Chemiluminescent multiassay of pesticides with horseradish peroxidase as a label

Competitive chemiluminescent immunoassay based on a combination of five antibodies was used in a combination with neural network to identify and estimate amounts of three cross-reacting s-triazines (atrazine, terbythylazine and ametryn). Antibodies with different cross-reactivity towards s-triazines were immobilized in separate wells an eight-well microtiter strip. Training of neural networks was carried out with four different learning procedures. The best topology for the data measured was a net with two hidden layers with ten neurons in the first and 15 in the second layer trained with the Schmidhuber method. s-Triazine classification of environmental samples containing various analyte mixtures was correct in 70-100% of all cases depending on the type of analyte. The test developed can be proposed as an alternative field test for multianalyte environmental monitoring.