Platelet RNA signature independently predicts ovarian cancer prognosis by deep learning neural network model.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu CJ
PROVIDER: S-EPMC10392027 | biostudies-literature | 2023 Aug
REPOSITORIES: biostudies-literature
Publications
Platelet RNA signature independently predicts ovarian cancer prognosis by deep learning neural network model.
Liu Chun-Jie CJ Li Hua-Yi HY Gao Yue Y Xie Gui-Yan GY Chi Jian-Hua JH Li Gui-Ling GL Zeng Shao-Qing SQ Xiong Xiao-Ming XM Liu Jia-Hao JH Shi Lin-Li LL Li Xiong X Cheng Xiao-Dong XD Song Kun K Ma Ding D Guo An-Yuan AY Gao Qing-Lei QL
Protein & cell 20230801 8
Similar Datasets
Project description:BackgroundPredicting hepatocellular carcinoma (HCC) prognosis is important for treatment selection, and it is increasingly interesting to predict prognosis through gene expression data. Currently, the prognosis remains of low accuracy due to the high dimension but small sample size of liver cancer omics data. In previous studies, a transfer learning strategy has been developed by pre-training models on similar cancer types and then fine-tuning the pre-trained models on the target dataset. However, transfer learning has limited performance since other cancer types are similar at different levels, and it is not trivial to balance the relations with different cancer types.MethodsHere, we propose an adaptive transfer-learning-based deep Cox neural network (ATRCN), where cancers are represented by 12 phenotype and 10 genotype features, and suitable cancers were adaptively selected for model pre-training. In this way, the pre-trained model can learn valuable prior knowledge from other cancer types while reducing the biases.ResultsATRCN chose pancreatic and stomach adenocarcinomas as the pre-training cancers, and the experiments indicated that our method improved the C-index of 3.8% by comparing with traditional transfer learning methods. The independent tests on three additional HCC datasets proved the robustness of our model. Based on the divided risk subgroups, we identified 10 HCC prognostic markers, including one new prognostic marker, TTC36. Further wet experiments indicated that TTC36 is associated with the progression of liver cancer cells.ConclusionThese results proved that our proposed deep-learning-based method for HCC prognosis prediction is robust, accurate, and biologically meaningful.
| S-EPMC8504135 | biostudies-literature
Project description:High-grade serous ovarian carcinoma (HGSOC) is an epithelial cancer that accounts for most ovarian cancer deaths. Metabolic abnormalities such as extensive aerobic glycolysis and aberrant lipid metabolism are well-known characteristics of cancer cells. Indeed, accumulation of lipid droplets (LDs) in certain types of malignant tumors has been known for more than 50 years. Here, we investigated the correlation between LD accumulation and clinical prognosis. In 96 HGSOC patients, we found that high expression of the LD marker adipophilin was associated with poor progression-free and overall survival (p = 0.0022 and p = 0.014, respectively). OVCAR-3 ovarian carcinoma cells accumulated LDs in a glucose-dependent manner, which suggested the involvement of aerobic glycolysis and subsequently enhanced lipogenesis, with a result being LD accumulation. The acyl-CoA: cholesterol acyltransferase 1 inhibitor K604 and the hydroxymethylglutaryl-CoA reductase inhibitor pitavastatin blocked LD accumulation in OVCAR-3 cells and reduced phosphorylation of the survival-related kinases Akt and ERK1/2, both of which have been implicated in malignancy. Our cell-based assays thus suggested that enhanced aerobic glycolysis resulted in LD accumulation and activation of survival-related kinases. Overall, our results support the idea that cancers with lipogenic phenotypes are associated with poor clinical prognosis, and we suggest that adipophilin may serve as an independent indicator of a poor prognosis in HGSOC.
| S-EPMC8533764 | biostudies-literature
Project description:Ovarian cancer (OV) is the most lethal gynecological malignancy worldwide, with high recurrence rates. Anoikis, a newly-acknowledged form of programmed cell death, plays an essential role in cancer progression, though studies focused on prognostic patterns of anoikis in OV are still lacking. We filtered 32 potential anoikis-related genes (ARGs) among the 6406 differentially expressed genes (DEGs) between the 180 normal controls and 376 TCGA-OV samples. Through the LASSO-Cox analysis, a 2-gene prognostic signature, namely AKT2, and DAPK1, was finally distinguished. We then demonstrated the promising prognostic value of the signature through the K-M survival analysis and time-dependent ROC curves (p-value < 0.05). Moreover, based on the signature and clinical features, we constructed and validated a nomogram model for 1-year, 3-year, and 5-year overall survival, with reliable prognostic values in both TCGA-OV training cohort (p-value < 0.001) and ICGC-OV validation cohort (p-value = 0.030). We evaluated the tumor immune landscape through the CIBERSORT algorithm, which indicated the upregulation of resting Myeloid Dendritic Cells (DCs), memory B cells, and naïve B cells and high expression of key immune checkpoint molecules (CD274 and PDCD1LG2) in the high-risk group. Interestingly, the high-risk group exhibited better sensitivity toward immunotherapy and less sensitivity toward chemotherapies, including Cisplatin and Bleomycin. Especially, based on the IHC of tissue microarrays among 125 OV patients at our institution, we reported that aberrant upregulation of DAPK1 was related to poor prognosis. Conclusively, the anoikis-related signature was a promising tool to evaluate prognosis and predict therapy responses, thus assisting decision-making in the realm of OV precision medicine.
