Abstract
Lab experiments are a crucial part of research in natural sciences. High-throughput screening is leveraged to generate hypotheses, by evaluating a wide range of experimental parameter values and accumulating a wealth of data on the corresponding experimental outcomes. The data is subsequently analyzed to design new rounds of experiments. While discriminative models have previously proven useful for screening data analytics, they do not account for randomness inherent to lab experiments, and do not have the capacity to capture the potentially high-dimensional relationship between the experiment input parameters and outcomes. Instead, we take a data-driven simulation perspective on the problem. Inspired by biomaterials research experiments, we consider a case where both the input parameter space and the outcome space have a high-dimensional (image) representation. We propose a deep generative model that serves simultaneously as a simulation model of the experiment, i.e. allows to generate potential outcomes conditioned on the experiment input, and as a tool for inverse design, i.e. generating instances of inputs that could lead to a given experiment outcome. A proof-of-concept evaluation on a synthetic dataset shows that the model is able to learn the embedded relationship between the properties of the input and of the output in a probabilistic manner and allows for experiment simulation and design application scenarios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The source code and the data are available at https://github.com/stepanveret/biomatsim.
- 2.
The width w of the sliding window regulates the variance of the dependency.
- 3.
\(KL_i\) stands for the average \(KL \,\big (q_{\varphi _{f_i}}(z_{f_i} | p) \,||\,p_{\theta ^*_{pr, i}}(z_{f_i})\big )\).
References
Beijer, N., et al.: TopoWellPlate: a well-plate-based screening platform to study cell-surface topography interactions. Adv. Biosyst. 1, 1700002 (2017)
Beijer, N.R., et al.: Dynamic adaptation of mesenchymal stem cell physiology upon exposure to surface micropatterns. Sci. Rep. 9(1), 1–14 (2019)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 2, 2672–2680 (2014). https://dl.acm.org/doi/10.5555/2969033.2969125
Hulshof, F.F., et al.: Mining for osteogenic surface topographies: in silico design to in vivo osseo-integration. Biomaterials 137, 49–60 (2017)
Hulsman, M., et al.: Analysis of high-throughput screening reveals the effect of surface topographies on cellular morphology. Acta Biomater. 15, 29–38 (2015)
Ilse, M., Tomczak, J.M., Louizos, C., Welling, M.: DIVA: domain invariant variational autoencoders. In: Medical Imaging with Deep Learning, pp. 322–348. PMLR (2020)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Larsen, A.B.L., Sønderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. In: International Conference on Machine Learning, pp. 1558–1566. PMLR (2016)
Mayr, L.M., Bojanic, D.: Novel trends in high-throughput screening. Curr. Opin. Pharmacol. 9(5), 580–588 (2009)
Reimer, A., et al.: Scalable topographies to support proliferation and oct4 expression by human induced pluripotent stem cells. Sci. Rep. 6, 18948 (2016)
Sanchez-Lengeling, B., Aspuru-Guzik, A.: Inverse molecular design using machine learning: generative models for matter engineering. Science 361(6400), 360–365 (2018)
Unadkat, H.V., et al.: An algorithm-based topographical biomaterials library to instruct cell fate. Proc. Natl. Acad. Sci. 108(40), 16565–16570 (2011)
Vasilevich, A.S., et al.: Designed surface topographies control ICAM-1 expression in tonsil-derived human stromal cells. Front. Bioeng. Biotechnol. 6, 87 (2018)
Vassey, M.J., et al.: Immune modulation by design: Using topography to control human monocyte attachment and macrophage differentiation. Adv. Sci. 7(11), 1903392 (2020)
Wang, L., Chan, Y.C., Ahmed, F., Liu, Z., Zhu, P., Chen, W.: Deep generative modeling for mechanistic-based learning and design of metamaterial systems. Comput. Methods Appl. Mech. Eng. 372, 113377 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Veretennikov, S., Minartz, K., Menkovski, V., Gumuscu, B., de Boer, J. (2022). Simulation of Scientific Experiments with Generative Models. In: Bouadi, T., Fromont, E., Hüllermeier, E. (eds) Advances in Intelligent Data Analysis XX. IDA 2022. Lecture Notes in Computer Science, vol 13205. Springer, Cham. https://doi.org/10.1007/978-3-031-01333-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-01333-1_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01332-4
Online ISBN: 978-3-031-01333-1
eBook Packages: Computer ScienceComputer Science (R0)