UgenTec Artificial Intelligence Algorithm
Today, the most commonly used principle to determine whether a curve displays amplification is to set a threshold at a certain fluorescence value. If the curve passes this threshold, the target is considered detected. If not, the result is set to not detected. However, this is an oversimplification of the real situation: it does not take any of the biological phenomena that can occur into account, such as optical mixing, presence of air bubbles and relative fluorescence values.
The artificial intelligence (AI) algorithm developed by Velsera, however, analyses the amplification data in an intelligent way, transforming and interpreting it on a multitude of curve features. The algorithm includes but is not limited to a proprietary baseline correction, Cq determination method and curve calling. This allows the raw data to be converted to a result in a standardized and objective manner.
What is the difference between Ct and Cq value?
There is no difference between Cq and Ct. “Cq or Quantification cycle” is the correct naming according the MIQE guidelines as described in Bustin et al.; Clinical Chemistry 55:4; 2009.
“The nomenclature describing the fractional PCR cycle used for quantification is inconsistent, with threshold cycle (Ct), crossing point (Cp), and take-off point (TOP) currently used in the literature. These terms all refer to the same value from the real-time instrument and were coined by competing manufacturers of real-time instruments for reasons of product differentiation, not scientific accuracy or clarity. We propose the use of quantification cycle (Cq), according to the RDML (Real-Time PCR Data Markup Language) data standard (www.rdml.org) (27 )."
Whitepaper
Want to know more about our algorithm? Request a copy of our whitepaper on Artificial Intelligence via support@velsera.com. This whitepaper will give you more insights in the difference between Machine learning versus Expert AI, how the Cq value is determined, how you can optimize the algorithm and how to best look at the data within FastFinder Analysis.