Elsevier

Drug Discovery Today

Volume 24, Issue 3, March 2019, Pages 773-780
Drug Discovery Today

Review
Informatics
Artificial intelligence in drug development: present status and future prospects

https://doi.org/10.1016/j.drudis.2018.11.014Get rights and content

Highlights

  • Advances in artificial intelligence (AI) are modernising several aspects of our lives.

  • The pharma industry is facing challenges to overcome the high attrition rates in drug development.

  • The pharma industry is collaborating with AI industries to overcome challenges.

  • AI will improve the efficiency of the drug development process.

Artificial intelligence (AI) uses personified knowledge and learns from the solutions it produces to address not only specific but also complex problems. Remarkable improvements in computational power coupled with advancements in AI technology could be utilised to revolutionise the drug development process. At present, the pharmaceutical industry is facing challenges in sustaining their drug development programmes because of increased R&D costs and reduced efficiency. In this review, we discuss the major causes of attrition rates in new drug approvals, the possible ways that AI can improve the efficiency of the drug development process and collaboration of pharmaceutical industry giants with AI-powered drug discovery firms.

Introduction

Artificial intelligence (AI) is the simulation of the human intelligence process by computers. The process includes acquiring information, developing rules for using the information, drawing approximate or definite conclusions and self-correction. The advancement of AI can be seen as a double-edged sword: many fear that it will threaten their employment; by contrast, every advance in AI is celebrated because of the belief that it will vastly contribute to the betterment of society. AI is used in various sectors from innovating educational methods to automating business processes. The sprouting idea of adopting AI in the drug development process has shifted from hype to hope. In this review, the possible applications of AI in the drug development pipeline in drug development strategies and processes, the pharmaceutical R&D efficiency and attrition, and partnerships between AI and pharmaceutical companies are discussed.

Section snippets

AI, machine learning and deep learning

The incorporation of AI into the healthcare industry is concisely shown in Fig. 1. AI is described as the use of techniques that enable computers to mimic human behaviour (Fig. 1). AI also contains a subfield called machine learning (ML), which uses statistical methods with the ability to learn with or without being explicitly programmed 1, 2, 3. ML is categorised into supervised, unsupervised and reinforcement learning. Supervised learning comprises classification and regression methods where

Drug development process

The feedback-driven drug development process starts from existing results obtained from various sources such as high-throughput compound and fragment screening, computational modelling and information available in the literature. This process alternates between induction and deduction. This inductive–deductive cycle eventually leads to optimised hit and lead compounds. Automation of specific parts of the cycle reduces randomness and errors and improves the efficiency of drug development. De novo

Applications of AI in drug development

The tasks of finding successful new drugs is daunting and predominantly the most difficult part of drug development. This is caused by the vast size of what is known as chemical space, which is estimated to be in the order of 1060 molecules [27]. The technologies that incorporate AI have become versatile tools that can be applied ubiquitously in various stages of drug development, such as identification and validation of drug targets, designing of new drugs, drug repurposing, improving the R&D

Partnerships between the pharma industry and AI companies

With the rapid introduction of AI in healthcare, especially in the years 2016 and 2017, numerous pharmaceutical companies have made investments in and have joint ventures with AI companies in the hopes of developing better healthcare tools. These include the improvements in diagnostics or biomarkers and the identification of drug targets and designing new drugs [66]. The transition from general medicine to modern AI healthcare focuses on the basis of the data [67]. The analyses of these

Concluding remarks

Currently, there are no developed drugs that have utilised AI approaches but, based on the advances described in this review, it is likely that it will take a further 2–3 years for a drug to be developed. Interestingly, experts strongly believe that AI will permanently change the pharmaceutical industry and the way drugs are discovered. However, for an individual to be efficient in drug development using AI, the individual should know how to train algorithms, requiring domain expertise. This

Conflicts of interest

There are no funding sources to declare for the writing of this manuscript. Both authors contributed to the drafting, analysis, editing and submission of the manuscript.