| S-EPMC10837903 | biostudies-literature
Project description:Background/Objectives: This study aimed to construct a risk score (RS) based on necroptosis-associated genes to predict the prognosis of patients with advanced epithelial ovarian cancer (EOC). Methods: EOC data from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) series 140082 (GSE140082) were used. Based on known necroptosis-associated genes, clustering was performed to identify molecular subtypes of EOC. A least absolute shrinkage and selection operator (LASSO)-Cox regression analysis identified key genes related to prognosis. The expression of one of them, RIPK3, was analyzed via immunohistochemistry in an EOC cohort. Results: An RS made from ten genes (IDH2, RIPK3, FASLG, BRAF, ITPK1, TNFSF10, ID1, PLK1, MLKL and HSPA4) was developed. Tumor samples were divided into a high-risk group (HRG) and low-risk group (LRG) using the RS. The model is able to predict the overall survival (OS) of EOC and distinguish the prognosis of different clinical subgroups. Immunohistochemical verification of the receptor-interacting serine/threonine-protein kinase (RIPK) 3 confirmed that high nuclear expression is correlated with a longer OS. In addition, the score can predict the response to a programmed death ligand 1 (PD-L1) blockade treatment in selected solid malignancies. Patients from the LRG seem to benefit more from it than patients from the HRG. Conclusions: Our RS based on necroptosis-associated genes might help to predict the prognosis of patients with advanced EOC and gives an idea on how the use of immunotherapy can potentially be guided.
| S-EPMC11763378 | biostudies-literature
Project description:Substantial progress has been made in using deep learning for cancer detection and diagnosis in medical images. Yet, there is limited success on prediction of treatment response and outcomes, which has important implications for personalized treatment strategies. A significant hurdle for clinical translation of current data-driven deep learning models is lack of interpretability, often attributable to a disconnect from the underlying pathobiology. Here, we present a biology-guided deep learning approach that enables simultaneous prediction of the tumor immune and stromal microenvironment status as well as treatment outcomes from medical images. We validate the model for predicting prognosis of gastric cancer and the benefit from adjuvant chemotherapy in a multi-center international study. Further, the model predicts response to immune checkpoint inhibitors and complements clinically approved biomarkers. Importantly, our model identifies a subset of mismatch repair-deficient tumors that are non-responsive to immunotherapy and may inform the selection of patients for combination treatments.
| S-EPMC10447467 | biostudies-literature
Project description:We have previously reported surrogate biomarkers of VEGF pathway activities with the potential to provide predictive information for anti-VEGF therapies. The aim of this study was to systematically evaluate a new VEGF-dependent gene signature (VDGs) in relation to molecular subtypes of ovarian cancer and patient prognosis. Using microarray profiling and cross-species analysis, we identified 140-gene mouse VDGs and corresponding 139-gene human VDGs, which displayed enrichment of vasculature and basement membrane genes. In patients who received bevacizumab therapy and showed partial response, the expressions of VDGs (summarized to yield VDGs scores) were markedly decreased in post-treatment biopsies compared with pre-treatment baselines. In contrast, VDGs scores were not significantly altered following bevacizumab treatment in patients with stable or progressive disease. Analysis of VDGs in ovarian cancer showed that VDGs as a prognostic signature was able to predict patient outcome. Correlation estimation of VDGs scores and molecular features revealed that VDGs was overrepresented in mesenchymal subtype and BRCA mutation carriers. These findings highlighted the prognostic role of VEGF-mediated angiogenesis in ovarian cancer, and proposed a VEGF-dependent gene signature as a molecular basis for developing novel diagnostic strategies to aid patient selection for VEGF-targeted agents.
| S-EPMC4976329 | biostudies-literature
Project description:DNA methylation is a promising biomarker for cancer. The epigenetic effects of cell adhesion molecules may affect the therapeutic outcome and the present study examined their effects on survival in ovarian cancer. We integrated methylomics and genomics datasets in The Cancer Genome Atlas (n = 391) and identified 106 highly methylated adhesion-related genes in ovarian cancer tissues. Univariate analysis revealed the methylation status of eight genes related to progression-free survival. In multivariate Cox regression analysis, four highly methylated genes (CD97, CTNNA1, DLC1, HAPLN2) and three genes (LAMA4, LPP, MFAP4) with low methylation were significantly associated with poor progression-free survival. Low methylation of VTN was an independent poor prognostic factor for overall survival after adjustment for age and stage. Patients who carried any two of CTNNA1, DLC1 or MFAP4 were significantly associated with poor progression-free survival (hazard ratio: 1.59; 95% confidence interval: 1.23, 2.05). This prognostic methylation signature was validated in a methylomics dataset generated in our lab (n = 37, hazard ratio: 16.64; 95% confidence interval: 2.68, 103.14) and in another from the Australian Ovarian Cancer Study (n = 91, hazard ratio: 2.43; 95% confidence interval: 1.11, 5.36). Epigenetics of cell adhesion molecules is related to ovarian cancer prognosis. A more comprehensive methylomics of cell adhesion molecules is needed and may advance personalized treatment with adhesion molecule-related drugs.
