TKOA-GPNN: a model framework for genotype-to-phenotype prediction in Duroc pigs
Jiali Zhou, Zuhong Liu, Kaiyue Liu, Bing Deng, Jianghui Wen · 2026
Read TKOA-GPNN: a model framework for genotype-to-phenotype prediction in Duroc pigs by Jiali Zhou, Zuhong Liu, Kaiyue Liu, Bing Deng, Jianghui Wen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13474873.txt.
Description
Zhou and colleagues present a computer model in 2026 that predicts growth traits in Duroc pigs from DNA alone, aiming to speed up breeding choices. Their model, named TKOA-GPNN, first narrows the genome to the markers most tied to growth, then feeds those markers into a neural network, a pattern-learning program loosely modeled on brain cells. Two selection stages use correlation screening and an optimization search inspired by Kepler's laws of planetary motion.
Tested against 14 existing prediction models, the new framework gave the best accuracy while also running efficiently on the study's pig data. It held up on offspring records, on cheaper genotyping array data, and on full genome sequencing data, which the authors cite as proof of robustness. Growth traits such as days to reach 100 kilograms matter economically in China, the world's largest pig producer with about 700 million pigs a year.
Catalog record
| CREATOR | Jiali Zhou, Zuhong Liu, Kaiyue Liu, Bing Deng, Jianghui Wen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |