Unified rational protein engineering with sequence-based deep representation learning.

Abstract:

:Rational protein engineering requires a holistic understanding of protein function. Here, we apply deep learning to unlabeled amino-acid sequences to distill the fundamental features of a protein into a statistical representation that is semantically rich and structurally, evolutionarily and biophysically grounded. We show that the simplest models built on top of this unified representation (UniRep) are broadly applicable and generalize to unseen regions of sequence space. Our data-driven approach predicts the stability of natural and de novo designed proteins, and the quantitative function of molecularly diverse mutants, competitively with the state-of-the-art methods. UniRep further enables two orders of magnitude efficiency improvement in a protein engineering task. UniRep is a versatile summary of fundamental protein features that can be applied across protein engineering informatics.

journal_name

Nat Methods

journal_title

Nature methods

authors

Alley EC,Khimulya G,Biswas S,AlQuraishi M,Church GM

doi

10.1038/s41592-019-0598-1

subject

Has Abstract

pub_date

2019-12-01 00:00:00

pages

1315-1322

issue

12

eissn

1548-7091

issn

1548-7105

pii

10.1038/s41592-019-0598-1

journal_volume

16

pub_type

杂志文章
  • Optimized ratiometric calcium sensors for functional in vivo imaging of neurons and T lymphocytes.

    abstract::The quality of genetically encoded calcium indicators (GECIs) has improved dramatically in recent years, but high-performing ratiometric indicators are still rare. Here we describe a series of fluorescence resonance energy transfer (FRET)-based calcium biosensors with a reduced number of calcium binding sites per sens...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2773

    authors: Thestrup T,Litzlbauer J,Bartholomäus I,Mues M,Russo L,Dana H,Kovalchuk Y,Liang Y,Kalamakis G,Laukat Y,Becker S,Witte G,Geiger A,Allen T,Rome LC,Chen TW,Kim DS,Garaschuk O,Griesinger C,Griesbeck O

    更新日期:2014-02-01 00:00:00

  • Fluorogenic DNA sequencing in PDMS microreactors.

    abstract::We developed a multiplex sequencing-by-synthesis method combining terminal phosphate-labeled fluorogenic nucleotides (TPLFNs) and resealable polydimethylsiloxane (PDMS) microreactors. In the presence of phosphatase, primer extension by DNA polymerase using nonfluorescent TPLFNs generates fluorophores, which are confin...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1629

    authors: Sims PA,Greenleaf WJ,Duan H,Xie XS

    更新日期:2011-06-12 00:00:00

  • Genetic incorporation of unnatural amino acids into proteins in mammalian cells.

    abstract::We developed a general approach that allows unnatural amino acids with diverse physicochemical and biological properties to be genetically encoded in mammalian cells. A mutant Escherichia coli aminoacyl-tRNA synthetase (aaRS) is first evolved in yeast to selectively aminoacylate its tRNA with the unnatural amino acid ...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth1016

    authors: Liu W,Brock A,Chen S,Chen S,Schultz PG

    更新日期:2007-03-01 00:00:00

  • Marker-independent identification of glioma-initiating cells.

    abstract::Tumor-initiating cells with stem cell properties are believed to sustain the growth of gliomas, but proposed markers such as CD133 cannot be used to identify these cells with sufficient specificity. We report an alternative isolation method purely based on phenotypic qualities of glioma-initiating cells (GICs), avoidi...

    journal_title:Nature methods

    pub_type: 杂志文章,收录出版

    doi:10.1038/nmeth.1430

    authors: Clément V,Marino D,Cudalbu C,Hamou MF,Mlynarik V,de Tribolet N,Dietrich PY,Gruetter R,Hegi ME,Radovanovic I

    更新日期:2010-03-01 00:00:00

  • Single-cell genomics.

    abstract::Methods for genomic analysis at single-cell resolution enable new understanding of complex biological phenomena. Single-cell techniques, ranging from flow cytometry and microfluidics to PCR and sequencing, are used to understand the cellular composition of complex tissues, find new microbial species and perform genome...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth0411-311

    authors: Kalisky T,Quake SR

    更新日期:2011-04-01 00:00:00

  • Automated identification of functional dynamic contact networks from X-ray crystallography.

