In this review, we discuss machine-learning models and algorithms for identifying and characterising susceptibility genes in common, complex, multifactorial human diseases. We focus on the following machine-lea
Space Ranger uses two different methods for clustering spots by expression similarity, both of which operate in the PCA representation.Graph-basedThe graph-based clustering algorithm consists of building a sparse nearest-neighbor graph (where spots are linked if they are among the k nearest Euclidean...
Yet, it is still an open problem as state-of-the-art algorithms are often not able to process large amounts of data within reasonable time. Furthermore, many of the existing methods predict numerous false positives and have limited capabilities to integrate other sources of information, such ...
One of the approaches to use artificial intelligence is machine learning (ML). ML utilizes algorithms that learn from data to make predictions. There are two main types of ML: supervised and unsupervised (Alloghani et al.2020). In supervised learning, there is some information about the data ...
Ever since the development of high-throughput sequencing technologies, gene module detection methods have been a cornerstone for the biological interpretation of large gene compendia. Numerous approaches and algorithms have been proposed for the detection of gene modules through measuring gene expression3,...
One example is Monte Carlo methods and their extensions, which randomly change parameters and then enrich for changes that improve network performance [44, 45]. Another approach that has had great success is evolutionary algorithms [46]. Here, populations of gene circuits are ‘evolved’ in an ...
Mathematical models and algorithms are used to build these networks for their experimental testing. This allows to study more thoroughly the complex gene regulatory networks that are involved for example in the control of cell embryogenesis, cell differentiation, and tissue development. View chapter ...
Computational methods for essential gene prediction can overcome this drawback, particularly when intrinsic (e.g. from the protein sequence) as well as extrinsic features (e.g. from transcription profiles) are considered. In this work, we employed machine learning to predict essential genes in ...
The method can best be thought of as an analysis approach, to guide and assist in the use of any of a wide range of available clustering algorithms. We call the new methodology consensus clustering, and in conjunction with resampling techniques, it provides for a method to represent the ...
Generally, these and similar methods have been successful in some cases but may also suffer from epistasis detection power loss. Furthermore, they embed a degree of subjectivity due to the choice of filtering or dimensionality reduction technique; different choices often leading to quite different res...