Salp-J Colony Optimization-based advanced hybrid ensemble deep predictor with LSTM for protein structure prediction

Abstract

Protein structure prediction (PSP) is a key concern in computational biology, which is considered a challenging task that is vital to determine the structure and the protein function since each protein possesses a definite shape, whereas the protein secondary structure prediction (PSSP) is the foundation for three-dimensional PSP. An Advanced hybrid ensemble deep predictor is utilized for predicting the structure of a protein using Long-Short Term Memory (LSTM), in which the performance of the predictor is improved for obtaining the features through the Salp-J Colony Optimization, which is developed by integrating the features of three optimizations the exploration behavior of Ulmaris, the immune system of virus colony and the teamwork of salp for solution update that helps to predict the accurate protein structure. The proposed method achieved the value of 99.1% accuracy, 99.5% sensitivity, 98.85% specificity, and 0.9% error at the 80% of training percentage 90 using CullPDB. Similarly, in Protein Net, the attained value of accuracy is 97.27%, sensitivity is 98.13%, specificity is 97%, and error is 2.7% concerning training percentage 90%.

Communicated by Ramaswamy H. Sarma

Keywords:

• Protein structure prediction
• deep predictor
• long short‐term memory
• Salp-J Colony Optimization
• hybrid ensemble deep predictor

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.