This package provides composable optimization strategies for maximum likelihood estimation (MLE). Solvers are first-class functions that combine via sequential chaining, parallel racing, and random restarts. Implements gradient ascent, Newton-Raphson, quasi-Newton (BFGS), and derivative-free methods with support for constrained optimization and tracing. Returns mle objects compatible with algebraic.mle for downstream analysis. Methods based on Nocedal J, Wright SJ (2006) "Numerical Optimization" <doi:10.1007/978-0-387-40065-5>.

R package for transcriptional analysis based on transcriptograms, a method to analyze transcriptomes that projects expression values on a set of ordered proteins, arranged such that the probability that gene products participate in the same metabolic pathway exponentially decreases with the increase of the distance between two proteins of the ordering. Transcriptograms are, hence, genome wide gene expression profiles that provide a global view for the cellular metabolism, while indicating gene sets whose expressions are altered.

This package implements the Block-wise Rank in Similarity Graph Edge-count test (BRISE), a rank-based two-sample test designed for block-wise missing data. The method constructs (pattern) pair-wise similarity graphs and derives quadratic test statistics with asymptotic chi-square distribution or permutation-based p-values. It provides both vectorized and congregated versions for flexible inference. The methodology is described in Zhang, Liang, Maile, and Zhou (2025) <doi:10.48550/arXiv.2508.17411>.

Imports conversation transcripts into R, concatenates them into a single dataframe appending event identifiers, cleans and formats the text, then yokes user-specified psycholinguistic database values to each word. ConversationAlign then computes alignment indices between two interlocutors across each transcript for >40 possible semantic, lexical, and affective dimensions. In addition to alignment, ConversationAlign also produces a table of analytics (e.g., token count, type-token-ratio) in a summary table describing your particular text corpus.

Implementation of the Future API <doi:10.32614/RJ-2021-048> on top of the batchtools package. This allows you to process futures, as defined by the future package, in parallel out of the box, not only on your local machine or ad-hoc cluster of machines, but also via high-performance compute ('HPC') job schedulers such as LSF', OpenLava', Slurm', SGE', and TORQUE / PBS', e.g. y <- future.apply::future_lapply(files, FUN = process)'.

Inference of ligand-receptor (L-R) interactions from single-cell expression (transcriptomics/proteomics) data. SingleCellSignalR v2 inferences rely on the statistical model we introduced in the BulkSignalR package as well as the original SingleCellSignalR LR-score (both are available). SingleCellSignalR v2 can be regarded as a wrapper to BulkSignalR fundamental classes. This also enables v2 users to work with any species, whereas only Mus musculus & Homo sapiens were available before in SingleCellSignalR v1.

Extensions of "hyper data frame" (from package spatstat.geom') with a grouping structure. The author has retired from academic research. Accordingly, this package should not be considered a validated tool for use in peer-reviewed publications or as the basis for grant applications. Backward compatibility with user-code published in <doi:10.1093/bioinformatics/btaf430> is not maintained in versions >= 0.4.0 (June 2026) of this package. The authors of those publications are the appropriate contacts for reproducibility inquiries.

Testing for trajectory presence and heterogeneity on multivariate data. Two statistical methods (Tenha & Song 2022) <doi:10.1371/journal.pcbi.1009829> are implemented. The tree dimension test quantifies the statistical evidence for trajectory presence. The subset specificity measure summarizes pattern heterogeneity using the minimum subtree cover. There is no user tunable parameters for either method. Examples are included to illustrate how to use the methods on single-cell data for studying gene and pathway expression dynamics and pathway expression specificity.

The aim is to take in data.frame inputs and utilises methods, such as recursive feature engineering, to enable the features to be removed. What this does differently from the other packages, is that it gives you the choice to remove the variables manually, or it automated this process. Feature selection is a concept in machine learning, and statistical pipelines, whereby unimportant, or less predictive variables are eliminated from the analysis, see Boughaci (2018) <doi:10.1007/s40595-018-0107-y>.

