Multi-level machine learning prediction of protein-protein interactions in Saccharomyces cerevisiae.

Abstract:

:Accurate identification of protein-protein interactions (PPI) is the key step in understanding proteins' biological functions, which are typically context-dependent. Many existing PPI predictors rely on aggregated features from protein sequences, however only a few methods exploit local information about specific residue contacts. In this work we present a two-stage machine learning approach for prediction of protein-protein interactions. We start with the carefully filtered data on protein complexes available for Saccharomyces cerevisiae in the Protein Data Bank (PDB) database. First, we build linear descriptions of interacting and non-interacting sequence segment pairs based on their inter-residue distances. Secondly, we train machine learning classifiers to predict binary segment interactions for any two short sequence fragments. The final prediction of the protein-protein interaction is done using the 2D matrix representation of all-against-all possible interacting sequence segments of both analysed proteins. The level-I predictor achieves 0.88 AUC for micro-scale, i.e., residue-level prediction. The level-II predictor improves the results further by a more complex learning paradigm. We perform 30-fold macro-scale, i.e., protein-level cross-validation experiment. The level-II predictor using PSIPRED-predicted secondary structure reaches 0.70 precision, 0.68 recall, and 0.70 AUC, whereas other popular methods provide results below 0.6 threshold (recall, precision, AUC). Our results demonstrate that multi-scale sequence features aggregation procedure is able to improve the machine learning results by more than 10% as compared to other sequence representations. Prepared datasets and source code for our experimental pipeline are freely available for download from: http://zubekj.github.io/mlppi/ (open source Python implementation, OS independent).

journal_name

PeerJ

journal_title

PeerJ

authors

Zubek J,Tatjewski M,Boniecki A,Mnich M,Basu S,Plewczynski D

doi

10.7717/peerj.1041

subject

Has Abstract

pub_date

2015-07-02 00:00:00

pages

e1041

issn

2167-8359

pii

1041

journal_volume

3

pub_type

杂志文章

相关文献

PeerJ文献大全
  • CRISPR/Cas9-mediated VDR knockout plays an essential role in the growth of dermal papilla cells through enhanced relative genes.

    abstract:Background:Hair follicles in cashmere goats are divided into primary and secondary hair follicles (HFs). HF development, which determines the morphological structure, is regulated by a large number of vital genes; however, the key functional genes and their interaction networks are still unclear. Although the vitamin D...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7230

    authors: Gao Y,Jin M,Niu Y,Yan H,Zhou G,Chen Y

    更新日期:2019-07-03 00:00:00

  • Tiny pollen grains: first evidence of Saururaceae from the Late Cretaceous of western North America.

    abstract:BACKGROUND:The Saururaceae, a very small family of Piperales comprising only six species in four genera, have a relatively scanty fossil record outside of Europe. The phylogenetic relationships of the four genera to each other are resolved, with the type genus Saururus occurring in both eastern North America and East A...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.3434

    authors: Grímsson F,Grimm GW,Zetter R

    更新日期:2017-06-13 00:00:00

  • The homeodomain factor Gbx1 is required for locomotion and cell specification in the dorsal spinal cord.

    abstract::Dorsal horn neurons in the spinal cord integrate and relay sensory information to higher brain centers. These neurons are organized in specific laminae and different transcription factors are involved in their specification. The murine homeodomain Gbx1 protein is expressed in the mantle zone of the spinal cord at E12....

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.142

    authors: Meziane H,Fraulob V,Riet F,Krezel W,Selloum M,Geffarth M,Acampora D,Hérault Y,Simeone A,Brand M,Dollé P,Rhinn M

    更新日期:2013-08-29 00:00:00

  • Expression analysis of vitellogenins in the workers of the red imported fire ant (Solenopsis invicta).

    abstract::Vitellogenin has been proposed to regulate division of labor and social organization in social insects. The red imported fire ant (Solenopsis invicta) harbors four distinct, adjacent vitellogenin genes (Vg1, Vg2, Vg3, and Vg4). Contrary to honey bees that have a single Vg ortholog as well as potentially fertile nurses...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.4875

    authors: Hawkings C,Tamborindeguy C

    更新日期:2018-05-28 00:00:00

  • The influence of bait on remote underwater video observations in shallow-water coastal environments associated with the North-Eastern Atlantic.

