Machine Learning–Based Identification and Validation of PYCR1 and PYGM as Prognostic Biomarkers for Osteosarcoma

Guoyong Xu, Chong Liu, Jiang Xue, Jiarui Chen, Zhuan Zou, Sen Mo, Zhongxian Zhou, Xinli Zhan · 2026

Read Machine Learning–Based Identification and Validation of PYCR1 and PYGM as Prognostic Biomarkers for Osteosarcoma by Guoyong Xu, Chong Liu, Jiang Xue, Jiarui Chen, Zhuan Zou, Sen Mo, Zhongxian Zhou, Xinli Zhan (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-13219957.txt.

Description

Guoyong Xu and colleagues use machine learning on gene expression data to nominate two biomarkers for osteosarcoma in a 2026 study. Osteosarcoma is an aggressive bone cancer of children and adolescents with poor outcomes, and doctors lack molecular warnings of which tumors behave worst. The team mined eighty-eight tumor samples from a public platform, using four hundred normal samples as the comparison set.

Genes were screened by regression, pruned by a shrinkage method, and used to split patients into subtypes and risk groups with immune landscapes. Two genes survived the pipeline. PYCR1, an enzyme of proline metabolism, was overproduced in tumors and marked poor prognosis. PYGM, a glycogen-breaking enzyme, behaved more subtly: lower in tumors than in normal tissue, yet higher inside the high-risk group. Bench assays on tumor tissue confirmed proteins' presence and location. The authors present the pair as candidate biomarkers for refining osteosarcoma prognosis.

Catalog record

CREATORGuoyong Xu, Chong Liu, Jiang Xue, Jiarui Chen, Zhuan Zou, Sen Mo, Zhongxian Zhou, Xinli Zhan
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13219957

Browse the full library · About the Tower of Babel