Prediction of 8-state protein secondary structures by a novel deep learning architecture

Background

Protein secondary structure can be regarded as an information bridge that links the primary sequence and tertiary structure. Accurate 8-state secondary structure prediction can significantly give more precise and high resolution on structure-based properties analysis.

Results

We present a novel deep learning architecture which exploits an integrative synergy of prediction by a convolutional neural network, residual network, and bidirectional recurrent neural network to improve the performance of protein secondary structure prediction. A local block comprised of convolutional filters and original input is designed for capturing local sequence features. The subsequent bidirectional recurrent neural network consisting of gated recurrent units can capture global context features. Furthermore, the residual network can improve the information flow between the hidden layers and the cascaded recurrent neural network. Our proposed deep network achieved 71.4% accuracy on the benchmark CB513 dataset for the 8-state prediction; and the ensemble learning by our model achieved 74% accuracy. Our model generalization capability is also evaluated on other three independent datasets CASP10, CASP11 and CASP12 for both 8- and 3-state prediction. These prediction performances are superior to the state-of-the-art methods.

Conclusion

Our experiment demonstrates that it is a valuable method for predicting protein secondary structure, and capturing local and global features concurrently is very useful in deep learning.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2280-5) contains supplementary material, which is available to authorized users.

Is supplemental regional anesthesia associated with more complications and readmissions after ankle fracture surgery in the inpatient and outpatient setting?

BACKGROUND

There is concern that regional anesthesia is associated with increased risk of complications, including return to the hospital for uncontrolled pain once the regional anesthetic wears off.

METHODS

Retrospective database review of patients who underwent open reduction and internal fixation of a closed ankle fracture from 2014-16 who received general anesthesia alone (GA) or general anesthesia plus regional anesthesia (RA).

RESULTS

9459 patients met inclusion criteria. Patients in the RA group had significantly longer operative duration in both inpatient (GAI=71min vs RAI=79min, p=0.002) and outpatient setting (GAO=66min vs RAI=72min, p<0.001), lower overall LOS (GA=1.7 days vs RA=1.1 days, p<0.001), and higher readmission rate for pain (RAO=4 [0.3%] vs GAO=1 [0.0%], p=0.007).

CONCLUSIONS

Patients who received supplemental regional anesthesia had shorter hospital LOS, increased operative time, and increased readmission rates for rebound pain. However, the small number of patients needing readmission are not clinically significant demonstrating that regional anesthesia is safe, effective and readmission for rebound pain should not be a concern.

LEVEL OF EVIDENCE

III.