    abstract::The use of baited remote underwater video (BRUV) for examining and monitoring marine biodiversity in temperate marine environments is rapidly growing, however many aspects of their effectiveness relies on assumptions based on studies from the Southern Hemisphere. The addition of bait to underwater camera systems acts ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.9744

    authors: Jones RE,Griffin RA,Januchowski-Hartley SR,Unsworth RKF

    更新日期:2020-08-27 00:00:00

  • Direct imaging of APP proteolysis in living cells.

    abstract::Alzheimer's disease is a multifactorial disorder caused by the interaction of genetic, epigenetic and environmental factors. The formation of cytotoxic oligomers consisting of Aβ peptide is widely accepted as being one of the main key events triggering the development of Alzheimer's disease. Aβ peptide production resu...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.3086

    authors: Parenti N,Del Grosso A,Antoni C,Cecchini M,Corradetti R,Pavone FS,Calamai M

    更新日期:2017-04-12 00:00:00

  • Low-carbohydrate diets differing in carbohydrate restriction improve cardiometabolic and anthropometric markers in healthy adults: A randomised clinical trial.

    abstract:Background:Low-carbohydrate, high-fat (LCHF) diets are useful for treating a range of health conditions, but there is little research evaluating the degree of carbohydrate restriction on outcome measures. This study compares anthropometric and cardiometabolic outcomes between differing carbohydrate-restricted diets. O...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.6273

    authors: Harvey CJDC,Schofield GM,Zinn C,Thornley SJ,Crofts C,Merien FLR

    更新日期:2019-02-05 00:00:00

  • Kelpie: generating full-length 'amplicons' from whole-metagenome datasets.

    abstract:Introduction:Whole-metagenome sequencing can be a rich source of information about the structure and function of entire metagenomic communities, but getting accurate and reliable results from these datasets can be challenging. Analysis of these datasets is founded on the mapping of sequencing reads onto known genomic r...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.6174

    authors: Greenfield P,Tran-Dinh N,Midgley D

    更新日期:2019-01-30 00:00:00

  • miR-27b attenuates apoptosis induced by transmissible gastroenteritis virus (TGEV) infection via targeting runt-related transcription factor 1 (RUNX1).

    abstract::Transmissible gastroenteritis virus (TGEV), belonging to the coronaviridae family, is the key cause of the fatal diarrhea of piglets and results in many pathological processes. microRNAs (miRNAs) play a key role in the regulation of virus-induced apoptosis. During the process of apoptosis induced by TGEV infection in ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.1635

    authors: Zhao X,Song X,Bai X,Fei N,Huang Y,Zhao Z,Du Q,Zhang H,Zhang L,Tong D

    更新日期:2016-02-04 00:00:00

  • The sugarcane mitochondrial genome: assembly, phylogenetics and transcriptomics.

    abstract:Background:Chloroplast genomes provide insufficient phylogenetic information to distinguish between closely related sugarcane cultivars, due to the recent origin of many cultivars and the conserved sequence of the chloroplast. In comparison, the mitochondrial genome of plants is much larger and more plastic and could c...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7558

    authors: Lloyd Evans D,Hlongwane TT,Joshi SV,Riaño Pachón DM

    更新日期:2019-09-24 00:00:00

  • Resistance strategies of Phragmites australis (common reed) to Pb pollution in flood and drought conditions.

    abstract::Resistance strategies of clonal organs, and parent and offspring shoots of Phragmites australis (common reed) to heavy metal pollution in soils are not well known. To clarify the tolerance or resistance strategies in reeds, we conducted a pot experiment with five levels of Pb concentration (0∼4,500 mg kg-1) in flood a...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.4188

    authors: Zhang N,Zhang J,Li Z,Chen J,Zhang Z,Mu C

    更新日期:2018-01-03 00:00:00

  • Anatomy, feeding ecology, and ontogeny of a transitional baleen whale: a new genus and species of Eomysticetidae (Mammalia: Cetacea) from the Oligocene of New Zealand.

    abstract::The Eocene history of cetacean evolution is now represented by the expansive fossil record of archaeocetes elucidating major morphofunctional shifts relating to the land to sea transition, but the change from archaeocetes to modern cetaceans is poorly established. New fossil material of the recently recognized family ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.1129

    authors: Boessenecker RW,Fordyce RE

    更新日期:2015-09-10 00:00:00

  • Digging the compromise: investigating the link between limb bone histology and fossoriality in the aardvark (Orycteropus afer).

    abstract::Bone microstructure has long been known as a powerful tool to investigate lifestyle-related biomechanical constraints, and many studies have focused on identifying such constraints in the limb bones of aquatic or arboreal mammals in recent years. The limb bone microstructure of fossorial mammals, however, has not been...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.5216

    authors: Legendre LJ,Botha-Brink J

    更新日期:2018-07-11 00:00:00

  • Identification of WRKY gene family and characterization of cold stress-responsive WRKY genes in eggplant.

