FastTENET

FastTENET accelerates the reconstruction of gene regulatory networks from single-cell RNA sequencing data by implementing an array-computing version of the TENET algorithm optimized for manycore processors such as GPUs.

Key Features:

• GPU Acceleration: FastTENET achieves up to 973× performance improvement over the original TENET algorithm through optimization for manycore processors.
• Array Computing: FastTENET counts the unique patterns of joint events to compute transfer entropy based on array computing.

Scientific Applications:

• Gene Regulatory Network Reconstruction: FastTENET reconstructs gene regulatory networks from single-cell RNA sequencing data using transfer entropy.

Methodology:

FastTENET implements an array-computing version of the TENET algorithm that counts unique patterns of joint events to compute transfer entropy, optimized for acceleration on manycore processors such as GPUs.