Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.

Generative artificial intelligence empowers digital twins in drug discovery and clinical trials

Open access
Bordukova, Maria, Makarov, Nikita, Rodriguez-Esteban, Raul, Schmich, Fabian, Menden, Michael P. · 2024 · Expert Opinion on Drug Discovery

Abstract

INTRODUCTION: The concept of Digital Twins (DTs) translated to drug development and clinical trials describes virtual representations of systems of various complexities, ranging from individual cells to entire humans, and enables in silico simulations and experiments. DTs increase the efficiency of drug discovery and development by digitalizing processes associated with high economic, ethical, or social burden. The impact is multifaceted: DT models sharpen disease understanding, support biomarker discovery and accelerate drug development, thus advancing precision medicine. One way to realize DTs is by generative artificial intelligence (AI), a cutting-edge technology that enables the creation of novel, realistic and complex data with desired properties. AREAS COVERED: The authors provide a brief introduction to generative AI and describe how it facilitates the modeling of DTs. In addition, they compare existing implementations of generative AI for DTs in drug discovery and clinical trials. Finally, they discuss technical and regulatory challenges that should be addressed before DTs can transform drug discovery and clinical trials. EXPERT OPINION: The current state of DTs in drug discovery and clinical trials does not exploit the entire power of generative AI yet and is limited to simulation of a small number of characteristics. Nonetheless, generative AI has the potential to transform the field by leveraging recent developments in deep learning and customizing models for the needs of scientists, physicians and patients.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1080/17460441.2023.2273839

Cites

62 of 62 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY-NC-ND · From the PDF
Image 2
CC-BY-NC-ND · From the PDF
Image 3
CC-BY-NC-ND · From the PDF
Image 4
CC-BY-NC-ND · From the PDF
Figure 1 Digital twins (DTs) are virtual representations of real biological entities. here exemplified are DTs of (a) cell lines, (b) whole organs and (c) entire human patients. There is a bidirectional information flow between a biological entity and its DT, whereby a DT is initialized with measurements from a real biological entity and returns predictions or simulation results of virtual experiments influencing decision making related to the biological entity. (d) DTs impact all stages of drug discovery and development, including clinical trials. Created with BioRender.com.
Figure 1 Digital twins (DTs) are virtual representations of real biological entities. here exemplified are DTs of (a) cell lines, (b) whole organs and (c) entire human patients. There is a bidirectional information flow between a biological entity and its DT, whereby a DT is initialized with measurements from a real biological entity and returns predictions or simulation results of virtual experiments influencing decision making related to the biological entity. (d) DTs impact all stages of drug discovery and development, including clinical trials. Created with BioRender.com.CC-BY-NC-ND · From the PDF
Figure 2 Generative digital twins (DTs) can be realized by various deep learning (DL) architectures. (a) input data consisting of patient history. (b) uniform manifold approximation and projection (UMAP) applied to the last layer of a discriminative model predicting the probability of toxicity. (c) dimensionality reduction method UMAP applied to the last layer of a generative DT model at time t+1 of the predicted future patient trajectory. Created with BioRender.com.
Figure 2 Generative digital twins (DTs) can be realized by various deep learning (DL) architectures. (a) input data consisting of patient history. (b) uniform manifold approximation and projection (UMAP) applied to the last layer of a discriminative model predicting the probability of toxicity. (c) dimensionality reduction method UMAP applied to the last layer of a generative DT model at time t+1 of the predicted future patient trajectory. Created with BioRender.com.CC-BY-NC-ND · From the PDF
Figure 3 Digital twin (DT) architectures and use cases in clinical trials. (a) the flow of information between DTs and real patients is bidirectional, as DTs are virtual representations of patients that can help improve patient treatment. Simplified visualization of existing generative DT architectures: (b) conditional restricted Boltzmann machine (CRBM) and (c) variational autoencoder (VAE). Potential generative DT architectures are (d) generative adversarial networks (GAN), (e) stable diffusion, (f) neural ordinary differential equations (neural ODE) and (g) transformers. (h) DT use cases enabled by predicting future patient states given their history. (i) use cases supported by DT predictions of intermediate states given their measured states. (j) DT use cases by predicting population effects for a given population and their parameters, for example, to determine the inclusion criteria for a clinical trial. Created with BioRender.com.
Figure 3 Digital twin (DT) architectures and use cases in clinical trials. (a) the flow of information between DTs and real patients is bidirectional, as DTs are virtual representations of patients that can help improve patient treatment. Simplified visualization of existing generative DT architectures: (b) conditional restricted Boltzmann machine (CRBM) and (c) variational autoencoder (VAE). Potential generative DT architectures are (d) generative adversarial networks (GAN), (e) stable diffusion, (f) neural ordinary differential equations (neural ODE) and (g) transformers. (h) DT use cases enabled by predicting future patient states given their history. (i) use cases supported by DT predictions of intermediate states given their measured states. (j) DT use cases by predicting population effects for a given population and their parameters, for example, to determine the inclusion criteria for a clinical trial. Created with BioRender.com.CC-BY-NC-ND · From the PDF
Image 8
CC-BY-NC-ND · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 57 references

Research works printed but not linked: 3

  1. How digital twins of human cells are accelerating drug discovery [internet] DeepLife. 2022 Jun cited 2023 Sep 18. Available from https://www.nature.com/articles/d43747-022-00108-3
  2. Murphy KP. Probabilistic machine learning: an introduction. Cambridge, Massachusetts: MIT press. 2022 Mar 1.
  3. Chen RT Rubanova Y Bettencourt J et al. Neural ordinary differential equations. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS'18); Red Hook NY USA. Curran Associates Inc; 2018. p. 6572–6583. https://proceedings.neurips.cc/paper_files/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html

Cited by

See all 235

Metadata

Authors
Bordukova, M., Makarov, N., Rodriguez-Esteban, R., Schmich, F., & Menden, M. P.
Affiliations
  • Helmholtz Munich (DE)
  • Data & Analytics, Pharmaceutical Research and Early Development, Roche Innovation Center Basel (RICB), Basel, Switzerland
  • Data & Analytics, Pharmaceutical Research and Early Development, Roche Innovation Center Munich (RICM), Penzberg, Germany
  • The University of Melbourne (AU)
Corresponding author
  • Schmich, Fabian
  • Menden, Michael P.
Venue
Expert Opinion on Drug Discovery
Published
2023-10-27
Volume
19
Issue
1
Pages
33-42
ISSN
  • 1746-0441 (ISSN-L)
  • 1746-045X
OpenAlex
W4387966880
Cited by
235
References
57
Citations by year
2026: 82 · 2025: 104 · 2024: 49
FWCI
3.99
Type
journal article
Language
en
Open access
Locations
  • Expert Opinion on Drug Discovery (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Funders
European Union’s Horizon 2020 Research and Innovation Programme
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
digital twin, generative AI, drug discovery, clinical trials, in silico modeling, precision medicine, biomarker discovery, regulatory challenges, deep learning
MeSH terms
Drug Development, Artificial Intelligence, Clinical Trials as Topic, Computer Simulation, Humans, Biomedical Research, Drug Discovery

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Generative artificial intelligence empowers digital twins in drug discovery and clinical trials. https://app.cochat.ai/papers/10.1080/17460441.2023.2273839
The paper
Bordukova, M., Makarov, N., Rodriguez-Esteban, R., Schmich, F., & Menden, M. P. (2024). Generative artificial intelligence empowers digital twins in drug discovery and clinical trials. Expert Opinion on Drug Discovery. https://doi.org/10.1080/17460441.2023.2273839

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.