63
views
0
recommends
+1 Recommend
0
shares
    • Review: found
    Is Open Access

    Review of 'Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives'

    EDITOR
    Bookmark
    5
    Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectivesCrossref
    Average rating:
        Rated 4.5 of 5.
    Level of importance:
        Rated 4 of 5.
    Level of validity:
        Rated 4 of 5.
    Level of completeness:
        Rated 5 of 5.
    Level of comprehensibility:
        Rated 5 of 5.
    Competing interests:
    None

    Reviewed article

    • Record: found
    • Abstract: found
    • Article: found
    Is Open Access

    Machine Learning and Artificial Intelligence in drug repurposing – challenges and perspectives

    Artificial Intelligence (AI) and Machine Learning (ML) techniques play an increasingly crucial role in the field of drug repurposing.As the number of computational tools grows, it is essential to not only understand and carefully select the method itself, but also consider the input data used for building predictive models. This review aims to take a dive into current computational methods that leverage AI and ML to drive and accelerate compound and drug target selection, in addition to address the existing challenges and provide perspectives.While there is no doubt that AI and ML-based tools are transforming traditional approaches, especially with recent advancements in graph-based methods, they present novel challenges that require the human eye and expert intervention. The growing complexity of OMICs data further emphasizes the importance of data standardization and quality.
      Bookmark

      Review information

      10.14293/S2199-1006.1.SOR-COMPSCI.AI2CCP.v1.RKISZH
      This work has been published open access under Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Conditions, terms of use and publishing policy can be found at www.scienceopen.com.

      Bioinformatics & Computational biology,Artificial intelligence,Pharmacology & Pharmaceutical medicine
      artificial intelligence,drug repurposing,machine learning,neural networks

      Review text

      This review covers the field of computationa repurposing from several perspectives, which make it particularly useful for people new to the field, and also for having a quite comprehensive and updated references section available in one article.

      The details of each methodology cannot be explianed in this review, but the examples and figures provided in some of the paragraphs help in that direction.

      A few typos that I found through the document are summarized / proposed changes below:

      . AI-based tools leveraging deep learning and neural networks are particularly promising to, for instance, screen compounds, predict new drug-target combinations, and assess adverse, which can ultimately speed up the selection of existing targets and drugs for new applications [15] [16] [17].

      Should it be adverse drug reactions?

      ---------------------------

      s. It stands to potentially save millions of dollars in the costs associated with running clinical trials by predicting the likelihood of drug approval for specific indications in advance.

      I would change it to:

      s. It stands to potentially reduce significantly the costs associated with running clinical trials, by predicting the likelihood of drug approval for specific indications in advance, so that clinical trial priorities could be established.

      -------

      The hope is that deep learning strategies will learn latent data structures

      Should it be?:

      The hope is that deep learning strategies will learn from latent data structures

      ---------------

      the move from repositioning molecules to positioning using these methods and they are now being used across the industrial and academic settings.

      Should be:

      the move from repositioning molecules to positioning using these methods is now more often used across the industrial and academic settings.

      --------------------------

      has highlighted the direct gene to protein relationship

      should be:

      has highlighted that the direct gene to protein relationship

      -----------------------

      cell machinery. Ranging

      should be:

      cell machinery, ranging

      -----------------

      RWD allows to real-time assessment

      Should be:

      RWD allows for real-time assessment

      ----------------------

      setting up standardized method

      should be:

      setting up standardized methods

      --------------------

      Comments

      Thank you for reviewing the preprint!

      We agree with the comments expect for the following one:

      "The hope is that deep learning strategies will learn latent data structures" should remain as is, as the models are supposed to learn the latent structure of the data. (M.List, J.Bernett)


       

       

      2024-05-24 05:26 UTC
      +1

      Comment on this review