TAILIEUCHUNG - Deep learning identified glioblastoma subtypes based on internal genomic expression ranks

Glioblastoma (GBM) can be divided into subtypes according to their genomic features, includ‑ ing Proneural (PN), Neural (NE), Classical (CL) and Mesenchymal (ME). However, it is a difficult task to unify various genomic expression profiles which were standardized with various procedures from different studies and to manually classify a given GBM sample into a subtype. | Mao et al. BMC Cancer 2022 22 86 https s12885-022-09191-2 RESEARCH Open Access Deep learning identified glioblastoma subtypes based on internal genomic expression ranks Xing gang Mao1 Xiao yan Xue2 Ling Wang3 Wei Lin1 and Xiang Zhang1 Abstract Background Glioblastoma GBM can be divided into subtypes according to their genomic features includ ing Proneural PN Neural NE Classical CL and Mesenchymal ME . However it is a difficult task to unify various genomic expression profiles which were standardized with various procedures from different studies and to manually classify a given GBM sample into a subtype. Methods An algorithm was developed to unify the genomic profiles of GBM samples into a standardized normal distribution SND based on their internal expression ranks. Deep neural networks DNN and convolutional DNN CDNN models were trained on original and SND data. In addition expanded SND data by combining various The Cancer Genome Atlas TCGA datasets were used to improve the robustness and generalization capacity of the CDNN models. Results The SND data kept unimodal distribution similar to their original data and also kept the internal expres sion ranks of all genes for each sample. CDNN models trained on the SND data showed significantly higher accuracy compared to DNN and CDNN models trained on primary expression data. Interestingly the CDNN models classified the NE subtype with the lowest accuracy in the GBM datasets expanded datasets and in IDH wide type GBMs con sistent with the recent studies that NE subtype should be excluded. Furthermore the CDNN models also recognized independent GBM datasets even with small set of genomic expressions. Conclusions The GBM expression profiles can be transformed into unified SND data which can be used to train CDNN models with high accuracy and generalization capacity. These models suggested NE subtype may be not com patible with the 4 subtypes classification system. Keywords Deep neural network Proneural .

• Y khoa - Dược
• BMC Cancer
• Deep neural network
• Machine learning
• Molecular subtype
• Artificial intelligence
• Support vector machines
• Cancer patient pathways
• Colorectal cancer
• Lung cancer
• Breast cancer
• Prostate cancer
• Ovarian cancer
• Cancer detection
• Ovarian cancer symptoms
• Ovarian cancer signs
• Ovarian cancer tests
• Cancer biomarkers
• Pediatric cancer
• Familial cancer predisposition
• Hereditary cancer syndrome
• Genetic cancer susceptibility
• Advanced cancer
• Biliary tract cancer
• Multimodal intervention
• Pancreatic cancer
• Physical activity
• Breast cancer screening
• Familial breast cancer
• Young breast cancer survivors
• High risk relatives
• Randomized trial
• Childhood cancer
• Childhood cancer survivor
• Thyroid cancer screening
• Secondary cancer
• Cancer screening
• Community awareness
• Cancer education
• Cervical cancer
• Prior cancer
• Cancer survivors
• Cancer registry
• Second cancer
• Surgical oncology
• Cancer imaging
• Radiation oncologists
• Medical oncologists
• Oesophagogastric cancer
• Liver cancer
• Hepatobiliary cancer
• Multidisciplinary rehabilitation
• EGFR mutation
• Family history of cancer
• Inherited susceptibility
• Cancer predisposition genes
• Lung cancer aetiology
• Cancer stem cells
• Oct4 overexpressing lung cancer
• Human lung cancer xenograft model
• Disease free survivals
• Cancer hallmarks
• Cancer genesis
• Defiant disease
• Mutational signature
• Cancer diagnosis
• Cancer genomics
• Molecular medicine
• Whole genome sequencing
• Cancer susceptibility gene
• Breast cancer prognosis
• Next generation sequencing
• Quality of care
• Quality indicators
• Shifting cancer care
• German cancer society
• Colorectal cancer screening
• Stomach cancer screening
• Lung cancer survivor
• Physician recommendation
• Total number of lymph nodes
• Lymph node ratio
• Left colon cancer
• Right colon cancer
• Overall survival
• Cumulative incidence
• Esophageal cancer
• Head and neck cancer
• Metachronous cancer
• Young onset
• Reproductive cancer
• Risk factor
• Early detection of cancer
• Gastric cancer incidence
• Population based specialized registry
• Gastric cancer survival
• Gastric cancer clinical characteristics
• Gastric cancer pathological characteristics
• Lung Cancer Screening
• Racial disparities
• Lung Cancer diagnosis
• Screening adherence
• Second primary colorectal cancer
• Standardized incidence ratio
• Left sided colon cancer
• Right sided colon cancer
• Quality of cancer care
• Population based study