change multimodal data integration task name to matching modalities (#778)

* change task name to matching modalities in README and folder name

* make kNN AUC description modality-agnostic

* add other folders in here

* removed old multimodal integration folder

* removed backup README

* Rename multimodal_data_integration in tasks/__init__

* Update procrustes.py

* Markdown lint

* Rename hardcoded reference

---------

Co-authored-by: Scott Gigante <84813314+scottgigante-immunai@users.noreply.github.com>
Co-authored-by: Scott Gigante <scott.gigante@immunai.com>
Former-commit-id: d77a949

Author: LuckyMD

openproblems/tasks/__init__.py

@@ -1,7 +1,7 @@
 from . import denoising
 from . import dimensionality_reduction
 from . import label_projection
-from . import multimodal_data_integration
+from . import matching_modalities
 from . import regulatory_effect_prediction
 from . import spatial_decomposition
 from ._batch_integration import batch_integration_embed

…ks/multimodal_data_integration/README.md …lems/tasks/matching_modalities/README.mdopenproblems/tasks/multimodal_data_integration/README.md renamed to openproblems/tasks/matching_modalities/README.md openproblems/tasks/multimodal_data_integration/README.md renamed to openproblems/tasks/matching_modalities/README.md

@@ -1,4 +1,4 @@
-# Multimodal data integration
+# Matching modalities
 
 ## The task
 
@@ -25,13 +25,13 @@ observations sharing the same coordinates in the latent space.
 
 ## The metrics
 
-Metrics for multimodal data integration aim to characterize how well the aligned
+Metrics for matching modalities aim to characterize how well the aligned
 datasets correspond to the ground truth.
 
-* **kNN AUC**: Let $f(i) ∈ F$ be the scRNA-seq measurement of cell $i$, and $g(i) ∈ G$
-  be the scATAC- seq measurement of cell $i$. kNN-AUC calculates the average percentage
-  overlap of neighborhoods of $f(i)$ in $F$ with neighborhoods of $g(i)$ in $G$. Higher
-  is better.
+* **kNN AUC**: Let $f(i) ∈ F$ be the modality 1 (e.g., scRNA-seq) measurement of cell $i$,
+  and $g(i) ∈ G$ be the modality 2 (e.g., scATAC-seq) measurement of cell $i$. kNN-AUC
+  calculates the average percentage overlap of neighborhoods of $f(i)$ in $F$ with
+  neighborhoods of $g(i)$ in $G$. Higher is better.
 * **MSE**: Mean squared error (MSE) is the average distance between each pair of matched
   observations of the same cell in the learned latent space. Lower is better.