Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Nadia Terranova; Didier Renard; Mohamed H. Shahin; Sujatha Menon; Cornelis E.C.A. Hop; Sean Hayes; Kumpal Madrasi; Sven Stodtmann; Thomas Tensfeldt; Pavan Vaddady; Nicholas Ellinwood; James Lu

doi:10.1002/cpt.3053

journal article Open Access Oct 06, 2023

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Nadia Terranova

Didier Renard

Mohamed H. Shahin Sujatha Menon Cornelis E.C.A. Hop Sean Hayes Kumpal Madrasi

Clinical Pharmacology & Therapeutics Vol. 115 No. 4 pp. 658-672 · Wiley

View at Publisher Save 10.1002/cpt.3053

Abstract

Recent breakthroughs in artificial intelligence (AI) and machine learning (ML) have ushered in a new era of possibilities across various scientific domains. One area where these advancements hold significant promise is model‐informed drug discovery and development (MID3). To foster a wider adoption and acceptance of these advanced algorithms, the Innovation and Quality (IQ) Consortium initiated the AI/ML working group in 2021 with the aim of promoting their acceptance among the broader scientific community as well as by regulatory agencies. By drawing insights from workshops organized by the working group and attended by key stakeholders across the biopharma industry, academia, and regulatory agencies, this white paper provides a perspective from the IQ Consortium. The range of applications covered in this white paper encompass the following thematic topics: (i) AI/ML‐enabled Analytics for Pharmacometrics and Quantitative Systems Pharmacology (QSP) Workflows; (ii) Explainable Artificial Intelligence and its Applications in Disease Progression Modeling; (iii) Natural Language Processing (NLP) in Quantitative Pharmacology Modeling; and (iv) AI/ML Utilization in Drug Discovery. Additionally, the paper offers a set of best practices to ensure an effective and responsible use of AI, including considering the context of use, explainability and generalizability of models, and having human‐in‐the‐loop. We believe that embracing the transformative power of AI in quantitative modeling while adopting a set of good practices can unlock new opportunities for innovation, increase efficiency, and ultimately bring benefits to patients.

Topics

No keywords indexed for this article. Browse by subject →

References

107

[1]

10.1002/psp4.12049

[2]

10.1111/bcp.14801

[3]

An Introduction to Machine Learning

Solveig Badillo, Balazs Banfai, Fabian Birzele et al.

Clinical Pharmacology & Therapeutics 10.1002/cpt.1796

[4]

10.1002/cpt.1771

[5]

10.1002/cpt.2668

[6]

10.1002/cpt.1914

[7]

10.1208/s12248-012-9387-9

[8]

10.1007/s10928-015-9417-1

[9]

FDA Guidance for Industry.Exposure‐Response Relationships — Study Design Data Analysis and Regulatory Applications<https://www.fda.gov/media/71277/download> (April 2003). Accessed May 30 2023.

[10]

Multimodal biomedical AI

Julian N. Acosta, Guido J. Falcone, Pranav Rajpurkar et al.

Nature Medicine 10.1038/s41591-022-01981-2

[11]

10.1002/psp4.12709

[12]

Chan J.R. "Current practices for QSP model assessment: an IQ consortium survey" J Pharmacokinet Pharmacodyn (2022)

[13]

10.1080/19466315.2020.1797867

[14]

International Consortium for Innovation & Quality in Pharmaceutical Development<https://iqconsortium.org/> (2023). Accessed May 30 2023.

[15]

IQ Consortium Working Group for Artificial Intelligence & Machine Learning<https://iqconsortium.org/initiatives/working‐groups/artificial‐intelligence‐and‐machine‐learning/> (2022). Accessed May 30 2023.

[16]

10.1007/s10928-021-09757-w

[17]

10.1007/s10928-021-09793-6

[18]

10.5414/cp203800

[19]

Neural-ODE for pharmacokinetics modeling and its advantage to alternative machine learning models in predicting new dosing regimens

James Lu, Kaiwen Deng, Xinyuan Zhang et al.

iScience 10.1016/j.isci.2021.102804

[20]

10.1038/s42256-021-00357-4

[21]

10.1038/s41746-021-00381-z

[22]

10.2217/cer-2020-0230

[23]

10.1038/s41598-019-49656-2

[24]

10.1164/rccm.201908-1600oc

[25]

10.1038/s41598-020-78212-6

[26]

Qian Z.Z. William R. Fleuren Lucas M. Elbers P.&van derSchaar M.Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression. <https://arxiv.org/abs/2106.02875ttps://arxiv.org/pdf/2106.02875.pdf> (2021). Accessed May 30 2023.

