Introduction

💦 Basic information

GSClassifier is an R-based comprehensive classification tool for subtypes modeling and personalized calling based on pure transcriptomics. It could be used for precision medicine, such as cancer diagnosis.
The inspiration of GSClassifier come from ImmuneSubtypeClassifier, an R package for classification of PanCancer immune subtypes based on the work of Gibbs et al. [1,2]
Lots of surprising features in GSClassifier as follows:
- Optimized for just one sample
- Available for modeling and calling of brand-new GEPs-based subtypes in any diseases (cancers)
- No limitation of the amount of gene signatures(≥1) or subtypes(≥2)
- Normalization insensitive due to the use of the individual gene rank matrix
- More ensemble and repeatable modeling process
- More optimizations in the parallel computing
- New useful functions as supplements
ATTENTION! In the future, there might be third-party contributors in GSClassifier platform, with some useful models for specific usages. If you use models provided by these people, you had better know more details as possible, including designs, data sources, destinations, training scripts and limitations of models, expecially those from studies under peer-review.
MORE PROJECTS:
- The Principle of GSClassifier: A eBook with more details about GSClassifier package
- luckyModel: Model ensemble for third-party lucky series, such GSClassifier

With XXX.Rmd files here, users could easily customize its code for practices and applications of the GSClassifier package.

Beautiful html webs for visulization of tutorial codes.

GSClassifier is released under the Apache-2.0 license. See LICENSE for details.

Thorsson V, Gibbs D L, Brown S D, et al. The Immune Landscape of Cancer[J]. Immunity, 2018, 48(4): 812-830 e814.
Gibbs D L J B. Robust classification of Immune Subtypes in Cancer[J]. 2020