Ensemble learning prediction of protein-protein interactions using proteins functional annotations.

Abstract:

:Protein-protein interactions are important for the majority of biological processes. A significant number of computational methods have been developed to predict protein-protein interactions using protein sequence, structural and genomic data. Vast experimental data is publicly available on the Internet, but it is scattered across numerous databases. This fact motivated us to create and evaluate new high-throughput datasets of interacting proteins. We extracted interaction data from DIP, MINT, BioGRID and IntAct databases. Then we constructed descriptive features for machine learning purposes based on data from Gene Ontology and DOMINE. Thereafter, four well-established machine learning methods: Support Vector Machine, Random Forest, Decision Tree and Naïve Bayes, were used on these datasets to build an Ensemble Learning method based on majority voting. In cross-validation experiment, sensitivity exceeded 80% and classification/prediction accuracy reached 90% for the Ensemble Learning method. We extended the experiment to a bigger and more realistic dataset maintaining sensitivity over 70%. These results confirmed that our datasets are suitable for performing PPI prediction and Ensemble Learning method is well suited for this task. Both the processed PPI datasets and the software are available at .

journal_name

Mol Biosyst

journal_title

Molecular bioSystems

authors

Saha I,Zubek J,Klingström T,Forsberg S,Wikander J,Kierczak M,Maulik U,Plewczynski D

doi

10.1039/c3mb70486f

subject

Has Abstract

pub_date

2014-04-01 00:00:00

pages

820-30

issue

4

eissn

1742-206X

issn

1742-2051

journal_volume

10

pub_type

杂志文章
  • Evaluation of cell-free tumour DNA and RNA in patients with breast cancer and benign breast disease.

    abstract::High levels of DNA and RNA released by apoptotic and necrotic cells circulate in the blood of cancer patients. In the present study we determined the applicability of the quantification of nucleic acids and their genetic alterations as minimally invasive tool for breast cancer screening. The relative concentrations of...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05197k

    authors: Schwarzenbach H,Müller V,Milde-Langosch K,Steinbach B,Pantel K

    更新日期:2011-10-01 00:00:00

  • Transcription regulatory networks in Caenorhabditis elegans inferred through reverse-engineering of gene expression profiles constitute biological hypotheses for metazoan development.

    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

    authors: Vermeirssen V,Joshi A,Michoel T,Bonnet E,Casneuf T,Van de Peer Y

    更新日期:2009-12-01 00:00:00

  • Chemical biology suggests a role for calcium signaling in mediating sustained JNK activation during apoptosis.

    abstract::Calcium (Ca(2+)) is used as a signaling molecule to regulate many cellular processes. Calcium signaling generally involves transient elevations of the concentration of free Ca(2+) in the cytosol. More pronounced and sustained elevations of intracellular Ca(2+) concentrations are observed during apoptosis (programmed c...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章,评审

    doi:10.1039/b920805d

    authors: Brnjic S,Olofsson MH,Havelka AM,Linder S

    更新日期:2010-05-01 00:00:00

  • Enhancing specificity in the Janus kinases: a study on the thienopyridine JAK2 selective mechanism combined molecular dynamics simulation.

    abstract::The selective inhibition for JAK2 over the other JAK family kinases (JAK1, JAK3 and TYK2) has shared an immense challenge due to high conservatism. In this paper, the highly JAK2 selective mechanism of the thienopyridine derivative was identified at the molecular level, based on insights into the inhibitory effects of...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00747j

    authors: Li JJ,Cheng P,Tu J,Zhai HL,Zhang XY

    更新日期:2016-02-01 00:00:00

  • Stochastic analysis of a miRNA-protein toggle switch.

    abstract::Within systems biology there is an increasing interest in the stochastic behavior of genetic and biochemical reaction networks. An appropriate stochastic description is provided by the chemical master equation, which represents a continuous time Markov chain (CTMC). In this paper we consider the stochastic properties ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05086a

    authors: Giampieri E,Remondini D,de Oliveira L,Castellani G,Lió P

    更新日期:2011-10-01 00:00:00

  • Induced genome maintenance pathways in pre-cancer tissues describe an anti-cancer barrier in tumor development.

    abstract::A recent model proposing that a barrier is raised against tumor evolution in pre-cancer tissues is investigated. For that we quantify expression alterations in genome maintenance pathways: DNA damage response, death pathways and cell cycle and also differentially expressed genes in transcriptomes of pre-cancerous and ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c2mb25242b

    authors: Simão ÉM,Sinigaglia M,Bugs CA,Castro MA,Librelotto GR,Alves R,Mombach JC

