Robust pathway sampling in phenotype prediction. Application to triple negative breast cancer

Abstract

Background: Phenotype prediction problems are usually considered ill-posed, as the amount of samples is very limited with respect to the scrutinized genetic probes. This fact complicates the sampling of the defective genetic pathways due to the high number of possible discriminatory genetic networks involved. In this research, we outline three novel sampling algorithms utilized to identify, classify and characterize the defective pathways in phenotype prediction problems, such as the Fisher's ratio sampler, the Holdout sampler and the Random sampler, and apply each one to the analysis of genetic pathways involved in tumor behavior and outcomes of triple negative breast cancers (TNBC). Altered biological pathways are identified using the most frequently sampled genes and are compared to those obtained via Bayesian Networks (BNs). Results: Random, Fisher's ratio and Holdout samplers were more accurate and robust than BNs, while providing comparable insights about disease genomics. Conclusions: The three samplers tested are good alternatives to Bayesian Networks since they are less computationally demanding algorithms. Importantly, this analysis confirms the concept of "biological invariance" since the altered pathways should be independent of the sampling methodology and the classifier used for their inference. Nevertheless, still some modifications are needed in the Bayesian networks to be able to sample correctly the uncertainty space in phenotype prediction problems, since the probabilistic parameterization of the uncertainty space is not unique and the use of the optimum network might falsify the pathways analysis. L Ã ðgÞ: g ∈ R s →C ¼ f1; 2g ð 1Þ The simplest case is to divide the phenotype in healthy controls and disease samples, but others problems

Analysis of transcriptomic responses to SARS-CoV-2 reveals plausible defective pathways responsible for increased susceptibility to infection and complications and helps to develop fast-track repositioning of drugs against COVID-19

“…The second one introduce a novel feature selection strategy integrating repeated random sampling with consensus scoring and evaluating the consistency of gene rank among different datasets was constructed [ 40 ]. In our case; and similarly to Li et al and Yang et al, we utilized a holdout sampler [ 41 , 42 ] in combination to the Fisher's ratio in order to filter the highest discriminatory genes according to this parameter [ 43 ].…”

A Machine Learning Model for Evaluating Imported Disease Screening Strategies in Immigrant Populations

“…The machine learning methodology could be improved by sampling the equivalent networks of discriminatory variables (see, e.g., Cernea et al 21 ) and create a consensus classifier for each imported disease. Nevertheless, in this paper we have focused in presenting the small-scale signature for each disease.…”

Addressing Noise and Estimating Uncertainty in Biomedical Data through the Exploration of Chemical Space

“…In this expression, is the prior distribution for sampling the genetic signatures, and is the likelihood of the genetic signature , which depends on its predictive accuracy . These algorithms have been recently applied to perform the robust sampling of the altered pathways in different diseases: Parkinson’s, Alzheimer’s, multiple sclerosis, multiple myeloma, and triple-negative cancer [ 19 , 20 , 21 , 22 , 23 ].…”