Network modeling of patients' biomolecular profiles for clinical phenotype/outcome prediction.

Jessica Gliozzo, Paolo Perlasca, Marco Mesiti, Elena Casiraghi, Viviana Vallacchi, Elisabetta Vergani, Marco Frasca, Giuliano Grossi, Alessandro Petrini, Matteo Re, Alberto Paccanaro, Giorgio Valentini

Research output: Contribution to journalArticlepeer-review


Methods for phenotype and outcome prediction are largely based on inductive supervised models that use selected biomarkers to make predictions, without explicitly considering the functional relationships between individuals. We introduce a novel network-based approach named Patient-Net (P-Net) in which biomolecular profiles of patients are modeled in a graph-structured space that represents gene expression relationships between patients. Then a kernel-based semi-supervised transductive algorithm is applied to the graph to explore the overall topology of the graph and to predict the phenotype/clinical outcome of patients. Experimental tests involving several publicly available datasets of patients afflicted with pancreatic, breast, colon and colorectal cancer show that our proposed method is competitive with state-of-the-art supervised and semi-supervised predictive systems. Importantly, P-Net also provides interpretable models that can be easily visualized to gain clues about the relationships between patients, and to formulate hypotheses about their stratification.
Original languageEnglish
Pages (from-to)3612
Number of pages1
JournalSci. Rep.
Issue number1
Publication statusPublished - Feb 1 2020


  • Female
  • Humans
  • Male
  • Prognosis
  • Algorithms
  • Treatment Outcome
  • Transcriptome
  • Phenotype
  • Datasets as Topic
  • *Gene Regulatory Networks
  • *Neural Networks
  • Computer
  • Artificial Intelligence
  • Breast Neoplasms/*diagnosis/epidemiology
  • Colorectal Neoplasms/*diagnosis/epidemiology
  • Computational Biology/methods
  • Individuality
  • Pancreatic Neoplasms/*diagnosis/epidemiology


Dive into the research topics of 'Network modeling of patients' biomolecular profiles for clinical phenotype/outcome prediction.'. Together they form a unique fingerprint.

Cite this