Dataset Information

Random survival forest model identifies novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia

ABSTRACT: Graphical abstract High-risk pediatric B-ALL patients experience 5-year negative event rates up to 25%. Although some biomarkers of relapse are utilized in the clinic, their ability to predict outcomes in high-risk patients is limited. Here, we propose a random survival forest (RSF) machine learning model utilizing interpretable genomic inputs to predict relapse/death in high-risk pediatric B-ALL patients. We utilized whole exome sequencing profiles from 156 patients in the TARGET-ALL study (with samples collected at presentation) further stratified into training and test cohorts (109 and 47 patients, respectively). To avoid overfitting and facilitate the interpretation of machine learning results, input genomic variables were engineered using a stepwise approach involving univariable Cox models to select variables directly associated with outcomes, genomic coordinate-based analysis to select mutational hotspots, and correlation analysis to eliminate feature co-linearity. Model training identified 7 genomic regions most predictive of relapse/death-free survival. The test cohort error rate was 12.47%, and a polygenic score based on the sum of the top 7 variables effectively stratified patients into two groups, with significant differences in time to relapse/death (log-rank P = 0.001, hazard ratio = 5.41). Our model outperformed other EFS modeling approaches including an RSF using gold-standard prognostic variables (error rate = 24.35%). Validation in 174 standard-risk patients and 3 patients who failed to respond to induction therapy confirmed that our RSF model and polygenic score were specific to high-risk disease. We propose that our feature selection/engineering approach can increase the clinical interpretability of RSF, and our polygenic score could be utilized for enhance clinical decision-making in high-risk B-ALL.

SUBMITTER: Bohannan Z

PROVIDER: S-EPMC8777142 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose Children with acute myeloid leukemia (AML) whose disease is refractory to standard induction chemotherapy therapy or who experience relapse after initial response have dismal outcomes. We sought to comprehensively profile pediatric AML microRNA (miRNA) samples to identify dysregulated genes and assess the utility of miRNAs for improved outcome prediction. Patients and Methods To identify miRNA biomarkers that are associated with treatment failure, we performed a comprehensive sequence-based characterization of the pediatric AML miRNA landscape. miRNA sequencing was performed on 1,362 samples-1,303 primary, 22 refractory, and 37 relapse samples. One hundred sixty-four matched samples-127 primary and 37 relapse samples-were analyzed by using RNA sequencing. Results By using penalized lasso Cox proportional hazards regression, we identified 36 miRNAs the expression levels at diagnosis of which were highly associated with event-free survival. Combined expression of the 36 miRNAs was used to create a novel miRNA-based risk classification scheme (AMLmiR36). This new miRNA-based risk classifier identifies those patients who are at high risk (hazard ratio, 2.830; P ? .001) or low risk (hazard ratio, 0.323; P ? .001) of experiencing treatment failure, independent of conventional karyotype or mutation status. The performance of AMLmiR36 was independently assessed by using 878 patients from two different clinical trials (AAML0531 and AAML1031). Our analysis also revealed that miR-106a-363 was abundantly expressed in relapse and refractory samples, and several candidate targets of miR-106a-5p were involved in oxidative phosphorylation, a process that is suppressed in treatment-resistant leukemic cells. Conclusion To assess the utility of miRNAs for outcome prediction in patients with pediatric AML, we designed and validated a miRNA-based risk classification scheme. We also hypothesized that the abundant expression of miR-106a could increase treatment resistance via modulation of genes that are involved in oxidative phosphorylation.

Project description:UNLABELLED:Genetic lesions such as BCR-ABL1, E2A-PBX1, and MLL rearrangements (MLLr) are associated with unfavorable outcomes in adult B-cell precursor acute lymphoblastic leukemia (B-ALL). Leukemia oncoproteins may directly or indirectly disrupt cytosine methylation patterning to mediate the malignant phenotype. We postulated that DNA methylation signatures in these aggressive B-ALLs would point toward disease mechanisms and useful biomarkers and therapeutic targets. We therefore conducted DNA methylation and gene expression profiling on a cohort of 215 adult patients with B-ALL enrolled in a single phase III clinical trial (ECOG E2993) and normal control B cells. In BCR-ABL1-positive B-ALLs, aberrant cytosine methylation patterning centered around a cytokine network defined by hypomethylation and overexpression of IL2RA(CD25). The E2993 trial clinical data showed that CD25 expression was strongly associated with a poor outcome in patients with ALL regardless of BCR-ABL1 status, suggesting CD25 as a novel prognostic biomarker for risk stratification in B-ALLs. In E2A-PBX1-positive B-ALLs, aberrant DNA methylation patterning was strongly associated with direct fusion protein binding as shown by the E2A-PBX1 chromatin immunoprecipitation (ChIP) sequencing (ChIP-seq), suggesting that E2A-PBX1 fusion protein directly remodels the epigenome to impose an aggressive B-ALL phenotype. MLLr B-ALL featured prominent cytosine hypomethylation, which was linked with MLL fusion protein binding, H3K79 dimethylation, and transcriptional upregulation, affecting a set of known and newly identified MLL fusion direct targets with oncogenic activity such as FLT3 and BCL6. Notably, BCL6 blockade or loss of function suppressed proliferation and survival of MLLr leukemia cells, suggesting BCL6-targeted therapy as a new therapeutic strategy for MLLr B-ALLs. SIGNIFICANCE:We conducted the first integrative epigenomic study in adult B-ALLs, as a correlative study to the ECOG E2993 phase III clinical trial. This study links for the first time the direct actions of oncogenic fusion proteins with disruption of epigenetic regulation mediated by cytosine methylation. We identify a novel clinically actionable biomarker in B-ALLs: IL2RA (CD25), which is linked with BCR-ABL1 and an inflammatory signaling network associated with chemotherapy resistance. We show that BCL6 is a novel MLL fusion protein target that is required to maintain the proliferation and survival of primary human adult MLLr cells and provide the basis for a clinical trial with BCL6 inhibitors for patients with MLLr.

Dataset Information

Random survival forest model identifies novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets