plaid

PLAID computes single-sample enrichment scores for gene expression or proteomics data by calculating the average intensity of genes or proteins within gene sets.

Key Features:

• Ultra-fast computation: PLAID utilizes sparse matrix computation to achieve exceptional runtime efficiency and minimal memory requirements.
• Multi-algorithm integration: PLAID uniquely integrates the most widely used gene set scoring algorithms, enabling cross-validation with outstanding efficiency.
• Gene set score output: PLAID produces a gene set score matrix suitable for further analyses.

Scientific Applications:

• Single-cell transcriptomics: PLAID delivers highly accurate gene set scoring for single-cell gene expression profiles.
• Bulk transcriptomics: PLAID surpasses the performance of current methods for bulk RNA sequencing data.
• Proteomics: PLAID computes enrichment scores for proteomics datasets.
• Patient stratification: PLAID enables identification of unique molecular profiles to advance personalized medicine.
• Population biobanks: PLAID addresses computational inefficiencies in large-scale population datasets.

Methodology:

PLAID computes the gene set score as the average intensity of the genes or proteins in the gene set for each sample, utilizing sparse matrix computation for optimization.