Implement tableGrob object as a clickable image map. The clickableImageMap package is designed to be more convenient and more configurable than the edit() function. Limitations that I have encountered with edit() are cannot control (1) positioning (2) size (3) appearance and formatting of fonts In contrast, when the table is implemented as a tableGrob', all of these features are controllable. In particular, the ggplot2 grid system allows exact positioning of the table relative to other graphics etc.

This package provides tools for downloading and processing data on the Brazilian Amazon region from a variety of official sources. Covers environmental, agricultural, economic, and social indicators, including deforestation and land use, greenhouse gas emissions, climate, agricultural and livestock production, mining, energy, and foreign trade, from providers such as the Brazilian Institute of Geography and Statistics (IBGE), the National Institute for Space Research (INPE), and MapBiomas. Data are cleaned and standardized for analysis at the municipality, state, and regional levels.

Systematic conservation prioritization with robust optimization techniques. This is important because conservation prioritizations typically only consider the most likely outcome associated with a conservation action (e.g., establishing a protected area will safeguard a threatened species population) and fail to consider other outcomes and their consequences for meeting conservation objectives. By extending the prioritizr package, this package can be used to generate conservation prioritizations that account of uncertainty in the climate change scenario projections, species distribution models, ecosystem service models, and measurement errors. In particular, prioritizations can be generated to be fully robust to uncertainty by minimizing (or maximizing) objectives under the worst possible outcome. Since reducing the uncertainty associated with achieving conservation objectives may sacrifice other objectives (e.g., minimizing protected area implementation costs), prioritizations can also be generated to be partially robust based on a specified confidence level parameter. Partially robust prioritizations can be generated based on the chance constrained programming problem (Charnes & Cooper 1959, <doi:10.1287/mnsc.6.1.73>) and the conditional value-at-risk problem (Rockafellar & Uryasev 2000, <doi:10.21314/JOR.2000.038>).

The XCB util module provides a number of libraries which sit on top of libxcb, the core X protocol library, and some of the extension libraries. These experimental libraries provide convenience functions and interfaces which make the raw X protocol more usable. Some of the libraries also provide client-side code which is not strictly part of the X protocol but which has traditionally been provided by Xlib.

The XCB util-renderutil module provides the following library:

- renderutil: Convenience functions for the Render extension.

The packages provides position specific weight matrices (PWMs) for 303 human serine/threonine and 93 tyrosine kinases originally published in Johnson et al. 2023 (doi:10.1038/s41586-022-05575-3) and Yaron-Barir et al. 2024 (doi:10.1038/s41586-024-07407-y). The package includes basic functionality to score user provided phosphosites. It also includes pre-computed PWM scores ("background scores") for a large collection of curated human phosphosites which can be used to rank PWM scores relative to the background scores ("percentile rank").

This package provides a comprehensive toolkit for discovering differential and difference equations from empirical time series data using symbolic regression. The package implements a complete workflow from data preprocessing (including Total Variation Regularized differentiation for noisy economic data), visual exploration of dynamical structure, and symbolic equation discovery via genetic algorithms. It leverages a high-performance Julia backend ('SymbolicRegression.jl') to provide industrial-grade robustness, physics-informed constraints, and rigorous out-of-sample validation. Designed for economists, physicists, and researchers studying dynamical systems from observational data.

With this package you can build a Storable instance of a record type from Storable instances of its elements in an elegant way. It does not do any magic, just a bit arithmetic to compute the right offsets, that would be otherwise done manually or by a preprocessor like C2HS. There is no guarantee that the generated memory layout is compatible with that of a corresponding C struct. However, the module generates the smallest layout that is possible with respect to the alignment of the record elements.

