Nimbus is a ruby gem implementing random forest algorithm for genomic selection contexts.
http://www.nimbusgem.org
Presentation from the EAAP 2011 conference in Stavanger, Norway.
4. The Problem
Massive amount of information from high troughput genotyping platforms.
Need to extract knowledge from large, noisy, redundant, missing and fuzzy data.
5. The Problem
Massive amount of information from high troughput genotyping platforms.
Need to extract knowledge from large, noisy, redundant, missing and fuzzy data.
Massive amount of information consumes the attention of its recipients.
We need to allocate that attention efciently.
7. Why Random Forest?
Using Machine Learning techniques we can extract hidden relationships that
exist in these huge volumes of data and do not follow a particular parametric
design.
8. Why Random Forest?
Using Machine Learning techniques we can extract hidden relationships that
exist in these huge volumes of data and do not follow a particular parametric
design.
Random Forest have desirable statistical properties.
9. Why Random Forest?
Using Machine Learning techniques we can extract hidden relationships that
exist in these huge volumes of data and do not follow a particular parametric
design.
Random Forest have desirable statistical properties.
Random Forest scales well computationally.
10. Why Random Forest?
Using Machine Learning techniques we can extract hidden relationships that
exist in these huge volumes of data and do not follow a particular parametric
design.
Random Forest have desirable statistical properties.
Random Forest scales well computationally.
Random Forest performs extremely well in a variety of possible complex
domains (Breiman, 2001; Gonzalez-Recio & Forni, 2011).
12. The Algorithm
Ensemble methods:
- Combination of diferent methods (usually simple models).
- They have very good predictive ability because use additivity of models performances.
Based on Classifcation And Regression Trees (CART).
Use Randomization and Bagging.
Performs Feature Subset Selection.
Convenient for classifcation problems.
Fast computation.
Simple interpretation of results for human minds.
Previous work in genome-wide prediction (Gonzalez-Recio and Forni, 2011)
13. The Algorithm
Perform bootstrap on data: Ψ* = (y, X)
Build a CART ( fi (y, X) = ht (x) ) using only mtry proportion of SNPs in each node.
Repeat M times to reduce residuals by a factor of M.
Average estimates c0 = μ ; ci = 1/M
14. The Algorithm
Classifcation and regression trees:
Let Ψ = (y, X) be a set of data, with
y = vector of phenotypes (response variables)
X = (x1, x2) = matrix of features
y1 x11 x12
… … ...
yi xi1 xi2
… … ...
yn xn1 xn2
22. Nimbus library
Features, use cases:
Training of a prediction forest
Using a training set of individuals
Nimbus creates a reutilizable forest
Generalization error are computed for every tree in the forest
Nimbus calculates SNP importances
Genomic Prediction of a testing sample
Using a new trained forest
Using a custom/reused forest, specif ed via conf g.yml
i i