Variable Penalty Dynamic Time Warping (VPdtw) for aligning chromatographic signals. With an appropriate penalty this method performs good alignment of chromatographic data without deforming the peaks (Clifford, D., Stone, G., Montoliu, I., Rezzi S., Martin F., Guy P., Bruce S., and Kochhar S.(2009) <doi:10.1021/ac802041e>; Clifford, D. and Stone, G. (2012) <doi:10.18637/jss.v047.i08>).

Implementation of Azure DevOps <https://azure.microsoft.com/> API calls. It enables the extraction of information about repositories, build and release definitions and individual releases. It also helps create repositories and work items within a project without logging into Azure DevOps'. There is the ability to use any API service with a shell for any non-predefined call.

Fits hierarchical regularized regression models to incorporate potentially informative external data, Weaver and Lewinger (2019) <doi:10.21105/joss.01761>. Utilizes coordinate descent to efficiently fit regularized regression models both with and without external information with the most common penalties used in practice (i.e. ridge, lasso, elastic net). Support for standard R matrices, sparse matrices and big.matrix objects.

This package provides PLUS-derived extensions for positive and unlabeled (PU) learning from unbalanced cases and sparse structures, based on Zhou et al. (2022) <doi:10.1371/journal.pcbi.1009956>. Iteratively relabels unlabeled observations via penalised logistic regression and pseudo-label updates, then refits a final sparse model. Includes weighted bootstrap sampling, convergence diagnostics, prediction, coefficient extraction, and assessment utilities.

T (extent of the primary tumor), N (absence or presence and extent of regional lymph node metastasis) and M (absence or presence of distant metastasis) are three components to describe the anatomical tumor extent. TNM stage is important in treatment decision-making and outcome predicting. The existing oropharyngeal Cancer (OPC) TNM stages have not made distinction of the two sub sites of Human papillomavirus positive (HPV+) and Human papillomavirus negative (HPV-) diseases. We developed novel criteria to assess performance of the TNM stage grouping schemes based on parametric modeling adjusting on important clinical factors. These criteria evaluate the TNM stage grouping scheme in five different measures: hazard consistency, hazard discrimination, explained variation, likelihood difference, and balance. The methods are described in Xu, W., et al. (2015) <https://www.austinpublishinggroup.com/biometrics/fulltext/biometrics-v2-id1014.php>.

This package provides colour choice in information visualisation. It important in order to avoid being mislead by inherent bias in the used colour palette. This package provides access to the perceptually uniform and colour-blindness friendly palettes developed by Fabio Crameri and released under the "Scientific Colour-Maps" moniker. The package contains 24 different palettes and includes both diverging and sequential types.

This package provides a production-grade AI toolkit for R featuring a layered architecture (Specification, Utilities, Providers, Core), request interception support, robust error handling with exponential retry delays, support for multiple AI model providers (OpenAI, Anthropic, etc.), local small language model inference, distributed MCP ecosystem, multi-agent orchestration, progressive knowledge loading through skills, and a global skill store for sharing AI capabilities.

This package contains various tools for working with and evaluating cross-validated area under the ROC curve (AUC) estimators. The primary functions of the package are ci.cvAUC and ci.pooled.cvAUC, which report cross-validated AUC and compute confidence intervals for cross-validated AUC estimates based on influence curves for i.i.d. and pooled repeated measures data, respectively.

This package provides resampling procedures to assess the stability of selected variables with additional finite sample error control for high-dimensional variable selection procedures such as Lasso or boosting. Both, standard stability selection (Meinshausen & Buhlmann, 2010) and complementary pairs stability selection with improved error bounds (Shah & Samworth, 2013) are implemented. The package can be combined with arbitrary user specified variable selection approaches.

This package provides methods to detect the differential composition abundances between conditions in singel-cell RNA-seq experiments, with or without replicates. It aims to correct bias introduced by missclaisification and enable controlling of confounding covariates. To avoid the influence of proportion change from big cell types, DCATS can use either total cell number or specific reference group as normalization term.

This package provides diagnostics for assessing genomic DNA contamination in RNA-seq data, as well as plots representing these diagnostics. Moreover, the package can be used to get an insight into the strand library protocol used and, in case of strand-specific libraries, the strandedness of the data. Furthermore, it provides functionality to filter out reads of potential gDNA origin.

