jvecfor
Drop-in replacement for BiocNeighbors::findKNN using the jvecfor Java library, which builds on the jvector library to leverage the Java Vector API for portable SIMD acceleration across AVX2, AVX-512, and ARM NEON hardware. jvecfor/jvector implements HNSW-DiskANN approximate search and VP-tree exact search. The package achieves approximately 2x speedup over Annoy-based search at n >= 50K cells while returning output structurally identical to BiocNeighbors, making it suitable for seamless integration into existing Bioconductor single-cell workflows. Convenience wrappers delegate shared nearest-neighbor (SNN) and k-nearest-neighbor (KNN) graph construction to the bluster package.
README
jvecfor jvecfor — a fast R/Bioconductor package for k-nearest-neighbor (KNN) and shared-nearest-neighbor (SNN) graph construction in single-cell RNA-seq workflows. Drop-in replacement for BiocNeighbors::findKNN + bluster::makeSNNGraph, powered by a Java backend via jvector (HNSW-DiskANN), SIMD-accelerated with AVX2/AVX-512). About jvecfor is a R/Bioconductor package that exposes a clean R API for fast KNN search and graph construction, delegating heavy computation to the jvecfor Java library…
- Repository
- github.com/gkanogiannis/jvecfor
Source attribution
- Bioconductor — jvecfor
- GitHub — github.com/gkanogiannis/jvecfor
Related resources
A comprehensive toolkit that bridges popular Python-based immune repertoire analysis tools and Hugging Face protein language models into the R environment. Provides unified interfaces for TCR distance calculations (tcrdist3), sequence generation probability (OLGA), selection inference (soNNia), clustering (clusTCR), protein embeddings (ESM-2), metaclone discovery (metaclonotypist). Fully compatible with the scRepertoire and immApex ecosystem for single-cell immune repertoire analysis.
This package calculates a similarity coefficient using the fold changes of shared features (e.g. genes) among clusters of different samples/batches/datasets. The similarity coefficient is calculated using the dot-product (Hadamard product) of every pairwise combination of Fold Changes between a source cluster i of sample/dataset n and all the target clusters j in sample/dataset m
CHETAH (CHaracterization of cEll Types Aided by Hierarchical classification) is an accurate, selective and fast scRNA-seq classifier. Classification is guided by a reference dataset, preferentially also a scRNA-seq dataset. By hierarchical clustering of the reference data, CHETAH creates a classification tree that enables a step-wise, top-to-bottom classification. Using a novel stopping rule, CHETAH classifies the input cells to the cell types of the references and to "intermediate types": more general classifications that ended in an intermediate node of the tree.
ChromSCape - Chromatin landscape profiling for Single Cells - is a ready-to-launch user-friendly Shiny Application for the analysis of single-cell epigenomics datasets (scChIP-seq, scATAC-seq, scCUT&Tag, ...) from aligned data to differential analysis & gene set enrichment analysis. It is highly interactive, enables users to save their analysis and covers a wide range of analytical steps: QC, preprocessing, filtering, batch correction, dimensionality reduction, vizualisation, clustering, differential analysis and gene set analysis.
Pigengene package provides an efficient way to infer biological signatures from gene expression profiles. The signatures are independent from the underlying platform, e.g., the input can be microarray or RNA Seq data. It can even infer the signatures using data from one platform, and evaluate them on the other. Pigengene identifies the modules (clusters) of highly coexpressed genes using coexpression network analysis, summarizes the biological information of each module in an eigengene, learns a Bayesian network that models the probabilistic dependencies between modules, and builds a decision tree based on the expression of eigengenes.