What question did this study set out to answer?

This research aims to analyze evolutionary constraints and clinical variants of TP53 to highlight functionally important residues.

February 28, 2026Open Access

Phylogenomics to structure: evolutionary and clinical signals in the TP53 DNA-binding core through LOOCV-validated ensemble learning

Key Points

This research aims to analyze evolutionary constraints and clinical variants of TP53 to highlight functionally important residues.
Developed a computational pipeline integrating evolutionary genomics and structural biology.
Performed genome-wide alignment and phylogenetic estimation based on 19 vertebrate orthologs.
Conducted selection analysis to identify functionally critical residues in the TP53 DNA-binding domain.
Mapped evolutionary signals onto AlphaFold-predicted structures and analyzed human variants from ClinVar and UniProt.
Applied machine learning with leave-one-out cross-validation for robust predictive performance.
Identified five sites under positive selection, particularly codon 129 as a critical site.
Pathogenic variants concentrated at the DNA-contacting interface, especially residues 239-248.
Achieved high predictive accuracy with a multi-branch deep neural network and Ridge-ExtraTrees ensemble.
Found that Random Forest underperformed due to bias in class imbalance.

Abstract

TP53 encodes a master tumor suppressor, and understanding its evolutionary constraints is critical for interpreting pathogenic variation. We developed a fully reproducible computational pipeline integrating evolutionary genomics, structural biology, and clinical variant analysis to systematically prioritize functionally critical residues in TP53. We used fixed effects likelihood and fast unconstrained Bayesian approximation to perform genome-wide alignment, maximum-likelihood phylogenetic estimation, and site-specific selection testing over 19 vertebrate orthologs. We mapped these evolutionary signals onto the AlphaFold-predicted structure and integrated 3936 human variants from ClinVar and UniProt. Selection analysis identified five sites under positive or diversifying selection, with a single consensus position detected by both methods: multiple-sequence-alignment position 606 (human codon 129) in the DNA-binding domain. Structural mapping revealed that pathogenic variants concentrate at the DNA-contacting interface, with residues 239-248 emerging as the highest-priority targets based on our composite scoring system that integrates evolutionary constraint, pathogenic burden, hotspot density, and domain importance. Machine learning validation under leave-one-out cross-validation (LOOCV) demonstrated robust predictive performance. A Ridge-ExtraTrees ensemble achieved MAE (mean absolute error) =2. 84, RMSE (root mean squared error) =3. 72, R^2=0. 91 for phylogenetic-distance regression and 89. 5% accuracy (17/19) for clade classification. A multi-branch deep neural network attained comparable results (MAE=2. 33, RMSE=2. 56, R^2=0. 86), while Random Forest substantially underperformed (MAE 7. 19, RMSE 8. 82, R^2 0. 47, accuracy 63\%) due to shrinkage and class-imbalance bias. Our findings show that evolutionary signals and clinical variants converge within the structurally constrained DNA-binding core of TP53, with codon 129 representing a robust positive-selection site and residues 239-248 constituting the primary pathogenic hotspot. This AlphaFold-anchored, LOOCV-validated framework offers a systematic, generalizable approach for residue-level prioritization to guide mechanistic studies and potentially inform precision oncology applications pending experimental validation.

Phylogenomics to structure: evolutionary and clinical signals in the TP53 DNA-binding core through LOOCV-validated ensemble learning

Key Points

Abstract

Cite This Study