Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers.

Abstract:

:High-quality and high-throughput prediction of enzyme commission (EC) numbers is essential for accurate understanding of enzyme functions, which have many implications in pathologies and industrial biotechnology. Several EC number prediction tools are currently available, but their prediction performance needs to be further improved to precisely and efficiently process an ever-increasing volume of protein sequence data. Here, we report DeepEC, a deep learning-based computational framework that predicts EC numbers for protein sequences with high precision and in a high-throughput manner. DeepEC takes a protein sequence as input and predicts EC numbers as output. DeepEC uses 3 convolutional neural networks (CNNs) as a major engine for the prediction of EC numbers, and also implements homology analysis for EC numbers that cannot be classified by the CNNs. Comparative analyses against 5 representative EC number prediction tools show that DeepEC allows the most precise prediction of EC numbers, and is the fastest and the lightest in terms of the disk space required. Furthermore, DeepEC is the most sensitive in detecting the effects of mutated domains/binding site residues of protein sequences. DeepEC can be used as an independent tool, and also as a third-party software component in combination with other computational platforms that examine metabolic reactions.

authors

Ryu JY,Kim HU,Lee SY

doi

10.1073/pnas.1821905116

subject

Has Abstract

pub_date

2019-07-09 00:00:00

pages

13996-14001

issue

28

eissn

0027-8424

issn

1091-6490

pii

1821905116

journal_volume

116

pub_type

杂志文章
  • Structure of spinach chloroplast F1-ATPase complexed with the phytopathogenic inhibitor tentoxin.

    abstract::Tentoxin, a natural cyclic tetrapeptide produced by phytopathogenic fungi from the Alternaria species affects the catalytic function of the chloroplast F(1)-ATPase in certain sensitive species of plants. In this study, we show that the uncompetitive inhibitor tentoxin binds to the alphabeta-interface of the chloroplas...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.052546099

    authors: Groth G

    更新日期:2002-03-19 00:00:00

  • Synthesis and bioassay of improved mosquito repellents predicted from chemical structure.

    abstract::Mosquito repellency data on acylpiperidines derived from the U.S. Department of Agriculture archives were modeled by using molecular descriptors calculated by CODESSA PRO software. An artificial neural network model was developed for the correlation of these archival results and used to predict the repellent activity ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0800571105

    authors: Katritzky AR,Wang Z,Slavov S,Tsikolia M,Dobchev D,Akhmedov NG,Hall CD,Bernier UR,Clark GG,Linthicum KJ

    更新日期:2008-05-27 00:00:00

  • Continuous attraction toward phonological competitors.

    abstract::Certain models of spoken-language processing, like those for many other perceptual and cognitive processes, posit continuous uptake of sensory input and dynamic competition between simultaneously active representations. Here, we provide compelling evidence for this continuity assumption by using a continuous response,...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0503903102

    authors: Spivey MJ,Grosjean M,Knoblich G

    更新日期:2005-07-19 00:00:00

  • Lesion-induced increase in nerve growth factor mRNA is mediated by c-fos.

    abstract::Lesion of the sciatic nerve caused a rapid increase in c-fos and c-jun mRNA that was followed about 2 hr later by an increase in nerve growth factor (NGF) mRNA. To evaluate whether the initial increase in c-fos mRNA is causally related to the subsequent increase in NGF mRNA, we performed experiments with fibroblasts o...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.87.10.3899

    authors: Hengerer B,Lindholm D,Heumann R,Rüther U,Wagner EF,Thoenen H

    更新日期:1990-05-01 00:00:00

  • Direct measurement of oligonucleotide substrate binding to wild-type and mutant ribozymes from Tetrahymena.

    abstract::Like protein enzymes, RNA enzymes (ribozymes) provide specific binding sites for their substrates. We now show that equilibrium dissociation constants for complexes between the Tetrahymena ribozyme and its RNA substrates and products can be directly measured by electrophoresis in polyacrylamide gels containing divalen...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.87.21.8187

    authors: Pyle AM,McSwiggen JA,Cech TR

    更新日期:1990-11-01 00:00:00

  • Detection and localization of virus-specific DNA by in situ hybridization of cells during infection and rapid transformation by the murine sarcoma-leukemia virus.

    abstract::Cytological preparations of interphase nuclei and chromosomes from mouse 3T6 cells prepared at various times after infection with the murine sarcomaleukemia virus complex were hybridized with the [(3)H]DNA product of the viral RNA-directed DNA polymerase. While uninfected nuclei had an average of 4 autoradiographic gr...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.71.9.3418

    authors: Loni MC,Green M

    更新日期:1974-09-01 00:00:00

  • RNA-directed DNA polymerase from human leukemic blood cells and from primate type-C virus-producing cells: high- and low-molecular-weight forms with variant biochemical and immunological properties.

