputs"
+
+
+# ground truth and predicted pseudotime
+TRUE_COL = "pseudotime_true"
+INFERRED_COL = "pseudotime_inferred"
+
+true_vals = pd.to_numeric(input_solution.obs[TRUE_COL], errors='coerce').values
+inferred_vals = pd.to_numeric(input_prediction.obs[INFERRED_COL], errors='coerce').values
+
+# generate results
+print('Compute metrics', flush=True)
+# metric_ids and metric_values can have length > 1
+# but should be of equal length
+
+score = compute_spearman(true_vals, inferred_vals)
+
+uns_metric_ids = [ 'spearman_corr' ]
+uns_metric_values = [ score ]
+
+# Write output data to file
+print("Write output AnnData to file...", flush=True)
+
+output = ad.AnnData(
+    obs=pd.DataFrame(index=pd.Index(np.array([], dtype=str))),
+    var=pd.DataFrame(index=pd.Index(np.array([], dtype=str))),
+    uns={
+        'dataset_id': input_solution.uns.get('dataset_id', 'unknown'),
+        'normalization_id': input_solution.uns.get('normalization_id', 'unknown'),
+        'method_id': input_prediction.uns.get('method_id', 'unknown'),
+        'metric_ids': uns_metric_ids,
+        'metric_values': uns_metric_values,
+    }
+)
+
+output.write_h5ad(par['output'], compression='gzip')