LogBTF: gene regulatory network inference using Boolean threshold network model from single-cell gene expression data

Abstract

Motivation From a systematic perspective, it is crucial to infer and analyze gene regulatory network (GRN) from high-throughput single-cell RNA sequencing (scRNA-seq) data. However, most existing GRN inference methods mainly focus on the network topology, only few of them consider how to explicitly describe the updated logic rules of regulation in GRNs to obtain their dynamics. Moreover, some inference methods also fail to deal with the over-fitting problem caused by the noise in time series data. Results In this paper, we propose a novel embedded Boolean threshold network method called LogBTF, which effectively infers GRN by integrating regularized logistic regression and Boolean threshold function. First, the continuous gene expression values are converted into Boolean values and the elastic net regression model is adopted to fit the binarized time series data. Then, the estimated regression coefficients are applied to represent the unknown Boolean threshold function of the candidate Boolean threshold network as the dynamical equations. To overcome the multi-collinearity and over-fitting problems, a new and effective approach is designed to optimize the network topology by adding a perturbation design matrix to the input data and thereafter setting sufficiently small elements of the output coefficient vector to zeros. In addition, the cross-validation procedure is implemented into the Boolean threshold network model framework to strengthen the inference capability. Finally, extensive experiments on one simulated Boolean value dataset, dozens of simulation datasets and three real scRNA-seq datasets demonstrate that the LogBTF method can infer GRNs from time series data more accurately than some other alternative methods for GRN inference. Availability and implementation The source data and code are available at https://github.com/zpliulab/LogBTF. Supplementary information Supplementary data are available at Bioinformatics online.

SAILoR: Structure-Aware Inference of Logic Rules

“…We compared the performance of SAILoR with the performance of other Boolean network inference approaches, namely Best-Fit [ 15 ], REVEAL [ 7 ], MIBNI [ 8 ], GABNI [ 5 ], ATEN [ 4 ], and LogBTF [ 10 ]. Our results show that SAILoR retained the ability to infer Boolean networks with high dynamic accuracy while improving the correctness of the underlying influence network (see Fig 9 ).…”

“…Errors often occur in real experimental data due to noisy conditions and measurement errors [ 62 ]. Finally, Li et al [ 10 ] evaluated the dynamic performance of LogBTF on the training data, while 10-fold cross-validation was used in our case. This may additionally explain the discrepancy between our results and the results reported by Li et al…”

“…Many computational methods for inference of Boolean networks from time-series data have been proposed. These utilize either heuristic algorithms [ 4 – 6 ], entropy and mutual information [ 7 , 8 ], or machine learning approaches [ 9 , 10 ]. For example, Li et al [ 10 ] developed LogBTF, which utilizes regularized logistic regression to obtain regression coefficients, which act as weights in the Boolean threshold network model.…”

“…These utilize either heuristic algorithms [ 4 – 6 ], entropy and mutual information [ 7 , 8 ], or machine learning approaches [ 9 , 10 ]. For example, Li et al [ 10 ] developed LogBTF, which utilizes regularized logistic regression to obtain regression coefficients, which act as weights in the Boolean threshold network model. The utilization of Boolean threshold functions for the description of GRNs is supported by recent analyses [ 11 , 12 ] of expert-curated Boolean network models, which revealed a high prevalence of nested canalizing functions, where specific values of single inputs with different priorities determine the function value.…”

scGREAT: Transformer-based deep-language model for gene regulatory network inference from single-cell transcriptomics

“… 1 Gene regulatory network (GRN) illustrates the intricate interactions among genes, consisting of regulatory relationships among a variety of molecular entities. 2 Accurate reconstruction of GRN is essential for understanding the behavior of different genes, 3 , 4 such as gene expression mechanisms within cells, and advancing research in disease pathology. 5 Single-cell technology has brought opportunities for GRN inference but also unprecedented challenges, especially complexity and inherent noise in scRNA-seq data post unique challenges.…”