    更新日期:2012-11-01 00:00:00

  • Metabonomic characterization of aging and investigation on the anti-aging effects of total flavones of Epimedium.

    abstract::A liquid chromatography coupled with mass spectrometry (LC/MS) based metabonomics approach was applied to characterize the aging of rats, and the anti-aging effect of total flavones of Epimedium (TFE), a traditional Chinese medicine, has also been investigated. Serum samples collected from 4, 10, 18 and 24 month-old r...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/b816407j

    authors: Yan S,Wu B,Lin Z,Jin H,Huang J,Yang Y,Zhang X,Shen Z,Zhang W

    更新日期:2009-10-01 00:00:00

  • Synergy evaluation by a pathway-pathway interaction network: a new way to predict drug combination.

    abstract::Drug combinations have been widely applied to treat complex diseases, like cancer, HIV and cardiovascular diseases. One of the most important characteristics for drug combinations is the synergistic effects among different drugs, that is to say, the combination effects are larger than the sum of individual effects. Al...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00599j

    authors: Chen D,Zhang H,Lu P,Liu X,Cao H

    更新日期:2016-02-01 00:00:00

  • Integrating multiple omics data for the discovery of potential Beclin-1 interactions in breast cancer.

    abstract::Breast cancer has been reported as one of the most frequently diagnosed malignant diseases and the leading cause of cancer death in women all around the world. Furthermore, this complicated cancer is divided into multiple subtypes which present different clinical symptoms and need correspondingly directed therapy. We ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c6mb00653a

    authors: Chen Y,Wang X,Wang G,Li Z,Wang J,Huang L,Qin Z,Yuan X,Cheng Z,Zhang S,Yin Y,He J

    更新日期:2017-05-02 00:00:00

  • Inhibition mechanism exploration of quinoline derivatives as PDE10A inhibitors by in silico analysis.

    abstract::As a potential target for the treatment of schizophrenia, the dual cAMP/cGMP hydrolyzing enzyme PDE10A has attracted a significant amount of attention. In the present work, the inhibition mechanism of 116 structurally diverse quinoline derivatives as PDE10A inhibitors was explored by 3D-QSAR, molecular docking and mol...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c2mb25501d

    authors: Wu Q,Gao Q,Guo H,Li D,Wang J,Gao W,Han C,Li Y,Yang L

    更新日期:2013-03-01 00:00:00

  • Bivalent inhibitors of the tyrosine kinases ABL and SRC: determinants of potency and selectivity.

    abstract::We recently reported a chemical genetic method for generating bivalent inhibitors of protein kinases. This method relies on the use of the DNA repair enzyme O(6)-alkylguanine-DNA alkyltransferase (AGT) to display an ATP-competitive inhibitor and a ligand that targets a secondary binding domain. With this method potent...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c0mb00108b

    authors: Hill ZB,Perera BG,Maly DJ

    更新日期:2011-02-01 00:00:00

  • Inhibition of lysine biosynthesis: an evolving antibiotic strategy.

    abstract::Bacterial biosynthesis of lysine has come under increased scrutiny as a target for novel antibacterial agents as it provides lysine for protein synthesis and both lysine and meso-diaminopimelate for construction of the bacterial peptidoglycan cell wall. In this Highlight article we review recent advances in the valida...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章,评审

    doi:10.1039/b705624a

    authors: Hutton CA,Perugini MA,Gerrard JA

    更新日期:2007-07-01 00:00:00

  • Energy based approach for understanding the recognition mechanism in protein-protein complexes.

    abstract::Protein-protein interactions play an essential role in the regulation of various cellular processes. Understanding the recognition mechanism of protein-protein complexes is a challenging task in molecular and computational biology. In this work, we have developed an energy based approach for identifying the binding si...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/B904161N

    authors: Gromiha MM,Yokota K,Fukui K

    更新日期:2009-12-01 00:00:00

  • iLoc-Animal: a multi-label learning classifier for predicting subcellular localization of animal proteins.

    abstract::Predicting protein subcellular localization is a challenging problem, particularly when query proteins have multi-label features meaning that they may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing methods can only be used to deal with the single-label ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c3mb25466f

    authors: Lin WZ,Fang JA,Xiao X,Chou KC

    更新日期:2013-04-05 00:00:00

  • Methodology of reversible protein labeling for ratiometric fluorescent measurement.