| S-EPMC5581121 | biostudies-literature
Project description:DNA methylation contributes to tumor formation, development and metastasis. Epigenetic dysregulation of stem cells is thought to predispose to malignant development. The clinical significance of DNA methylation in ovarian tumor-initiating cells (OTICs) remains unexplored. We analyzed the methylomic profiles of OTICs (CP70sps) and their derived progeny using a human methylation array. qRT-PCR, quantitative methylation-specific PCR (qMSP) and pyrosequencing were used to verify gene expression and DNA methylation in cancer cell lines. The methylation status of genes was validated quantitatively in cancer tissues and correlated with clinicopathological factors. ATG4A and HIST1H2BN were hypomethylated in OTICs. Methylation analysis of ATG4A and HIST1H2BN by qMSP in 168 tissue samples from patients with ovarian cancer showed that HIST1H2BN methylation was a significant and independent predictor of progression-free survival (PFS) and overall survival (OS). Multivariate Cox regression analysis showed that patients with a low level of HIST1H2BN methylation had poor PFS (hazard ratio (HR), 4.5; 95% confidence interval (CI), 1.4-14.8) and OS (HR, 4.3; 95% CI, 1.3-14.0). Hypomethylation of both ATG4A and HIST1H2BN predicted a poor PFS (HR, 1.8; 95% CI, 1.0-3.6; median, 21 months) and OS (HR, 1.7; 95% CI, 1.0-3.0; median, 40 months). In an independent cohort of ovarian tumors, hypomethylation predicted early disease recurrence (HR, 1.7; 95% CI, 1.1-2.5) and death (HR, 1.4; 95% CI, 1.0-1.9). The demonstration that expression of ATG4A in cells increased their stem properties provided an indication of its biological function. Hypomethylation of ATG4A and HIST1H2BN in OTICs predicts a poor prognosis for ovarian cancer patients.
| S-EPMC3943526 | biostudies-literature
Project description:Cancer prognosis analysis is of essential interest in clinical practice. In order to explore the prognostic power of computational histopathology and genomics, this paper constructs a multi-modality prognostic model for survival prediction. We collected 346 patients diagnosed with hepatocellular carcinoma (HCC) from The Cancer Genome Atlas (TCGA), each patient has 1-3 whole slide images (WSIs) and an mRNA expression file. WSIs were processed by a multi-instance deep learning model to obtain the patient-level survival risk scores; mRNA expression data were processed by weighted gene co-expression network analysis (WGCNA), and the top hub genes of each module were extracted as risk factors. Information from two modalities was integrated by Cox proportional hazard model to predict patient outcomes. The overall survival predictions of the multi-modality model (Concordance index (C-index): 0.746, 95% confidence interval (CI): ±0.077) outperformed these based on histopathology risk score or hub genes, respectively. Furthermore, in the prediction of 1-year and 3-year survival, the area under curve of the model achieved 0.816 and 0.810. In conclusion, this paper provides an effective workflow for multi-modality prognosis of HCC, the integration of histopathology and genomic information has the potential to assist clinical prognosis management.
| S-EPMC9601633 | biostudies-literature
Project description:The concept of biological age has emerged as a measurement that reflects physiological and functional decline with ageing. Here we aimed to develop a deep neural network (DNN) model that predicts biological age from optical coherence tomography (OCT). A total of 84,753 high-quality OCT images from 53,159 individuals in the UK Biobank were included, among which 12,631 3D-OCT images from 8,541 participants without any reported medical conditions at baseline were used to develop an age prediction model. For the remaining 44,618 participants, OCT age gap, the difference between the OCT-predicted age and chronological age, was calculated for each participant. Cox regression models assessed the association between OCT age gap and mortality. The DNN model predicted age with a mean absolute error of 3.27 years and showed a strong correlation of 0.85 with chronological age. After a median follow-up of 11.0 years (IQR 10.9-11.1 years), 2,429 deaths (5.44%) were recorded. For each 5-year increase in OCT age gap, there was an 8% increased mortality risk (hazard ratio [HR] = 1.08, CI:1.02-1.13, P = 0.004). Compared with an OCT age gap within ± 4 years, OCT age gap less than minus 4 years was associated with a 16% decreased mortality risk (HR = 0.84, CI: 0.75-0.94, P = 0.002) and OCT age gap more than 4 years showed an 18% increased risk of death incidence (HR = 1.18, CI: 1.02-1.37, P = 0.026). OCT imaging could serve as an ageing biomarker to predict biological age with high accuracy and the OCT age gap, defined as the difference between the OCT-predicted age and chronological age, can be used as a marker of the risk of mortality.
| S-EPMC10828229 | biostudies-literature