Back

A Mathematical Methodology to Predict Phenotype from Genotype

Lee, J.; Choi, K. Y.

2025-03-17 bioinformatics
10.1101/2025.03.17.643655 bioRxiv
Show abstract

From a mathematical perspective, a genome can be viewed as categorical data whose elements include genetic variants in SNPs. Then, the problem of predicting phenotype from genotype can be reduced to the problem of classifying categorical data. We will define a metric function at each SNPs position of an individual such that the arithmetic mean of a specific phenotype group is always less than or equal to that of the comparison group. Then, in light of a mathematical principle, calculating the sum of the distances(metrics) of some SNPs positions could clearly classify the two groups, when difficult to classify them with one specific position. Using this methodology, we found that even small differences in each SNPs combined could classify phenotypes ; combining 51 SNPs positions in autosomes made possible to distinguish males from females with great accuracy. We also found that East Asian people could be distinguished from other people with 100% accuracy, so we obtained a mathematical definition of East Asian people. The mathematical methodology classifies phenotypes with collecting small differences of genotypes throughout the entire genome, which could be useful for predicting diseases affected by the genome and be useful in pharmacogenomics.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.