Multilevel heterogeneous omics data integration with kernel fusion

MEMMAL: A tool for expanding large-scale mechanistic models with machine learned associations and big datasets

Computational models that can explain and predict complex sub-cellular, cellular, and tissue-level drug response mechanisms could speed drug discovery and prioritize patient-specific treatments (i.e., precision medicine). Some models are mechanistic with detailed equations describing known (or supposed) physicochemical processes, while some are statistical or machine learning-based approaches, that explain datasets but have no mechanistic or causal guarantees. These two types of modeling are rarely combined, missing the opportunity to explore possibly causal but data-driven new knowledge while explaining what is already known. Here, we explore combining machine learned associations with mechanistic models to develop computational models that could more fully represent cellular behavior. In this proposed MEMMAL (MEchanistic Modeling with MAchine Learning) framework, machine learning/statistical models built using omics datasets provide predictions for new interactions between genes and proteins where there is physicochemical uncertainty. These interactions are used as a basis for new reactions in mechanistic models. As a test case, we focused on incorporating novel IFNγ/PD-L1 related associations into a large-scale mechanistic model for cell proliferation and death to better recapitulate the recently released NIH LINCS Consortium MCF10A dataset and enable description of the cellular response to checkpoint inhibitor immunotherapies. This work is a template for combining big-data-inferred interactions with mechanistic models, which could be more broadly applicable for building multi-scale precision medicine and whole cell models.

IUSMMT: Survival mediation analysis of gene expression with multiple DNA methylation exposures and its application to cancers of TCGA

Effective and powerful survival mediation models are currently lacking. To partly fill such knowledge gap, we particularly focus on the mediation analysis that includes multiple DNA methylations acting as exposures, one gene expression as the mediator and one survival time as the outcome. We proposed IUSMMT (intersection-union survival mixture-adjusted mediation test) to effectively examine the existence of mediation effect by fitting an empirical three-component mixture null distribution. With extensive simulation studies, we demonstrated the advantage of IUSMMT over existing methods. We applied IUSMMT to ten TCGA cancers and identified multiple genes that exhibited mediating effects. We further revealed that most of the identified regions, in which genes behaved as active mediators, were cancer type-specific and exhibited a full mediation from DNA methylation CpG sites to the survival risk of various types of cancers. Overall, IUSMMT represents an effective and powerful alternative for survival mediation analysis; our results also provide new insights into the functional role of DNA methylation and gene expression in cancer progression/prognosis and demonstrate potential therapeutic targets for future clinical practice.

Integration strategies of multi-omics data for machine learning analysis

Increased availability of high-throughput technologies has generated an ever-growing number of omics data that seek to portray many different but complementary biological layers including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. New insight from these data have been obtained by machine learning algorithms that have produced diagnostic and classification biomarkers. Most biomarkers obtained to date however only include one omic measurement at a time and thus do not take full advantage of recent multi-omics experiments that now capture the entire complexity of biological systems.

Multi-omics data integration strategies are needed to combine the complementary knowledge brought by each omics layer. We have summarized the most recent data integration methods/ frameworks into five different integration strategies: early, mixed, intermediate, late and hierarchical. In this mini-review, we focus on challenges and existing multi-omics integration strategies by paying special attention to machine learning applications.

Risk Prediction in Patients With Heart Failure With Preserved Ejection Fraction Using Gene Expression Data and Machine Learning

Heart failure with preserved ejection fraction (HFpEF) has become a major health issue because of its high mortality, high heterogeneity, and poor prognosis. Using genomic data to classify patients into different risk groups is a promising method to facilitate the identification of high-risk groups for further precision treatment. Here, we applied six machine learning models, namely kernel partial least squares with the genetic algorithm (GA-KPLS), the least absolute shrinkage and selection operator (LASSO), random forest, ridge regression, support vector machine, and the conventional logistic regression model, to predict HFpEF risk and to identify subgroups at high risk of death based on gene expression data. The model performance was evaluated using various criteria. Our analysis was focused on 149 HFpEF patients from the Framingham Heart Study cohort who were classified into good-outcome and poor-outcome groups based on their 3-year survival outcome. The results showed that the GA-KPLS model exhibited the best performance in predicting patient risk. We further identified 116 differentially expressed genes (DEGs) between the two groups, thus providing novel therapeutic targets for HFpEF. Additionally, the DEGs were enriched in Gene Ontology terms and Kyoto Encyclopedia of Genes and Genomes pathways related to HFpEF. The GA-KPLS-based HFpEF model is a powerful method for risk stratification of 3-year mortality in HFpEF patients.

How Can Gene-Expression Information Improve Prognostic Prediction in TCGA Cancers: An Empirical Comparison Study on Regularization and Mixed Cox Models

Background

Previous cancer prognostic prediction models often consider only the most important transcriptomic expressions, and their power is limited. It is unknown whether prediction power can be further improved when additional transcriptomic information is incorporated.

Methods

To integrate transcriptomes, four models are compared based on 32 types of cancer in the Cancer Genome Atlas, including the general Cox model with only clinical covariates, the Cox model with a lasso penalty (coxlasso), the Cox model with an elastic net penalty (coxenet), and the mixed-effects Cox model (coxlmm). Furthermore, we partition the survival variance into the relative contribution of clinical and transcriptomic components within the framework of coxlmm. Finally, the influence of different numbers of genes was evaluated in the context of coxlmm.

Results

Compared with the clinical covariates–only Cox model, the average prediction gain was 2.4% for coxlasso, 4.2% for coxenet, and 7.2% for coxlmm across 16 low-censored cancers; a significant elevation of prediction power was observed for SARC, SKCM, LGG, PAAD, and HNSC. Similar findings were observed for all 32 cancers with the average prediction gain of 2.7, 3.8, and 5.8% for coxlasso, coxenet, and coxlmm. Coxlmm always had comparable or better prediction performance relative to coxlasso and coxenet with an average of 2.8% prediction improvement across the 16 low-censored cancers. In addition, it is shown that the predictive accuracy of coxlmm generally increases with the number of genes included. The survival variance partition analysis demonstrates that the transcriptomic contribution was higher for some cancers (e.g., LGG, CESC, PAAD, SKCM, and SARC) and lower for others (e.g., BRCA, COAD, KIRC, and STAD).

Conclusion

This study demonstrates that the integration of transcriptomic information can substantially improve prognostic prediction accuracy, but the prediction performance is cancer-specific and varies across cancer types. It further reveals that gene expression exhibits distinct contributions to survival variation across cancers.