Available Models

• Interactive Glycemic Index Map

  This interactive map shows the glycemic index for each country in a map

• Dipeptide (germinated, important)

• Dipeptide (germinated, MRMR3)

• Predict Phenolic and Mineral Content

  Based on Mathematical modeling to predict rice’s phenolic and mineral content through multispectral imaging. by Buenafe, R. J., Tiozon, R., Boyd, L. A., Sartagoda, K. J., & Sreenivasulu, N. (2022). (https://doi.org/10.1016/j.focha.2022.100141)

• Anti-colon cancer properties of rice

  This predictive model estimates the anti-colon cancer potential of rice, quantified by MTT assay results (expressed as 1/IC₅₀), using only single nucleotide polymorphisms (SNPs). The model focuses on six key SNP markers: Rd (red pericarp and seed coat, dihydroflavonol 4-reductase), LOC_Os03g27630 (retrotransposon, putative, centromere-specific), Rc (brown pericarp and seed coat), OsENS-98 (rice allergen 14B, endosperm-specific gene 98), LOC_Os08g24820 (expressed protein), and OsFbox598 (F-box protein 598, F-box-type E3 ubiquitin ligase X480).

• Classification of texture properties of rice based on viscosity (random forest)

  This classification model predicts the texture properties of a particular rice sample from properties derived from viscosity analysis through a Rapid Visco Analyzer (RVA). The model requires the peak viscosity, breakdown viscosity, setback viscosity, final viscosity, peak time, and pasting temperature.

• Classification of rice’s glycemic index (GI) group (polished, phenotypic, random forest)

  This classification model predicts the glycemic index (GI) superclass of pigmented rice by analyzing its phenotypic properties derived from viscosity analysis through a Rapid Visco Analyzer (RVA) and chain length distribution analysis through size exclusion chromatography (SEC). The model requires the proportion of resistant starch, amylose, short- and medium-chain amylopectin, chalkiness, and the various viscosity parameters.

• Classification of rice’s glycemic index (GI) group (polished, genotypic, random forest)

  This classification model predicts the glycemic index (GI) superclass of pigmented rice by analyzing its genotypic properties. The model requires the state of two single nucleotide polymorphism (SNP) markers of the rice variety, specifically snp_02_19362520, A→G and snp_02_31023080, A→T.

• Classification of rice’s glycemic index (GI) group (whole grain, random forest)

  This classification model predicts the glycemic index (GI) group of pigmented rice by deriving from chain length distribution analysis through SEC. The model requires the properties of whole grain rice, specifically the resistant starch content, digestible carbohydrates, fractions of amylose, and short-chain and medium-chain amylopectin of whole grain rice.

• Classification of rice’s cluster/group (whole grain, random forest)

  This classification model predicts the cluster of pigmented rice by deriving from chain length distribution analysis through SEC. The model requires the properties of whole grain rice, specifically the resistant starch content, digestible carbohydrates, fractions of amylose, and short-chain and medium-chain amylopectin of whole grain rice.

• Prediction of rice’s glycemic index (whole grain, regression)

  This predictive model predicts the glycemic index of rice by deriving from chain length distribution analysis through SEC. The model requires the unmilled starch fraction from whole grain rice, specifically the percentages for each range of degree of polymerization (DP) of the glucose chains.

• Prediction of rice’s glycemic index (polished rice, regression)

  This predictive model predicts the glycemic index of rice by deriving from chain length distribution analysis through SEC. The model requires the properties of polished rice, specifically fractions of short-chain and medium-chain amylopectin, amylose, and the resistant starch content of polished rice.