Bridging the gap between mechanistic biological models and machine learning surrogates.

Ioana M Gherman, Zahraa S Abdallah, Wei Pang, Thomas E Gorochowski, Claire S Grierson, Lucia Marucci

April 2023 PLoS Comput Biol

Synopsis of Social media discussions

The reviews and discussions reflect an overall positive reception, with language like 'bridging the gap' and 'congrats' indicating support and recognition of the publication's importance; the tone suggests that these models are seen as promising tools for future biological research and disease understanding.

A
Agreement
 Moderate agreement

Most discussions acknowledge the value and relevance of integrating mechanistic models with machine learning surrogates, as seen in supportive comments like 'big congrats' and mentions of the article's review of their applications.

I
Interest
 Moderate level of interest

The posts demonstrate moderate interest, highlighting advancements in biological modeling and potential applications in neurodegenerative diseases, indicating engagement with the subject matter.

E
Engagement
 Moderate level of engagement

Discussions show some depth, referencing specific concepts like the efficiency of ML surrogates and their role in understanding complex biological systems, suggesting active engagement.

I
Impact
 Moderate level of impact

Participants perceive positive implications, emphasizing the potential of these models to revolutionize biological research and medical applications, implying significant impact.

Social Mentions

YouTube

1 Videos

Twitter

15 Posts

Metrics

Video Views

21

Total Likes

49

Extended Reach

27,821

Social Features

16

Timeline: Posts about article

Top Social Media Posts

Posts referencing the article

Integrating Biological Mechanistic Models with Machine Learning Surrogates

Integrating Biological Mechanistic Models with Machine Learning Surrogates

Mechanistic models illustrate complex biological processes but pose computational challenges. This review explores how machine learning surrogates can efficiently approximate these models, enabling simulations on standard computers.

Social RTCL TV

July 23, 2023

21 views

  • qyliang
    @qyliang1 (Twitter)

    RT @O_Borkowski: Bridging the gap between mechanistic biological models and machine learning surrogates https://t.co/rAKKFKH3iT https://t.c…
    view full post

    June 14, 2023

    3

  • Brian Dean
    @bdean_ (Twitter)

    RT @O_Borkowski: Bridging the gap between mechanistic biological models and machine learning surrogates https://t.co/rAKKFKH3iT https://t.c…
    view full post

    June 13, 2023

    3

  • ☀️ ℝ
    @rravi (Twitter)

    RT @O_Borkowski: Bridging the gap between mechanistic biological models and machine learning surrogates https://t.co/rAKKFKH3iT https://t.c…
    view full post

    June 13, 2023

    3

  • Olivier Borkowski
    @O_Borkowski (Twitter)

    Bridging the gap between mechanistic biological models and machine learning surrogates https://t.co/rAKKFKH3iT https://t.co/JzgixYTPG7
    view full post

    June 13, 2023

    19

    3

  • L Brielmaier
    @BrielmaierL (Twitter)

    #PLOSCompBio: Bridging the gap between mechanistic biological models and machine learning surrogates https://t.co/LUifluwVya Software, AI, ML & GPT are coming to the neurodegenerative diseases. Who will lead?
    view full post

    May 1, 2023

  • Bristol BioDesign Institute
    @BrisBioDesign (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 24, 2023

    10

  • Domenico Bellomo
    @BellomoDomenico (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Claire G
    @PR0FG (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Pablo Carbonell
    @pablocarb (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Eric Velasco Yépez
    @EricAndreVY (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • CSSB Lab
    @cssb_lab (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Gonzalo Vidal
    @Gonza10V (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Irene Otero-Muras
    @Otero_Muras (Twitter)

    RT @chofski: Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surroga…
    view full post

    April 22, 2023

    10

  • Thomas Gorochowski
    @chofski (Twitter)

    Big congrats to @ioanagherman5 on her new review @PLOSCompBiol covering the complementary uses of mechanistic ⚙️ & #ML surrogate computer models for understanding and engineering biology
    view full post

    April 22, 2023

    30

    10

  • Preprints.org
    @Preprints_org (Twitter)

    Bridging the Gap between Mechanistic Biological Models and Machine Learning Surrogates https://t.co/HE7dYZswh4 #EngPreprints #PreprintsOrg
    view full post

    September 29, 2022

Abstract Synopsis

  • Mechanistic models have traditionally been used to illustrate complex biological processes, but their increasing complexity has raised computational challenges for simulations and real-time analysis.
  • Surrogate machine learning (ML) models can provide a more efficient approximation of these complex models, significantly reducing computational requirements once they are trained.
  • The paper reviews existing literature on ML surrogates, focusing on their design, training, and practical applications in biological modeling, suggesting their potential to enable complex biological system simulations on standard computer setups.