Deep Learning based multi-omics integration robustly predicts survival in liver cancer

By Kumardeep Chaudhary, Olivier B. Poirion, Liangqun Lu, Lana X. Garmire. 2017

858 citations recorded by the source corpus.

Identifying robust survival subgroups of hepatocellular carcinoma (HCC) will significantly improve patient care. Currently, endeavor of integrating multi-omics data to explicitly predict HCC survival from multiple patient cohorts is lacking. To fill this gap, we present a deep learning (DL)–based model on HCC that robustly differentiates survival subpopulations of patients in six cohorts. We built the DL-based, survival-sensitive model on 360 HCC patients' data using RNA sequencing (RNA-Seq), miRNA sequencing (miRNA-Seq), and methylation data from The Cancer Genome Atlas (TCGA), which predicts prognosis as good as an alternative model where genomics and clinical data are both considered. This DL-based model provides two optimal subgroups of patients with significant survival differences (P = 7.13e−6) and good model fitness [concordance index (C-index) = 0.68]. More aggressive subtype is associated with frequent TP53 inactivation mutations, higher expression of stemness markers (KRT19 and EPCAM) and tumor marker BIRC5, and activated Wnt and Akt signaling pathways. We validated this multi-omics model on five external datasets of various omics types: LIRI-JP cohort (n = 230, C-index = 0.75), NCI cohort (n = 221, C-index = 0.67), Chinese cohort (n = 166, C-index = 0.69), E-TABM-36 cohort (n = 40, C-index = 0.77), and Hawaiian cohort (n = 27, C-index = 0.82). This is the first study to employ DL to identify multi-omics features linked to the differential survival of patients with HCC. Given its robustness over multiple cohorts, we expect this workflow to be useful at predicting HCC prognosis prediction. Clin Cancer Res; 24(6); 1248–59. ©2017 AACR.

Subfields: Hepatology, Pulmonary and Respiratory Medicine, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Hepatology

In Pulmonary and Respiratory Medicine

In Surgery

Citations in the corpus

Application of Artificial Intelligence Technology in Oncology: Towards the Establishment of Precision Medicine (2020, methodology): “For example, a method for dimensionality reduction using an autoencoder has been proposed for large amounts of multi-omics data [105], and we have also used this method to stratify lung cancer patients [32].”
Opportunities and obstacles for deep learning in biology and medicine (2017, methodology): “[419] trained a deep autoencoder model jointly on RNA-seq, miRNA-seq, and methylation data from The Cancer Genome Atlas to predict survival subgroups of hepatocellular carcinoma patients.”
Artificial Intelligence in Cancer Research and Precision Medicine (2021, neutral): “Sun (98, 99).”
The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges (2019, methodology): “When there is not enough data to train a supervised deep learning model, an auto-encoder provides an alternative method to extract deep learning features [71-73].”
Integration strategies of multi-omics data for machine learning analysis (2021, background): “For a similar goal, Chaudhary et al (2018) [70] implemented instead of the common fully connected neural network an autoencoder to reduce the dimensionality of the multi-omics matrix and extract meaningful and compact DL-based variables on which clustering was done with the k-mean algorithm.”
MOLI: multi-omics late integration with deep neural networks for drug response prediction (2019, background): “…(Dimitrakopoulos et al. , 2018; Mo et al. , 2013; Shrestha et al. , 2017; Singh et al. , 2019), patient stratiﬁcation (Khakabimamaghani and Ester, 2016), survival prediction (Chaudhary et al. , 2018), subgroup discovery (Liang et al. , 2015), and drug response prediction (Ding et al. , 2018).”
Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine (2018, methodology): “Anticipation of the diagnosis of cancerous lesions in oncologic patients using texture analysis and other advanced approaches [58].”
Predicting Deep Learning Based Multi-Omics Parallel Integration Survival Subtypes in Lung Cancer Using Reverse Phase Protein Array Data (2020, methodology): “Data were preprocessed according to the previous publications with following changes [12,13].”
The Application of Deep Learning in Cancer Prognosis Prediction (2020, methodology): “built a NN model using multi-omics data of 360 HCC samples from TCGA database [68].”
Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification (2018, methodology): “formance for predicting cell phenotypes from transcriptomics data [119], drug response in cancer [120], seizure-inducing side effects of preclinical drugs [121], patient survival from multi-omic data [36], drug-induced liver injury prediction [58], and classifying genomic variants into adverse drug ”
How Machine Learning will Transform Biomedicine (2020, neutral): “…samples (Way and Greene, 2019; Way et al., 2018), predicting genomic features of brain cancers using magnetic resonance images (Chang et al., 2018a), and forecasting cancer patient outcomes based on multi-omics (Chaudhary et al., 2018) or imaging-omics integrations (Mobadersany et al., 2018).”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, background): “and to better understand HCC heterogeneity among patients using gene expression, miRNA expression, DNA methylation and clinical information, a deep learning framework was proposed [104].”