Abstract:
:At the intersection between artificial intelligence and statistics, supervised learning allows algorithms to automatically build predictive models from just observations of a system. During the last twenty years, supervised learning has been a tool of choice to analyze the always increasing and complexifying data generated in the context of molecular biology, with successful applications in genome annotation, function prediction, or biomarker discovery. Among supervised learning methods, decision tree-based methods stand out as non parametric methods that have the unique feature of combining interpretability, efficiency, and, when used in ensembles of trees, excellent accuracy. The goal of this paper is to provide an accessible and comprehensive introduction to this class of methods. The first part of the review is devoted to an intuitive but complete description of decision tree-based methods and a discussion of their strengths and limitations with respect to other supervised learning methods. The second part of the review provides a survey of their applications in the context of computational and systems biology.
journal_name
Mol Biosystjournal_title
Molecular bioSystemsauthors
Geurts P,Irrthum A,Wehenkel Ldoi
10.1039/b907946gsubject
Has Abstractpub_date
2009-12-01 00:00:00pages
1593-605issue
12eissn
1742-206Xissn
1742-2051journal_volume
5pub_type
杂志文章,评审abstract::Structural and functional changes in albumin are of particular interest as numerous studies in vivo have reported a strong involvement of glycated-HSA in the development and progression of chronic diabetic complications. Non-enzymatic addition of glucose molecules to a protein induces structural changes in it. These c...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c6mb00324a
更新日期:2016-07-19 00:00:00
abstract::Cellular heterogeneity and stochastic fluctuation play key roles in biological processes. Single molecule approaches have the key advantage of avoiding ensemble averaging, allowing the observation of transient intermediates and heterogeneity (both static and dynamic). Thus they have revolutionised the way many biologi...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/b702845h
更新日期:2007-06-01 00:00:00
abstract::The Parkinson's disease (PD) associated gene PINK1 encodes a protein kinase that mediates the phosphorylation of multiple proteins involved in mitochondrial homeostasis. The broader downstream signaling events mediated by PINK1 kinase activity have not been well documented. We combine quantitative phosphoproteomic str...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c3mb70565j
更新日期:2014-07-01 00:00:00
abstract::Although angiotensin (Ang)II-induced Janus-activated kinase (JAK)2 phosphorylation was reported to be enhanced in failing human cardiomyocytes, the downstream balance between cardio-protective (signal transducer and activator of transcription-STAT3) and the pro-inflammatory (STAT2 and STAT5) response remains unexplore...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c2mb25120e
更新日期:2012-09-01 00:00:00
abstract::Intrinsically disordered regions in proteins are known to evolve rapidly while maintaining their function. However, given their lack of structure and sequence conservation, the means through which they stay functional is not clear. Poor sequence conservation also hampers the classification of these regions into functi...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c2mb25202c
更新日期:2012-10-30 00:00:00
abstract::The investigation of the structure and dynamics of signal transduction systems through data-based mathematical models in ordinary differential equations or other paradigms has proven to be a successful approach in recent times. Extending this concept, we here analysed the use of kinetic models based on power-law terms...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c0mb00018c
更新日期:2010-11-01 00:00:00
abstract::Protein methylation catalyzed by methyltransferases carries many important biological functions. Methylation and their regulatory enzymes are involved in a variety of human disease states, raising the possibility that abnormally methylated proteins can be disease markers and methyltransferases are potential therapeuti...
