Machine learning based analysis of single-cell data reveals evidence of subject-specific single-cell gene expression profiles in acute myeloid leukaemia patients and healthy controls

• Published in: Biochimica et biophysica acta. Gene regulatory mechanisms Vol. 1867; no. 4; p. 195062
• Main Authors: Chrysostomou, Andreas, Furlan, Cristina, Saccenti, Edoardo
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2024
• Subjects: Case-Control Studies; Classification; Gene Expression Profiling; Gene Expression Regulation, Leukemic; Gene regulation; Genomics; Humans; Leukemia, Myeloid, Acute - genetics; Machine Learning; Personalized medicine; Single-Cell Analysis - methods; Transcriptome; Personalized medicine; Genomics; Gene regulation; Classification
• ISSN: 1874-9399; 1876-4320; 1876-4320
• DOI: 10.1016/j.bbagrm.2024.195062

Acute Myeloid Leukaemia (AML) is characterized by uncontrolled growth of immature myeloid cells, disrupting normal blood production. Treatment typically involves chemotherapy, targeted therapy, and stem cell transplantation but many patients develop chemoresistance, leading to poor outcomes due to the disease's high heterogeneity. In this study, we used publicly available single-cell RNA sequencing data and machine learning to classify AML patients and healthy, monocytes, dendritic and progenitor cells population. We found that gene expression profiles of AML patients and healthy controls can be classified at the individual level with high accuracy (>70 %) when using progenitor cells, suggesting the existence of subject-specific single cell transcriptomics profiles. The analysis also revealed molecular determinants of patient heterogeneity (e.g. TPSD1, CT45A1, and GABRA4) which could support new strategies for patient stratification and personalized treatment in leukaemia. •Acute Myeloid Leukaemia (AML) treatment often has poor outcomes due to the disease's high level of heterogeneity.•Use of publicly available single-cell transcriptomics data and Random Forest to classify AML patients’ heterogeneity.•Gene expression of AML patients and controls can be accurately classified at the individual level using progenitor cells.•Random Forest modelling identifies molecular determinants of patient heterogeneity.•Findings support new strategies for patient stratification and future personalized treatment in AML.