Omics Data Integration Using Kernel Methods

Kernel-based methods are powerful methods for integrating heterogeneous types of data. mixKernel aims at providing methods to combine kernel for unsupervised exploratory analysis. Different solutions are provided to compute a meta-kernel, in a consensus way or in a way that best preserves the original topology of the data. mixKernel also integrates kernel PCA to visualize similarities between samples in a non linear space and from the multiple source point of view. Functions to assess and display important variables are also provided in the package. Jerome Mariette and Nathalie Villa-Vialaneix (2018) .

SOM Bound to Realize Euclidean and Relational Outputs

The stochastic (also called on-line) version of the Self-Organising Map (SOM) algorithm is provided. Different versions of the algorithm are implemented, for numeric and relational data and for contingency tables as described, respectively, in Kohonen (2001) , Olteanu & Villa-Vialaneix (2005) and Cottrell et al (2004) . The package also contains many plotting features (to help the user interpret the results) and a graphical user interface based on 'shiny'.

Log-Linear Poisson Graphical Model with Hot-Deck Multiple Imputation

Infer log-linear Poisson Graphical Model with an auxiliary data set. Hot-deck multiple imputation method is used to improve the reliability of the inference with an auxiliary dataset. Standard log-linear Poisson graphical model can also be used for the inference and the Stability Approach for Regularization Selection (StARS) is implemented to drive the selection of the regularization parameter. The method is fully described in .

Sparse Interval Sliced Inverse Regression

An interval fusion procedure for functional data in the semiparametric framework of SIR, as described in . Standard ridge and sparse SIR are also included in the package.

Adjacency-Constrained Clustering of a Block-Diagonal Similarity Matrix

Implements a constrained version of hierarchical agglomerative clustering, in which each observation is associated to a position, and only adjacent clusters can be merged. Typical application fields in bioinformatics include Genome-Wide Association Studies or Hi-C data analysis, where the similarity between items is a decreasing function of their genomic distance. Taking advantage of this feature, the implemented algorithm is time and memory efficient. This algorithm is described in Ambroise et al (2019) < https://almob.biomedcentral.com/articles/10.1186/s13015-019-0157-4>.

Weighted Cox-Regression for Nested Case-Control Data

Fit Cox proportional hazard models with a weighted partial likelihood. It handles one or multiple endpoints, additional matching and makes it possible to reuse controls for other endpoints.

Inverse Probability of Censoring Weights to Deal with Treatment Switch in Randomized Clinical Trials

Contains functions for formatting clinical trials data and implementing inverse probability of censoring weights to handle treatment switches when estimating causal treatment effect in randomized clinical trials.

Inference about the standardized mortality ratio when evaluating the effect of a screening program on survival.

The InferenceSMR package provides functions to make inference about the standardized mortality ratio (SMR) when evaluating the effect of a screening program. The package is based on methods described in Sasieni (2003) and Talbot et al. (2011).

Construct Consensus Genetic Maps and Estimate Recombination Rates

Construct consensus genetic maps with LPmerge, see Endelman and Plomion (2014) and model the relationship between physical distance and genetic distance using thin-plate regression splines, see Wood (2003) . Perform quality control on input data and visualise intermediate steps.

Spatial Oblique Decision Tree

SPODT is a spatial partitioning method based on oblique decision trees, in order to classify study area into zones of different risks, determining their boundaries