KBoost

KBoost reconstructs gene regulatory networks from gene expression data using kernel PCA regression, boosting, and Bayesian model averaging for fast and accurate inference of transcription factor-target relationships.

Key Features:

• Kernel PCA regression: KBoost employs kernel principal component analysis regression as a core component of its network reconstruction algorithm.
• Boosting: KBoost incorporates boosting to improve prediction accuracy in regulatory network inference.
• Bayesian model averaging: KBoost uses Bayesian model averaging to combine multiple models and enhance robustness of network predictions.
• Prior network integration: KBoost can incorporate a prior network built on previously known transcription factor targets to integrate existing biological knowledge.

Scientific Applications:

• Gene regulatory network reconstruction: KBoost infers gene regulatory networks from gene expression data to understand biological processes.
• Transcription factor activity inference: KBoost reconstructs transcription factor activity to elucidate regulatory mechanisms underlying biological processes.

Methodology:

KBoost uses kernel PCA regression, boosting, and Bayesian model averaging. The algorithm can incorporate a prior network based on previously known transcription factor targets.