Unknown

Dataset Information

0

PiPred - a deep-learning method for prediction of ?-helices in protein sequences.

ABSTRACT: Canonical ?-helices are short, relatively unstable secondary structure elements found in proteins. They comprise seven or more residues and are present in 15% of all known protein structures, often in functionally important regions such as ligand- and ion-binding sites. Given their similarity to ?-helices, the prediction of ?-helices is a challenging task and none of the currently available secondary structure prediction methods tackle it. Here, we present PiPred, a neural network-based tool for predicting ?-helices in protein sequences. By performing a rigorous benchmark we show that PiPred can detect ?-helices with a per-residue precision of 48% and sensitivity of 46%. Interestingly, some of the ?-helices mispredicted by PiPred as ?-helices exhibit a geometry characteristic of ?-helices. Also, despite being trained only with canonical ?-helices, PiPred can identify 6-residue-long ?/?-bulges. These observations suggest an even higher effective precision of the method and demonstrate that ?-helices, ?/?-bulges, and other helical deformations may impose similar constraints on sequences. PiPred is freely accessible at: https://toolkit.tuebingen.mpg.de/#/tools/quick2d . A standalone version is available for download at: https://github.com/labstructbioinf/PiPred , where we also provide the CB6133, CB513, CASP10, and CASP11 datasets, commonly used for training and validation of secondary structure prediction methods, with correctly annotated ?-helices.

SUBMITTER: Ludwiczak J 

PROVIDER: S-EPMC6499831 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

PiPred - a deep-learning method for prediction of π-helices in protein sequences.

Ludwiczak Jan J   Winski Aleksander A   da Silva Neto Antonio Marinho AM   Szczepaniak Krzysztof K   Alva Vikram V   Dunin-Horkawicz Stanislaw S  

Scientific reports 20190503 1

Canonical π-helices are short, relatively unstable secondary structure elements found in proteins. They comprise seven or more residues and are present in 15% of all known protein structures, often in functionally important regions such as ligand- and ion-binding sites. Given their similarity to α-helices, the prediction of π-helices is a challenging task and none of the currently available secondary structure prediction methods tackle it. Here, we present PiPred, a neural network-based tool for  ...[more]

Similar Datasets

Unknown Protein Secondary Structure Prediction With a Reductive Deep Learning Method.
| S-EPMC8240957 | biostudies-literature
Unknown Characterizing Promoter and Enhancer Sequences by a Deep Learning Method.
| S-EPMC8239401 | biostudies-literature
Unknown DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences.
| S-EPMC6594651 | biostudies-literature
Unknown DeepM6ASeq: prediction and characterization of m6A-containing sequences using deep learning.
| S-EPMC6311933 | biostudies-literature
Unknown DeepDISE: DNA Binding Site Prediction Using a Deep Learning Method.
| S-EPMC8197219 | biostudies-literature
Unknown EFG-CS: Predicting chemical shifts from amino acid sequences with protein structure prediction using machine learning and deep learning models.
| S-EPMC11232051 | biostudies-literature
Unknown MU-PseUDeep: A deep learning method for prediction of pseudouridine sites.
| S-EPMC7387732 | biostudies-literature
Unknown Automatic Meningioma Segmentation and Grading Prediction: A Hybrid Deep-Learning Method.
| S-EPMC8401675 | biostudies-literature
Other miRBind: a Deep Learning Method for miRNA Binding Classification
2022-12-22 | GSE218466 | GEO
Unknown DeepHLAPred: a deep learning-based method for non-classical HLA binder prediction.
| S-EPMC10666343 | biostudies-literature