Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.
Ontology highlight
ABSTRACT:
SUBMITTER: Ching T
PROVIDER: S-EPMC5909924 | biostudies-literature |
REPOSITORIES: biostudies-literature
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:BackgroundDeep learning has made tremendous successes in numerous artificial intelligence applications and is unsurprisingly penetrating into various biomedical domains. High-throughput omics data in the form of molecular profile matrices, such as transcriptomes and metabolomes, have long existed as a valuable resource for facilitating diagnosis of patient statuses/stages. It is timely imperative to compare deep learning neural networks against classical machine learning methods in the setting of matrix-formed omics data in terms of classification accuracy and robustness.ResultsUsing 37 high throughput omics datasets, covering transcriptomes and metabolomes, we evaluated the classification power of deep learning compared to traditional machine learning methods. Representative deep learning methods, Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN), were deployed and explored in seeking optimal architectures for the best classification performance. Together with five classical supervised classification methods (Linear Discriminant Analysis, Multinomial Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machine), MLP and CNN were comparatively tested on the 37 datasets to predict disease stages or to discriminate diseased samples from normal samples. MLPs achieved the highest overall accuracy among all methods tested. More thorough analyses revealed that single hidden layer MLPs with ample hidden units outperformed deeper MLPs. Furthermore, MLP was one of the most robust methods against imbalanced class composition and inaccurate class labels.ConclusionOur results concluded that shallow MLPs (of one or two hidden layers) with ample hidden neurons are sufficient to achieve superior and robust classification performance in exploiting numerical matrix-formed omics data for diagnosis purpose. Specific observations regarding optimal network width, class imbalance tolerance, and inaccurate labeling tolerance will inform future improvement of neural network applications on functional genomics data.
| S-EPMC6399893 | biostudies-literature
Project description:SummaryCox-nnet is a neural-network based prognosis prediction method, originally applied to genomics data. Here we propose the version 2 of Cox-nnet, with significant improvement on efficiency and interpretability, making it suitable to predict prognosis based on large-scale population data, including those electronic medical records (EMR) datasets. We also add permutation-based feature importance scores and the direction of feature coefficients. When applied on a kidney transplantation dataset, Cox-nnet v2.0 reduces the training time of Cox-nnet up to 32 folds (n = 10,000) and achieves better prediction accuracy than Cox-PH (p < 0.05). It also achieves similarly superior performance on a publicly available SUPPORT data (n = 8,000). The high efficiency and accuracy make Cox-nnet v2.0 a desirable method for survival prediction in large-scale EMR data.Availability and implementationCox-nnet v2.0 is freely available to the public at https://github.com/lanagarmire/Cox-nnet-v2.0.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8428611 | biostudies-literature
Project description:Pathological images are easily accessible data with the potential of prognostic biomarkers. Moreover, integration of heterogeneous data types from multi-modality, such as pathological image and gene expression data, is invaluable to help predicting cancer patient survival. However, the analytical challenges are significant. Here, we take the hepatocellular carcinoma (HCC) pathological image features extracted by CellProfiler, and apply them as the input for Cox-nnet, a neural network-based prognosis prediction model. We compare this model with the conventional Cox proportional hazards (Cox-PH) model, CoxBoost, Random Survival Forests and DeepSurv, using C-index and log-rank P-values. The results show that Cox-nnet is significantly more accurate than Cox-PH and Random Survival Forests models and comparable with CoxBoost and DeepSurv models, on pathological image features. Further, to integrate pathological image and gene expression data of the same patients, we innovatively construct a two-stage Cox-nnet model, and compare it with another complex neural-network model called PAGE-Net. The two-stage Cox-nnet complex model combining histopathology image and transcriptomic RNA-seq data achieves much better prognosis prediction, with a median C-index of 0.75 and log-rank P-value of 6e-7 in the testing datasets, compared to PAGE-Net (median C-index of 0.68 and log-rank P-value of 0.03). Imaging features present additional predictive information to gene expression features, as the combined model is more accurate than the model with gene expression alone (median C-index 0.70). Pathological image features are correlated with gene expression, as genes correlated to top imaging features present known associations with HCC patient survival and morphogenesis of liver tissue. This work proposes two-stage Cox-nnet, a new class of biologically relevant and interpretable models, to integrate multiple types of heterogenous data for survival prediction.
