Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural network.

Vikas Upadhyay, Veda Sheersh Boorla, Costas D Maranas

July 2023 Metab Eng

Synopsis of Social media discussions

The overall tone reflects a positive perception of the article's significance, with phrases like 'revolutionary method' and 'game-changer' implying high interest and perceived impact. Technical references, such as enzyme reengineering and neural network models, demonstrate engagement and understanding of the subject, shaping a consensus that this work could advance bioengineering fields.

A
Agreement
 Moderate agreement

Most discussions acknowledge the relevance of the research, with some expressing strong support for its potential, indicating general agreement on its importance.

I
Interest
 High level of interest

The discussions show high curiosity and enthusiasm, highlighting excitement about innovative approaches like CNN in enzyme engineering.

E
Engagement
 Moderate level of engagement

Participants delve into technical aspects and implications, such as enzyme reengineering methods, reflecting moderate but meaningful engagement.

I
Impact
 Moderate level of impact

Multiple comments suggest the publication could significantly influence future research and practical applications, indicating perceived high impact.

Social Mentions

YouTube

2 Videos

Twitter

6 Posts

Blogs

2 Articles

Metrics

Video Views

126

Total Likes

23

Extended Reach

37,207

Social Features

10

Timeline: Posts about article

Top Social Media Posts

Posts referencing the article

AlphaSynthesis nouveauStoic 2.0 for Computational Biosynthesis Planning

AlphaSynthesis nouveauStoic 2.0 for Computational Biosynthesis Planning

Access novoStoic 2.0 to efficiently design bioconversion pathways considering enzyme transformations, pathway complexity, thermodynamics, and microbial chassis. The tool integrates known and putative steps for optimized pathway planning.

Molecule Maker Lab Institute

April 15, 2025

86 views

novoStoic 2.0: Advanced Platform for Retrobiosynthesis Pathway Design

novoStoic 2.0: Advanced Platform for Retrobiosynthesis Pathway Design

Access novoStoic 2.0 at httpsnovostoicplatformmoleculemakerorg. Watch the tutorial on computational biosynthesis planning to learn how this platform facilitates pathway design, enzyme selection, and thermodynamic assessment for innovative biochemical production routes.

Molecule Maker Lab Institute

May 6, 2025

41 views

  • 新Mmの憂鬱
    @miyatamitsuru (Twitter)

    AIの応用で酵素をもし自在に設計できるようになると、スマートセルも空想とばかり言えなくなる。 Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural network - PubMed、 https://t.co/WyRa1DwcNS
    view full post

    June 11, 2023

    8

  • David Vallenet
    @vallenet (Twitter)

    RT @bionet_papers: Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neur…
    view full post

    June 11, 2023

    1

  • BioNetPapers
    @bionet_papers (Twitter)

    Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural network https://t.co/4iClrm2bug
    view full post

    June 11, 2023

    1

  • Omar Arias-Gaguancela, PhD
    @omar_arias_g (Twitter)

    RT @and_protein: Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural…
    view full post

    June 11, 2023

    3

  • Shiva Shankar S
    @BioShankar (Twitter)

    RT @and_protein: Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural…
    view full post

    June 11, 2023

    3

  • Protein Engineering and Directed Evolution Papers
    @and_protein (Twitter)

    Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural network https://t.co/qLl9dpO3Cc
    view full post

    June 11, 2023

    8

    3

Abstract Synopsis

  • The text describes EnzRank, a convolutional neural network (CNN) model designed to rank existing enzymes based on their potential for successful reengineering to accept new substrates, which helps improve pathways for producing biofuels, bio-renewables, or bioactive molecules.
  • EnzRank is trained on data from the BRENDA database, using known enzyme-substrate pairs as positives and scrambled pairs as negatives, achieving approximately 80% accuracy in predicting suitable enzyme-substrate interactions.
  • A user-friendly web interface has been developed, allowing users to input substrate SMILES strings and enzyme sequences to easily predict enzyme activity, supporting pathway design and enzyme reengineering efforts for novel biochemical reactions.]