https://github.com/unixjunkie/rankers
Reference implementation of the Vanishing Ranking Kernels (VRK) method
https://github.com/unixjunkie/rankers
applicability-domain bandwidth-selection cadd chemoinformatics classification hts kde lbvs ocaml-program qsar vrk
Last synced: about 2 months ago
JSON representation
Reference implementation of the Vanishing Ranking Kernels (VRK) method
- Host: GitHub
- URL: https://github.com/unixjunkie/rankers
- Owner: UnixJunkie
- License: other
- Created: 2019-11-14T09:18:02.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-01-05T03:15:44.000Z (over 2 years ago)
- Last Synced: 2025-03-27T19:39:35.250Z (2 months ago)
- Topics: applicability-domain, bandwidth-selection, cadd, chemoinformatics, classification, hts, kde, lbvs, ocaml-program, qsar, vrk
- Language: OCaml
- Size: 361 KB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# RanKers
Reference implementation of the Vanishing Ranking Kernels (VRK) method
[](https://doi.org/10.5281/zenodo.3546697)
# How to install the software
For beginners/non opam users:
download and execute the latest self-installer
shell script from (https://github.com/UnixJunkie/rankers/releases).
Then execute:
```
./rankers-1.0.0.sh ~/usr/rankers-1.0.0
```
This will create ~/usr/rankers-1.0.0/bin/rankers_bwmine, among other things
in the same directory.
For opam users:
```
opam install rankers
```
Do not hesitate to contact the author in case you have problems installing
or using the software or if you have any question.
# Example
*Example ROC curve on a hold-out test set. The test set had 38 active
molecules and 664 inactives. ROC AUC: 0.861; BEDROC AUC: 0.766; PR AUC: 0.678.
The ROC curve is in purple; the precision-recall (PR) curve in cyan. The
probability of activity given a raw score is the red curve.
The green curve is the number of actives divided by the
number of decoys as a function of the scores filtering threshold.*
Train and test a model:
```
rankers_bwmine -i data/tox21_nrar_ligands_std_rand_01.txt
```
Same, but using 16 cores :
```
rankers_bwmine -np 16 -i data/tox21_nrar_ligands_std_rand_01.txt
```
# Usage
```
rankers_bwmine -i
[-p ]: proportion of the (randomized) dataset
used to train (default=0.80)
[-k {uni|tri|epa|biw}]: kernel function choice (default=biw)
[-np ]: max number of processes (default=1)
[-o ]: write raw test scores to file
[--train ]: training set (overrides -p)
[--valid ]: validation set (overrides -p)
[--test ]: test set (overrides -p)
[-n ]: max number of optimization steps; default=150
[--capf ]: keep only fraction of decoys
[--capx ]: keep only X decoys per active
[--capi ]: limit total number of molecules
(but keep all actives)
[--seed : fix random seed]
[--pr]: use PR AUC instead of ROC AUC during optimization
[-kb ]: user-chosen kernel bandwidth
[--mcc-scan]: scan classif. threshold to maximize MCC
[--tap]: tap the train-valid-test partitions to disk
[-q|--quick]: exit early; just after model training
[--noplot]: turn off gnuplot
[-v]: verbose/debug mode
[-h|--help]: show this help message
```