| S-EPMC7985035 | biostudies-literature
Project description:An mRNA transcript contains many potential antisense oligodeoxynucleotide target sites. Identification of the most efficacious targets remains an important and challenging problem. Building on separate work that revealed a strong correlation between the inclusion of short sequence motifs and the activity level of an oligo, we have developed a predictive artificial neural network system for mapping tetranucleotide motif content to antisense oligo activity. Trained for high-specificity prediction, the system has been cross-validated against a database of 348 oligos from the literature and a larger proprietary database of 908 oligos. In cross- validation tests the system identified effective oligos (i.e. oligos capable of reducing target mRNA expression to <25% that of the control) with 53% accuracy, in contrast to the <10% success rates commonly reported for trial-and-error oligo selection, suggesting a possible 5-fold reduction in the in vivo screening required to find an active oligo. We have implemented a web interface to a trained neural network. Given an RNA transcript as input, the system identifies the most likely oligo targets and provides estimates of the probabilities that oligos targeted against these sites will be effective.
| S-EPMC140555 | biostudies-literature
Project description:BackgroundStratification of patient subpopulations that respond favorably to treatment or experience and adverse reaction is an essential step toward development of new personalized therapies and diagnostics. It is currently feasible to generate omic-scale biological measurements for all patients in a study, providing an opportunity for machine learning models to identify molecular markers for disease diagnosis and progression. However, the high variability of genetic background in human populations hampers the reproducibility of omic-scale markers. In this paper, we develop a biological network-based regularized artificial neural network model for prediction of phenotype from transcriptomic measurements in clinical trials. To improve model sparsity and the overall reproducibility of the model, we incorporate regularization for simultaneous shrinkage of gene sets based on active upstream regulatory mechanisms into the model.ResultsWe benchmark our method against various regression, support vector machines and artificial neural network models and demonstrate the ability of our method in predicting the clinical outcomes using clinical trial data on acute rejection in kidney transplantation and response to Infliximab in ulcerative colitis. We show that integration of prior biological knowledge into the classification as developed in this paper, significantly improves the robustness and generalizability of predictions to independent datasets. We provide a Java code of our algorithm along with a parsed version of the STRING DB database.ConclusionIn summary, we present a method for prediction of clinical phenotypes using baseline genome-wide expression data that makes use of prior biological knowledge on gene-regulatory interactions in order to increase robustness and reproducibility of omic-scale markers. The integrated group-wise regularization methods increases the interpretability of biological signatures and gives stable performance estimates across independent test sets.
| S-EPMC5735940 | biostudies-literature
Project description:Many studies have proven the power of gene expression profile in cancer identification, however, the explosive growth of genomics data increasing needs of tools for cancer diagnosis and prognosis in high accuracy and short times. Here, we collected 6136 human samples from 11 cancer types, and integrated their gene expression profiles and protein-protein interaction (PPI) network to generate 2D images with spectral clustering method. To predict normal samples and 11 cancer tumor types, the images of these 6136 human cancer network were separated into training and validation dataset to develop convolutional neural network (CNN). Our model showed 97.4% and 95.4% accuracies in identification of normal versus tumors and 11 cancer types, respectively. We also provided the results that tumors located in neighboring tissues or in the same cell types, would induce machine make error classification due to the similar gene expression profiles. Furthermore, we observed some patients may exhibit better prognosis if their tumors often misjudged into normal samples. As far as we know, we are the first to generate thousands of cancer networks to predict and classify multiple cancer types with CNN architecture. We believe that our model not only can be applied to cancer diagnosis and prognosis, but also promote the discovery of multiple cancer biomarkers.
