PFBNet: a priori-fused boosting method for gene regulatory network inference

Abstract

Background: Inferring gene regulatory networks (GRNs) from gene expression data remains a challenge in system biology. In past decade, numerous methods have been developed for the inference of GRNs. It remains a challenge due to the fact that the data is noisy and high dimensional, and there exists a large number of potential interactions. Results: We present a novel method, namely priori-fused boosting network inference method (PFBNet), to infer GRNs from time-series expression data by using the non-linear model of Boosting and the prior information (e.g., the knockout data) fusion scheme. Specifically, PFBNet first calculates the confidences of the regulation relationships using the boosting-based model, where the information about the accumulation impact of the gene expressions at previous time points is taken into account. Then, a newly defined strategy is applied to fuse the information from the prior data by elevating the confidences of the regulation relationships from the corresponding regulators. Conclusions: The experiments on the benchmark datasets from DREAM challenge as well as the E.coli datasets show that PFBNet achieves significantly better performance than other state-of-the-art methods (Jump3, GEINE3-lag, HiDi, iRafNet and BiXGBoost).

Using explainable artificial intelligence to identify patient-specific breast cancer subtypes

“…Additionally, studies can also be conducted using multiplex families, or large extended pedigrees, which can provide more powerful statistical power to detect genetic associations. Our research helps to solve these problems: with the use of gradient-boosted tree algorithms, we can study a wide array of genomes and detect low-frequency genetic variants (15,16).…”

“…Additionally, studies can also be conducted using multiplex families, or large extended pedigrees, which can provide more powerful statistical power to detect genetic associations. Our research helps to solve these problems: with the use of gradient-boosted tree algorithms, we can study a wide array of genomes and detect low-frequency genetic variants (15,16).Neural networks within explainable AI (XAI) have increased drastically over the years, especially within the medical field (17). In this research, we classified breast cancer subtypes…”

Periodic synchronization of isolated network elements facilitates simulating and inferring gene regulatory networks including stochastic molecular kinetics

“…Since the reaction consumes the species n 1 , n 2 , we need to calculate the flux of the respective elements into the species f . This flux is calculated by (41)…”

“…Using knockout data, a confidence matrix for network interactions was obtained [37]. Recent progress to the inference problem has been made using time trajectories of gene product levels [38][39][40][41]. Approaches such as WASABI [42] infer how perturbations of gene product levels propagate through a network.…”

Framework to simulate gene regulatory networks with stochastic molecular kinetics and to infer steady-state network structure

“…Using knockout data, a confidence matrix for network interactions was obtained 37 . Recent progress to the inference problem has been made using time trajectories of gene product levels 38–41 . Approaches such as WASABI 42 infer how perturbations of gene product levels propagate through a network.…”