Patient-level proteomic network prediction by explainable artificial intelligence
Standard
Patient-level proteomic network prediction by explainable artificial intelligence. / Keyl, Philipp; Michael, Bockmayr; Heim, Daniel; Dernbach, Gabriel; Montavon, Grégoire; Müller, Klaus-Robert; Klauschen, Frederick.
In: NPJ PRECIS ONCOL, Vol. 6, No. 1, 35, 07.06.2022.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Patient-level proteomic network prediction by explainable artificial intelligence
AU - Keyl, Philipp
AU - Michael, Bockmayr
AU - Heim, Daniel
AU - Dernbach, Gabriel
AU - Montavon, Grégoire
AU - Müller, Klaus-Robert
AU - Klauschen, Frederick
N1 - © 2022. The Author(s).
PY - 2022/6/7
Y1 - 2022/6/7
N2 - Understanding the pathological properties of dysregulated protein networks in individual patients' tumors is the basis for precision therapy. Functional experiments are commonly used, but cover only parts of the oncogenic signaling networks, whereas methods that reconstruct networks from omics data usually only predict average network features across tumors. Here, we show that the explainable AI method layer-wise relevance propagation (LRP) can infer protein interaction networks for individual patients from proteomic profiling data. LRP reconstructs average and individual interaction networks with an AUC of 0.99 and 0.93, respectively, and outperforms state-of-the-art network prediction methods for individual tumors. Using data from The Cancer Proteome Atlas, we identify known and potentially novel oncogenic network features, among which some are cancer-type specific and show only minor variation among patients, while others are present across certain tumor types but differ among individual patients. Our approach may therefore support predictive diagnostics in precision oncology by inferring "patient-level" oncogenic mechanisms.
AB - Understanding the pathological properties of dysregulated protein networks in individual patients' tumors is the basis for precision therapy. Functional experiments are commonly used, but cover only parts of the oncogenic signaling networks, whereas methods that reconstruct networks from omics data usually only predict average network features across tumors. Here, we show that the explainable AI method layer-wise relevance propagation (LRP) can infer protein interaction networks for individual patients from proteomic profiling data. LRP reconstructs average and individual interaction networks with an AUC of 0.99 and 0.93, respectively, and outperforms state-of-the-art network prediction methods for individual tumors. Using data from The Cancer Proteome Atlas, we identify known and potentially novel oncogenic network features, among which some are cancer-type specific and show only minor variation among patients, while others are present across certain tumor types but differ among individual patients. Our approach may therefore support predictive diagnostics in precision oncology by inferring "patient-level" oncogenic mechanisms.
U2 - 10.1038/s41698-022-00278-4
DO - 10.1038/s41698-022-00278-4
M3 - SCORING: Journal article
C2 - 35672443
VL - 6
JO - NPJ PRECIS ONCOL
JF - NPJ PRECIS ONCOL
SN - 2397-768X
IS - 1
M1 - 35
ER -