Proteomics-based clustering of lung adenocarcinoma identifies three subtypes with significantly different clinical and molecular features.

BACKGROUND: Lung adenocarcinoma (LUAD) is a predominant subtype of lung cancer. Although molecular classification of LUAD has been widely explored, proteomics-based subtyping of LUAD remains scarce. METHODS: We proposed a subtyping method for LUAD based on the expression profiles of 500 proteins with the largest expression variability across LUAD. Furthermore, we comprehensively compared molecular and clinical features among the LUAD subtypes. RESULTS: Consensus clustering identified three subtypes of LUAD, namely MtE, DrE, and StE. We demonstrated this subtyping method to be reproducible by analyzing two independent LUAD cohorts. MtE was characterized by high enrichment of metabolic pathways, high EGFR mutation rate, low stemness, proliferation, invasion, metastasis and inflammation signatures, favorable prognosis; DrE was characterized by high enrichment of DNA repair pathways, high TP53 mutation rate, and high levels of genomic instability, stemness, proliferation, and intratumor heterogeneity (ITH); and StE was characterized by high enrichment of stroma-related pathways, high KRAS mutation rate, and low levels of genomic instability. CONCLUSIONS: The proteomics-based clustering analysis identified three LUAD subtypes with significantly different molecular and clinical properties. The novel subtyping method offers new perspectives on the cancer biology and holds promise in improving the clinical management of LUAD.

PreCanCell: An ensemble learning algorithm for predicting cancer and non-cancer cells from single-cell transcriptomes.

We propose PreCanCell, a novel algorithm for predicting malignant and non-malignant cells from single-cell transcriptomes. PreCanCell first identifies the differentially expressed genes (DEGs) between malignant and non-malignant cells commonly in five common cancer types-associated single-cell transcriptome datasets. The five common cancer types include renal cell carcinoma (RCC), head and neck squamous cell carcinoma (HNSCC), melanoma, lung adenocarcinoma (LUAD), and breast cancer (BC). With each of the five datasets as the training set and the DEGs as the features, a single cell is classified as malignant or non-malignant by k-NN (k = 5). Finally, the single cell is determined as malignant or non-malignant by the majority vote of the five k-NN classification results. We tested the predictive performance of PreCanCell in 19 single-cell datasets, and reported classification accuracy, sensitivity, specificity, balanced accuracy (the average of sensitivity and specificity) and the area under the receiver operating characteristic curve (AUROC). In all these datasets, PreCanCell achieved above 0.8 accuracy, sensitivity, specificity, balanced accuracy and AUROC. Finally, we compared the predictive performance of PreCanCell with that of seven other algorithms, including CHETAH, SciBet, SCINA, scmap-cell, scmap-cluster, SingleR, and ikarus. Compared to these algorithms, PreCanCell displays the advantages of higher accuracy and simpler implementation. We have developed an R package for the PreCanCell algorithm, which is available at https://github.com/WangX-Lab/PreCanCell.