Novel Diagnostic and Therapeutic Options for KMT2A-Rearranged Acute Leukemias

Abstract

The KMT2A (MLL) gene rearrangements (KMT2A-r) are associated with a diverse spectrum of acute leukemias. Although most KMT2A-r are restricted to nine partner genes, we have recently revealed that KMT2A-USP2 fusions are often missed during FISH screening of these genetic alterations. Therefore, complementary methods are important for appropriate detection of any KMT2A-r. Here we use a machine learning model to unravel the most appropriate markers for prediction of KMT2A-r in various types of acute leukemia. A Random Forest and LightGBM classifier was trained to predict KMT2A-r in patients with acute leukemia. Our results revealed a set of 20 genes capable of accurately estimating KMT2A-r. The SKIDA1 (AUC: 0.839; CI: 0.799-0.879) and LAMP5 (AUC: 0.746; CI: 0.685-0.806) overexpression were the better markers associated with KMT2A-r compared to CSPG4 (also named NG2; AUC: 0.722; CI: 0.659-0.784), regardless of the type of acute leukemia. Of importance, high expression levels of LAMP5 estimated the occurrence of all KMT2A-USP2 fusions. Also, we performed drug sensitivity analysis using IC50 data from 345 drugs available in the GDSC database to identify which ones could be used to treat KMT2A-r leukemia. We observed that KMT2A-r cell lines were more sensitive to 5-Fluorouracil (5FU), Gemcitabine (both antimetabolite chemotherapy drugs), WHI-P97 (JAK-3 inhibitor), Foretinib (MET/VEGFR inhibitor), SNX-2112 (Hsp90 inhibitor), AZD6482 (PI3Kβ inhibitor), KU-60019 (ATM kinase inhibitor), and Pevonedistat (NEDD8-activating enzyme (NAE) inhibitor). Moreover, IC50 data from analyses of ex-vivo drug sensitivity to small-molecule inhibitors reveals that Foretinib is a promising drug option for AML patients carrying FLT3 activating mutations. Thus, we provide novel and accurate options for the diagnostic screening and therapy of KMT2A-r leukemia, regardless of leukemia subtype.

Keywords: KMT2A; MLL; acute leukemia; biomarker; machine learning; therapy.

FIGURE 1

Machine learning performance. (A) ROC curve of the selected machine learning model with 247 genes, and the confusion matrix with performance measures of testing data. The darker the quadrant color, the greater the number of patients. Respective performance measures are below the matrix. (B) Feature contributions according to the shapley values. On the x-axis, positive and negative values are correlated with prediction of KMT2A-r and KMT2A-WT, respectively. Each dot represents one patient, colored according to the feature value (red fading to blue means high to low values).

FIGURE 2

Testing and validation of potential KMT2A-r predictors. (A) ROC curve and confusion matrix of the test cohort for the machine learning model with top 20 genes. The darker the quadrant color, the greater the number of patients. The machine learning performance measures are beside the matrix. (B) Feature contributions of each gene included in this model according to the shapley values. On the x-axis, positive and negative values are correlated with prediction of KMT2A-r and KMT2A-WT, respectively. Each dot represents one patient, colored according to the feature value (red fading to blue means high to low values). (C) The performance measures of our model in an independent cohort (TCGA dataset including AML patients), represented by the confusion matrix, and a (D) heatmap illustrating the expression of 11 KMT2A-r predictor genes as indicated by the machine learning analysis. The clusterization was performed in the French dataset with ALL patients.

FIGURE 3

Relationship between SKIDA1, LAMP5, and CSPG4 expression and KMT2A-r in acute leukemia. (A) ROC curves and AUC values of each gene transcript according to acute leukemia subtypes. (B) Transcript expression among varied KMT2A fusions.

FIGURE 4

Identification of therapeutic drugs for KMT2A-r leukemia. (A) Comparison of the IC50 data, available in the GDSC database, to several drugs between KMT2A-WT and KMT2A-r leukemia cell lines. The KG-1 (red point) is a human AML cell line, with a variant, KG-1a, known to be resistant to chemotherapy. Comparison of the sensitivity to foretinib between (B) AML molecular subgroups and KMT2A-r, as well as (C) FLT3 wild-type (red boxplot) and FLT3 mutated (yellow boxplot). (D) Transcript expression compared between KMT2A-WT and KMT2A-r in acute leukemia samples included in this study.