    abstract:Background:WRKY proteins play a vital role in the plants response to different stresses, growth and development. Studies of WRKY proteins have been mainly focused on model plant Arabidopsis and a few other vegetable plants. However, the systematical study of eggplant WRKY transcription factor superfamily is scarce. Me...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.8777

    authors: Yang Y,Liu J,Zhou X,Liu S,Zhuang Y

    更新日期:2020-03-17 00:00:00

  • Integrating structure-from-motion photogrammetry with geospatial software as a novel technique for quantifying 3D ecological characteristics of coral reefs.

    abstract::The structural complexity of coral reefs plays a major role in the biodiversity, productivity, and overall functionality of reef ecosystems. Conventional metrics with 2-dimensional properties are inadequate for characterization of reef structural complexity. A 3-dimensional (3D) approach can better quantify topography...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.1077

    authors: Burns J,Delparte D,Gates RD,Takabayashi M

    更新日期:2015-07-07 00:00:00

  • Crossmodal congruency effect scores decrease with repeat test exposure.

    abstract::The incorporation of feedback into a person's body schema is well established. The crossmodal congruency task (CCT) is used to objectively quantify incorporation without being susceptible to experimenter biases. This visual-tactile interference task is used to calculate the crossmodal congruency effect (CCE) score as ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.6976

    authors: Blustein D,Gill S,Wilson A,Sensinger J

    更新日期:2019-05-22 00:00:00

  • An enigmatic decoupling between heat stress and coral bleaching on the Great Barrier Reef.

    abstract::Ocean warming threatens the functioning of coral reef ecosystems by inducing mass coral bleaching and mortality events. The link between temperature and coral bleaching is now well-established based on observations that mass bleaching events usually occur when seawater temperatures are anomalously high. However, times...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7473

    authors: DeCarlo TM,Harrison HB

    更新日期:2019-08-12 00:00:00

  • Transcriptome-wide identification and characterization of the Sox gene family and microsatellites for Corbicula fluminea.

    abstract::The Asian clam, Corbicula fluminea, is a commonly consumed small freshwater bivalve in East Asia. However, available genetic information of this clam is still limited. In this study, the transcriptome of female C. fluminea was sequenced using the Illumina HiSeq 2500 platform. A total of 89,563 unigenes were assembled ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7770

    authors: Zhu C,Zhang L,Ding H,Pan Z

    更新日期:2019-10-22 00:00:00

  • The effect of climate change on the distribution of a tropical zoanthid (Palythoa caribaeorum) and its ecological implications.

    abstract::Palythoa caribaeorum is a zoanthid often dominant in shallow rocky environments along the west coast of the Atlantic Ocean, from the tropics to the subtropics. This species has high environmental tolerance and is a good space competitor in reef environments. Considering current and future scenarios in the global clima...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.4777

    authors: Durante LM,Cruz ICS,Lotufo TMC

    更新日期:2018-05-17 00:00:00

  • Identification of key genes and pathways associated with cholangiocarcinoma development based on weighted gene correlation network analysis.

    abstract:Background:As the most frequently occurred tumor in biliary tract, cholangiocarcinoma (CCA) is mainly characterized by its late diagnosis and poor outcome. It is therefore urgent to identify specific genes and pathways associated with its progression and prognosis. Materials and Methods:The differentially expressed ge...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7968

    authors: Liu J,Liu W,Li H,Deng Q,Yang M,Li X,Liang Z

    更新日期:2019-10-31 00:00:00

  • Computer modelling reveals new conformers of the ATP binding loop of Na+/K+-ATPase involved in the transphosphorylation process of the sodium pump.

    abstract::Hydrolysis of ATP by Na+/K+-ATPase, a P-Type ATPase, catalyzing active Na+ and K+ transport through cellular membranes leads transiently to a phosphorylation of its catalytical α-subunit. Surprisingly, three-dimensional molecular structure analysis of P-type ATPases reveals that binding of ATP to the N-domain connecte...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.3087

    authors: Tejral G,Sopko B,Necas A,Schoner W,Amler E

    更新日期:2017-03-14 00:00:00

  • The concept of Watson's carative factors in nursing and their (dis)harmony with patient satisfaction.

    abstract:BACKGROUND:Constant reviews of the caring behavior of nurses and patient satisfaction help to improve the quality of nursing. The aim of our research was to explore relationships between the level of nursing education, the perception of nurses and nursing assistants of Watson's carative factors, and patient satisfactio...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.2940

    authors: Pajnkihar M,Štiglic G,Vrbnjak D

    更新日期:2017-02-07 00:00:00

  • Insight into plant cell wall degradation and pathogenesis of Ganoderma boninense via comparative genome analysis.

    abstract:Background:G. boninense is a hemibiotrophic fungus that infects oil palms (Elaeis guineensis Jacq.) causing basal stem rot (BSR) disease and consequent massive economic losses to the oil palm industry. The pathogenicity of this white-rot fungus has been associated with cell wall degrading enzymes (CWDEs) released durin...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.8065

    authors: Ramzi AB,Che Me ML,Ruslan US,Baharum SN,Nor Muhammad NA

    更新日期:2019-12-18 00:00:00

  • Alu elements in primates are preferentially lost from areas of high GC content.

    abstract::The currently-accepted dogma when analysing human Alu transposable elements is that 'young' Alu elements are found in low GC regions and 'old' Alus in high GC regions. The correlation between high GC regions and high gene frequency regions make this observation particularly difficult to explain. Although a number of s...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.78

    authors: Hellen EH,Brookfield JF

    更新日期:2013-05-21 00:00:00

  • Transcriptome analysis of immature xylem in the Chinese fir at different developmental phases.

    abstract::Background.Chinese fir [Cunninghamia lanceolata (Lamb.) Hook.] is one of the most important native tree species for timber production in southern China. An understanding of overall fast growing stage, stem growth stage and senescence stage cambium transcriptome variation is lacking. We used transcriptome sequencing to...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.2097

    authors: Zhang Y,Han X,Sang J,He X,Liu M,Qiao G,Zhuo R,He G,Hu J

    更新日期:2016-06-07 00:00:00

  • Connecting laboratory behavior to field function through stable isotope analysis.

    abstract::Inherent difficulties of tracking and observing organisms in the field often leave researchers with no choice but to conduct behavioral experiments under laboratory settings. However, results of laboratory experiments do not always translate accurately to natural conditions. A fundamental challenge in ecology is there...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.1918

    authors: Glon MG,Larson ER,Pangle KL

    更新日期:2016-04-11 00:00:00

  • Antioxidant activity and mechanism of commercial Rama Forte persimmon fruits (Diospyros kaki).

    abstract::This study aimed to characterize the antioxidant properties of Rama Forte persimmon, a tannin-rich fruit variety produced in Brazil. Extracts prepared with lyophilized pulps from fruits obtained in local markets were analyzed individually to evaluate the extent of antioxidant protection and investigate the antioxidant...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.5223

    authors: Dalvi LT,Moreira DC,Alonso A,de Avellar IGJ,Hermes-Lima M

    更新日期:2018-07-25 00:00:00

  • Genome-wide identification and characterization of heat shock protein family 70 provides insight into its divergent functions on immune response and development of Paralichthys olivaceus.

    abstract::Flatfish undergo extreme morphological development and settle to a benthic in the adult stage, and are likely to be more susceptible to environmental stress. Heat shock proteins 70 (hsp70) are involved in embryonic development and stress response in metazoan animals. However, the evolutionary history and functions of ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7781

    authors: Liu K,Hao X,Wang Q,Hou J,Lai X,Dong Z,Shao C

    更新日期:2019-11-11 00:00:00

  • Plasma antioxidants and oxidative stress status in obese women: correlation with cardiopulmonary response.

    abstract:Introduction:A high body fat coupled with low cardiopulmonary fitness and an increase in oxidative stress has been connoted as contributing factors in developing cardiovascular comorbidities. This study aimed to investigate the correlation between antioxidants and oxidative stress status with cardiopulmonary responses ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.9230

    authors: Adenan DM,Jaafar Z,Jayapalan JJ,Abdul Aziz A

    更新日期:2020-05-19 00:00:00

  • Plant density and life history traits of Aconitum spicatum in North-central Nepal: effects of elevation and anthropogenic disturbances.

    abstract::Increasing cross-border trade of medicinal and aromatic plants (MAPs) has put heavy pressure on a considerable number of species in the Himalayas. One of the threatened species in Nepal is Aconitum spicatum. Unfortunately for this species and for many others, our knowledge on population ecology and performance across ...

    journal_title:PeerJ

    pub_type: 杂志文章

    doi:10.7717/peerj.7574

    authors: Chapagain DJ,Meilby H,Ghimire SK

    更新日期:2019-09-10 00:00:00