Patient-level proteomic network prediction by explainable artificial intelligence

Abstract

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.

Single-cell gene regulatory network prediction by explainable AI

“…Subsequently, LRP is applied to estimate the relevance of every gene for this prediction. This extends our previous explainable AI approach to predict protein networks for individual patients from bulk proteomic profiling data ( 19 ). We further develop the approach here for scRNA-seq data analysis, which poses additional challenges due to the often small transcript counts per cell and the frequent occurrence of dropouts and examine its performance on synthetic data ( 6 ).…”

“…The investigation of XAI has been associated with a growing number of applications in biological research, such as the prediction of proteomic networks for individual patients ( 19 ) and the identification of molecular network modules associated to specific disease phenotypes ( 17 , 18 , 57 ). The use of XAI for the prediction of single-cell gene regulatory networks offers promising opportunities, but several difficulties still need to be considered.…”

“…We used a simple neural network architecture with hyperparameter heuristics based on our previous study ( 19 ): The NN was constructed with two hidden layers of width 10 · N in order to vary the NN capacity according to the data set. The NN was tasked to perform imputation for a set of N genes, P of which are missing.…”

“…onto the layer of neuron j ), we use the propagation rule: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$$\begin{eqnarray*} R_j &=& \sum _k \frac{a_j^+ \cdot (w_{jk} + \gamma w_{jk}^+)+a_j^- \cdot (w_{jk} + \gamma w_{jk}^-)}{\sum _{0,j} a_j^+ \cdot (w_{jk} + \gamma w_{jk}^+)+a_j^- \cdot (w_{jk} + \gamma w_{jk}^-)} \cdot 1_{a_k >0} \cdot R_k \\ && +\, \sum _k \frac{a_j^+ \cdot (w_{jk} + \gamma w_{jk}^-)+a_j^- \cdot (w_{jk} + \gamma w_{jk}^+)}{\sum _{0,j} a_j^+ \cdot (w_{jk} + \gamma w_{jk}^-)+a_j^- \cdot (w_{jk} + \gamma w_{jk}^+)} \cdot 1_{a_k < 0} \cdot R_k \end{eqnarray*}$$\end{document} where ( · ) + and ( · ) − are shortcut notations for max (0, ·) and min (0, ·). This rule is known as ‘generalized LRP-γ’, and used in ( 19 , 26 ). The parameter γ is a hyperparameter that needs to be selected to maximize explanation quality.…”

Imaging bridges pathology and radiology

“…The information of the cell can be additionally enriched by molecular features through the detection of proteins (immunohistochemistry), RNAs ( in situ hybridization), and DNA mutation analysis (deep sequencing, methylation, and others). 12 , 13 …”