Acknowledgements

The authors thank the International Medical University for the library facilities.

References (72)

  • T. VoPham

    Emerging trends in geospatial artificial intelligence (geoAI): potential applications for environmental epidemiology

    Environ. Health

    (2018)
  • J.-G. Lee

    Deep learning in medical imaging: general overview

    Korean J. Radiol.

    (2017)
  • G. Gunčar

    An application of machine learning to haematological diagnosis

    Sci. Rep.

    (2018)
  • H. Koohy

    The rise and fall of machine learning methods in biomedical research

    F1000 Res.

    (2017)
  • J.D. Young

    Unsupervised deep learning reveals prognostically relevant subtypes of glioblastoma

    BMC Bioinf.

    (2017)
  • B.T. Grys

    Machine learning and computer vision approaches for phenotypic profiling

    J. Cell Biol.

    (2017)
  • D.L. Labovitz

    Using artificial intelligence to reduce the risk of nonadherence in patients on anticoagulation therapy

    Stroke

    (2017)
  • F. Jiang

    Artificial intelligence in healthcare: past, present and future

    Stroke Vasc. Neurol.

    (2017)
  • N. Fleming

    How artificial intelligence is changing drug discovery

    Nature

    (2018)
  • Y. Yuan

    LigBuilder 2: a practical de novo drug design approach

    J. Chem. Inf. Model.

    (2011)
  • T. Zhu

    Hit identification and optimization in virtual screening: practical recommendations based on a critical literature analysis

    J. Med. Chem.

    (2013)
  • A.C. Anderson

    Structure-based functional design of drugs: from target to lead compound

    Methods Mol. Biol.

    (2012)
  • D.R. Hall

    Hot spot analysis for driving the development of hits into leads in fragment-based drug discovery

    J. Chem. Inf. Model.

    (2012)
  • A. Alanine

    Lead generation-enhancing the success of drug discovery by investing in the hit to lead process

    Comb. Chem. High Throughput Screen.

    (2003)
  • J.A. DiMasi

    The cost of drug development

    N. Engl. J. Med.

    (2015)
  • J.W. Scannell

    Diagnosing the decline in pharmaceutical R&D efficiency

    Nat. Rev. Drug Discov.

    (2012)
  • A.S. Reddy et al.

    Polypharmacology: drug discovery for the future

    Expert Rev. Clin. Pharmacol.

    (2013)
  • P. Tormay

    Big data in pharmaceutical R&D: creating a sustainable R&D engine

    Pharm. Med.

    (2015)
  • I. Kola et al.

    Can the pharmaceutical industry reduce attrition rates?

    Nat. Rev. Drug Discov.

    (2004)
  • E.W. Esch

    Organs-on-chips at the frontiers of drug discovery

    Nat. Rev. Drug Discov.

    (2015)
  • K.R. Acharya

    Ace revisited: a new target for structure-based drug design

    Nat. Rev. Drug Discov.

    (2003)
  • N. Black

    Cross sectional survey of multicentre clinical databases in the United Kingdom

    BMJ

    (2004)
  • M. Noordzij

    Sample size calculations: basic principles and common pitfalls

    Nephrol. Dial. Transplant.

    (2010)
  • A. Mullard

    Parsing clinical success rates

    Nat. Rev. Drug Discov.

    (2016)
  • M.H.S. Segler

    Generating focused molecule libraries for drug discovery with recurrent neural networks

    ACS Cent. Sci.

    (2018)
  • Z. Huang

    Data mining for biomedicine and healthcare

    J. Healthc. Eng.

    (2017)
  • Cited by (395)

    • Computational resources and chemoinformatics for translational health research

      2024, Advances in Protein Chemistry and Structural Biology
    • Strategies of Artificial intelligence tools in the domain of nanomedicine

      2024, Journal of Drug Delivery Science and Technology
    View all citing articles on Scopus
    View full text