    abstract::Protein function often depends on the exchange between conformational substates. Allosteric ligand binding or distal mutations can stabilize specific active-site conformations and consequently alter protein function. Observing alternative conformations at low levels of electron density, in addition to comparison of in...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2592

    authors: van den Bedem H,Bhabha G,Yang K,Wright PE,Fraser JS

    更新日期:2013-09-01 00:00:00

  • mRNA-Seq whole-transcriptome analysis of a single cell.

    abstract::Next-generation sequencing technology is a powerful tool for transcriptome analysis. However, under certain conditions, only a small amount of material is available, which requires more sensitive techniques that can preferably be used at the single-cell level. Here we describe a single-cell digital gene expression pro...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1315

    authors: Tang F,Barbacioru C,Wang Y,Nordman E,Lee C,Xu N,Wang X,Bodeau J,Tuch BB,Siddiqui A,Lao K,Surani MA

    更新日期:2009-05-01 00:00:00

  • Protein-RNA networks revealed through covalent RNA marks.

    abstract::Protein-RNA networks are ubiquitous and central in biological control. We present an approach termed RNA Tagging that enables the user to identify protein-RNA interactions in vivo by analyzing purified cellular RNA, without protein purification or cross-linking. An RNA-binding protein of interest is fused to an enzyme...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.3651

    authors: Lapointe CP,Wilinski D,Saunders HA,Wickens M

    更新日期:2015-12-01 00:00:00

  • Conditional genome engineering in Toxoplasma gondii uncovers alternative invasion mechanisms.

    abstract::We established a conditional site-specific recombination system based on dimerizable Cre recombinase-mediated recombination in the apicomplexan parasite Toxoplasma gondii. Using a new single-vector strategy that allows ligand-dependent, efficient removal of a gene of interest, we generated three knockouts of apicomple...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2301

    authors: Andenmatten N,Egarter S,Jackson AJ,Jullien N,Herman JP,Meissner M

    更新日期:2013-02-01 00:00:00

  • Conformal nanopatterning of extracellular matrix proteins onto topographically complex surfaces.

    abstract::Our Patterning on Topography (PoT) printing technique enables fibronectin, laminin and other proteins to be applied to biomaterial surfaces in complex geometries that are inaccessible using traditional soft lithography techniques. Engineering combinatorial surfaces that integrate topographical and biochemical micropat...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.3210

    authors: Sun Y,Jallerat Q,Szymanski JM,Feinberg AW

    更新日期:2015-02-01 00:00:00

  • Mass spectrometry-based functional proteomics: from molecular machines to protein networks.

    abstract::The study of protein-protein interactions by mass spectrometry is an increasingly important part of post-genomics strategies to understand protein function. A variety of mass spectrometry-based approaches allow characterization of cellular protein assemblies under near-physiological conditions and subsequent assignmen...

    journal_title:Nature methods

    pub_type: 杂志文章,评审

    doi:10.1038/nmeth1093

    authors: Köcher T,Superti-Furga G

    更新日期:2007-10-01 00:00:00

  • In vivo three-photon imaging of activity of GCaMP6-labeled neurons deep in intact mouse brain.

    abstract::High-resolution optical imaging is critical to understanding brain function. We demonstrate that three-photon microscopy at 1,300-nm excitation enables functional imaging of GCaMP6s-labeled neurons beyond the depth limit of two-photon microscopy. We record spontaneous activity from up to 150 neurons in the hippocampal...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.4183

    authors: Ouzounov DG,Wang T,Wang M,Feng DD,Horton NG,Cruz-Hernández JC,Cheng YT,Reimer J,Tolias AS,Nishimura N,Xu C

    更新日期:2017-04-01 00:00:00

  • Quantitative analysis of gene expression in a single cell by qPCR.

    abstract::We developed a quantitative PCR method featuring a reusable single-cell cDNA library immobilized on beads for measuring the expression of multiple genes in a single cell. We used this method to analyze multiple cDNA targets (from several copies to several hundred thousand copies) with an experimental error of 15.9% or...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1338

    authors: Taniguchi K,Kajiyama T,Kambara H

    更新日期:2009-07-01 00:00:00

  • Imputing gene expression from selectively reduced probe sets.

    abstract::Measuring complete gene expression profiles for a large number of experiments is costly. We propose an approach in which a small subset of probes is selected based on a preliminary set of full expression profiles. In subsequent experiments, only the subset is measured, and the missing values are inputed. We developed ...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2207

    authors: Donner Y,Feng T,Benoist C,Koller D

    更新日期:2012-11-01 00:00:00

  • A versatile tool for conditional gene expression and knockdown.

