Format

Send to

Choose Destination
Sci Rep. 2016 Oct 24;6:35652. doi: 10.1038/srep35652.

Knowledge-guided fuzzy logic modeling to infer cellular signaling networks from proteomic data.

Author information

1
Biomedical Informatics Lab, School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore.
2
Lab of Information Management, Changzhou University, Jiangsu, 213164 China.
3
Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai 200433, China.
4
Genome Institute of Singapore (GIS), A*STAR, Biopolis, Singapore 138672, Singapore.

Abstract

Modeling of signaling pathways is crucial for understanding and predicting cellular responses to drug treatments. However, canonical signaling pathways curated from literature are seldom context-specific and thus can hardly predict cell type-specific response to external perturbations; purely data-driven methods also have drawbacks such as limited biological interpretability. Therefore, hybrid methods that can integrate prior knowledge and real data for network inference are highly desirable. In this paper, we propose a knowledge-guided fuzzy logic network model to infer signaling pathways by exploiting both prior knowledge and time-series data. In particular, the dynamic time warping algorithm is employed to measure the goodness of fit between experimental and predicted data, so that our method can model temporally-ordered experimental observations. We evaluated the proposed method on a synthetic dataset and two real phosphoproteomic datasets. The experimental results demonstrate that our model can uncover drug-induced alterations in signaling pathways in cancer cells. Compared with existing hybrid models, our method can model feedback loops so that the dynamical mechanisms of signaling networks can be uncovered from time-series data. By calibrating generic models of signaling pathways against real data, our method supports precise predictions of context-specific anticancer drug effects, which is an important step towards precision medicine.

PMID:
27774993
PMCID:
PMC5075921
DOI:
10.1038/srep35652
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center