Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data

Makoto Yamada*, Jiliang Tang, Jose Lugo-Martinez, Ermin Hodzic, Raunak Shrestha, Avishek Saha, Hua Ouyang, Dawei Yin, Hiroshi Mamitsuka, Cenk Sahinalp, Predrag Radivojac, Filippo Menczer, Yi Chang

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

19 Citations (Scopus)


Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here, we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximally predictive features with minimal redundancy, yielding higher predictive power and improved interpretability. Its effectiveness is demonstrated through applications to classify phenotypes based on module expression in human prostate cancer patients and to detect enzymes among protein structures. We achieve high accuracy with as few as 20 out of one million features - a dimensionality reduction of 99.998 percent. Our algorithm can be implemented on commodity cloud computing platforms. The dramatic reduction of features may lead to the ubiquitous deployment of sophisticated prediction models in mobile health care applications.

Original languageEnglish
Pages (from-to)1352-1365
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Issue number7
Publication statusPublished - 1 Jul 2018
MoE publication typeA1 Journal article-refereed


  • biomarker discovery
  • Feature selection
  • Hilbert-Schmidt independence criterion
  • kernel methods

Fingerprint Dive into the research topics of 'Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data'. Together they form a unique fingerprint.

Cite this