June 2025: Top 40 New R CRAN Packages, Featuring AI & Data Tools

Feedburner

In June, 123 new packages were added to CRAN, the comprehensive R archive network. From this collection, a selection of 40 notable packages has been highlighted across 21 diverse categories, including AI, Chess, Computational Methods, Data, Decision Analysis, Ecology, Epidemiology, Finance, Genomics, Linguistics, Machine Learning, Mathematics, Medical Statistics, Music Theory, Networks, Programming, Statistics, Time Series, Utilities, and Visualization.

AI

  • statlingua v0.1.0: Facilitates the transformation of complex statistical results into clear, context-aware natural language descriptions using Large Language Models (LLMs). It integrates with popular LLM providers such as OpenAI, Google AI Studio, and Anthropic.

  • vitals v0.1.0: Provides an R port of Inspect, a widely adopted Python framework for evaluating large language models. This package supports prompt engineering, tool usage, multi-turn dialogue, and model-graded evaluations, specifically designed for ellmer users to assess their LLM-based products.

Chess

  • chess2plyrs v0.3.0: Implements a chess program based on the Minimax chess engine, allowing users to create games and manage FEN (Forsyth-Edwards Notation) data.

Computational Methods

  • tvdenoising v1.0.0: Implements total variation denoising, a method for approximating noisy data sequences with piecewise constant functions that feature adaptively chosen breakpoints (Johnson, 2013).

  • wideRhino v1.0.2: Offers functions to construct canonical Variate Analysis biplots using Generalized Singular Value Decomposition. This is particularly useful when the number of samples is less than the number of variables (Gower et al., 2011; Edelman & Wang, 2020).

Data

  • avilistr v0.0.1: Provides easy access to the AviList Global Avian Checklist, a unified global bird taxonomy that harmonizes differences between major ornithological checklists (International Ornithological Committee, Clements, and BirdLife).

  • ecoteach v0.1.0: A collection of curated educational datasets for teaching ecology and agriculture concepts. It includes documented data from published scientific studies on wildlife monitoring, plant treatments, and ecological observations.

  • jpinfect v0.1.2: Offers functions to download and post-process infectious disease case data from the Japan Institute for Health Security.

  • LBDiscover v0.1.0: A suite of tools for literature-based discovery in biomedical research. It includes functions for retrieving scientific articles from PubMed and other NCBI databases, extracting biomedical entities, building co-occurrence networks, and applying various discovery models.

  • Rdatasets v0.0.1: Provides functions to search, download, and view documentation for thousands of datasets from R packages included in the Rdatasets archive, available in both CSV and Parquet formats.

Decision Analysis

  • RMCDA v0.3: Implements various methods to support multiple criteria decision making (MCDM), including AHP, TOPSIS, PROMETHEE, VIKOR, Stratified MCDM, and the Stratified Best–Worst Method (Najafi & Mirzaei, 2025).

Ecology

  • climodr v1.0.0: Provides tools to automate workflows for predictive climate mapping using climate station data and to create reproducible climate models (Meyer, 2019; Meyer, 2022).

  • movedesign v0.3.1: Offers a toolbox and a Shiny application to assist researchers in designing movement ecology studies. It focuses on estimating animal home range areas and fine-scale movement behaviors like speed and distance traveled (Silva et al., 2023).

Epidemiology

  • infectiousR v0.1.0: Provides functions to access real-time infectious disease data from the disease.sh API, including global COVID-19 data, vaccination coverage, and influenza-like illness data from the CDC. It also includes curated datasets on various infectious diseases.

  • rifttable v0.7.1: Automates the production of reproducible, presentation-ready tables for epidemiologists. Users can specify table designs with rows and columns defined by exposures, effect modifiers, and estimands (Rothman, 2017).

Finance

  • fEGarch v1.01: Provides functions to implement and fit a variety of short-memory and long-memory models from the broad family of exponential generalized autoregressive conditional heteroskedasticity (EGARCH) models, including MEGARCH, FIEGARCH, and FIMLog-GARCH.

Genomics

  • multiDEGGs 1.0.0: Offers functions to perform multi-omic differential network analysis, identifying differential interactions between molecular entities (genes, proteins, transcription factors) across provided omic datasets (Sciacca et al., 2023). It constructs comprehensive visualizations of differential networks for each dataset.

  • rsynthbio v2.0.0: Implements a wrapper for the Synthesize Bio API, enabling users to generate realistic gene expression data based on specified biological conditions. Researchers can access AI-generated transcriptomic data for various modalities, including bulk RNA-seq, single-cell RNA-seq, and microarray data.

Linguistics

  • tidynorm v0.3.0: Implements tidy speaker vowel normalization, offering generic functions for defining new normalization methods for points, format tracks, and Discrete Cosine Transform coefficients, along with convenience functions for established methods (Johnson, 2020; Lobanov, 1971; Watt & Fabricius, 2002).

