Integrative Network Fusion: a multi-omics approach in molecular profiling

Abstract

Recent technological advances and international efforts, such as The Cancer Genome Atlas (TCGA), have made available several pan-cancer datasets encompassing multiple omics layers with detailed clinical information in large collection of samples. The need has thus arisen for the development of computational methods aimed at improving cancer subtyping and biomarker identification from multi-modal data. Here we apply the Integrative Network Fusion (INF) pipeline, which combines multiple omics layers exploiting Similarity Network Fusion (SNF) within a machine learning predictive framework. INF includes a feature ranking scheme (rSNF) on SNF-integrated features, used by a classifier over juxtaposed multi-omics features (juXT). In particular, we show instances of INF implementing Random Forest (RF) and linear Support Vector Machine (LSVM) as the classifier, and two baseline RF and LSVM models are also trained on juXT. A compact RF model, called rSNFi, trained on the intersection of top-ranked biomarkers from the two approaches juXT and rSNF is finally derived. All the classifiers are run in a 10x5-fold crossvalidation schema to warrant reproducibility, following the guidelines for an unbiased Data Analysis Plan by the US FDA-led initiatives MAQC/SEQC. INF is demonstrated on four classification tasks on three multi-modal TCGA oncogenomics datasets. Gene expression, protein abundances and copy number variants are used to predict estrogen receptor status (BRCA-ER, N=381) and breast invasive carcinoma subtypes (BRCA-subtypes, N=305), while gene expression, miRNA expression and methylation data is used as predictor layers for acute myeloid leukemia and renal clear cell carcinoma survival (AML-OS, N=157; KIRC-OS, N=181). In test, INF achieved similar Matthews Correlation Coefficient (MCC) values and 97% to 83% smaller feature sizes (FS), compared with juXT for BRCA-ER (MCC: 0.83 vs 0.80; FS: 56 vs 1801) and BRCA-subtypes 1 Chierici et al. INF(0.84 vs 0.80; 302 vs 1801), improving KIRC-OS performance (0.38 vs 0.31; 111 vs 2319). INF predictions are generally more accurate in test than one-dimensional omics models, with smaller signatures too, where transcriptomics consistently play the leading role. Overall, the INF framework effectively integrates multiple data levels in oncogenomics classification tasks, improving over the performance of single layers alone and naive juxtaposition, and provides compact signature sizes 1 .

Similarity network fusion for the integration of multi-omics and microbiomes in respiratory disease

“…Importantly, since integrated SNF networks retain only similarity information between patients in the input space, implementation of supervised analysis is not straightforward and needs modification. Examples of this include integrative network fusion which implements feature-ranked SNF within a machine learning framework or SNF-NN that implements deep learning alongside SNF [11,12]. Alternatively, semi-supervised or unsupervised analysis can be pursued.…”

“…While modifications to SNF including Integrative Network Fusion (INF), Affinity Network Fusion (ANF), Similarity Kernel Fusion (SKF), association-signal-annotation boosted Similarity Network Fusion (ab-SNF), Robust Similarity Network Fusion (RSNF), local scaling SNF (Ls-SNF) and weighted Similarity Network Fusion (wSNF) can all improve the various limitations of SNF, no single integrative approach is best, and each has to be considered in terms of 'best-use case', and its own inherent advantages and limitations [4,11,[21][22][23][24][25]. It is also important to note that SNF-derived associations are still inferred, and experimental manipulations are required to definitively confirm causation.…”