Prediction
PncsHub incoporates three predictions for prediction of homologues non-classical secreted proteins and novel non-classical secreted proteins: Retrained PeNGaRoo, a Hidden Markov Model (HMM) based predictor and Original PeNGaRoo . Users can use the checkbox below to select one or more of the three predictors to customize different prediction scenarios.
Enter sequences  
Examples

OR

You can upload a sequence file in the FASTA format: (example.fasta)
  Default mode   Fast mode
  Retrained PeNGaRoo   HMM based predictor   Original PeNGaRoo  
  All data   All data excluding MV   MV only data  
  For common use   For benchmarking test



If you find PncsHub is useful in your research, please cite:
  • Dai W, Li J et al. PcnsHub: a universal platform for annotating and analyzing non-classically secreted proteins of Gram-positive bacteria. Nucleic Acids Research. DOI: 10.1093/nar/gkab814.
As PncsHub incorporates PeNGaRoo into its Prediction Module, please also consider to cite the original paper:
  • Zhang Y, Yu S, Xie R et al. PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins. Bioinformatics 2020;36(3):704-712. DOI: 10.1093/bioinformatics/btz629.