journal_title:Molecular bioSystems
pub_type: 杂志文章,评审
doi:10.1039/c5mb00259a
更新日期:2015-10-01 00:00:00
abstract::The ectonucleotide phosphodiesterase/pyrophosphatase-1 (NPP1) is a type II transmembrane glycoprotein that regulates extracellular inorganic purine nucleotide and inorganic diphosphate levels through the hydrolysis of ATP into AMP and diphosphate. NPP1 is a promising drug target as it plays a role in several disorders...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c7mb00095b
更新日期:2017-05-30 00:00:00
abstract::The complex web of interactions between the host immune system and the pathogen determines the outcome of any infection. A computational model of this interaction network, which encodes complex interplay among host and bacterial components, forms a useful basis for improving the understanding of pathogenesis, in filli...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/b912129c
更新日期:2010-03-01 00:00:00
abstract::In the pathogenesis of renal fibrosis, oxidative stress (OS) enhances the production of reactive oxygen species (ROS) leading to sustained cell growth, inflammation, excessive tissue remodelling and accumulation, which results in the development and acceleration of renal damage. In our previous work (Eltoweissy et al....
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c5mb00887e
更新日期:2016-05-24 00:00:00
abstract::Blockage of the interactions between immunologic checkpoint protein PD-1 and its ligand PD-L1 showed efficacy for cancer treatment. X-ray structures have captured static conformational snapshots of PD-1 and revealed that the CC' loop adopts an open conformation in the apo-protein but turns into a closed form and inter...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c7mb00036g
更新日期:2017-05-02 00:00:00
abstract::The use of Cyan Fluorescent Proteins, with a distinctive lifetime signature, opens up new alternatives to track and semi-quantify the relative expression of proteins in vivo using a single excitation source and emission channel. ...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/b815445g
更新日期:2009-02-01 00:00:00
abstract::The mono-site mutations of the absolutely conserved residues, (464)LGR(466), in the α-helix 5 (h5) of HPV16 L1 completely disrupted the pentamer formation. The implication of this finding is the potential usage of a h5-like peptide as the reagent to interfere with the pentamer formation and stability as an anti-HPV re...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c3mb70550a
更新日期:2014-04-01 00:00:00
abstract::An intracellular signal transduction network constitutes an assembled machinery to control the dynamics of kinase-phosphatase cascade and gene expression. Spatio-temporal analyses of the cellular process can explain the biochemical role of the receptor tyrosine kinases in cancer development from a system point of view...
journal_title:Molecular bioSystems
pub_type: 杂志文章,评审
doi:10.1039/b612800a
更新日期:2007-02-01 00:00:00
abstract::Infectious diseases caused by bacterial pathogens pose a major concern to public health and, thus, greater attention must be given to providing insightful knowledge on host-pathogen interactions. There are several theories addressing the dynamics of complex mechanisms of host-pathogen interactions. The availability of...
journal_title:Molecular bioSystems
pub_type: 杂志文章,评审
doi:10.1039/c7mb00372b
更新日期:2017-11-21 00:00:00
abstract::Disordered regions within proteins have increasingly been associated with various cellular functions. Identifying the specific roles played by disorder in these functions has proved difficult. However, the development of reliable prediction algorithms has expanded the study of disorder from a few anecdotal examples to...
journal_title:Molecular bioSystems
pub_type: 杂志文章,评审
doi:10.1039/c1mb05235g
更新日期:2012-01-01 00:00:00
abstract::A major mode of signal transduction in bacteria is the two-component system, which involves phosphorylation of an output-generating receiver protein by a signal-sensing histidine kinase. This differs from the more common one-component system--where both signal sensing and output generation are performed by the same pr...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c1mb05260h
更新日期:2011-11-01 00:00:00
abstract::Normalization of high-throughput molecular expression profiles secures differential expression analysis between samples of different phenotypes or biological conditions, and facilitates comparison between experimental batches. While the same general principles apply to microRNA (miRNA) normalization, there is mounting...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c4mb00711e
更新日期:2015-05-01 00:00:00
abstract::Oxygen dependent modulation of red blood cell metabolism is a long investigated issue. However, the recent introduction of novel mass spectrometry-based approaches lends itself to implement our understanding of the effects of red blood cell prolonged exposure to anaerobiosis. Indeed, most of the studies conducted so f...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c3mb25575a
更新日期:2013-06-01 00:00:00
abstract::In order to elucidate the effect of flexible linker length on the catalytic efficiency of fusion proteins, two short flexible peptide linkers of various lengths were fused between Arabidopsis thaliana 4-coumaroyl-CoA ligase (4CL) and Polygonum cuspidatum stilbene synthase (STS) to generate fusion proteins 4CL-(GSG)n-S...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c6mb00563b
更新日期:2017-02-28 00:00:00
abstract::As one of the most important trace elements within an organism, zinc has been shown to be involved in numerous biological processes and closely implicated in various diseases. The zinc ion is important for proteins to perform their functional roles. To provide in-depth functional annotation of zinc-binding proteins, a...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c3mb70100j
更新日期:2013-09-01 00:00:00
abstract::G protein-coupled receptors (GPCRs) are key signaling proteins that regulate how cells interact with their environment. Traditional signaling cascades involving GPCRs have been well described and are well established and very important clinical targets. With the development of more recent technologies, hints about the...