    abstract::RNA-directed DNA polymerase (reverse transcriptase) from leukocytes of individual leukemic patients can be grouped by velocity gradient analyses into two distinct classes, a low-molecular-weight (LMW) class of approximately 70,000 and a high-molecular-weight (HMW) class of 130,000 to 140,000. The reverse transcriptase...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.72.3.1194

    authors: Mondal H,Gallagher RE,Gallo RC

    更新日期:1975-03-01 00:00:00

  • Expression and crystallization of the complex of HLA-DR2 (DRA, DRB1*1501) and an immunodominant peptide of human myelin basic protein.

    abstract::HLA-DR2 is associated with susceptibility to multiple sclerosis (MS). A peptide from human myelin basic protein (MBP, residues 85-99) was previously found to bind to purified HLA-DR2 (DRA, DRB1*1501) and to be recognized by human MBP-specific T cell clones. Soluble HLA-DR2 was expressed in the baculovirus system by re...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.95.20.11828

    authors: Gauthier L,Smith KJ,Pyrdol J,Kalandadze A,Strominger JL,Wiley DC,Wucherpfennig KW

    更新日期:1998-09-29 00:00:00

  • Quantitative effects of antihydrophobic agents on binding constants and solubilities in water.

    abstract::The effects of urea and of guanidinium chloride on binding constants in water for 6-(4-tert-butylanilino)-naphthalene-2-sulfonate and of bis(p-tert-butylphenyl) phosphate binding to beta-cyclodextrin and to N,N'-bis(6-beta-cyclo-dextrinyl)imidazolium ion have been determined. Their effects on the water solubility of p...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.89.15.6916

    authors: Breslow R,Halfon S

    更新日期:1992-08-01 00:00:00

  • Expression of the antiapoptotic baculovirus p35 gene in tomato blocks programmed cell death and provides broad-spectrum resistance to disease.

    abstract::The sphinganine analog mycotoxin, AAL-toxin, induces a death process in plant and animal cells that shows apoptotic morphology. In nature, the AAL-toxin is the primary determinant of the Alternaria stem canker disease of tomato, thus linking apoptosis to this disease caused by Alternaria alternata f. sp. lycopersici. ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.232579799

    authors: Lincoln JE,Richael C,Overduin B,Smith K,Bostock R,Gilchrist DG

    更新日期:2002-11-12 00:00:00

  • Inflammation induces dermal Vγ4+ γδT17 memory-like cells that travel to distant skin and accelerate secondary IL-17-driven responses.

    abstract::Gamma delta (γδ) T cells represent a major IL-17 committed T-cell population (γδT17 cells) in the mouse dermis. Following exposure to the inflammatory agent imiquimod (IMQ) the Vγ4(+) subset of γδT cells produce IL-17 in the skin and expand rapidly in draining lymph nodes (LNs). Local IMQ treatment in humans is known ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.1508990112

    authors: Ramírez-Valle F,Gray EE,Cyster JG

    更新日期:2015-06-30 00:00:00

  • Escherichia coli genes regulated by cell-to-cell signaling.

    abstract::Utilizing the bicistronic reporter transposon mini-Tn5 lacZ-tet/1, we have identified lacZ fusions to four Escherichia coli genes/operons that are strongly activated by the accumulation of self-produced extracellular signals. These fusions were designated cma9, cma48, cma113, and cma114 for conditioned medium activate...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.96.8.4610

    authors: Baca-DeLancey RR,South MM,Ding X,Rather PN

    更新日期:1999-04-13 00:00:00

  • Amyloidogenic light chains induce cardiomyocyte contractile dysfunction and apoptosis via a non-canonical p38alpha MAPK pathway.

    abstract::Patients with primary (AL) cardiac amyloidosis suffer from progressive cardiomyopathy with a median survival of less than 8 months and a 5-year survival of <10%. Contributing to this poor prognosis is the fact that these patients generally do not tolerate standard heart failure therapies. The molecular mechanisms unde...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0912263107

    authors: Shi J,Guan J,Jiang B,Brenner DA,Del Monte F,Ward JE,Connors LH,Sawyer DB,Semigran MJ,Macgillivray TE,Seldin DC,Falk R,Liao R

    更新日期:2010-03-02 00:00:00

  • The transforming activity of Wnt effectors correlates with their ability to induce the accumulation of mammary progenitor cells.

