Machine Learning in Drug Discovery and Development Part 1: A Primer

Talevi, Alan; Morales, Juan Francisco; Hather, Gregory; Podichetty, Jagdeep T.; Kim, Sarah; Bloomingdale, Peter; Kim, Samuel; Burton, Jackson; Brown, Joshua D.; Winterstein, Almut G.; Schmidt, Stephan; White, Jensen Kael; Conrado, Daniela J.

doi:10.1002/psp4.12491

Cited by 54 publications

(57 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to immune biomarkers, measurements of bacterial DNA or mRNA may be used in translation. Moreover, artificial intelligence and machine‐learning methods may facilitate identification of biomarkers from broad protein assays and imaging data that would be of value to characterize and explore as predictors in mechanistic models 75 . Eventually, comprehensive modeling frameworks that account for both safety and efficacy should be the norm to efficiently explore dosing strategies 76 .…”

Section: Pharmacometric Models For Human Datamentioning

confidence: 99%

Pivotal Role of Translation in Anti‐Infective Development

Friberg

2021

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

The value of model‐based translation in drug discovery and development is now effectively being recognized in many disease areas and among various stakeholders. Such quantitative approaches are expected to facilitate the selection on which compound to prioritize for successful development, predict the human efficacious dose based on preclinical data with adequate precision, guide design, and de‐risk later development stages. The importance of time‐dependencies, which are typically species‐dependent due to different turnover rates of biological processes, is, however, often neglected. For bacterial infections, the choice of dosing regimen is typically relying on preclinical pharmacokinetic (PK) and pharmacodynamic (PD) data, because the bacterial load and disease severity, and consequently the PK/PD relationship, cannot be quantified well on clinical data, given the low‐information end points used. It is time to recognize the limitations of using time‐collapsed approaches for translation (i.e., methods where targets are based on summary measures of exposure and response). Models describing the full time‐course captures important quantitative information of drug distribution, bacterial growth, antibiotic killing, and resistance development, and can account for species‐differences in the PK profiles driving the killing. Furthermore, with a model‐based approach for translation, we can take a holistic approach in development of a joint model for in vitro, in vivo, and clinical data, as well as incorporating information on the contribution of the immune system. Such advancements are anticipated to facilitate rational decision making during various stages of drug development and in the optimization of treatment regimens for different groups of patients.

show abstract

Section: Pharmacometric Models For Human Datamentioning

confidence: 99%

Pivotal Role of Translation in Anti‐Infective Development

Friberg

2021

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

show abstract

“…Pharmaceutical companies have greatly benefited from the utilization of various ML algorithms in drug discovery. ML algorithms have been used to develop various models for predicting chemical, biological, and physical characteristics of compounds in drug discovery [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. ML algorithms can be incorporated in all steps of the process of drug discovery.…”

Section: ML Algorithms Used In Drug Discoverymentioning

confidence: 99%

Machine Learning Methods in Drug Discovery

et al. 2020

View full text Add to dashboard Cite

The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.

show abstract

“…23 Several recent reviews have attempted to provide a specific rationale for incorporating ML in population PK/PD modelling. [24][25][26][27] historical drug discovery data on 500 failed GSK drugs, bioassay data and molecular properties. 28 The adaptation, integration and application of big data and ML in PMX has yet to reach fruition.…”

Section: Machine Learning and Pmx: Opportunities Applications And Challengesmentioning

confidence: 99%

Machine learning in pharmacometrics: Opportunities and challenges

McComb

Bies

Ramanathan

2021

Brit J Clinical Pharma

View full text Add to dashboard Cite

The explosive growth in medical devices, imaging and diagnostics, computing, and communication and information technologies in drug development and healthcare has created an ever-expanding data landscape that the pharmacometrics (PMX) research community must now traverse. The tools of machine learning (ML) have emerged as a powerful computational approach in other data-rich disciplines but its effective utilization in the pharmaceutical sciences and PMX modelling is in its infancy. ML-based methods can complement PMX modelling by enabling the information in diverse sources of big data, e.g. population-based public databases and disease-specific clinical registries, to be harnessed because they are capable of efficiently identifying salient variables associated with outcomes and delineating their interdependencies. ML algorithms are computationally efficient, have strong predictive capabilities and can enable learning in the big data setting. ML algorithms can be viewed as providing a computational bridge from big data to complement PMX modelling. This review provides an overview of the strengths and weaknesses of ML approaches vis-à-vis population methods, assesses current research into ML applications in the pharmaceutical sciences and provides perspective for potential opportunities and strategies for the successful integration and utilization of ML in PMX.

show abstract

Machine Learning in Drug Discovery and Development Part 1: A Primer

Cited by 54 publications

References 59 publications

Pivotal Role of Translation in Anti‐Infective Development

Pivotal Role of Translation in Anti‐Infective Development

Machine Learning Methods in Drug Discovery

Machine learning in pharmacometrics: Opportunities and challenges

Contact Info

Product

Resources

About