High-throughput transcriptome profiling indicates ribosomal RNAs to be associated with resistance to immunotherapy in non-small cell lung cancer (NSCLC).

BACKGROUND: Despite the impressive outcomes with immune checkpoint inhibitor (ICI) in non-small cell lung cancer (NSCLC), only a minority of the patients show long-term benefits from ICI. In this study, we used retrospective cohorts of ICI treated patients with NSCLC to discover and validate spatially resolved protein markers associated with resistance to programmed cell death protein-1 (PD-1) axis inhibition. METHODS: Pretreatment samples from 56 patients with NSCLC treated with ICI were collected and analyzed in a tissue microarray (TMA) format in including four different tumor regions per patient using the GeoMx platform for spatially informed transcriptomics. 34 patients had assessable tissue with tumor compartment in all 4 TMA spots, 22 with leukocyte compartment and 12 with CD68 compartment. The patients' tissue that was not assessable in fourfold redundancy in each compartment was designated as the validation cohort; cytokeratin (CK) (N=22), leukocytes CD45 (N=31), macrophages, CD68 (N=43). The human whole transcriptome, represented by~18,000 individual genes assessed by oligonucleotide-tagged in situ hybridization, was sequenced on the NovaSeq platform to quantify the RNAs present in each region of interest. RESULTS: 54,000 gene variables were generated per case, from them 25,740 were analyzed after removing targets with expression lower than a prespecified frequency. Cox proportional-hazards model analysis was performed for overall and progression-free survival (OS, PFS, respectively). After identifying genes significantly associated with limited survival benefit (HR>1)/progression per spot per patient, we used the intersection of them across the four TMA spots per patient. This resulted in a list of 12 genes in the tumor-cell compartment (RPL13A, GNL3, FAM83A, CYBA, ACSL4, SLC25A6, EPAS1, RPL5, APOL1, HSPD1, RPS4Y1, ADI1). RPL13A, GNL3 in tumor-cell compartment were also significantly associated with OS and PFS, respectively, in the validation cohort (CK: HR, 2.48; p=0.02 and HR, 5.33; p=0.04). In CD45 compartment, secreted frizzled-related protein 2, was associated with OS in the discovery cohort but not in the validation cohort. Similarly, in the CD68 compartment ARHGAP and PNN interacting serine and arginine rich protein were significantly associated with PFS and OS, respectively, in the majority but not all four spots per patient. CONCLUSION: This work highlights RPL13A and GNL3 as potential indicative biomarkers of resistance to PD-1 axis blockade that might help to improve precision immunotherapy strategies for lung cancer.

Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees.

We define an iterative method for dimensionality reduction using categorical gradient boosted trees and Shapley values and created four machine learning models which potentially could be used as diagnostic tests for acute myeloid leukaemia (AML). For the final Catboost model we use a dataset of 2177 individuals using as features 16 probe sets and the age in order to classify if someone has AML or is healthy. The dataset is multicentric and consists of data from 27 organizations, 25 cities, 15 countries and 4 continents. The performance of our last model is specificity: 0.9909, sensitivity: 0.9985, F1-score: 0.9976 and its ROC-AUC: 0.9962 using ten fold cross validation. On an inference dataset the perormance is: specificity: 0.9909, sensitivity: 0.9969, F1-score: 0.9969 and its ROC-AUC: 0.9939. To the best of our knowledge the performance of our model is the best one in the literature, as regards the diagnosis of AML using similar or not data. Moreover, there has not been any bibliographic reference which associates AML or any other type of cancer with the 16 probe sets we used as features in our final model.