Prediction and interpretation of cancer survival using graph convolution neural networks

Ramirez, Ricardo; Chiu, Yi-Chang; Zhang, Songyao; Ramirez, Joshua; Chen, Yidong; Huang, Yufei; Jin, Yufang

doi:10.1016/j.ymeth.2021.01.004

Cited by 42 publications

(21 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The major bottleneck existed in this technique was minor upgrading in performance level. Ramirez et al 14 developed a graph convolutional neural network (GCNN) scheme named Surv_GCNN for survival detection for 13 various cancer categories utilizing TCGA dataset. The developed approach extracted important biomarkers for breast cancer survival.…”

Section: Literature Surveymentioning

confidence: 99%

“…The high breakthrough and evolution of machine learning over few years have motivated progression of survival classifiers trained on information samples consisting of effective predictive features. From this, it is observed that the high significance of any given predictor can be quantified and thereby recommended of its efficiency for diagnosis purpose 14 …”

Section: Introductionmentioning

confidence: 99%

“…From this, it is observed that the high significance of any given predictor can be quantified and thereby recommended of its efficiency for diagnosis purpose. 14 This research develops an effective strategy for survival prediction of cancer patients using gene expression data. Initially, input data is acquired from gene expression data and input is passed to perform task of data transformation.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data

Prabhakar¹,

Vairamuthu

Rani

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

SummaryOncology treatment accuracy relies on providing information from a variety of sources to have a accurate assessment of a patient's health status and prediction. With the advancement in medical field, accurate prediction allows prescription of more effective treatments and customized medical services to individual patient's. Next generation sequencing has put pressure on cancer researchers in recent years by giving doctors access to vast amounts of data from RNA‐seq high‐throughput fields. Effectual survival prediction can save patient's life from threatening at earlier stage. In addition, traditional techniques of gene expression datasets failed to trade off balance among huge genes and low number of samples available, thereby resulting low level of survival prediction rate. Therefore, this research proposes an efficient model for survival prediction of cancer patients using proposed gray wolf‐student psychology optimization‐based deep long short term memory (GW‐SPO based deep LSTM). The proposed GW‐SPO is derived by incorporating gray wolf optimization (GWO) and student psychology based optimization (SPBO). However, survival prediction is performed effectively using deep LSTM and network classifier is trained using proposed GW‐SPO. Nevertheless, proposed GW‐SPO has achieved superior results with minimum RMSE of 0.325, and minimum prediction error of 0.110 for analysis with cluster size of 5.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data

Prabhakar¹,

Vairamuthu

Rani

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…We individually compare our model to other models predicting survival time on 23 different cancer types, and find that our joint model improves over predictive performance observed in other models on the same datasets (see Table 1). In addition to our deep [29] Pancancer model (pancancer) [29] Surv-GCNN [30] Survival-Net [31] Cox-PASNet [32] Coxnnet [ Table 1. Performance comparison based on the C-index.…”

Section: Integration and Analysis Of Multi-omics Data In Graph Neuralmentioning

confidence: 99%

DeepMOCCA: A pan-cancer prognostic model identifies personalized prognostic markers through graph attention and multi-omics data integration

Althubaiti

Kulmanov

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Combining multiple types of genomic, transcriptional, proteomic, and epigenetic datasets has the potential to reveal biological mechanisms across multiple scales, and may lead to more accurate models for clinical decision support. Developing efficient models that can derive clinical outcomes from high-dimensional data remains problematical; challenges include the integration of multiple types of omics data, inclusion of biological background knowledge, and developing machine learning models that are able to deal with this high dimensionality while having only few samples from which to derive a model. We developed DeepMOCCA, a framework for multi-omics cancer analysis. We combine different types of omics data using biological relations between genes, transcripts, and proteins, combine the multi-omics data with background knowledge in the form of protein-protein interaction networks, and use graph convolution neural networks to exploit this combination of multi-omics data and background knowledge. DeepMOCCA predicts survival time for individual patient samples for 33 cancer types and outperforms most existing survival prediction methods. Moreover, DeepMOCCA includes a graph attention mechanism which prioritizes driver genes and prognostic markers in a patient-specific manner; the attention mechanism can be used to identify drivers and prognostic markers within cohorts and individual patients.

show abstract

“…Deep learning (DL) is a class of machine learning (ML) methods that uses multilayered neural networks to extract high-order features. DL is increasingly being used in genomics research for cancer survival (11,12) and cancer classification (13)(14)(15). DL methods have also been applied to pharmacogenomics for predicting drug sensitivity and synergy (16,17).…”

Section: Introductionmentioning

confidence: 99%

Predicting and characterizing a cancer dependency map of tumors with deep learning

Chiu¹,

Zheng²,

Wang³

et al. 2021

Sci. Adv.

Self Cite

View full text Add to dashboard Cite

Genome-wide loss-of-function screens have revealed genes essential for cancer cell proliferation, called cancer dependencies. It remains challenging to link cancer dependencies to the molecular compositions of cancer cells or to unscreened cell lines and further to tumors. Here, we present DeepDEP, a deep learning model that predicts cancer dependencies using integrative genomic profiles. It uses a unique unsupervised pretraining that captures unlabeled tumor genomic representations to improve the learning of cancer dependencies. We demonstrated DeepDEP's improvement over conventional machine learning methods and validated the performance with three independent datasets. By systematic model interpretations, we extended the current dependency maps with functional characterizations of dependencies and a proof-of-concept in silico assay of synthetic essentiality. We applied DeepDEP to pan-cancer tumor genomics and built the first pan-cancer synthetic dependency map of 8000 tumors with clinical relevance. In summary, DeepDEP is a novel tool for investigating cancer dependency with rapidly growing genomic resources.

show abstract

Prediction and interpretation of cancer survival using graph convolution neural networks

Cited by 42 publications

References 54 publications

Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data

Gray wolf‐student psychology optimization‐based deep long short term memory for survival prediction using cancer gene‐expression data

DeepMOCCA: A pan-cancer prognostic model identifies personalized prognostic markers through graph attention and multi-omics data integration

Predicting and characterizing a cancer dependency map of tumors with deep learning

Contact Info

Product

Resources

About