|
# Supervised machine learning
|
|
# Supervised machine learning
|
|
|
|
|
|
We have developed a supervised machine learning tool called TargetMate.
|
|
We have developed a supervised machine learning tool called Target Mate (TM). Code for this tool can be found in the CC repository: `tool/targetmate/`.
|
|
|
|
|
|
|
|
TM uses CC signatures as features, similar to the use of structural descriptors used in structure-activity relationship (SAR) studies.
|
|
|
|
|
|
#### Machine-learning problem
|
|
#### Machine-learning problem
|
|
|
|
|
|
* Binary classification
|
|
* [x] Binary classification
|
|
* Single-output regression
|
|
* [ ] Single-output regression
|
|
|
|
|
|
#### Algorithms
|
|
#### Algorithms
|
|
|
|
|
... | @@ -32,9 +34,9 @@ Conformal prediction |
... | @@ -32,9 +34,9 @@ Conformal prediction |
|
* Stratified
|
|
* Stratified
|
|
* Scaffold-based
|
|
* Scaffold-based
|
|
|
|
|
|
#### Model interpretation
|
|
#### Model explanation
|
|
|
|
|
|
* Shapely analysis
|
|
* [Shapley analysis](https://github.com/slundberg/shap)
|
|
|
|
|
|
#### Negative sampling
|
|
#### Negative sampling
|
|
|
|
|
... | | ... | |