Implementation of Kernelized score functions and other semi-supervised learning algorithms for node label ranking in biomolecular networks. RANKS can be easily applied to a large set of different relevant problems in computational biology, ranging from automatic protein function prediction, to gene disease prioritization and drug repositioning, and more in general to any bioinformatics problem that can be formalized as a node label ranking problem in a graph. The modular nature of the implementation allows to experiment with different score functions and kernels and to easily compare the results with baseline network-based methods such as label propagation and random walk algorithms, as well as to enlarge the algorithmic scheme by adding novel user-defined score functions and kernels.
|Author||Giorgio Valentini -- AnacletoLab, Dipartimento di Informatica, Universita' degli Studi di Milano|
|Date of publication||2015-12-10 10:04:15|
|Maintainer||Giorgio Valentini <firstname.lastname@example.org>|
|License||GPL (>= 2)|
do.GBA: GBA cross-validation experiments with multiple classes
do.loo.RANKS: RANKS leave-one-out experiments with multiple classes
do.RANKS: RANKS cross-validation experiments with multiple classes
do.RW: Random walk cross-validation experiments with multiple...
do.RWR: Random walk with restart cross-validation experiments with...
find.optimal.thresh.cv: Function to find the optimal RANKS score thereshold
GBAmax: Guilt By Association (GBA) using the maximum rule
GBAsum: Guilt By Association (GBA) using the sum rule
kernel.functions: Kernel functions
ker.score.classifier.cv: Multiple cross-validation with RANKS for classification
ker.score.classifier.holdout: RANKS held-out procedure for a single class
ker.score.cv: RANKS cross-validation for a single class
label.prop: Label propagation
multiple.ker.score.cv: RANKS multiple cross-validation for a single class
multiple.ker.score.thresh.cv: Function for RANKS multiple cross-validation and optimal...
multiple.RW.cv: Random walk, GBA and labelprop multiple cross-validation for...
RANKS-package: Ranking of Nodes with Kernelized Score Functions
RW: Random walk on a graph
RW.cv: Random walk, GBA and labelprop cross-validation for a single...
rw.kernel-methods: Random walk kernel
RWR: Random walk with Restart on a graph
score.multiple.vertex-methods: Multiple vertex score functions
score.single.vertex-methods: Single vertex score functions
Utilities: Utility functions