Back

Elucidating human ageing-related phenotypic abnormalities with a novel hierarchical feature selection-based knowledge discovery framework

Wan, C.; Barton, C.

2023-05-26 bioinformatics
10.1101/2023.05.26.542395 bioRxiv
Show abstract

Ageing is a complex biological process involving multiple genes that are also related to phenotypic abnormalities. However, the micro view of the associations between ageing and human phenotypic abnormalities is still under-studied. We propose a new hierarchical feature selection method namely HIP+, which selects positive hierarchical information-preserving features according to pre-defined hierarchical ontology information. The experimental results confirm that HIP+ obtained better performance than the state-of-the-art hierarchical feature selection method in predicting human phenotypic abnormalities annotations. We further propose a HIP+-based knowledge discovery framework that also successfully highlights some important associations between biological processes and human phenotypic abnormalities.

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.