Multidimensional proteomics and explainable AI feature selection identify cross-platform lung cancer molecular signature in blood plasma

Lung cancer is the leading cause of cancer mortality worldwide despite the availability of low-dose computed tomography (LDCT) for screening in high-risk populations. To develop an approach and identify blood-based protein signatures for lung cancer that can be deployed across platforms, we combined data-independent acquisition mass-spectrometry (DIA-MS) and proximity extension assay (PEA) with explainable artificial intelligence (XAI)-led machine learning (ML) for plasma-based biomarker discovery. Using a cohort of 490 lung cancer patients and 124 matched controls, ML models were trained to predict lung cancer and XAI was used to characterise networks of model-consistent features. We then introduced a DNA-aptamer based proteomic approach to assess cross-platform concordance and define a cross-platform signature. This signature was subsequently evaluated using an external cohort. Here we show that ML models achieve an AUROC of 0.91 [95% CI: 0.88-0.93] and 0.97 [95% CI: 0.92-0.98] in DIA-MS and PEA, respectively, using a 80/20% train/holdout split. XAI further characterises networks of model-consistent features related to chemotaxis, cell adhesion, wound healing and immune response. Introduction of the DNA-aptamer proteomic approach identifies a cross-platform signature, with performances of 0.88 [95% CI: 0.80-0.90] and 0.88 [95% CI: 0.81-0.95] in DIA-MS and PEA, respectively. Assessment of this signature in an external cohort separates lung cancer from control cases. This study develops an approach combining multi-dimensional proteomics with XAI-ML and demonstrates the characterisation of cross-platform biomarker signatures for lung cancer. Gushterov, Hankey, Kaneva et al. deploy an explainable AI approach for blood biomarker discovery in a multidimensional proteomics dataset for a high-risk lung cancer population. They identify a cross-platform blood-based molecular signature for lung cancer that has the potential to be transferable across protein detection platforms Lung cancer is the leading cause of cancer deaths globally despite the availability of imaging to screen for the disease in people at high-risk. Computer algorithms that allow users to understand their decision-making rationale (XAI) can identify protein patterns in the blood linked to lung cancer. In this study, we combined different ways of measuring proteins in the blood to identify patterns linked to lung cancer. XAI allowed us to understand how components of these patterns contribute to disease prediction. This led to the identification of a pattern linked to lung cancer that can be used across different ways of protein measurement. These findings contribute to developing an approach for the identification of blood tests for specific disease of interest.