Open AccessMoSBi: Automated signature mining for molecular stratification and subtyping
Author(s) -
Tim Rose,
Thibault Bechtler,
Octavia-Andreea Ciora,
Kim Anh Lilian Le,
Florian Molnar,
Nikolai Köhler,
Jan Baumbach,
Richard Röttger,
Josch Pauling
Publication year - 2022
Publication title -
proceedings of the national academy of sciences of the united states of america
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.011
H-Index - 771
eISSN - 1091-6490
pISSN - 0027-8424
DOI - 10.1073/pnas.2118210119
Subject(s) - subtyping , biclustering , computer science , data mining , cluster analysis , scalability , machine learning , profiling (computer programming) , artificial intelligence , pattern recognition (psychology) , database , cure data clustering algorithm , correlation clustering , programming language , operating system
Significance Molecular patient stratification and disease subtyping are ongoing and high-impact problems that rely on the identification of characteristic molecular signatures. Current computational methods show high sensitivity to custom parameterization, which leads to inconsistent performance on different molecular data. Our new method, MoSBi (molecular signature identification using biclustering), 1) enables so far unmatched high performance for stratification and subtyping across datasets of various different biomolecules, 2) provides a scalable solution for visualizing the results and their correspondence to clinical factors, and 3) has immediate practical relevance through its automatic workflow where individual selection, parameterization, screening, and visualization of biclustering algorithms is not required. MoSBi is a major step forward with a high impact for clinical and wet-lab researchers.