    abstract::The first fluorescent labeling technology, which can induce not only an increase in the fluorescence intensity but also a shift in the fluorescence spectrum, has been developed for "ratiometric" measurements for a protein by utilizing a newly designed "field-sensitive" fluorescent probe and its corresponding unique am...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/b515777c

    authors: Soh N,Seto D,Nakano K,Imato T

    更新日期:2006-02-01 00:00:00

  • Repeats are one of the main characteristics of RNA-binding proteins with prion-like domains.

    abstract::It is not surprising that a large number of diseases related to amyloid fibril depositions are formed in various organs. Therefore, it is necessary to understand the transformation of native proteins into amyloid fibrils in order to clarify which key elements of this process determine the pathway of protein misfolding...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00273g

    authors: Galzitskaya OV

    更新日期:2015-08-01 00:00:00

  • Optimized protocols for the isolation of specific protein-binding peptides or peptoids from combinatorial libraries displayed on beads.

    abstract::Many methods have been published by which combinatorial libraries may be screened for compounds capable of manipulating the function(s) of a target protein. One of the simplest approaches is to identify compounds in a library that bind the protein of interest, since these binding events usually occur on functionally i...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/b514349g

    authors: Kodadek T,Bachhawat-Sikder K

    更新日期:2006-01-01 00:00:00

  • Competitive profiling of celastrol targets in human cervical cancer HeLa cells via quantitative chemical proteomics.

    abstract::Celastrol, isolated from the traditional Chinese medicinal herb Tripterygium wilfordii Hook. f. (Thunder God's Vine), has been used to treat cancer, chronic inflammatory, autoimmune and other human diseases. However, to date, the protein targets and the mechanism of action of celastrol have remained elusive. In this s...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c6mb00691d

    authors: Zhou Y,Li W,Wang M,Zhang X,Zhang H,Tong X,Xiao Y

    更新日期:2016-12-20 00:00:00

  • A red-fluorescent substrate microarray for lipase fingerprinting.

    abstract::A lipase substrate microarray was obtained by printing aliphatic C2-C12 monoesters of (5R)- and (5S)-3-(5,6-dihydroxyhexyloxy)benzaldehyde by reductive alkylation on amine-functionalized glass slides coated with bovine serum albumin and a short PEG linker. The microarray features 12 substrates and their 66 possible bi...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/b609275f

    authors: Grognux J,Reymond JL

    更新日期:2006-10-01 00:00:00

  • Serum metabolic profiling and features of papillary thyroid carcinoma and nodular goiter.

    abstract::Thyroid carcinoma is a common endocrine malignancy worldwide, accounting for approximately 1% of all diagnosed cancers and about 91.5% of the malignancies of head and neck. However, differentiating malignant thyroid nodules from benign ones remains a diagnostic challenge. Thus, novel molecular markers that enable non-...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05029j

    authors: Yao Z,Yin P,Su D,Peng Z,Zhou L,Ma L,Guo W,Ma L,Xu G,Shi J,Jiao B

    更新日期:2011-09-01 00:00:00

  • NMR- and MS-based metabolomics: various organ responses following naphthalene intervention.

    abstract::Naphthalene, a polycyclic aromatic hydrocarbon, is a ubiquitous environmental pollutant capable of causing illness. In this study, we deconvoluted the metabolites related to naphthalene intervention in various organs by using nuclear magnetic resonance (NMR) and liquid chromatography-tandem mass spectrometry (LC-MS/MS...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c4mb00090k

    authors: Ling YS,Liang HJ,Chung MH,Lin MH,Lin CY

    更新日期:2014-07-01 00:00:00

  • Effects of culture media on metabolic profiling of the human gastric cancer cell line SGC7901.

    abstract::Cell culture metabolomics has demonstrated significant advantages in cancer research. However, its applications have been impeded by some influencing factors such as culture media, which could significantly affect cellular metabolic profiles and lead to inaccuracy and unreliability of comparative metabolomic analysis ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00019j

    authors: Huang Z,Shao W,Gu J,Hu X,Shi Y,Xu W,Huang C,Lin D

    更新日期:2015-07-01 00:00:00

  • Long-range chromosomal interactions and gene regulation.

