Crate cyanea_stats 

Statistical methods for the Cyanea bioinformatics ecosystem.

cyanea-stats provides pure-Rust implementations of common statistical methods used in bioinformatics workflows:

• Descriptive statistics — descriptive::describe, descriptive::mean, descriptive::variance, quantiles, IQR, MAD
• Ranking — rank::rank with multiple tie-breaking strategies
• Correlation — correlation::pearson, correlation::spearman, correlation::CorrelationMatrix
• Hypothesis testing — testing::t_test_one_sample, testing::t_test_two_sample, testing::mann_whitney_u
• Multiple testing correction — correction::bonferroni, correction::benjamini_hochberg
• Distributions — distribution::Normal, distribution::Poisson, plus numerical helpers distribution::erf, distribution::ln_gamma, distribution::betai

Example

use cyanea_stats::descriptive::describe;

let data = [2.0, 4.0, 4.0, 4.0, 5.0, 5.0, 7.0, 9.0];
let stats = describe(&data).unwrap();
assert_eq!(stats.count, 8);
assert!((stats.mean - 5.0).abs() < 1e-10);

Re-exports

pub use bayesian::Beta;

pub use bayesian::Dirichlet;

pub use bayesian::Gamma;

pub use bayesian::NormalConjugate;

pub use combinatorics::binomial;

pub use combinatorics::combinations;

pub use combinatorics::factorial;

pub use combinatorics::ln_binomial;

pub use combinatorics::ln_factorial;

pub use combinatorics::ln_multinomial;

pub use combinatorics::ln_permutations;

pub use combinatorics::multinomial;

pub use combinatorics::permutations;

pub use combinatorics::Combinations;

pub use correction::CorrectionMethod;

pub use correlation::CorrelationMatrix;

pub use descriptive::DescriptiveStats;

pub use diffexpr::DeGeneResult;

pub use diffexpr::DeMethod;

pub use diffexpr::DeResults;

pub use diffexpr::VolcanoPoint;

pub use enrichment::GeneSet;

pub use enrichment::GoAnnotation;

pub use enrichment::GoEnrichmentConfig;

pub use enrichment::GoEnrichmentResult;

pub use enrichment::GoNamespace;

pub use enrichment::GoTerm;

pub use enrichment::GseaResult;

pub use enrichment::OraResult;

pub use distribution::Binomial;

pub use distribution::ChiSquared;

pub use distribution::Distribution;

pub use distribution::FDistribution;

pub use distribution::NegativeBinomial;

pub use distribution::Normal;

pub use distribution::Poisson;

pub use popgen::AlleleFrequencies;

pub use popgen::DiversityStats;

pub use popgen::FstMethod;

pub use popgen::FstResult;

pub use popgen::HweResult;

pub use popgen::LdResult;

pub use popgen::TajimaD;

pub use rank::RankMethod;

pub use survival::CoxPhResult;

pub use survival::KmResult;

pub use survival::KmStep;

pub use survival::LogRankResult;

pub use testing::TestResult;

pub use diversity::alpha_diversity;

pub use diversity::alpha_rarefaction;

pub use diversity::bray_curtis;

pub use diversity::bray_curtis_matrix;

pub use diversity::chao1;

pub use diversity::hill_numbers;

pub use diversity::jaccard;

pub use diversity::jaccard_matrix;

pub use diversity::rarefaction_curve;

pub use diversity::shannon_index;

pub use diversity::simpson_index;

pub use diversity::weighted_jaccard;

pub use diversity::AlphaDiversity;

pub use multivariate::amova;

pub use multivariate::anosim;

pub use multivariate::bioenv;

pub use multivariate::mantel_test;

pub use multivariate::permanova;

pub use multivariate::AmovaResult;

pub use multivariate::AnosimResult;

pub use multivariate::BioenvResult;

pub use multivariate::MantelResult;

pub use multivariate::PermanovaResult;

pub use ordination::cca;

pub use ordination::nmds;

pub use ordination::pcoa;

pub use ordination::procrustes;

pub use ordination::rda;

pub use ordination::ConstrainedOrdinationResult;

pub use ordination::NmdsConfig;

pub use ordination::NmdsResult;

pub use ordination::PcoaResult;

pub use ordination::ProcrustesResult;

Modules

bayesian

Bayesian conjugate prior distributions.

combinatorics

Combinatorics utilities.

correction

Multiple testing correction.

correlation

Correlation analysis.

descriptive

Descriptive statistics for numeric data.

diffexpr

Differential expression analysis for count data.

distribution

Probability distributions and numerical helpers.

diversity

Alpha and beta diversity metrics for microbial ecology.

effect_size

Effect size measures for quantifying the magnitude of statistical effects.

enrichment

Gene set enrichment and over-representation analysis.

multivariate

Multivariate statistical tests for community ecology.

normalization

Count normalization for RNA-seq and related assays.

null_model

Wright-Fisher simulation and null model generators.

ordination

Ordination methods for multivariate ecological analysis.

popgen

Population genetics — allele frequencies, HWE, Fst, diversity, Tajima’s D, LD, genotype PCA.

rank

Ranking methods for numeric data.

reduction

Dimensionality reduction — Principal Component Analysis (PCA).

survival

Survival analysis — Kaplan-Meier estimator, log-rank test, Cox proportional hazards.

testing

Hypothesis testing.