Abstract
In this study, the deep belief network (DBN) algorithm was used to identify the Wilm’s tumor 1 (WT1) gene expression levels, and then, the role of WT1 expression in the classification of acute myeloid leukemia (AML) was explored. 121 AML patients diagnosed in the hospital from 2017.10 to 2019.10 were selected as the research subjects and set as the AML group. Another 9 non-leukemia patients were selected as the control group. The expression levels of WT1 in the two groups were compared, and DBN was used to classify the patients based on the WT1 expression levels. The real-time quantitative PCR was used to detect the abnormalities of FLT3, PML-RAR, and other molecular markers at different WT1 expression levels. The results showed that the expression of WT1 in AML patients was significantly higher than that in non-leukemia patients. The expression of WT1 in patients of M3 type was the highest, and that was the lowest in patients of the M5 type. The accuracy, precision, recall, and F1 indexes for WT1 expression identification using deep belief network were 94.06%, 93.82%, 93.59%, and 93.63%, respectively. In conclusion, deep learning technology is very sensitive in identifying the molecular biology markers in AML patients, which provides a reference for efficient and intelligent disease diagnosis.
Similar content being viewed by others
References
Dohner H, Weisdorf DJ, Bloomfield CD (2015) Acute myeloid leukemia. N Engl J Med 373(12):1136–1152
De Kouchkovsky I, Abdul-Hay M (2016) Acute myeloid leukemia: a comprehensive review and 2016 update. Blood Cancer 6(7):e441
Prada-Arismendy J, Arroyave JC, Rothlisberger S (2017) Molecular biomarkers in acute myeloid leukemia. Blood Rev 31(1):63–76
Bullinger L, Dohner K, Dohner H (2017) Genomics of acute myeloid leukemia diagnosis and pathways. J Clin Oncol 35(9):934–946
Chapuis AG, Egan DN, Bar M et al (2019) T cell receptor gene therapy targeting WT1 prevents acute myeloid leukemia relapse post-transplant. Nat Med 25(7):1064–1072
Du D, Zhu L, Wang Y et al (2019) Expression of WT1 gene and its prognostic value in patients with acute myeloid leukemia. Zhejiang Da Xue Xue Bao Yi Xue Ban 48(1):50–57
Niktoreh N, Walter C, Zimmermann M et al (2019) Mutated WT1, FLT3-ITD, and NUP98-NSD1 fusion in various combinations define a poor prognostic group in pediatric acute myeloid leukemia. J Oncol 2019:1609128
Pan C, Schoppe O, Parra-Damas A et al (2019) Deep Learning Reveals Cancer Metastasis and Therapeutic Antibody Targeting in the Entire Body. Cell 179(7):1661–1676
Coudray N, Ocampo PS, Sakellaropoulos T et al (2018) Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med 24(10):1559–1567
Zuo Y, Cheng Y, Zhang L et al (2019) Wilms’ tumor 1 mRNA expression: a good tool for differentiating between myelodysplastic syndrome and aplastic anemia in children? Hematology 24(1):480–486
Pandey S, Moazam M, Ghimirey N et al (2019) WT1 regulates cyclin A1 expression in K562 cells. Oncol Rep 42(5):2016–2028
Han Z, Wei B, Zheng Y et al (2017) Breast cancer multi-classification from histopathological images with structured deep learning model. Sci Rep 7(1):4172
Suguna E, Farhana R, Kanimozhi E et al (2018) Acute myeloid leukemia: diagnosis and management based on current molecular genetics approach. Cardiovasc Hematol Disord Drug Targets 18(3):199–207
Smolander J, Dehmer M, Emmert-Streib F (2019) Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders. FEBS Open Bio 9(7):1232–1248
Yang JL, Zhao JJ, Qiang Y et al (2016) Classification of benign and malignant pulmonary nodules based on deep belief network. Sci Rep 16(032):69–74
Li ZC, Shi XY, Yu L et al (2019) Inhibition classification of CYP450 2C9 based on deep belief network. Sci Rep 36(02):195–199
Cancer Genome Atlas Research N, Ley TJ, Miller C et al (2013) Genomic and epigenomic landscapes of adult de novo acute myeloid leukemia. N Engl J Med 368(22):2059–2074
Zhang X, Yang C, Peng X, Chen X, Feng Y (2017) Acute WT1-positive promyelocytic leukemia with hypogranular variant morphology, bcr-3 isoform of PML-RARα and Flt3-ITD mutation: a rare case report. Sao Paulo Med J. 135(2):179–184
Papaemmanuil E, Gerstung M, Bullinger L et al (2016) Genomic classification and prognosis in acute myeloid leukemia. N Engl J Med 374(23):2209–2221
Huang HJ, Li B, Qin TJ, Xu ZF, Hu NB, Pan LJ, Qu SQ, Liu D, Zhang YD, Xiao ZJ (2020) Molecular features and prognostic value of RAS mutations in patients with myelodysplastic syndromes. Zhonghua Xue Ye Xue Za Zhi 41(9):723–730
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, L., Lu, Y., Pei, R. et al. Deep learning in molecular biology marker recognition of patients with acute myeloid leukemia. J Supercomput 78, 11283–11297 (2022). https://doi.org/10.1007/s11227-021-04104-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-04104-9