Publication detail

Protein Hotspot Prediction Using S-Transform

KAŠPÁREK, J. MADĚRÁNKOVÁ, D. TKACZ, E.

Original Title

Protein Hotspot Prediction Using S-Transform

Czech Title

Predikce aktivních míst v proteinech pomocí S-transformace

English Title

Protein Hotspot Prediction Using S-Transform

Type

journal article

Language

en

Original Abstract

Since experimental techniques of protein hotspot prediction are still financially extremely demanding and time consuming there is a strain to produce sufficiently reliable computational techniques for this particular task. We propose an algorithm based on Resonant Recognition Model relying heavily on signal processing techniques. Processed numerical signal is obtain solely form protein sequence using physical quantity EIIP. We therefore use no information of protein structure. The key element here is a time-frequency analysis tool – S-transform. This allows us to determine exact residues responsible for majority of performance on protein’s characteristic frequency. We achieve basic sensitivity of 85 % and PPV 49 %, while demanding very little computing resources, because simplicity is one of the biggest advantages of our approach.

Czech abstract

Vzhledem k tomu, že experimentální techniky predikce proteinových aktivních míst jsou stále finančně velmi náročná a časově náročné je potřeba vyvinout dostatečně spolehlivé výpočetnímetody. Navrhujeme algoritmus založený na rezonanční rozpoznávání modelu spoléhat se těžce na zpracování signálu techniky. Zpracované číselné signál je získat výhradně tvoří proteinové sekvence pomocí fyzikální veličiny EIIP. Proto používáme žádné informace o struktuře bílkovin. Klíčovým prvkem je zde časově-frekvenční analýza nástroje - S-transformace. To nám umožňuje určit přesné zbytky jsou odpovědné za většinu výkonu na charakteristickou frekvenci bílkoviny. Dosahujeme základní citlivost 85% a PPV 49%, zatímco náročné velmi málo výpočetních zdrojů, protože jednoduchost je jedna z největších výhod našeho přístupu.

English abstract

Since experimental techniques of protein hotspot prediction are still financially extremely demanding and time consuming there is a strain to produce sufficiently reliable computational techniques for this particular task. We propose an algorithm based on Resonant Recognition Model relying heavily on signal processing techniques. Processed numerical signal is obtain solely form protein sequence using physical quantity EIIP. We therefore use no information of protein structure. The key element here is a time-frequency analysis tool – S-transform. This allows us to determine exact residues responsible for majority of performance on protein’s characteristic frequency. We achieve basic sensitivity of 85 % and PPV 49 %, while demanding very little computing resources, because simplicity is one of the biggest advantages of our approach.

Keywords

Protein hotspots prediction, signal processing, electron-ion interaction potential, resonant recognition model protein sequence, S-transform, time-frequency analysis

RIV year

2014

Released

01.06.2014

Publisher

Springer International Publishing

Location

Německo

Pages from

327

Pages to

336

Pages count

11

BibTex


@article{BUT110406,
  author="Jan {Kašpárek} and Denisa {Maděránková} and Ewaryst {Tkacz}",
  title="Protein Hotspot Prediction Using S-Transform",
  annote="Since experimental techniques of protein hotspot prediction are still financially extremely demanding and time consuming there is a strain to produce sufficiently reliable computational techniques for this particular task. We propose an algorithm based on Resonant Recognition Model relying heavily on signal processing techniques. Processed numerical signal is obtain solely form protein sequence using physical quantity EIIP. We therefore use no information of protein structure. The key element here is a time-frequency analysis tool – S-transform. This allows us to determine exact residues responsible for majority of performance on protein’s characteristic frequency. We achieve basic sensitivity of 85 % and PPV 49 %, while demanding very little computing resources, because simplicity is one of the biggest advantages of our approach.",
  address="Springer International Publishing",
  chapter="110406",
  doi="10.1007/978-3-319-06593-9_29",
  howpublished="print",
  institution="Springer International Publishing",
  number="6",
  volume="283",
  year="2014",
  month="june",
  pages="327--336",
  publisher="Springer International Publishing",
  type="journal article"
}