    abstract::Ectopic activation of the Wnt signaling pathway is highly oncogenic for many human tissues. Here, we show that ectopic Wnt signaling increases the effective stem cell activity in mouse mammary glands in vivo. Furthermore, Wnt effectors induce the accumulation of mouse mammary epithelial progenitors (assayed by Hoechst...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0400699101

    authors: Liu BY,McDermott SP,Khwaja SS,Alexander CM

    更新日期:2004-03-23 00:00:00

  • Reversed voltage-dependent gating of a bacterial sodium channel with proline substitutions in the S6 transmembrane segment.

    abstract::Members of the voltage-gated-like ion channel superfamily have a conserved pore structure. Transmembrane helices that line the pore (M2 or S6) are thought to gate it at the cytoplasmic end by bending at a hinge glycine residue. Proline residues favor bending of alpha-helices, and substitution of proline for this glyci...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0408270101

    authors: Zhao Y,Scheuer T,Catterall WA

    更新日期:2004-12-21 00:00:00

  • Localization of calmodulin in rat tissues.

    abstract::The localization of calmodulin, a calcium-dependent modulator of many enzymes, was studied in rat liver, skeletal muscle, and adrenal slices. Calmodulin is found in liver cytoplasm, nucleus, and plasma membrane. Much of the cytoplasmic calmodulin is associated with glycogen particles presumably bound to enzymes involv...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.77.1.366

    authors: Harper JF,Cheung WY,Wallace RW,Huang HL,Levine SN,Steiner AL

    更新日期:1980-01-01 00:00:00

  • Loss of O-GlcNAc glycosylation in forebrain excitatory neurons induces neurodegeneration.

    abstract::O-GlcNAc glycosylation (or O-GlcNAcylation) is a dynamic, inducible posttranslational modification found on proteins associated with neurodegenerative diseases such as α-synuclein, amyloid precursor protein, and tau. Deletion of the O-GlcNAc transferase (ogt) gene responsible for the modification causes early postnata...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.1606899113

    authors: Wang AC,Jensen EH,Rexach JE,Vinters HV,Hsieh-Wilson LC

    更新日期:2016-12-27 00:00:00

  • Rewiring the RNAs of influenza virus to prevent reassortment.

    abstract::Influenza viruses contain segmented, negative-strand RNA genomes. Genome segmentation facilitates reassortment between different influenza virus strains infecting the same cell. This phenomenon results in the rapid exchange of RNA segments. In this study, we have developed a method to prevent the free reassortment of ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0908897106

    authors: Gao Q,Palese P

    更新日期:2009-09-15 00:00:00

  • Inhibition of prostate carcinogenesis in TRAMP mice by oral infusion of green tea polyphenols.

    abstract::Development of effective chemopreventive agents against prostate cancer (CaP) for humans requires conclusive evidence of their efficacy in animal models that closely emulates human disease. The autochthonous transgenic adenocarcinoma of the mouse prostate (TRAMP) model, which spontaneously develops metastatic CaP, is ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.171326098

    authors: Gupta S,Hastak K,Ahmad N,Lewin JS,Mukhtar H

    更新日期:2001-08-28 00:00:00

  • Sterically stabilized liposomes: improvements in pharmacokinetics and antitumor therapeutic efficacy.

    abstract::The results obtained in this study establish that liposome formulations incorporating a synthetic polyethylene glycol-derivatized phospholipid have a pronounced effect on liposome tissue distribution and can produce a large increase in the pharmacological efficacy of encapsulated antitumor drugs. This effect is substa...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.88.24.11460

    authors: Papahadjopoulos D,Allen TM,Gabizon A,Mayhew E,Matthay K,Huang SK,Lee KD,Woodle MC,Lasic DD,Redemann C

    更新日期:1991-12-15 00:00:00

  • Forecast and control of epidemics in a globalized world.

    abstract::The rapid worldwide spread of severe acute respiratory syndrome demonstrated the potential threat an infectious disease poses in a closely interconnected and interdependent world. Here we introduce a probabilistic model that describes the worldwide spread of infectious diseases and demonstrate that a forecast of the g...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0308344101

    authors: Hufnagel L,Brockmann D,Geisel T

    更新日期:2004-10-19 00:00:00

  • Inferring epigenetic dynamics from kin correlations.

    abstract::Populations of isogenic embryonic stem cells or clonal bacteria often exhibit extensive phenotypic heterogeneity that arises from intrinsic stochastic dynamics of cells. The phenotypic state of a cell can be transmitted epigenetically in cell division, leading to correlations in the states of cells related by descent....

