Elucidating human ageing-related phenotypic abnormalities with a novel hierarchical feature selection-based knowledge discovery framework
Wan, C.; Barton, C.
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.
Similar papers in this journal
- AE-LGBM: Sequence-Based Novel Approach To Detect Interacting Protein Pairs via Ensemble of Autoencoder and LightGBM. 94%
- SymScore: Machine Learning Accuracy Meets Transparency in a Symbolic Regression-Based Clinical Score Generator 93%
- Development of an absolute assignment predictor for triple-negative breast cancer subtyping using machine learning approaches 93%
Similar papers in this journal
Similar papers in this journal
- Improving protein function prediction by learning and integrating representations of protein sequences and function labels 93%
- Mining drug-target interactions from biomedical literature using chemical and gene descriptions-based ensemble transformer model. 93%
- Identification of Monotonically Classifying Pairs of Genes for Ordinal Disease Outcomes 92%
Similar papers in this journal
- Tensor decomposition- and principal component analysis-based unsupervised feature extraction to select more reasonable differentially expressed genes: Optimization of standard deviation versus state-of-art methods 93%
- Finding disease modules for cancer and COVID-19 in gene co-expression networks with the Core&Peel method 93%
- Novel AI-powered computational method using tensor decomposition for identification of common optimal bin sizes when integrating multiple Hi-C datasets 93%
"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.