| S-EPMC8526703 | biostudies-literature
Project description:BACKGROUND:Accurate prediction of operative transfusions is essential for resource allocation and identifying patients at risk of postoperative adverse events. This research examines the efficacy of using artificial neural networks (ANNs) to predict transfusions for all inpatient operations. METHODS:Over 1.6 million surgical cases over a two year period from the NSQIP-PUF database are used. Data from 2014 (750937 records) are used for model development and data from 2015 (885502 records) are used for model validation. ANN and regression models are developed to predict perioperative transfusions for surgical patients. RESULTS:Various ANN models and logistic regression, using four variable sets, are compared. The best performing ANN models with respect to both sensitivity and area under the receiver operator characteristic curve outperformed all of the regression models (p < .001) and achieved a performance of 70-80% specificity with a corresponding 75-62% sensitivity. CONCLUSION:ANNs can predict >75% of the patients who will require transfusion and 70% of those who will not. Increasing specificity to 80% still enables a sensitivity of almost 67%. The unique contribution of this research is the utilization of a single ANN model to predict transfusions across a broad range of surgical procedures.
| S-EPMC7039514 | biostudies-literature
Project description:ObjectivesTo compare two statistical models, namely logistic regression and artificial neural network (ANN), in prediction of vestibular schwannoma (VS) recurrence.MethodsSeven hundred eighty-nine patients with VS diagnosis completed an online survey. Potential predictors for recurrence were derived from univariate analysis by reaching the cut off P value of .05. Those nine potential predictors were years since treatment, surgeon's specialty, resection amount, and having incomplete eye closure, dry eye, double vision, facial pain, seizure, and voice/swallowing problem as a complication following treatment. Multivariate binary logistic regression model was compared with a four-layer 9-5-10-1 feedforward backpropagation ANN for prediction of recurrence.ResultsThe overall recurrence rate was 14.5%. Significant predictors of recurrence in the regression model were years since treatment and resection amount (both P < .001). The regression model did not show an acceptable performance (area under the curve [AUC] = 0.64; P = .27). The regression model's sensitivity and specificity were 44% and 69%, respectively and correctly classified 56% of cases. The ANN showed a superior performance compared to the regression model (AUC = 0.79; P = .001) with higher sensitivity (61%) and specificity (81%), and correctly classified 70% of cases.ConclusionThe constructed ANN model was superior to logistic regression in predicting patient-answered VS recurrence in an anonymous survey with higher sensitivity and specificity. Since artificial intelligence tools such as neural networks can have higher predictive abilities compared to logistic regression models, continuous investigation into their utility as complementary clinical tools in predicting certain surgical outcomes is warranted.
| S-EPMC7178452 | biostudies-literature
Project description:Most computational approaches for the analysis of omics data in the context of interaction networks have very long running times, provide single or partial, often heuristic, solutions and/or contain user-tuneable parameters.We introduce local enrichment analysis (LEAN) for the identification of dysregulated subnetworks from genome-wide omics datasets. By substituting the common subnetwork model with a simpler local subnetwork model, LEAN allows exact, parameter-free, efficient and exhaustive identification of local subnetworks that are statistically dysregulated, and directly implicates single genes for follow-up experiments.Evaluation on simulated and biological data suggests that LEAN generally detects dysregulated subnetworks better, and reflects biological similarity between experiments more clearly than standard approaches. A strong signal for the local subnetwork around Von Willebrand Factor (VWF), a gene which showed no change on the mRNA level, was identified by LEAN in transcriptome data in the context of the genetic disease Cerebral Cavernous Malformations (CCM). This signal was experimentally found to correspond to an unexpected strong cellular effect on the VWF protein. LEAN can be used to pinpoint statistically significant local subnetworks in any genome-scale dataset.The R-package LEANR implementing LEAN is supplied as supplementary material and available on CRAN ( https://cran.r-project.org ).benno@pasteur.fr or tournier-lasserve@univ-paris-diderot.fr.Supplementary data are available at Bioinformatics online.
| S-EPMC5408824 | biostudies-literature