supervised.md

@@ -2,8 +2,6 @@
 
 We have developed a supervised machine learning tool called TargetMate.
 
-### Features
-
 #### Machine-learning problem
 
 * Binary classification
@@ -11,11 +9,12 @@ We have developed a supervised machine learning tool called TargetMate.
 
 #### Algorithms
 
-* Vanilla
+* Vanilla algorithms
 * Automated
-  * Grid search
-  * TPOT
-  * AutoSklearn
+  * [Randomized search](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html#sklearn.model_selection.RandomizedSearchCV)
+  * [HyperOpt](https://github.com/hyperopt/hyperopt)
+  * [TPOT](https://github.com/EpistasisLab/tpot)
+  * [AutoSklearn](https://github.com/automl/auto-sklearn)
 
 #### Confidence
 
@@ -23,8 +22,26 @@ Conformal prediction
 
 #### Featurizers
 
-* Classical
+* Classical Morgan Fingerprint
 * Stacked CC signatures
 * Ensemble of CC signatures
 
+#### Train/test splits
+
+* Random
+* Stratified
+* Scaffold-based
+
+#### Model interpretation
+
+* Shapely analysis
+
+#### Negative sampling
+
+* Random
+* Diversity oriented and reliable negatives
+
+#### Parsers for tasks
 
+* [MoleculeNet](http://moleculenet.ai)
+* [ChEMBL](https://www.ebi.ac.uk/chembl/)