A massive number of transcriptomic profiles of blood samples from COVID-19 patients has been produced since pandemic COVID-19 begins, however, these big data from primary studies have not been well integrated by machine learning approaches. Taking advantage of modern machine learning arthrograms, we integrated and collected single cell RNA-seq (scRNA-seq) data from three independent studies, identified genes potentially available for interpretation of severity, and developed a high-performance deep learning-based deconvolution model AImmune that can predict the proportion of seven different immune cells from the bulk RNA-seq results of human peripheral mononuclear cells. This novel approach which can be used for clinical blood testing of COVID-19 on the ground that previous research shows that mRNA alternations in blood-derived PBMCs may serve as a severity indicator. Assessed on real-world data sets, the AImmune model outperformed the most recognized immune profiling model CIBERSORTx. The presented study showed the results obtained by the true scRNA-seq route can be consistently reproduced through the new approach AImmune, indicating a potential replacing the costly scRNA-seq technique for the analysis of circulating blood cells for both clinical and research purposes.

Background: For patients with non-small cell lung cancer (NSCLC), the PD-1/PD-L1 blockade treatment were incorporated into first-line treatment commonly. Despite the improved survival observed in PD-1 blockade treatment, a large proportion of patients do not respond while others actually progress during treatment. Method: Transcriptomic profiling was performed on whole blood samples from 30 patients received anti-PD-1 (Tislelizumab) plus chemotherapy. Expression levels of differentially expressed genes (DEGs) identified from two comparisons (post-and pre-treatment, responders and non-responders) were validated by real-time quantitative PCR, analyzed within tissue database and meta-analysis database, then followed by enrichment analysis in high-level representations and in silico leukocyte deconvolution. Results: A panel of blood-based gene signatures (FDR p<0.05, fold change<-2 or >2) were identified (DEG n=155 and 112 in two comparisons) and validated that not only differentially expressed between post- and pre- treatment or responders and non-responders but also in tissue samples between normal and tumor. Genes DLG5 and H3C10 were found negatively associated with overall survival (p<0.05). Enrichment of immunological and metabolism pathways and gene sets indicating activated circulating leukocytes were observed. Conclusion: The molecular and cellular signatures characterized in this study may provide potential blood-based predictors of the response to PD-1 blockade treatment in NSCLC patients.