FDPSM: Feature-Driven Prediction Modeling of Pathogenic Synonymous Mutations

Synonymous
mutations, once considered to be biologically neutral,
are now recognized to affect protein expression and function by altering
the RNA splicing, stability, or translation efficiency. These effects
can contribute to disease, making the prediction of the pathogenicity
a crucial task. Computational methods have been developed to analyze
the sequence features and biological functions of synonymous mutations,
but existing methods face limitations, including scarcity of labeled
data, reliance on other prediction tools, and insufficient representation
of feature interrelationships. Here, we present FDPSM, a novel prediction
method specifically designed to predict pathogenic synonymous mutations.
FDPSM was trained on a robust data set of 4251 positive and negative
training samples to enhance predictive accuracy. The method leveraged
a comprehensive set of features, including genomic context, conservation,
splicing effects, functional effects, and epigenomics, without relying
on prediction scores from other mutation pathogenicity tools. Recognizing
that original features alone may not fully capture the distinctions
between pathogenic and benign synonymous mutations, we enhanced the
feature set by extracting effective information from the interactions
and distribution of these features. The experimental results showed
that FDPSM significantly outperformed existing methods in predicting
the pathogenicity of synonymous mutations, offering a more accurate
and reliable tool for this important task. FDPSM is available at https://github.com/xialab-ahu/FDPSM.