A compiled accelerator for biological cell signaling simulations

The simulation of large systems of biochemical reactions is a key part of research into molecular signaling and information processing in biological cells. However, it can be impractical because many relevant reactions are modeled as stochastic, discrete event processes, and the complexity of the computing task scales with the number of discrete events in a simulation. Traditionally, such simulations are computed on general purpose CPUs, and sometimes in networks of such processors. We show that an alternative algorithm to the conventional approaches based on the Gillespie algorithm reveals a fine-grained parallel structure that is amenable to realization in FPGA hardware. A method is shown for compiling biochemical reaction systems into corresponding Verilog descriptions of simulators that employ this alternative algorithm. We describe a preliminary implementation of such a compiled accelerator that demonstrates the performance of this approach, achieving an initial performance that is 20 times faster than a competing general purpose CPU.