Machine Learning

  • midr v0.5.0: Implements Maximum Interpretation Decomposition, a functional decomposition technique that provides a model-agnostic method for interpreting and explaining black-box predictive models by creating a globally interpretable surrogate model (Asashiba et al., 2025).

Mathematics

  • polarzonoid v0.1-2: Implements applications of the polar zonoid, a generalization of the polar zonohedron in 3D, and includes a root solver for trigonometric polynomials.

Medical Statistics

  • bbssr v1.0.2: Provides comprehensive tools for blinded sample size re-estimation in two-arm clinical trials with binary endpoints, allowing for adaptive sample size adjustments while maintaining statistical integrity and study blinding. It implements five exact statistical tests: Pearson chi-squared, Fisher exact, Fisher mid-p, Z-pooled exact unconditional, and Boschloo exact unconditional tests (Mehrotra et al., 2003; Kieser, 2020).

  • causens v0.0.3: Implements methods for causal sensitivity analysis to adjust for potential unmeasured confounders when working with observational data. Methods include those developed by Brumback et al. (2004), Li et al. (2011), and the Bayesian and Monte Carlo approaches of McCandless et al. (2017).

  • door v0.0.2: Offers functions for the design, analysis, and interpretation of clinical trials and other research studies based on patient-centric benefit-risk evaluation (Hamasaki & Evans, 2025).

Music Theory

  • musicMCT v0.2.0: Provides functions to analyze musical scales using Modal Color Theory (Sherrill, 2025), work with conventional music pitch theory and the continuous geometries of Callender et al. (2008), and identify structural properties of scales.

Networks

  • INetTool v0.1.1: Implements methods to model complex systems as a consensus network where nodes represent statistical units or observed variables, and edges represent distance metrics or correlations between units (Policastro et al., 2024).

Programming

  • putior v0.1.0: Provides tools for extracting and processing structured annotations from R and Python source files to facilitate workflow visualization. It scans files for annotations defining nodes, connections, and metadata within a data processing workflow, generating visual representations of data flows across polyglot software environments (Knuth, 1984).

  • quickr v0.1.0: Offers compiled R functions annotated with type and shape declarations for fast performance and robust runtime type checking. It supports both just-in-time (JIT) and ahead-of-time (AOT) compilation by lowering R code to FORTRAN.

Statistics

  • aamatch v0.3.7: Implements a simplified version of multivariate matching using propensity scores, near-exact matching, near-fine balance, and robust Mahalanobis distance matching (Rosenbaum, 2020).

  • bayesmsm v1.0.0: Implements Bayesian marginal structural models for causal effect estimation with time-varying treatment and confounding, including an extension for informative right censoring (Saarela, 2015).

  • BCD v0.1.1: Implements bivariate binomial, geometric, and Poisson distributions based on conditional specifications. It includes tools for data generation and goodness-of-fit testing for these three distribution families (Ghosh et al., 2025; Ghosh et al., 2023; Ghosh et al., 202?).

  • lognGPD v0.1.0: Provides functions to estimate a lognormal, generalized Pareto mixture model via the Expectation-Maximization algorithm, along with functions for random number simulation and density evaluation (Bee & Santi, 2025).

  • QuantilePeer v0.0.1: Provides functions to simulate and estimate peer effect models, including quantile-based specifications (Houndetoungan, 2025) and models with Constant Elasticity of Substitution (CES)-based social norms (Boucher et al., 2024).

  • riskdiff v0.2.1: Offers functions to calculate risk differences (or prevalence differences for cross-sectional data) using generalized linear models with automatic link function selection (Austin, 2011; Donoghoe & Marschner, 2018).

  • survextrap v1.0: Provides functions for survival analysis using Bayesian models for individual-level right-censored data. Hazard functions are modeled with M-splines, and prior distributions can be customized. Posterior distributions are estimated using Stan (Jackson, 2023).

  • unsum v0.2.0: Reconstructs all possible raw data that could have led to reported summary statistics, providing a wrapper for the Rust implementation of the CLOSURE algorithm.

Time Series

  • gseries v3.0.2: Provides functions to improve the coherence of time series data using methods described by Dagum & Cholette (2006).

Utilities

  • blocking v1.0.1: Offers blocking methods for record linkage and deduplication using approximate nearest neighbor algorithms. It includes functions to generate shingles from character strings, similarity vectors for record comparison, and evaluation metrics for assessing blocking performance (Papadakis et al., 2020; Steorts et al., 2014; Dasylva and Goussanou, 2021; Dasylva and Goussanou, 2022).

  • flir v0.5.0: Provides functions to identify and correct “lints” (inefficient code patterns) in R code.

Visualization

  • fractalforest v1.0.1: Provides functions to create and visualize fractal trees and fractal forests based on the Lindenmayer system (L-system) (Lindenmayer, 1968a; Lindenmayer, 1968b).

  • ggtime v0.1.0: Extends ggplot2 by implementing a grammar of temporal graphics and helper functions for visualizing temporal patterns in time series graphics, time plots, season plots, and seasonal sub-series plots.