DNetPRO: A network approach for low-dimensional signatures from high-throughput data
Curti, N.; Giampieri, E.; Levi, G.; Castellani, G.; Remondini, D.
Show abstract
The objective of many high-throughput \"omics\" studies is to obtain a relatively low-dimensional set of observables - signature - for sample classification purposes (diagnosis, prognosis, stratification). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised signature identification method based on a bottom-up combinatorial approach that exploits the discriminant power of all variable pairs. The algorithm is easily scalable allowing efficient computing even for high number of observables (104 - 105). We show applications on real high-throughput genomic datasets in which our method outperforms existing results, or compares to them but with a smaller number of selected variables. Moreover the linearity of DNetPRO allows a clearer interpretation of the obtained signatures in comparison to non linear classification models
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DeepInsight-3D for precision oncology: an improved anti-cancer drug response prediction from high-dimensional multi-omics data with convolutional neural networks 95%
- Finding disease modules for cancer and COVID-19 in gene co-expression networks with the Core&Peel method 95%
- Accurate Prediction of Breast Cancer Survival through Coherent Voting Networks with Gene Expression Profiling 95%
Similar papers in this journal
- Assessing Random Forest self-reproducibility for optimal short biomarker signature discovery 94%
- Molecular Group and Correlation Guided Structural Learning for Multi-Phenotype Prediction 94%
- Blood-based transcriptomic signature panel identification for cancer diagnosis: Benchmarking of feature extraction methods 93%
Similar papers in this journal
"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.