[27]

10.1002/cpt.1907

[28]

Estimation and Inference of Heterogeneous Treatment Effects using Random Forests

Stefan Wager, Susan Athey

Journal of the American Statistical Association 10.1080/01621459.2017.1319839

[29]

10.1002/psp4.12491

[30]

10.1208/s12248-021-00593-x

[31]

Two heads are better than one: current landscape of integrating QSP and machine learning

Tongli Zhang, Ioannis P. Androulakis, Peter Bonate et al.

Journal of Pharmacokinetics and Pharmacodynamics 10.1007/s10928-022-09805-z

[32]

IQ Machine Intelligence for Quantitative Modeling in Drug Discovery & Development Applications Workshop<https://iqconsortium.org/initiatives/working‐groups/artificial‐intelligence‐and‐machine‐learning/>(September 2022). Accessed May 30 2023.

[33]

Explainable Machine Learning for Disease Progression Modeling & Digital Twins<https://www.go‐acop.org/default.asp?id=46&keuze=meeting&mid=21>(November 2022). Accessed May 30 2023.

[34]

10.1002/cpt.2422

[35]

10.1007/s10928-012-9258-0

[36]

10.1002/psp4.12754

[37]

10.1200/cci.22.00126

[38]

10.1002/psp4.12983

[39]

10.1007/s10928-021-09782-9

[40]

10.1021/js950433d

[41]

10.1021/js9604016

[42]

10.1002/jps.20384

[43]

10.1111/j.1365-2125.2007.02845.x

[44]

10.1002/psp4.12786

[45]

Rackauckas C.et al.Universal differential equations for scientific machine learning<https://arxiv.org/abs/2001.04385>(2020). Accessed May 30 2023. 10.21203/rs.3.rs-55125/v1

[46]

Poels K.A Machine Learning Based Approach for Toxicity Predictions in Immuno‐Oncology. Presented at IQ Machine Intelligence for Quantitative Modeling in Drug Discovery & Development Applications Workshop<https://iqconsortium.org/images/uploads/Session_1_‐_A_Machine_Learning_Based_Approach_for_Toxicity_Predictions_in_Immuno‐Oncology_‐‐_Kamrine_Poels_Pfizer.pdf>(September 2022). Accessed May 30 2023.

[47]

10.1002/psp4.12715

[48]

Hu M.BE ASSESSMENT MATE (BEAM) ‐ A Data Analytics Tool to Enhance Efficiency Quality and Consistency of Bioequivalence Assessment. Presented at 2021 FDA Science Forum<https://www.fda.gov/science‐research/fda‐science‐forum/2021‐fda‐science‐forum‐agenda> (2021). Accessed May 31 2023.

[49]

10.3389/frma.2021.670006

[50]

10.1111/cts.12541

Showing 50 of 107 references

Metrics

64

Citations

107

References

Details

Published: Oct 06, 2023
Vol/Issue: 115(4)
Pages: 658-672
License: View

Authors

N

Nadia Terranova

Quantitative Pharmacology Merck KGaA Lausanne Switzerland

D

Didier Renard

Full Development Pharmacometrics, Novartis Pharma AG Basel Switzerland

M

Mohamed H. Shahin

Clinical Pharmacology Pfizer Inc. Groton Connecticut USA

S

Sujatha Menon

Clinical Pharmacology Pfizer Inc. Groton Connecticut USA

C

Cornelis E.C.A. Hop

DMPK Genentech Inc. South San Francisco California USA

S

Sean Hayes

Quantitative Pharmacology & Pharmacometrics Merck & Co. Inc. Rahway New Jersey USA

K

Kumpal Madrasi

Modeling & Simulation Sanofi Bridgewater New Jersey USA

S

Sven Stodtmann

Pharmacometrics AbbVie Deutschland GmbH & Co. KG Ludwigshafen Germany

T

Thomas Tensfeldt

Clinical Pharmacology Pfizer Inc. Groton Connecticut USA

P

Pavan Vaddady

Quantitative Clinical Pharmacology Daiichi Sankyo, Inc. Basking Ridge New Jersey USA

N

Nicholas Ellinwood

Global PK/PD & Pharmacometrics Eli Lilly Indianapolis Indiana USA

J

James Lu

Clinical Pharmacology Genentech Inc. South San Francisco California USA

Cite This Article

Nadia Terranova, Didier Renard, Mohamed H. Shahin, et al. (2023). Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices. Clinical Pharmacology & Therapeutics, 115(4), 658-672. https://doi.org/10.1002/cpt.3053

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

You May Also Like