No packages match

KODAMA - Knowledge Discovery by Accuracy Maximization

Knowledge Discovery by Accuracy Maximization using KNN or SIMPLS followed by latent-space LDA. The portable source package vendors the MIT-licensed CPU implementation from the standalone 'kodama-cpp' library. Optional developer builds can link the same public interface to NVIDIA CUDA or Apple Metal backends. Reusable nearest-neighbor graphs, graph-aware visualization, preprocessing, and adapters for common single-cell containers are provided.

Last updated

softwareclassificationclusteringdimensionreductiongpupreprocessingvisualizationsinglecellspatialcpp

6.20 score 91 scripts 321 downloads

fastPLS - Fast Partial Least Squares for High-Dimensional Data

Fast implementations of partial least squares models for high-dimensional regression and classification. The 'fastPLS' software provides compiled implementations of PLS-SVD, a SIMPLS-family estimator, OPLS and kernel PLS, together with truncated singular value decomposition backends, discriminant classifiers, cross-validation utilities and optional 'CUDA' or Apple 'Metal' acceleration when the required system libraries are available. Compact latent prediction and memory-aware numerical routes support analyses with large predictor or multivariate-response matrices.

Last updated

softwaredimensionreductionclassificationregressiongenepredictiongeneexpressionmetabolomicssinglecellgpuopenblascpp

5.88 score 1 dependents 6 scripts 283 downloads

fibermargin - Categorical Mask and Spatial Label Refinement

Implements 'FiberMargin', a deterministic training-free operator for repairing categorical masks and spatial labels from coordinates and labels alone. Its primary multiclass operator uses rotated space-filling-curve charts and two-sided class enclosure at one fixed geometric transport range. A class-balanced, isolation-protected chart-disagreement rule provides pointwise repair decisions and audit scores. An auxiliary nearest-neighbour ballot handles binary masks. The 'C++' engine supports two- and three-dimensional coordinates, removes constant axes independently within each specimen, and reuses one deterministic CPU worker budget without nested process pools. Reproducible mask corruptions, planar and volumetric simulators, damage-aware evaluation, and compact licensed human dorsolateral prefrontal cortex and colorectal cancer benchmarks support assessment.

Last updated

cpp

4.78 score

faissR - FAISS-Backed Nearest Neighbours, kNN Models, and k-Means

Native nearest-neighbour search, k-nearest neighbour prediction, and k-means helpers for large dimensionality reduction workflows in high-throughput biological data analysis, including single-cell, flow cytometry, imaging, and mass spectrometry applications. Functional native builds require the FAISS C++ library, including CPU-only indexes, and can optionally use FAISS GPU indexes with NVIDIA cuVS integration or direct RAPIDS cuVS/CUDA indexes on NVIDIA machines. CPU-only systems do not need NVIDIA libraries, but NVIDIA CUDA/cuVS libraries are mandatory when a GPU-enabled build is explicitly requested. Unsupported WebAssembly and Bioconductor staging platforms may build diagnostic-only stubs that report the unavailable native functionality. Supervised kNN models use knn(Xtrain, Ytrain) and predict(), or knn(Xtrain, Ytrain, Xtest) for immediate prediction. Class probabilities are returned through predict(type = "prob") for kNN classification models.

Last updated

softwareinfrastructuregpusinglecellflowcytometrymassspectrometryimagingmassspectrometryproteomicsclusteringdimensionreductionclassificationfunctionalpredictionopenblasfortrancppopenmp

4.11 score

gpuinfo - Lightweight Hardware and GPU Compute Detection

Detects central processing unit and graphics processing unit hardware and reports the apparent availability of CUDA, Metal, ROCm, and OpenCL compute backends. Detection uses operating-system information and optional command-line utilities, without requiring a GPU framework, Python, or a vendor software development kit. Missing hardware, drivers, libraries, and utilities are handled safely.

Last updated

4.00 score

fastEmbedR - Native UMAP and Interpolation-Based t-SNE Embeddings

A native float32 UMAP implementation and a configurable interpolation-based t-SNE implementation for embeddings from data matrices or precomputed nearest-neighbor indices and distances. One-call workflows use package-native CPU HNSW and Apple Metal exact or IVF-Flat search. Optional CUDA support links directly to FAISS GPU and the RAPIDS cuVS C API while retaining nearest-neighbor results on the device. Preprocessing, graph or affinity construction, fixed-reference transform, and layout optimization use native code with explicit CPU, Metal, and CUDA backend reporting. UMAP exposes neighborhood, metric, graph mode, backend, seed, and preprocessing controls, while optimizer controls such as epochs, minimum distance, spread, learning rate, repulsion, and negative sampling follow a recorded release policy rather than a general-purpose sweep API. Optional graph utilities support downstream Louvain, Leiden, and Walktrap community detection.

Last updated

softwareinfrastructurepreprocessingdimensionreductionvisualizationclusteringsinglecellflowcytometrygeneexpressiongpucpp

3.78 score

clinical - Clinical Metadata Exploration and Feature Matching

A collection of tools to easily analyze clinical data, including functions for correlation analysis, and statistical testing. The package facilitates the integration of clinical metadata with other omics layers, enabling exploration of quantitative variables. It also includes the utility for frequency matching samples across a dataset based on patient variables.

Last updated

3.70 score 1 stars 5 scripts 313 downloads

musicNMR - Conversion of Nuclear Magnetic Resonance Spectra in Audio Files

A collection of functions for converting and visualization the free induction decay of mono dimensional nuclear magnetic resonance (NMR) spectra into an audio file. It facilitates the conversion of Bruker datasets in files WAV. The sound of NMR signals could provide an alternative to the current representation of the individual metabolic fingerprint and supply equally significant information. The package includes also NMR spectra of the urine samples provided by four healthy donors. Based on Cacciatore S, Saccenti E, Piccioli M. Hypothesis: the sound of the individual metabolic phenotype? Acoustic detection of NMR experiments. OMICS. 2015;19(3):147-56. <doi:10.1089/omi.2014.0131>.

Last updated

1.00 score 4 scripts 180 downloads