MOTIVATION: Multiomics data analysis is essential for scientific discovery in precision medicine. However, translating analysis results of omics data analysis into novel scientific hypotheses remains a significant challenge. Human experts must manually review analysis results and generate new hypotheses based on extensive and interconnected biomedical prior knowledge, which is subjective and not scalable. While large language models can accelerate the discovery, their reasoning improves when grounded in structured, auditable, and comprehensive biomedical prior knowledge. However, biomedical knowledge is scattered across heterogeneous databases that use diverse and inconsistent nomenclature systems, making it difficult to integrate resources into a unified format for scalable analysis. This fragmentation limits the ability of artificial intelligence systems to fully leverage biomedical data for scientific discovery. RESULTS: We developed BioMedGraphica, a novel all-in-one platform that harmonizes fragmented biomedical resources by integrating 11 entity types and 30 relation types from 43 databases into a unified textual prior knowledge graph containing 2 306 921 entities and 27 232 091 relations. In addition, we present a novel textual-numeric graph (TNG) data structure concept, where textual information captures prior biological knowledge (e.g. transcription start sites, functions, mechanisms), numeric values represent quantitative biomedical features, and the integrated relations can help uncover mechanisms. By bridging prior knowledge with user-specific data, TNG is a novel and ideal data structure for developing novel graph analysis models. AVAILABILITY AND IMPLEMENTATION: The code is available at: https://github.com/FuhaiLiAiLab/BioMedGraphica and BioMedGraphica knowledge graph database can be downloaded from huggingface dataset: https://huggingface.co/datasets/FuhaiLiAiLab/BioMedGraphica.

BACKGROUND: Survival analysis is an important part of cancer studies. In addition to the existing Cox proportional hazards model, deep learning models have recently been proposed in survival prediction, which directly integrates multi-omics data of a large number of genes using the fully connected dense deep neural network layers, which are hard to interpret. On the other hand, cancer signaling pathways are important and interpretable concepts that define the signaling cascades regulating cancer development and drug resistance. Thus, it is important to investigate potential associations between patient survival and individual signaling pathways, which can help domain experts to understand deep learning models making specific predictions. RESULTS: In this exploratory study, we proposed to investigate the relevance and influence of a set of core cancer signaling pathways in the survival analysis of cancer patients. Specifically, we built a simplified and partially biologically meaningful deep neural network, DeepSigSurvNet, for survival prediction. In the model, the gene expression and copy number data of 1967 genes from 46 major signaling pathways were integrated in the model. We applied the model to four types of cancer and investigated the influence of the 46 signaling pathways in the cancers. Interestingly, the interpretable analysis identified the distinct patterns of these signaling pathways, which are helpful in understanding the relevance of signaling pathways in terms of their application to the prediction of cancer patients' survival time. These highly relevant signaling pathways, when combined with other essential signaling pathways inhibitors, can be novel targets for drug and drug combination prediction to improve cancer patients' survival time. CONCLUSION: The proposed DeepSigSurvNet model can facilitate the understanding of the implications of signaling pathways on cancer patients' survival by integrating multi-omics data and clinical factors.