Functional networks inference from rule-based machine learning models

Abstract

BackgroundFunctional networks play an important role in the analysis of biological processes and systems. The inference of these networks from high-throughput (-omics) data is an area of intense research. So far, the similarity-based inference paradigm (e.g. gene co-expression) has been the most popular approach. It assumes a functional relationship between genes which are expressed at similar levels across different samples. An alternative to this paradigm is the inference of relationships from the structure of machine learning models. These models are able to capture complex relationships between variables, that often are different/complementary to the similarity-based methods.ResultsWe propose a protocol to infer functional networks from machine learning models, called FuNeL. It assumes, that genes used together within a rule-based machine learning model to classify the samples, might also be functionally related at a biological level. The protocol is first tested on synthetic datasets and then evaluated on a test suite of 8 real-world datasets related to human cancer. The networks inferred from the real-world data are compared against gene co-expression networks of equal size, generated with 3 different methods. The comparison is performed from two different points of view. We analyse the enriched biological terms in the set of network nodes and the relationships between known disease-associated genes in a context of the network topology. The comparison confirms both the biological relevance and the complementary character of the knowledge captured by the FuNeL networks in relation to similarity-based methods and demonstrates its potential to identify known disease associations as core elements of the network. Finally, using a prostate cancer dataset as a case study, we confirm that the biological knowledge captured by our method is relevant to the disease and consistent with the specialised literature and with an independent dataset not used in the inference process.AvailabilityThe implementation of our network inference protocol is available at: http://ico2s.org/software/funel.html Electronic supplementary materialThe online version of this article (doi:10.1186/s13040-016-0106-4) contains supplementary material, which is available to authorized users.

Lipidomes of lung cancer and tumour-free lung tissues reveal distinct molecular signatures for cancer differentiation, age, inflammation, and pulmonary emphysema

“…Linear models based upon PLS regression will be a valuable tool. However, other approaches based upon machine learning and nonlinear models 31 , 32 should be evaluated, in conjunction with increased case numbers. Besides computational improvements, translational and interdisciplinary cooperation to incorporate other omics’ results will be intensified.…”

Ten quick tips for biomarker discovery and validation analyses using machine learning

“…Common examples for learning approaches favoring interpretability are linear modeling methods [ 92 ] and rule-based machine learning methods, such as classification and regression trees [ 133 , 134 ], combinatorial rule learning approaches [ 135 , 136 ], and probabilistic and fuzzy rule learning methods [ 137 , 138 ]. While linear modeling approaches enable a relevance scoring and ranking of features by their absolute weights in a model, rule-based learning approaches can provide additional information on feature associations by computing statistics on their co-occurrence in decision rule sets [ 139 ]. Apart from these generic learning methods, more recently, domain-specific interpretable prediction and clustering approaches, which exploit prior biological knowledge from cellular pathways and molecular networks [ 140 – 142 ], have gained interest.…”

Characterising the Influence of Rule-Based Knowledge Representations in Biological Knowledge Extraction from Transcriptomics Data

“…FuNeL [14] is a recently proposed method to infer functional networks from rule-based machine learning models. As mentioned in the introduction, FuNeL applies the co-prediction principle: It infers that two biological elements (e.g.…”

“…A method in this latter category, which we will use in this paper, is FuNeL [14]. FuNeL generates biological functional networks from a labelled (classification) dataset by mining the rule sets generated by the BioHEL evolutionary machine learning system [1].…”