journal_title:Molecular bioSystems
pub_type: 杂志文章,评审
doi:10.1039/c2mb25429h
更新日期:2013-04-05 00:00:00
abstract::RNA-binding proteins (RBPs) are key regulators of gene expression. Some long non-coding RNAs (lncRNAs) affect gene expression by interacting with RBPs. However, whether this influences the biological characteristics of lncRNAs in diseases still remains unknown. Here, we classify lncRNAs into two categories, using the ...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c7mb00144d
更新日期:2017-06-01 00:00:00
abstract::The identification of genetic markers (e.g. genes, pathways and subnetworks) for cancer has been one of the most challenging research areas in recent years. A subset of these studies attempt to analyze genome-wide expression profiles to identify markers with high reliability and reusability across independent whole-tr...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c5mb00684h
更新日期:2016-03-01 00:00:00
abstract::It is now widely accepted that microRNAs (miRNAs or miRs) along with transcription factors (TFs) weave a complex inter-regulatory network within the cell that is responsible for the combinatorial regulation of gene expression. Recently we have shown that miRNAs and TFs that form network clusters are also associated wi...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c3mb25518b
更新日期:2013-06-01 00:00:00
abstract::Insights into the structure and dynamics of modular polyketide synthases (PKS) are essential for understanding the mechanistic details of the biosynthesis of a large number of pharmaceutically important secondary metabolites. The crystal structures of the KS-AT di-domain from erythromycin synthase have revealed the re...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c2mb05425f
更新日期:2012-04-01 00:00:00
abstract::Small molecule modulators are critical for dissecting and understanding signaling pathways at the molecular level. Interleukin 6 (IL-6) is a cytokine that signals via the JAK-STAT pathway and is implicated in cancer and inflammation. To identify modulators of this pathway, we screened a chemical collection against an ...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/b902021g
更新日期:2009-09-01 00:00:00
abstract::Ebola virus (EBOV) is highly lethal due to virally encoded immune antagonists, and the combination of EBOV VP24 with karyopherin alpha (KPNA) will trigger anti-interferon (IFN) signaling. The crystal structure of VP24-KPNA5 has been proposed in recent studies, but the precise binding mechanisms are still unclear. In o...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c7mb00136c
更新日期:2017-05-02 00:00:00
abstract::Differential gene expression governs the development, function and pathology of multicellular organisms. Transcription regulatory networks study differential gene expression at a systems level by mapping the interactions between regulatory proteins and target genes. While microarray transcription profiles are the most...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/B908108a
更新日期:2009-12-01 00:00:00
abstract::Human mitogen-activated protein kinase (MAPK) family members JNK and p38 are two homologous protein-serine/threonine kinases but play distinct roles in the pathological process of neurological disorders. Selective targeting of JNK over p38 has been established as a potential therapeutic approach to epilepsy and other ...
journal_title:Molecular bioSystems
pub_type: 杂志文章
doi:10.1039/c6mb00297h
更新日期:2016-07-19 00:00:00