Inference methods for factor copula models for continuous data in Krupskii and Joe (2013) <doi:10.1016/j.jmva.2013.05.001>, Krupskii and Joe (2015) <doi:10.1016/j.jmva.2014.11.002>, Fan and Joe (2024) <doi:10.1016/j.jmva.2023.105263>, one factor truncated vine models in Joe (2018) <doi:10.1002/cjs.11481>, and Gaussian oblique factor models. Functions for computing tail-weighted dependence measures in Lee, Joe and Krupskii (2018) <doi:10.1080/10485252.2017.1407414> and estimating tail dependence parameter.

Generative Adversarial Networks are applied to generate generative data for a data source. A generative model consisting of a generator and a discriminator network is trained. During iterative training the distribution of generated data is converging to that of the data source. Direct applications of generative data are the created functions for data evaluation, missing data completion and data classification. A software service for accelerated training of generative models on graphics processing units is available. Reference: Goodfellow et al. (2014) <doi:10.48550/arXiv.1406.2661>.

Interactive visualization of effects, response functions and marginal effects for different kinds of regression models. In this version linear regression models, generalized linear models, generalized additive models and linear mixed-effects models are supported. Major features are the interactive approach and the handling of the effects of categorical covariates: if two or more factors are used as covariates every combination of the levels of each factor is treated separately. The automatic calculation of marginal effects and a number of possibilities to customize the graphical output are useful features as well.

Nested Partially Balanced Bipartite Block (NPBBB) designs involve two levels of blocking: (i) The block design (ignoring sub-block classification) serves as a partially balanced bipartite block (PBBB) design, and (ii) The sub-block design (ignoring block classification) also serves as a PBBB design. More details on constructions of the PBBB designs and their characterization properties are available in Vinayaka et al.(2023) <doi:10.1080/03610926.2023.2251623>. This package calculates A-efficiency values for both block and sub-block structures, along with all parameters of a given NPBBB design.

This package implements Surprisal analysis for gene expression data such as RNA-seq or microarray experiments. Surprisal analysis is an information-theoretic method that decomposes gene expression data into a baseline state and constraint-associated deviations, capturing coordinated gene expression patterns under different biological conditions. References: Kravchenko-Balasha N. et al. (2014) <doi:10.1371/journal.pone.0108549>. Zadran S. et al. (2014) <doi:10.1073/pnas.1414714111>. Su Y. et al. (2019) <doi:10.1371/journal.pcbi.1007034>. Bogaert K. A. et al. (2018) <doi:10.1371/journal.pone.0195142>.

The stdlib-random package provides a stable and compiler-independent implementation of all the PRNGs used in the Random module. Those PRNGs are available in the various libraries: - stdlib-random.v3: OCaml 3.07 to 3.11 PRNG - stdlib-random.v4: OCaml 3.12 to 4.14 PRNG - stdlib-random.v5: current OCaml 5.0 PRNG - stdlib-random.v5o: pure OCaml version of the OCaml 5 PRNG All those libraries can be used together and the signature of their Random$n module has been extended to the latest signature whenever possible.

This package provides a set of tools to analyze and visualize the relationships between host-associated microbiomes of hybrid organisms and those of their progenitor species. Though not necessary, installing the microViz package is recommended as a check for phyloseq objects. To install microViz from R Universe use the following command: install.packages("microViz", repos = c(davidbarnett = "https://david-barnett.r-universe.dev", getOption("repos"))). To install microViz from GitHub use the following commands: install.packages("devtools") followed by devtools::install_github("david-barnett/microViz").

This package implements the methodology of Huling, Smith, and Chen (2020) <doi:10.1080/01621459.2020.1801449>, which allows for subgroup identification for semi-continuous outcomes by estimating individualized treatment rules. It uses a two-part modeling framework to handle semi-continuous data by separately modeling the positive part of the outcome and an indicator of whether each outcome is positive, but still results in a single treatment rule. High dimensional data is handled with a cooperative lasso penalty, which encourages the coefficients in the two models to have the same sign.