ProteInfer, deep neural networks for protein functional inference

  1. Theo Sanderson  Is a corresponding author
  2. Maxwell L Bileschi
  3. David Belanger
  4. Lucy J Colwell
  1. The Francis Crick Institute, United Kingdom
  2. Google AI, United States

Abstract

Predicting the function of a protein from its amino acid sequence is a long-standing challenge in bioinformatics. Traditional approaches use sequence alignment to compare a query sequence either to thousands of models of protein families or to large databases of individual protein sequences. Here we introduce ProteInfer, which instead employs deep convolutional neural networks to directly predict a variety of protein functions - EC numbers and GO terms - directly from an unaligned amino acid sequence. This approach provides precise predictions which complement alignment-based methods, and the computational efficiency of a single neural network permits novel and lightweight software interfaces, which we demonstrate with an in-browser graphical interface for protein function prediction in which all computation is performed on the user's personal computer with no data uploaded to remote servers. Moreover, these models place full-length amino acid sequences into a generalised functional space, facilitating downstream analysis and interpretation. To read the interactive version of this paper, please visit https://google-research.github.io/proteinfer/.

Data availability

Source code is available on GitHub from https://github.com/google-research/proteinfer. Processed TensorFlow files are available from the indicated URLs. Raw training data is from UniProt.

The following previously published data sets were used

Article and author information

Author details

  1. Theo Sanderson

    The Francis Crick Institute, London, United Kingdom
    For correspondence
    theo.sanderson@crick.ac.uk
    Competing interests
    Theo Sanderson, performed research as part of their employment at Google LLC. Google is a technology company that sells machine learning services as part of its business. Portions of this work are covered by US patent WO2020210591A1, filed by Google..
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-4177-2851
  2. Maxwell L Bileschi

    Google AI, Boston, United States
    Competing interests
    Maxwell L Bileschi, performed research as part of their employment at Google LLC. Google is a technology company that sells machine learning services as part of its business. Portions of this work are covered by US patent WO2020210591A1, filed by Google..
  3. David Belanger

    Google AI, Boston, United States
    Competing interests
    David Belanger, performed research as part of their employment at Google LLC. Google is a technology company that sells machine learning services as part of its business. Portions of this work are covered by US patent WO2020210591A1, filed by Google..
  4. Lucy J Colwell

    Google AI, Boston, United States
    Competing interests
    Lucy J Colwell, performed research as part of their employment at Google LLC. Google is a technology company that sells machine learning services as part of its business. Portions of this work are covered by US patent WO2020210591A1, filed by Google..

Funding

Google

  • Theo Sanderson
  • Maxwell L Bileschi
  • David Belanger
  • Lucy J Colwell

The authors were employed by the funder while completing this work.

Copyright

© 2023, Sanderson et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 8,427
    views
  • 1,013
    downloads
  • 70
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Theo Sanderson
  2. Maxwell L Bileschi
  3. David Belanger
  4. Lucy J Colwell
(2023)
ProteInfer, deep neural networks for protein functional inference
eLife 12:e80942.
https://doi.org/10.7554/eLife.80942

Share this article

https://doi.org/10.7554/eLife.80942

Further reading

    1. Computational and Systems Biology
    Dylan C Sarver, Muzna Saqib ... G William Wong
    Research Article

    Organ function declines with age, and large-scale transcriptomic analyses have highlighted differential aging trajectories across tissues. The mechanism underlying shared and organ-selective functional changes across the lifespan, however, still remains poorly understood. Given the central role of mitochondria in powering cellular processes needed to maintain tissue health, we therefore undertook a systematic assessment of respiratory activity across 33 different tissues in young (2.5 months) and old (20 months) mice of both sexes. Our high-resolution mitochondrial respiration atlas reveals: (1) within any group of mice, mitochondrial activity varies widely across tissues, with the highest values consistently seen in heart, brown fat, and kidney; (2) biological sex is a significant but minor contributor to mitochondrial respiration, and its contributions are tissue-specific, with major differences seen in the pancreas, stomach, and white adipose tissue; (3) age is a dominant factor affecting mitochondrial activity, especially across most brain regions, different fat depots, skeletal muscle groups, eyes, and different regions of the gastrointestinal tract; (4) age effects can be sex- and tissue-specific, with some of the largest effects seen in pancreas, heart, adipose tissue, and skeletal muscle; and (5) while aging alters the functional trajectories of mitochondria in a majority of tissues, some are remarkably resilient to age-induced changes. Altogether, our data provide the most comprehensive compendium of mitochondrial respiration and illuminate functional signatures of aging across diverse tissues and organ systems.

    1. Computational and Systems Biology
    Rob Bierman, Jui M Dave ... Julia Salzman
    Research Article

    Targeted low-throughput studies have previously identified subcellular RNA localization as necessary for cellular functions including polarization, and translocation. Furthermore, these studies link localization to RNA isoform expression, especially 3’ Untranslated Region (UTR) regulation. The recent introduction of genome-wide spatial transcriptomics techniques enables the potential to test if subcellular localization is regulated in situ pervasively. In order to do this, robust statistical measures of subcellular localization and alternative poly-adenylation (APA) at single-cell resolution are needed. Developing a new statistical framework called SPRAWL, we detect extensive cell-type specific subcellular RNA localization regulation in the mouse brain and to a lesser extent mouse liver. We integrated SPRAWL with a new approach to measure cell-type specific regulation of alternative 3’ UTR processing and detected examples of significant correlations between 3’ UTR length and subcellular localization. Included examples, Timp3, Slc32a1, Cxcl14, and Nxph1 have subcellular localization in the mouse brain highly correlated with regulated 3’ UTR processing that includes the use of unannotated, but highly conserved, 3’ ends. Together, SPRAWL provides a statistical framework to integrate multi-omic single-cell resolved measurements of gene-isoform pairs to prioritize an otherwise impossibly large list of candidate functional 3’ UTRs for functional prediction and study. In these studies of data from mice, SPRAWL predicts that 3’ UTR regulation of subcellular localization may be more pervasive than currently known.