Best practices for artificial intelligence in life sciences research

Макаров, Владимир Александрович; Stouch, Terry R.; Allgood, Brandon; Willis, Chris D.; Lynch, Nick

doi:10.1016/j.drudis.2021.01.017

Cited by 21 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More specifically, studies reported that the availability of FAIR data for its original purpose and beyond (primary and secondary use) can accelerate innovation and reduce the time needed to bring a drug to market [12]. Furthermore, this improvement in the discovery and development of innovative medicines has been driven by the exploitation of advanced analytical technologies, such as artificial intelligence (AI) and machine learning [23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Current Practices, Costs and Benefits of FAIR Implementation in Pharmaceutical Research and Development: A Qualitative Interview Study

et al. 2021

View full text Add to dashboard Cite

The findable, accessible, interoperable, reusable (FAIR) principles for scientific data management and stewardship aim to facilitate data reuse at scale by both humans and machines. Research and development (R&D) in the pharmaceutical industry is becoming increasingly data driven, but managing its data assets according to FAIR principles remains costly and challenging. To date, little scientific evidence exists about how FAIR is currently implemented in practice, what its associated costs and benefits are, and how decisions are made about the retrospective FAIRification of datasets in pharmaceutical R&D. This paper reports the results of semi-structured interviews with 14 pharmaceutical professionals who participate in various stages of drug R&D in 7 pharmaceutical businesses. Inductive thematic analysis identified three primary themes of the benefits and costs of FAIRification, and the elements that influence the decision-making process for FAIRifying legacy datasets. Participants collectively acknowledged the potential contribution of FAIRification to data reusability in diverse research domains and the subsequent potential for cost-savings. Implementation costs, however, were still considered a barrier by participants, with the need for considerable expenditure in terms of resources, and cultural change. How decisions were made about FAIRification was influenced by legal and ethical considerations, management commitment, and data prioritisation. The findings have significant implications for those in the pharmaceutical R&D industry who are engaged in driving FAIR implementation, and for external parties who seek to better understand existing practices and challenges.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring the Current Practices, Costs and Benefits of FAIR Implementation in Pharmaceutical Research and Development: A Qualitative Interview Study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Thus, users will be able to generate, test, and validate general prediction models and/or processes in their specific data domain. 6 The higher aggregation levels achievable in this way will pave the way to more-precise models of human health and disease at the molecular, cellular, tissue, and organismal levels.…”

Section: Fairification Challengesmentioning

confidence: 99%

“…5. , 6. Recent studies emphasise that the availability of virus, patient, and therapeutic discovery data in a FAIR format could have accelerated the response to the Coronavirus 2019 (COVID-19) pandemic by enabling large-scale analysis.…”

Section: Introductionmentioning

confidence: 99%

Selection of data sets for FAIRification in drug discovery and development: Which, why, and how?

Alharbi

Gadiya

Henderson

et al. 2022

Drug Discovery Today

View full text Add to dashboard Cite

“…Even though a high risk of failure to repeat experiments between laboratories is an inherent part of developing innovative therapies, some risks can be greatly reduced and avoided by adherence to evidence-based research practices using clearly identified measures to improve research rigor ( Vollert et al, 2020 ; Bespalov et al, 2021 ; Emmerich et al, 2021 ). Alternative initiatives have been introduced to increase data reporting and harmonization across laboratories [ARRIVE 2.0 ( Percie du Sert et al, 2020 ); EQUATOR network ( Simera, 2008 ); The International Brain Laboratory ( The International Brain Laboratory, 2017 ); FAIRsharing Information Resource ( Sansone et al, 2019 )], improve data management and analysis [Pistoia Alliance Database ( Makarov et al, 2021 ); NINDS Common Data Elements ( Stone, 2010 ); FITBIR: Traumatic Brain Injury network ( Tosetti et al, 2013 ); FITBIR: Preclinical Traumatic Brain Injury Common Data Elements ( LaPlaca et al, 2021 )], or publish novel methods and their refinements (Norecopa; Current Protocols in Neuroscience; protocols.io; The Journal of Neuroscience Methods). However, extrinsic and intrinsic factors that affect study outcomes in biomedical research have not yet been systematically considered or weighted and are the subject of “PEERS” ( P latform for the E xchange of E xperimental R esearch S tandards).…”

Section: Introduction and Rationalementioning

confidence: 99%

PEERS — An Open Science “Platform for the Exchange of Experimental Research Standards” in Biomedicine

Sil

Bespalov²,

Dalla

et al. 2021

Front. Behav. Neurosci.

View full text Add to dashboard Cite

Laboratory workflows and preclinical models have become increasingly diverse and complex. Confronted with the dilemma of a multitude of information with ambiguous relevance for their specific experiments, scientists run the risk of overlooking critical factors that can influence the planning, conduct and results of studies and that should have been considered a priori. To address this problem, we developed “PEERS” (Platform for the Exchange of Experimental Research Standards), an open-access online platform that is built to aid scientists in determining which experimental factors and variables are most likely to affect the outcome of a specific test, model or assay and therefore ought to be considered during the design, execution and reporting stages. The PEERS database is categorized into in vivo and in vitro experiments and provides lists of factors derived from scientific literature that have been deemed critical for experimentation. The platform is based on a structured and transparent system for rating the strength of evidence related to each identified factor and its relevance for a specific method/model. In this context, the rating procedure will not solely be limited to the PEERS working group but will also allow for a community-based grading of evidence. We here describe a working prototype using the Open Field paradigm in rodents and present the selection of factors specific to each experimental setup and the rating system. PEERS not only offers users the possibility to search for information to facilitate experimental rigor, but also draws on the engagement of the scientific community to actively expand the information contained within the platform. Collectively, by helping scientists search for specific factors relevant to their experiments, and to share experimental knowledge in a standardized manner, PEERS will serve as a collaborative exchange and analysis tool to enhance data validity and robustness as well as the reproducibility of preclinical research. PEERS offers a vetted, independent tool by which to judge the quality of information available on a certain test or model, identifies knowledge gaps and provides guidance on the key methodological considerations that should be prioritized to ensure that preclinical research is conducted to the highest standards and best practice.

show abstract

Best practices for artificial intelligence in life sciences research

Abstract: We describe 11 best practices for the successful use of Artificial Intelligence and Machine Learning in the pharmaceutical and biotechnology research, on the data, technology, and organizational management levels.

Cited by 21 publications

References 25 publications

Exploring the Current Practices, Costs and Benefits of FAIR Implementation in Pharmaceutical Research and Development: A Qualitative Interview Study

Exploring the Current Practices, Costs and Benefits of FAIR Implementation in Pharmaceutical Research and Development: A Qualitative Interview Study

Selection of data sets for FAIRification in drug discovery and development: Which, why, and how?

PEERS — An Open Science “Platform for the Exchange of Experimental Research Standards” in Biomedicine

Contact Info

Product

Resources

About