Background: Building biological networks with a certain function is a challenge in systems biology. For the functionality of small (less than ten nodes) biological networks, most methods are implemented by exhausting all possible network topological spaces. This exhaustive approach is difficult to scale to large-scale biological networks. And regulatory relationships are complex and often nonlinear or non-monotonic, which makes inference using linear models challenging. Results: In this paper, we propose a multi-layer perceptron-based differential equation method, which operates by training a fully connected neural network (NN) to simulate the transcription rate of genes in traditional differential equations. We verify whether the regulatory network constructed by the NN method can continue to achieve the expected biological function by verifying the degree of overlap between the regulatory network discovered by NN and the regulatory network constructed by the Hill function. And we validate our approach by adapting to noise signals, regulator knockout, and constructing large-scale gene regulatory networks using link-knockout techniques. We apply a real dataset (the mesoderm inducer Xenopus Brachyury expression) to construct the core topology of the gene regulatory network and find that Xbra is only strongly expressed at moderate levels of activin signaling. Conclusion: We have demonstrated from the results that this method has the ability to identify the underlying network topology and functional mechanisms, and can also be applied to larger and more complex gene network topologies.

Chromosomal instability (CIN) covers approximately 65 to 70% of colorectal cancer patients and plays an essential role in cancer progression. However, the molecular features and therapeutic strategies related to those patients are still controversial. R-loop binding proteins (RLBPs) exert significant roles in transcription and replication. Here, integrative colorectal cancer proteogenomic analysis identified two RLBPs subtypes correlated with distinct prognoses. Cluster I (CI), represented by high expression of RLBPs, was associated with the CIN phenotype. While Cluster II (CII) with the worst prognosis and low expression of RLBPs was composed of a high percentage of patients with mucinous adenocarcinoma or right-sided colon cancer. The molecular feature analysis revealed that the active RNA processing, ribosome synthesis, and aberrant DNA damage repair were shown in CI, a high inflammatory signaling pathway, and lymphocyte infiltration was enriched in CII. In addition, we revealed 42 tumor-associated RLBPs proteins. The CI with high expression of tumor-associated proteins was sensitive to drugs targeting genome integrity and EGFR in both cell and organoid models. Thus, our study unveils a significant molecular association of the CIN phenotype with RLBPs, and also provides a powerful resource for further functional exploration of RLBPs in cancer progression and therapeutic application.

Accurate prediction of gene regulation rules is important for understanding complex life processes. Existing computational algorithms designed for bulk transcriptome datasets typically require a large number of time points to infer gene regulatory networks (GRNs), are suitable for a small number of genes, and cannot efficiently detect potential regulatory relationships. We propose an approach based on a deep learning framework to reconstruct GRNs from bulk transcriptome datasets, assuming that the expression levels of transcription factors involved in gene regulation are strong predictors of the expression of their target genes. The algorithm uses multilayer perceptrons to infer the regulatory relationship between multiple transcription factors and a gene, and uses genetic algorithms to search for the best regulatory gene combination. The results show that our approach is more accurate than other methods for reconstructing gene regulatory networks on real-world and simulated bulk transcriptome gene expression datasets.