Send to

Choose Destination
Carbohydr Polym. 2013 Oct 15;98(1):116-21. doi: 10.1016/j.carbpol.2013.05.071. Epub 2013 May 31.

Anti-glycated activity prediction of polysaccharides from two guava fruits using artificial neural networks.

Author information

College of Pharmacy, Guangdong Pharmaceutical University, Guangzhou 510006, PR China.


High-efficiency ultrasonic treatment was used to extract the polysaccharides of Psidium guajava (PPG) and Psidium littorale (PPL). The aims of this study were to compare polysaccharide activities from these two guavas, as well as to investigate the relationship between ultrasonic conditions and anti-glycated activity. A mathematical model of anti-glycated activity was constructed with the artificial neural network (ANN) toolbox of MATLAB software. Response surface plots showed the correlation between ultrasonic conditions and bioactivity. The optimal ultrasonic conditions of PPL for the highest anti-glycated activity were predicted to be 256 W, 60 °C, and 12 min, and the predicted activity was 42.2%. The predicted highest anti-glycated activity of PPG was 27.2% under its optimal predicted ultrasonic condition. The experimental result showed that PPG and PPL possessed anti-glycated and antioxidant activities, and those of PPL were greater. The experimental data also indicated that ANN had good prediction and optimization capability.


Anti-glycated activity; Artificial neural networks; Polysaccharides; Psidium guajava Linn.; Psidium littorale Raddi; Ultrasonic extraction

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center