This package provides methods to perform trajectory analysis based on a minimum spanning tree constructed from cluster centroids. Computes pseudotemporal cell orderings by mapping cells in each cluster (or new cells) to the closest edge in the tree. Uses linear modelling to identify differentially expressed genes along each path through the tree. Several plotting and interactive visualization functions are also implemented.

Using a Bayesian estimation procedure, this package fits linear quantile regression models such as linear quantile models, linear quantile mixed models, quantile regression joint models for time-to-event and longitudinal data. The estimation procedure is based on the asymmetric Laplace distribution and the JAGS software is used to get posterior samples (Yang, Luo, DeSantis (2019) <doi:10.1177/0962280218784757>).

This package implements collaborative filtering methods for recommendation systems based on user-item interaction data. Supports both explicit feedback (ratings) and implicit feedback (consumption). The package uses efficient sparse matrix representations and provides incremental updates for users, items, and similarity structures through an R6 class-based architecture. See Aggarwal (2016) <doi:10.1007/978-3-319-29659-3> for an overview.

Implementations of the family of map() functions with frequent saving of the intermediate results. The contained functions let you start the evaluation of the iterations where you stopped (reading the already evaluated ones from cache), and work with the currently evaluated iterations while remaining ones are running in a background job. Parallel computing is also easier with the workers parameter.

Detects regions of differential abundance in single-cell transcriptomic data by applying a pre-trained neural network model to the labels of each cell's nearest neighbours. Tests for both local and global differential abundance, controlling the false discovery rate with the Benjamini-Yekutieli procedure. The method is described in Hall and Castellano (2023) <doi:10.1101/2023.05.05.539427>.

Standardised mapping of dates onto a discrete annual grid, together with exact date and duration arithmetic. This matters when the primary unit is years but the input data uses dates. Examples are actuarial mortality experience analysis and valuation of life assurance and annuities, for which mortality rates are defined per year but experience and valuation data are typically defined using dates.

Interact with the FRED API, <https://fred.stlouisfed.org/docs/api/fred/>, to fetch observations across economic series; find information about different economic sources, releases, series, etc.; conduct searches by series name, attributes, or tags; and determine the latest updates. Includes functions for creating panels of related variables with minimal effort and datasets containing data sources, releases, and popular FRED tags.

This package provides high-performance online changepoint detection in univariate and multivariate data streams. Implements efficient C++ backends for the focus', md-focus and np-focus algorithms, with an R interface for real-time monitoring and offline analysis. The package bundles code from Qhull <http://www.qhull.org/>, by C. B. Barber and The Geometry Center. See inst/COPYRIGHTS for details.

Contingency Tables are a pain to work with when you want to run regressions. This package takes them, flattens them into a long data frame, so you can more easily analyse them! As well, you can calculate other related statistics. All of this is done so in a tidy manner, so it should tie in nicely with tidyverse series of packages.

Data-driven approach for arriving at person-specific time series models. The method first identifies which relations replicate across the majority of individuals to detect signal from noise. These group-level relations are then used as a foundation for starting the search for person-specific (or individual-level) relations. See Gates & Molenaar (2012) <doi:10.1016/j.neuroimage.2012.06.026>.

Instrumental variable (IV) estimators for homogeneous and heterogeneous treatment effects with efficient machine learning instruments. The estimators are based on double/debiased machine learning allowing for nonlinear and potentially high-dimensional control variables. Details can be found in Scheidegger, Guo and Bühlmann (2025) "Inference for heterogeneous treatment effects with efficient instruments and machine learning" <doi:10.48550/arXiv.2503.03530>.

This package provides a gridded classification of weather types by applying the Jenkinson and Collison classification. For a given region (it can be either local region or the whole map),it computes at each grid the 11 weather types during the period considered for the analysis. See Otero et al., (2017) <doi:10.1007/s00382-017-3705-y> for more information.

This package provides an efficient implementation of univariate local polynomial kernel density estimators that can handle bounded, discrete, and zero-inflated data. See Geenens and Wang (2018) <doi:10.48550/arXiv.1602.04862>, Geenens (2014) <doi:10.48550/arXiv.1303.4121>, Nagler (2018a) <doi:10.48550/arXiv.1704.07457>, Nagler (2018b) <doi:10.48550/arXiv.1705.05431>.