A Two-Stage Exon Recognition Model Based on Synergetic Neural Network

Algorithm 1

Determination of initial exon region based on synergetic neural network.

(1) Let 𝑆 is a given gene sequence, 𝑆_start and 𝑆_end are the beginning and end of the

  sequence respectively, 𝑇₀ is throdthod of spectral values;

(2) Using 𝑍_Curve mapping converted gene sequence to the corresponding numeric sequence;

(3) Using fast Fourier transform to get spectral values 𝑅₁ and 𝑅₂ according to the formula (8);

(4) Calculating gene sequence order parameter:

     𝜉₁=𝑅₁𝑅₁+𝑅₂,  𝜉₂=𝑅₂𝑅₁+𝑅₂;

(5) Setting network parameter 𝜆_𝑘 and 𝐵,𝐶;

(6) Order parameter evolution according to formula (14);

(7) If 𝜉₁>𝑇₀ and 𝜉₂>𝑇₀, then [𝑆_start,𝑆_end] is recorded as a possible interal, and 𝑆 is divided

  equally into 𝑛 interals 𝑆₁,𝑆₂, …,  𝑆_𝑛, Repeat step 1 to step 7;

(8) End.