Robust and consistent biomarker candidates identification by a machine learning approach applied to pancreatic ductal adenocarcinoma metastasis.

BACKGROUND: Machine Learning (ML) plays a crucial role in biomedical research. Nevertheless, it still has limitations in data integration and irreproducibility. To address these challenges, robust methods are needed. Pancreatic ductal adenocarcinoma (PDAC), a highly aggressive cancer with low early detection rates and survival rates, is used as a case study. PDAC lacks reliable diagnostic biomarkers, especially metastatic biomarkers, which remains an unmet need. In this study, we propose an ML-based approach for discovering disease biomarkers, apply it to the identification of a PDAC metastatic composite biomarker candidate, and demonstrate the advantages of harnessing data resources. METHODS: We utilised primary tumour RNAseq data from five public repositories, pooling samples to maximise statistical power and integrating data by correcting for technical variance. Data were split into train and validation sets. The train dataset underwent variable selection via a 10-fold cross-validation process that combined three algorithms in 100 models per fold. Genes found in at least 80% of models and five folds were considered robust to build a consensus multivariate model. A random forest model was constructed using selected genes from the train dataset and tested in the validation set. We also assessed the goodness of prediction by recalibrating a model using only the validation data. The biological context and relevance of signals was explored through enrichment and pathway analyses using QIAGEN Ingenuity Pathway Analysis and GeneMANIA. RESULTS: We developed a pipeline that can detect robust signatures to build composite biomarkers. We tested the pipeline in PDAC, exploiting transcriptomics data from different sources, proposing a composite biomarker candidate comprised of fifteen genes consistently selected that showed very promising predictive capability. Biological contextualisation revealed links with cancer progression and metastasis, underscoring their potential relevance. All code is available in GitHub. CONCLUSION: This study establishes a robust framework for identifying composite biomarkers across various disease contexts. We demonstrate its potential by proposing a plausible composite biomarker candidate for PDAC metastasis. By reusing data from public repositories, we highlight the sustainability of our research and the wider applications of our pipeline. The preliminary findings shed light on a promising validation and application path.

Mesothelin Secretion by Pancreatic Cancer Cells Co-opts Macrophages and Promotes Metastasis.

Pancreatic ductal adenocarcinoma (PDAC) is a highly metastatic disease, yet effective treatments to inhibit PDAC metastasis are lacking. The rich PDAC tumor microenvironment plays a major role in disease progression. Macrophages are the most abundant immune cell population in PDAC tumors and can acquire a range of functions that either hinder or promote tumor growth and metastasis. Here, we identified that mesothelin secretion by pancreatic cancer cells co-opts macrophages to support tumor growth and metastasis of cancer cells to the lungs, liver, and lymph nodes. Mechanistically, secretion of high levels of mesothelin by metastatic cancer cells induced the expression of VEGF alpha (VEGFA) and S100A9 in macrophages. Macrophage-derived VEGFA fed back to cancer cells to support tumor growth, and S100A9 increased neutrophil lung infiltration and formation of neutrophil extracellular traps. These results reveal a role for mesothelin in regulating macrophage functions and interaction with neutrophils to support PDAC metastasis. SIGNIFICANCE: Mesothelin secretion by cancer cells supports pancreatic cancer metastasis by inducing macrophage secretion of VEGFA and S100A9 to support cancer cell proliferation and survival, recruit neutrophils, and stimulate neutrophil extracellular trap formation. See related commentary by Alewine, p. 513.

Blockade of Stromal Gas6 Alters Cancer Cell Plasticity, Activates NK Cells, and Inhibits Pancreatic Cancer Metastasis.

Pancreatic ductal adenocarcinoma (PDA) is one of the deadliest cancers due to its aggressive and metastatic nature. PDA is characterized by a rich tumor stroma with abundant macrophages, fibroblasts, and collagen deposition that can represent up to 90% of the tumor mass. Activation of the tyrosine kinase receptor AXL and expression of its ligand growth arrest-specific protein 6 (Gas6) correlate with a poor prognosis and increased metastasis in pancreatic cancer patients. Gas6 is a multifunctional protein that can be secreted by several cell types and regulates multiple processes, including cancer cell plasticity, angiogenesis, and immune cell functions. However, the role of Gas6 in pancreatic cancer metastasis has not been fully investigated. In these studies we find that, in pancreatic tumors, Gas6 is mainly produced by tumor associated macrophages (TAMs) and cancer associated fibroblasts (CAFs) and that pharmacological blockade of Gas6 signaling partially reverses epithelial-to-mesenchymal transition (EMT) of tumor cells and supports NK cell activation, thereby inhibiting pancreatic cancer metastasis. Our data suggest that Gas6 simultaneously acts on both the tumor cells and the NK cells to support pancreatic cancer metastasis. This study supports the rationale for targeting Gas6 in pancreatic cancer and use of NK cells as a potential biomarker for response to anti-Gas6 therapy.