Adult T-cell leukemia/lymphoma (ATLL) is pathogen-caused cancer that is progressed after the infection by human T-cell leukemia virus type 1. Four significant subtypes comprising acute, lymphoma, chronic, and smoldering have been identified for this cancer. However, there are no trustworthy prognostic biomarkers for these subtypes. We utilized a combination of two powerful network-based and machine-learning algorithms including differential co-expressed genes (DiffCoEx) and support vector machine-recursive feature elimination with cross-validation (SVM-RFECV) methods to categorize disparate ATLL subtypes from asymptomatic carriers (ACs). The results disclosed the significant involvement of CBX6, CNKSR1, and MAX in chronic, MYH10 and P2RY1 in acute, C22orf46 and HNRNPA0 in smoldering subtypes. These genes also can classify each ATLL subtype from AC carriers. The integration of the results of two powerful algorithms led to the identification of reliable gene classifiers and biomarkers for diverse ATLL subtypes.

Adult T-cell Leukemia/Lymphoma (ATLL) is a rapidly progressing type of T-cell non-Hodgkin lymphoma that is developed after the infection by human T-cell leukemia virus type 1 (HTLV-1). It could be categorized into four major subtypes, acute, lymphoma, chronic, and smoldering. These different subtypes have some shared clinical manifestations, and there are no trustworthy biomarkers for diagnosis of them.
We applied weighted-gene co-expression network analysis to find the potential gene and miRNA biomarkers for various ATLL subtypes. Afterward, we found reliable miRNA-gene interactions by identifying the experimentally validated-target genes of miRNAs.
The outcomes disclosed the interactions of miR-29b-2-5p and miR-342-3p with LSAMP in ATLL_acute, miR-575 with UBN2, miR-342-3p with ZNF280B, and miR-342-5p with FOXRED2 in ATLL_chronic, miR-940 and miR-423-3p with C6orf141, miR-940 and miR-1225-3p with CDCP1, and miR-324-3p with COL14A1 in ATLL_smoldering. These miRNA-gene interactions determine the molecular factors involved in the pathogenesis of each ATLL subtype and the unique ones could be considered biomarkers.
The above-mentioned miRNAs-genes interactions are suggested as diagnostic biomarkers for different ATLL subtypes.

BACKGROUND: Adult T-cell Leukemia/Lymphoma (ATLL) is a cancer disease that is developed due to the infection by human T-cell leukemia virus type 1. It can be classified into four main subtypes including, acute, chronic, smoldering, and lymphoma. Despite the clinical manifestations, there are no reliable diagnostic biomarkers for the classification of these subtypes.
METHODS: Herein, we employed a machine learning approach, namely, Support Vector Machine-Recursive Feature Elimination with Cross-Validation (SVM-RFECV) to classify the different ATLL subtypes from Asymptomatic Carriers (ACs). The expression values of multiple mRNAs and miRNAs were used as the features. Afterward, the reliable miRNA-mRNA interactions for each subtype were identified through exploring the experimentally validated-target genes of miRNAs.
RESULTS: The results revealed that miR-21 and its interactions with DAAM1 and E2F2 in acute, SMAD7 in chronic, MYEF2 and PARP1 in smoldering subtypes could significantly classify the diverse subtypes.
CONCLUSIONS: Considering the high accuracy of the constructed model, the identified mRNAs and miRNA are proposed as the potential therapeutic targets and the prognostic biomarkers for various ATLL subtypes.