Acute Leukemia Classification Using Transcriptional Profiles From Low-Cost Nanopore mRNA Sequencing

Abstract

PURPOSE Most cases of pediatric acute leukemia occur in low- and middle-income countries, where health centers lack the tools required for accurate diagnosis and disease classification. Recent research shows the robustness of using unbiased short-read RNA sequencing to classify genomic subtypes of acute leukemia. Compared with short-read sequencing, nanopore sequencing has low capital and consumable costs, making it suitable for use in locations with limited health infrastructure. MATERIALS AND METHODS We show the feasibility of nanopore mRNA sequencing on 134 cryopreserved acute leukemia specimens (26 acute myeloid leukemia [AML], 73 B-lineage acute lymphoblastic leukemia [B-ALL], 34 T-lineage acute lymphoblastic leukemia, and one acute undifferentiated leukemia). Using multiple library preparation approaches, we generated long-read transcripts for each sample. We developed a novel composite classification approach to predict acute leukemia lineage and major B-ALL and AML molecular subtypes directly from gene expression profiles. RESULTS We demonstrate accurate classification of acute leukemia samples into AML, B-ALL, or T-lineage acute lymphoblastic leukemia (96.2% of cases are classifiable with a probability of > 0.8, with 100% accuracy) and further classification into clinically actionable genomic subtypes using shallow RNA nanopore sequencing, with 96.2% accuracy for major AML subtypes and 94.1% accuracy for major B-lineage acute lymphoblastic leukemia subtypes. CONCLUSION Transcriptional profiling of acute leukemia samples using nanopore technology for diagnostic classification is feasible and accurate, which has the potential to improve the accuracy of cancer diagnosis in low-resource settings.

Real-time molecular classification of leukemias

“…Molecular profiling of acute leukemias via RNA-seq is a powerful tool for the characterization of disease heterogeneity, biomarker discovery and risk stratification of leukemia patients (2, 9–14 ). Our results demonstrate that nanopore sequencing and supervised machine learning can be used to diagnose and accurately classify molecular ALL subtypes in as little as 4 minutes of sequencing, or in ∼4 hours when factoring in RNA extraction and sample preparation time.…”

“…As for the second, after comparing multiple machine-learning classification models, the selected strategy employs a partial least-squares discriminant classifier trained on 1,036 samples from ALL lineages (B and T) and acute myeloid leukemia (AML) genomic subtypes. It produces binary predictions to be used as features that are input into a non-linear Support Vector Machine (SVM) classifier for 3 leukemia lineages and 8 subtypes (14) . Our classifier employs a feedforward neural network (FNN) trained on 1,134 ALL samples and outputs prediction probabilities for 16 ALL subtypes.…”

Enhancing Molecular Testing for Effective Delivery of Actionable Gene Diagnostics

“…By applying hybrid error correction tools, the long-read error rate is nowadays between 1-4% of that of short reads. Four main branches could use the advantages of ONT in clinical settings: (1) to identify the background of genetic diseases, (2) to molecularly diagnose cancer patients (e.g., acute leukaemias, solid tumors where certain molecular alterations may greatly influence the therapy of choice [ 19 , 20 ]), (3) rapid pathogen identification in an infectious disease scenario, and (4) to rapidly sequence the major histocompatibility of genes for recipient–donor tissues in transplantation medicine. The strength of nanopore sequencing relies in resolving long-range information, which is one of the main limitations of short-read sequencing technologies [ 21 ].…”

The role of relative advantage for development of sequencing‐based diagnostics for pediatric cancer in low‐ and middle‐income countries

“…Examples include Illumina RNA sequencing for acute leukemia, 3,4 Illumina DNA methylation for central nervous system (CNS) malignancy, 5,6 Nanostring for variant detection in multiple tumor types, 7,8 or other novel approaches using chemical ligation probebased assay (CLPA) 9 or Nanopore sequencing (Oxford Nanopore Technologies). 10 Because of the increased access to sequencing technologies through decreasing costs, improving analytic pipelines, and growing access to Cloud-based platforms for data management and computational algorithms, sequencing-based diagnostic technologies have the potential to improve on the current diagnostic approaches in LMIC. The resource requirements and characteristics for such platforms exist on a spectrum.…”