    abstract::Drug-inducible systems allowing the control of gene expression in mammalian cells are invaluable tools for genetic research, and could also fulfill essential roles in gene- and cell-based therapy. Currently available systems, however, often have limited in vivo functionality because of leakiness, insufficient levels o...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth846

    authors: Szulc J,Wiznerowicz M,Sauvain MO,Trono D,Aebischer P

    更新日期:2006-02-01 00:00:00

  • Nanoscale imaging of RNA with expansion microscopy.

    abstract::The ability to image RNA identity and location with nanoscale precision in intact tissues is of great interest for defining cell types and states in normal and pathological biological settings. Here, we present a strategy for expansion microscopy of RNA. We developed a small-molecule linker that enables RNA to be cova...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.3899

    authors: Chen F,Wassie AT,Cote AJ,Sinha A,Alon S,Asano S,Daugharthy ER,Chang JB,Marblestone A,Church GM,Raj A,Boyden ES

    更新日期:2016-08-01 00:00:00

  • A photoprotection strategy for microsecond-resolution single-molecule fluorescence spectroscopy.

    abstract::Time resolution of current single-molecule fluorescence techniques is limited to milliseconds because of dye blinking and bleaching. Here we introduce a photoprotection strategy that affords microsecond resolution by combining efficient triplet quenching by oxygen and Trolox with minimized bleaching via the oxygen rad...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1553

    authors: Campos LA,Liu J,Wang X,Ramanathan R,English DS,Muñoz V

    更新日期:2011-02-01 00:00:00

  • Universal light-sheet generation with field synthesis.

    abstract::We introduce field synthesis, a theorem and method that can be used to synthesize any scanned or dithered light sheet, including those used in lattice light-sheet microscopy (LLSM), from an incoherent superposition of one-dimensional intensity distributions. Compared to LLSM, this user-friendly and modular approach of...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/s41592-019-0327-9

    authors: Chang BJ,Kittisopikul M,Dean KM,Roudot P,Welf ES,Fiolka R

    更新日期:2019-03-01 00:00:00

  • Channelrhodopsin-2 and optical control of excitable cells.

    abstract::Electrically excitable cells are important in the normal functioning and in the pathophysiology of many biological processes. These cells are typically embedded in dense, heterogeneous tissues, rendering them difficult to target selectively with conventional electrical stimulation methods. The algal protein Channelrho...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth936

    authors: Zhang F,Wang LP,Boyden ES,Deisseroth K

    更新日期:2006-10-01 00:00:00

  • Annotating the unannotated.

    abstract::By combining activity-based proteomics and metabolomics, researchers have developed a new systems biology strategy for characterizing enzymes in the context of metabolic networks. ...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth0107-8b

    authors: Doerr A

    更新日期:2007-01-01 00:00:00

  • Dynamic characterization of growth and gene expression using high-throughput automated flow cytometry.

    abstract::Cells adjust to changes in environmental conditions using complex regulatory programs. These cellular programs are the result of an intricate interplay between gene expression, cellular growth and protein degradation. Technologies that enable simultaneous and time-resolved measurements of these variables are necessary...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2879

    authors: Zuleta IA,Aranda-Díaz A,Li H,El-Samad H

    更新日期:2014-04-01 00:00:00

  • In vivo cell-cycle profiling in xenograft tumors by quantitative intravital microscopy.

    abstract::Quantification of cell-cycle state at a single-cell level is essential to understand fundamental three-dimensional (3D) biological processes such as tissue development and cancer. Analysis of 3D in vivo images, however, is very challenging. Today's best practice, manual annotation of select image events, generates arb...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.3363

    authors: Chittajallu DR,Florian S,Kohler RH,Iwamoto Y,Orth JD,Weissleder R,Danuser G,Mitchison TJ

    更新日期:2015-06-01 00:00:00

  • CRISPR off-target analysis in genetically engineered rats and mice.

