PSG and Other Candidate Genes as Potential Biomarkers of Therapy Resistance in B-ALL: Insights from Chromosomal Microarray Analysis and Machine Learning

Abstract

Chromosomal microarray analysis (CMA) was performed for 40 patients with B-ALL undergoing treatment according to the ALL-2016 protocol to investigate the copy number alterations (CNAs) and copy neutral loss of heterozygosity (cnLOH) associated with minimal residual disease (MRD)-positive remission. Aberrations involving over 20,000 genes were identified, and a random forest approach was applied to isolate a subset of genes whose CNAs and cnLOH are significantly associated with poor therapeutic response. We have assembled the triple matched healthy population data and used that data as a reference, but not as a matched control. We identified a recurrent cluster of cnLOH in the 19q13.2-19q13.31 region, significantly enriched in MRD-positive patients (70% vs. 47% in the reference group vs. 16% in MRD-negative patients). This region includes the pregnancy-specific glycoprotein (PSG) gene family and the oncogene ERF, suggesting a potential role in leukemic persistence and treatment resistance. Additionally, we observed significant deletions involving 7p22.3 and 16q13, often as part of large-scale losses affecting almost the entire chromosomes 7 and 16, indicative of global chromosomal instability. These findings highlight specific genomic regions potentially involved in therapy resistance and may contribute to improved risk stratification in B-ALL. Our findings emphasize the value of high-resolution CMA in diagnostics and risk stratification and suggest that PSG genes and other candidate genes could serve as biomarkers for predicting treatment outcomes.

Keywords: acute B-lymphoblastic leukemia (B-ALL); copy neutral loss of heterozygosity (cnLOH); copy number alterations (CNAs); genes; machine learning.

Figure 1

Loss and gain aberrations for B-ALL patients at the onset of the disease. Aberrations exceeding 500 Kbase are presented. Blue color for gain aberrations, red for loss aberrations.

Figure 2

cnLOH for B-ALL patients at the onset of the disease. Aberrations exceeding 5000 Kbase are presented. Purple color for cnLOH.

Figure 3

Top 100 genes with MRD remission-associated aberrations: blue color for MRD⁺ remission risk factors, red for favorable MRD aberrations.

Figure 4

Permutation test: histogram of permuted model distribution and real accuracy red dot line.

Figure 5

Heatmap of aberrations in the top 200 RF-ranked genes across 35 patients. Purple for cn-LOH, red for loss, blue for gain.

Figure 6

Bar chart of top enriched terms from the Reactome Pathways 2024 gene set library [12]. The top 20 enriched terms for the input gene set are displayed based on the −log10(p-value), with the actual p-value shown next to each term. The terms that have significant overlap with the input query gene set are colored in blue.

Figure 7

Frequency of 19q13.2–19q13.31 aberrations in patients and reference group: red color for MRD⁺ patients, yellow for MRD⁻ patients, green for reference group.

Figure 8

Localization of top genes associated with MRD-status of B-ALL. Purple for cn-LOH, red for loss aberrations.

Figure 9

An example of verification of CMA-identified molecular karyotype aberrations (a) using STR analysis of paired tumor and normal DNA samples from a patient. (b) Duplications of chromosomes 10 and X are evidenced by allelic imbalance of the STR markers D10S1248 and Amelogenin (highlighted with blue frames).

Figure 9

An example of verification of CMA-identified molecular karyotype aberrations (a) using STR analysis of paired tumor and normal DNA samples from a patient. (b) Duplications of chromosomes 10 and X are evidenced by allelic imbalance of the STR markers D10S1248 and Amelogenin (highlighted with blue frames).