Identification of Six Diagnostic Biomarkers for Chronic Lymphocytic Leukemia Based on Machine Learning Algorithms

Genes selection using deep learning and explainable artificial intelligence for chronic lymphocytic leukemia predicting the need and time to therapy

Analyzing gene expression profiles (GEP) through artificial intelligence provides meaningful insight into cancer disease. This study introduces DeepSHAP Autoencoder Filter for Genes Selection (DSAF-GS), a novel deep learning and explainable artificial intelligence-based approach for feature selection in genomics-scale data. DSAF-GS exploits the autoencoder's reconstruction capabilities without changing the original feature space, enhancing the interpretation of the results. Explainable artificial intelligence is then used to select the informative genes for chronic lymphocytic leukemia prognosis of 217 cases from a GEP database comprising roughly 20,000 genes. The model for prognosis prediction achieved an accuracy of 86.4%, a sensitivity of 85.0%, and a specificity of 87.5%. According to the proposed approach, predictions were strongly influenced by CEACAM19 and PIGP, moderately influenced by MKL1 and GNE, and poorly influenced by other genes. The 10 most influential genes were selected for further analysis. Among them, FADD, FIBP, FIBP, GNE, IGF1R, MKL1, PIGP, and SLC39A6 were identified in the Reactome pathway database as involved in signal transduction, transcription, protein metabolism, immune system, cell cycle, and apoptosis. Moreover, according to the network model of the 3D protein-protein interaction (PPI) explored using the NetworkAnalyst tool, FADD, FIBP, IGF1R, QTRT1, GNE, SLC39A6, and MKL1 appear coupled into a complex network. Finally, all 10 selected genes showed a predictive power on time to first treatment (TTFT) in univariate analyses on a basic prognostic model including IGHV mutational status, del(11q) and del(17p), NOTCH1 mutations, β2-microglobulin, Rai stage, and B-lymphocytosis known to predict TTFT in CLL. However, only IGF1R [hazard ratio (HR) 1.41, 95% CI 1.08-1.84, P=0.013), COL28A1 (HR 0.32, 95% CI 0.10-0.97, P=0.045), and QTRT1 (HR 7.73, 95% CI 2.48-24.04, P<0.001) genes were significantly associated with TTFT in multivariable analyses when combined with the prognostic factors of the basic model, ultimately increasing the Harrell's c-index and the explained variation to 78.6% (versus 76.5% of the basic prognostic model) and 52.6% (versus 42.2% of the basic prognostic model), respectively. Also, the goodness of model fit was enhanced (χ2 = 20.1, P=0.002), indicating its improved performance above the basic prognostic model. In conclusion, DSAF-GS identified a group of significant genes for CLL prognosis, suggesting future directions for bio-molecular research.

Gene SH3BGRL3 regulates acute myeloid leukemia progression through circRNA_0010984 based on competitive endogenous RNA mechanism

Introduction: Acute myeloid leukemia (AML) is a malignant proliferative disease affecting the bone marrow hematopoietic system and has a poor long-term outcome. Exploring genes that affect the malignant proliferation of AML cells can facilitate the accurate diagnosis and treatment of AML. Studies have confirmed that circular RNA (circRNA) is positively correlated with its linear gene expression. Therefore, by exploring the effect of SH3BGRL3 on the malignant proliferation of leukemia, we further studied the role of circRNA produced by its exon cyclization in the occurrence and development of tumors. Methods: Genes with protein-coding function obtained from the TCGA database. we detected the expression of SH3BGRL3 and circRNA_0010984 by real-time quantitative polymerase chain reaction (qRT-PCR). We synthesized plasmid vectors and carried out cell experiments, including cell proliferation, cell cycle and cell differentiation by cell transfection. We also studied the transfection plasmid vector (PLVX-SHRNA2-PURO) combined with a drug (daunorubicin) to observe the therapeutic effect. The miR-375 binding site of circRNA_0010984 was queried using the circinteractome databases, and the relationship was validated by RNA immunoprecipitation and Dual-luciferase reporter assay. Finally, a protein-protein interaction network was constructed with a STRING database. GO and KEGG functional enrichment identified mRNA-related functions and signaling pathways regulated by miR-375. Results: We identified the related gene SH3BGRL3 in AML and explored the circRNA_0010984 produced by its cyclization. It has a certain effect on the disease progression. In addition, we verified the function of circRNA_0010984. We found that circSH3BGRL3 knockdown specifically inhibited the proliferation of AML cell lines and blocked the cell cycle. We then discussed the related molecular biological mechanisms. CircSH3BGRL3 acts as an endogenous sponge for miR-375 to isolate miR-375 and inhibits its activity, increases the expression of its target YAP1, and ultimately activates the Hippo signaling pathway involved in malignant tumor proliferation. Discussion: We found that SH3BGRL3 and circRNA_0010984 are important to AML. circRNA_0010984 was significantly up-regulated in AML and promoted cell proliferation by regulating miR-375 through molecular sponge action.