Detection and quantification in real-time polymerase chain reaction

Abou Keita (1) , Romain Hérault (1) , Colas Calbrix (2) , Stéphane Canu (1)

1 DocApp - LITIS - Equipe Apprentissage
2 PRIMACEN - Plate-Forme de Recherche en Imagerie Cellulaire de Haute-Normandie

The estimation of the concentration of an infectious agent in the environment is a key step to trigger an alert when there is a bio- logical threat. This concentration can be obtained trough a quantitative polymerase chain reaction (qPCR). Nevertheless, standard real-time pro- cedure do not address detection delay which is a main concern in alert triggering. Therefore, we propose a method based on Lasso regression and CUSUM change detection to accurately estimate the concentration while minimizing the detection delay. The trade-off between accuracy and delay can be managed through a parameter. We compare our results with those found by a standard method (threshold method) and promising results are obtained.

Mots clés: quantitative PCR (qPCR); Real-time PCR; Biological threat; Change detection; Lasso; CUSUM; Detection delay; Biological threat.

Domaines: Machine Learning [stat.ML]; Apprentissage [cs.LG]

Abou Keita, Romain Hérault, Colas Calbrix, Stéphane Canu. Detection and quantification in real-time polymerase chain reaction. European Symposium on Artificial Neural Networks, Apr 2013, Bruges, Belgium. pp.351. ⟨hal-00834417⟩