    abstract::Over the last few years important new insights into the process of long-range gene regulation have been obtained. Gene regulatory elements are found to engage in direct physical interactions with distant target genes and with loci on other chromosomes to modulate transcription. An overview of recently discovered long-...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章,评审

    doi:10.1039/b803580f

    authors: Miele A,Dekker J

    更新日期:2008-11-01 00:00:00

  • Effect of small molecules on cell reprogramming.

    abstract::The essential idea of regenerative medicine is to fix or replace tissues or organs with alive and patient-specific implants. Pluripotent stem cells are able to indefinitely self-renew and differentiate into all cell types of the body which makes them a potent substantial player in regenerative medicine. The easily acc...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章,评审

    doi:10.1039/c6mb00595k

    authors: Baranek M,Belter A,Naskręt-Barciszewska MZ,Stobiecki M,Markiewicz WT,Barciszewski J

    更新日期:2017-01-31 00:00:00

  • The network properties of myelodysplastic syndromes pathogenesis revealed by an integrative systems biological method.

    abstract::Insight into the molecular mechanism of complex diseases is an important topic in the current bio-medical research. However, different from the single-gene disorders, high heterogeneity of many of the complex diseases prevents scientists from the exact understanding of the etiology. In this study, we used Myelodysplas...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05018d

    authors: Ren X,Zhou X,Chang CC

    更新日期:2011-06-01 00:00:00

  • High performance screening, structural and molecular dynamics analysis to identify H1 inhibitors from TCM Database@Taiwan.

    abstract::New-type oseltamivir-resistant H1N1 influenza viruses have been a major threat to human health since the 2009 flu pandemic. To resolve the drug resistance issue, we aimed to identify a new type of inhibitors against H1 from traditional Chinese medicine (TCM) by employing the world's largest TCM database () for virtual...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05320e

    authors: Chang SS,Huang HJ,Chen CY

    更新日期:2011-12-01 00:00:00

  • Targeting GSTP1-1 induces JNK activation and leads to apoptosis in cisplatin-sensitive and -resistant human osteosarcoma cell lines.

    abstract::The effect of the glutathione transferase P1-1 (GSTP1-1) targeting has been investigated in both sensitive (U-2OS) and cisplatin-resistant (U-2OS/CDDP4 μg) human osteosarcoma cell lines. Despite the different enzyme's content, inhibition of GSTP1-1 by 6-(7-nitro-2,1,3-benzoxadiazol-4-ylthio)hexanol (NBDHEX) causes the...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c1mb05295k

    authors: Sau A,Filomeni G,Pezzola S,D'Aguanno S,Tregno FP,Urbani A,Serra M,Pasello M,Picci P,Federici G,Caccuri AM

    更新日期:2012-04-01 00:00:00

  • New insights into the complex regulation of the glycolytic pathway in Lactococcus lactis. II. Inference of the precisely timed control system regulating glycolysis.

    abstract::The dairy bacterium Lactococcus lactis has to master a complicated task. It must control its essentially linear glycolytic pathway in such a fashion that, when the substrate, glucose, runs out, it retains enough phosphoenolpyruvate and fructose-1,6-bisphosphate to be able to restart glycolysis as soon as new glucose b...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00726g

    authors: Dolatshahi S,Fonseca LL,Voit EO

    更新日期:2016-01-01 00:00:00

  • An immunochemical approach to detect oxidized protein tyrosine phosphatases using a selective C-nucleophile tag.

    abstract::Protein tyrosine phosphatases are crucial regulators of signal transduction and function as antagonists towards protein tyrosine kinases to control reversible tyrosine phosphorylation, thereby regulating fundamental physiological processes. Growing evidence has supported the notion that reversible oxidative inactivati...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c5mb00847f

    authors: Garcia FJ,Carroll KS

    更新日期:2016-05-24 00:00:00

  • A combined chemometric and quantitative NMR analysis of HIV/AIDS serum discloses metabolic alterations associated with disease status.

    abstract::Individuals infected with the human immunodeficiency virus (HIV) often suffer from concomitant metabolic complications. Treatment with antiretroviral therapy has also been shown to alter the metabolism of patients. Although chemometric analysis of nuclear magnetic resonance (NMR) spectra of human sera can distinguish ...

    journal_title:Molecular bioSystems

    pub_type: 杂志文章

    doi:10.1039/c4mb00347k

    authors: McKnight TR,Yoshihara HA,Sitole LJ,Martin JN,Steffens F,Meyer D

    更新日期:2014-11-01 00:00:00