Ensemble deep learning model for protein secondary structure prediction using NLP metrics and explainable AI
importance 4/10
partially solved
Protein Structure and Dynamics computational biology stage: research
Problem
Predicting protein secondary structure accurately is difficult, and better predictions are needed to understand protein function.
Why it matters
Protein structure underpins biological function and drug development.
What the AI did
An ensemble deep learning model predicted protein secondary structure, evaluated with the NLP metric ROUGE-L and explainable AI.
Results
Ensemble outscored individual models with best accuracy 94.41% and lowest validation loss 0.1585.
Impact
Ensemble improved prediction accuracy over its individual component models.
Record
| Venue | Results in Engineering |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Uvarani Vignesh, R. Parvathi, K. Gokul Ram |
| Citations | 24 (OpenAlex, at import time) |
| References | 71 |
| Model or method | Ensemble deep learning model (components not stated in source) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1016/j.rineng.2024.103435 |
| Open access | gold |
| Keywords | protein secondary structure, deep learning, ensemble, ROUGE-L, explainable AI |
Importance rating
4
real but narrower advance
Secondary structure prediction aids understanding of protein function, but the work is an incremental ensemble improvement (94.41% accuracy) building on AlphaFold/RoseTTAFold; no scale stated.