A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction
importance 6/10
ai assisted
Protein Structure and Dynamics protein science stage: research
Problem
Ab initio prediction of protein secondary structure, where accuracy had stagnated around 80 percent.
Why it matters
Secondary structure predictions feed tertiary structure prediction, increasingly demanded due to rapid protein discovery.
What the AI did
DNSS, a predictor combining PSI-BLAST position-specific scoring matrices with deep learning network architectures, trained efficiently using GPUs and CUDA.
Results
not stated in source
Impact
Peer-reviewed predictor in IEEE TCBB with 297 citations; abstract does not state achieved accuracy.
Record
| Venue | IEEE Transactions on Computational Biology and Bioinformatics |
|---|---|
| Published | 2014 |
| Work type | article |
| Authors | Matt Spencer, Jesse Eickholt, Jianlin Jack Cheng |
| Citations | 297 (OpenAlex, at import time) |
| References | 56 |
| Model or method | DNSS (deep learning network) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1109/tcbb.2014.2343960 |
| Open access | green |
| Keywords | deep learning, protein secondary structure, PSI-BLAST, DNSS, prediction |
Importance rating
6
significant — thousands to millions affected
Secondary-structure prediction feeds tertiary-structure prediction, increasingly demanded due to rapid protein discovery; foundational capability but no scale stated.