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.1504407112

    authors: Hormoz S,Desprat N,Shraiman BI

    更新日期:2015-05-05 00:00:00

  • Tropical birds have a slow pace of life.

    abstract::Tropical birds are relatively long-lived and produce few offspring, which develop slowly and mature relatively late in life, the slow end of the life-history axis, whereas temperate birds lie at the opposite end of this continuum. We tested the hypothesis that tropical birds have evolved a reduced basal metabolic rate...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0702212104

    authors: Wiersma P,Muñoz-Garcia A,Walker A,Williams JB

    更新日期:2007-05-29 00:00:00

  • Molecular genetic approach to human meningioma: loss of genes on chromosome 22.

    abstract::A molecular genetic approach employing polymorphic DNA markers has been used to investigate the role of chromosomal aberrations in meningioma, one of the most common tumors of the human nervous system. Comparison of the alleles detected by DNA markers in tumor DNA versus DNA from normal tissue revealed chromosomal alt...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.84.15.5419

    authors: Seizinger BR,de la Monte S,Atkins L,Gusella JF,Martuza RL

    更新日期:1987-08-01 00:00:00

  • Large-scale allosteric conformational transitions of adenylate kinase appear to involve a population-shift mechanism.

    abstract::Large-scale conformational changes in proteins are often associated with the binding of a substrate. Because conformational changes may be related to the function of an enzyme, understanding the kinetics and energetics of these motions is very important. We have delineated the atomically detailed conformational transi...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0706443104

    authors: Arora K,Brooks CL 3rd

    更新日期:2007-11-20 00:00:00

  • C-terminal truncation of the retinoblastoma gene product leads to functional inactivation.

    abstract::Mutational inactivation of the retinoblastoma (RB) gene has been implicated in the genesis of retinoblastoma, osteosarcoma, and other human tumors. Our strategy has been to characterize naturally occurring mutants from tumor cells to pinpoint potential domains of RB protein crucial for tumor suppression. We show here ...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.87.1.6

    authors: Shew JY,Lin BT,Chen PL,Tseng BY,Yang-Feng TL,Lee WH

    更新日期:1990-01-01 00:00:00

  • Low levels of linkage disequilibrium in wild barley (Hordeum vulgare ssp. spontaneum) despite high rates of self-fertilization.

    abstract::High levels of inbreeding cause populations to become composed of homozygous, inbred lines. High levels of homozygosity limit the effectiveness of recombination, and therefore, retard the rate of decay of linkage (gametic phase) disequilibrium (LD) among mutations. Inbreeding and recombination interact to shape the ex...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0409804102

    authors: Morrell PL,Toleno DM,Lundy KE,Clegg MT

    更新日期:2005-02-15 00:00:00

  • Use of a synthetic peptide antigen to generate antisera reactive with a proteolytic processing site in native human proinsulin: demonstration of cleavage within clathrin-coated (pro)secretory vesicles.

    abstract::Polyclonal antibodies reactive with a cleavage site in human proinsulin (HPI) (C-peptide-A-chain junction) have been raised (rabbit, guinea pig) using a synthetic peptide antigen coupled with keyhole limpet hemocyanin. These antisera recognize native HPI and des-31,32-HPI equally well but react 20-50 times less well w...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.84.17.6184

    authors: Steiner DF,Michael J,Houghten R,Mathieu M,Gardner PR,Ravazzola M,Orci L

    更新日期:1987-09-01 00:00:00

  • Metabolomics analysis reveals large effects of gut microflora on mammalian blood metabolites.

    abstract::Although it has long been recognized that the enteric community of bacteria that inhabit the human distal intestinal track broadly impacts human health, the biochemical details that underlie these effects remain largely undefined. Here, we report a broad MS-based metabolomics study that demonstrates a surprisingly lar...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.0812874106

    authors: Wikoff WR,Anfora AT,Liu J,Schultz PG,Lesley SA,Peters EC,Siuzdak G

    更新日期:2009-03-10 00:00:00

  • Combined molecular dynamics and neural network method for predicting protein antifreeze activity.

    abstract::Antifreeze proteins (AFPs) are a diverse class of proteins that depress the kinetically observable freezing point of water. AFPs have been of scientific interest for decades, but the lack of an accurate model for predicting AFP activity has hindered the logical design of novel antifreeze systems. To address this, we p...

    journal_title:Proceedings of the National Academy of Sciences of the United States of America

    pub_type: 杂志文章

    doi:10.1073/pnas.1814945115

    authors: Kozuch DJ,Stillinger FH,Debenedetti PG

    更新日期:2018-12-26 00:00:00