    abstract::Despite widespread use of CRISPR, comprehensive data on the frequency and impact of Cas9-mediated off-targets in modified rodents are limited. Here we present deep-sequencing data from 81 genome-editing projects on mouse and rat genomes at 1,423 predicted off-target sites, 32 of which were confirmed, and show that hig...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/s41592-018-0011-5

    authors: Anderson KR,Haeussler M,Watanabe C,Janakiraman V,Lund J,Modrusan Z,Stinson J,Bei Q,Buechler A,Yu C,Thamminana SR,Tam L,Sowick MA,Alcantar T,O'Neil N,Li J,Ta L,Lima L,Roose-Girma M,Rairdan X,Durinck S,Warming S

    更新日期:2018-07-01 00:00:00

  • Localization-based super-resolution imaging meets high-content screening.

    abstract::Single-molecule localization microscopy techniques have proven to be essential tools for quantitatively monitoring biological processes at unprecedented spatial resolution. However, these techniques are very low throughput and are not yet compatible with fully automated, multiparametric cellular assays. This shortcomi...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.4486

    authors: Beghin A,Kechkar A,Butler C,Levet F,Cabillic M,Rossier O,Giannone G,Galland R,Choquet D,Sibarita JB

    更新日期:2017-12-01 00:00:00

  • High-resolution mass spectrometry of small molecules bound to membrane proteins.

    abstract::Small molecules are known to stabilize membrane proteins and to modulate their function and oligomeric state, but such interactions are often hard to precisely define. Here we develop and apply a high-resolution, Orbitrap mass spectrometry-based method for analyzing intact membrane protein-ligand complexes. Using this...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.3771

    authors: Gault J,Donlan JA,Liko I,Hopper JT,Gupta K,Housden NG,Struwe WB,Marty MT,Mize T,Bechara C,Zhu Y,Wu B,Kleanthous C,Belov M,Damoc E,Makarov A,Robinson CV

    更新日期:2016-04-01 00:00:00

  • CLARITY for mapping the nervous system.

    abstract::With potential relevance for brain-mapping work, hydrogel-based structures can now be built from within biological tissue to allow subsequent removal of lipids without mechanical disassembly of the tissue. This process creates a tissue-hydrogel hybrid that is physically stable, that preserves fine structure, proteins ...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2481

    authors: Chung K,Deisseroth K

    更新日期:2013-06-01 00:00:00

  • Two-color, two-photon uncaging of glutamate and GABA.

    abstract::We developed a caged GABA (gamma-aminobutyric acid), which, when combined with an appropriate caged glutamate, allows bimodal control of neuronal membrane potential with subcellular resolution using optically independent two-photon uncaging of each neurotransmitter. We used two-color, two-photon uncaging to fire and b...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1413

    authors: Kantevari S,Matsuzaki M,Kanemoto Y,Kasai H,Ellis-Davies GC

    更新日期:2010-02-01 00:00:00

  • Fast, high-contrast imaging of animal development with scanned light sheet-based structured-illumination microscopy.

    abstract::Recording light-microscopy images of large, nontransparent specimens, such as developing multicellular organisms, is complicated by decreased contrast resulting from light scattering. Early zebrafish development can be captured by standard light-sheet microscopy, but new imaging strategies are required to obtain high-...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.1476

    authors: Keller PJ,Schmidt AD,Santella A,Khairy K,Bao Z,Wittbrodt J,Stelzer EH

    更新日期:2010-08-01 00:00:00

  • Terminal exon characterization with TECtool reveals an abundance of cell-specific isoforms.

    abstract::Sequencing of RNA 3' ends has uncovered numerous sites that do not correspond to the termination sites of known transcripts. Through their 3' untranslated regions, protein-coding RNAs interact with RNA-binding proteins and microRNAs, which regulate many properties, including RNA stability and subcellular localization....

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/s41592-018-0114-z

    authors: Gruber AJ,Gypas F,Riba A,Schmidt R,Zavolan M

    更新日期:2018-10-01 00:00:00

  • pLogo: a probabilistic approach to visualizing sequence motifs.

    abstract::Methods for visualizing protein or nucleic acid motifs have traditionally relied upon residue frequencies to graphically scale character heights. We describe the pLogo, a motif visualization in which residue heights are scaled relative to their statistical significance. A pLogo generation tool is publicly available at...

    journal_title:Nature methods

    pub_type: 杂志文章

    doi:10.1038/nmeth.2646

    authors: O'Shea JP,Chou MF,Quader SA,Ryan JK,Church GM,Schwartz D

    更新日期:2013-12-01 00:00:00