Abstract
The COVID-19 pandemic has prompted a surge in drug repurposing studies. However, many promising hits identified by modern neural networks failed in the preclinical research, which has raised concerns about the reliability of current drug discovery methods. Among studies that explore the therapeutic potential of drugs for COVID-19 treatment is RxRx19a. Its dataset was derived from High Throughput Screening (HTS) experiments conducted by the Recursion biotechnology company. Prior research on hit discovery using this dataset involved learning healthy and infected cells’ morphological features and utilizing this knowledge to estimate contaminated drugged cells’ scores. Nevertheless, models have never seen drugged cells during training, so these cells’ phenotypic features are out of their trained distribution. That being said, model estimations for treatment samples are not trusted in these methods and can lead to false positives. This work offers a first-in-field weakly-supervised drug efficiency estimation pipeline that utilizes the mixup methodology with a confidence score for its predictions. We applied our method to the RxRx19a dataset and showed that consensus between top hits predicted on different representation spaces increases using our confidence method. Further, we demonstrate that our pipeline is robust, stable, and sensitive to drug toxicity.
N. Mirzaie and M. V. Sanian—Contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ando, D.M., McLean, C.Y., Berndl, M.: Improving phenotypic measurements in high-content imaging screens. bioRxiv (2017). https://doi.org/10.1101/161422, https://www.biorxiv.org/content/early/2017/07/10/161422
Aslan, A., Aslan, C., Zolbanin, N.M., Jafari, R.: Acute respiratory distress syndrome in COVID-19: possible mechanisms and therapeutic management. Pneumonia 13(1), 14 (2021)
Caicedo, J.C., et al.: Data-analysis strategies for image-based cell profiling. Nat. Methods 14(9), 849–863 (2017)
Caicedo, J.C., McQuin, C., Goodman, A., Singh, S., Carpenter, A.E.: Weakly supervised learning of Single-Cell feature embeddings. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2018, 9309–9318 (2018)
DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). https://arxiv.org/abs/1512.03385
Heiser, K., et al.: Identification of potential treatments for COVID-19 through artificial intelligence-enabled phenomic analysis of human cells infected with SARS-CoV-2. bioRxiv (2020). https://doi.org/10.1101/2020.04.21.054387, https://www.biorxiv.org/content/early/2020/04/23/2020.04.21.054387
Li, Y., et al.: High-throughput screening and evaluation of repurposed drugs targeting the SARS-CoV-2 main protease. Signal Transduction Targeted Therapy 6(1), 356 (2021)
Li, Y., et al.: Remdesivir metabolite GS-441524 effectively inhibits SARS-CoV-2 infection in mouse models. J. Med. Chem. 65(4), 2785–2793 (2021)
Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems (2020)
Mascolini, A., Cardamone, D., Ponzio, F., Di Cataldo, S., Ficarra, E.: Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations. BMC Bioinform. 23(1), 295 (2022)
Mirabelli, C., et al.: Morphological cell profiling of SARS-CoV-2 infection identifies drug repurposing candidates for COVID-19. Proc. Natl. Acad. Sci. 118(36), e2105815118 (2021). https://doi.org/10.1073/pnas.2105815118, https://www.pnas.org/doi/abs/10.1073/pnas.2105815118
Pruijssers, A.J., et al.: Remdesivir inhibits SARS-CoV-2 in human lung cells and chimeric SARS-CoV expressing the SARS-CoV-2 RNA polymerase in mice. Cell Rep. 32(3), 107940 (2020)
Pushpakom, S., et al.: Drug repurposing: progress, challenges and recommendations. Nat. Rev. Drug Discov. 18(1), 41–58 (2018)
Rohban, M.H., et al.: Virtual screening for small-molecule pathway regulators by image-profile matching. Cell Syst. 13(9), 724–736.e9 (2022)
Saberian, M.S., et al.: DEEMD: drug efficacy estimation against SARS-CoV-2 based on cell morphology with deep multiple instance learning. IEEE Trans. Med. Imaging 41(11), 3128–3145 (2022). https://doi.org/10.1109/TMI.2022.3178523
Stirling, D.R., Swain-Bowden, M.J., Lucas, A.M., Carpenter, A.E., Cimini, B.A., Goodman, A.: Cell Profiler 4: improvements in speed, utility and usability. BMC Bioinform. 22(1), 433 (2021)
Torres Acosta, M.A., Singer, B.D.: Pathogenesis of COVID-19-induced ARDS: implications for an ageing population. Eur. Respir. J. 56(3), 2002049 (2020). https://doi.org/10.1183/13993003.02049-2020, https://erj.ersjournals.com/content/56/3/2002049
Van Norman, G.A.: Drugs, devices, and the FDA: Part 1: an overview of approval processes for drugs. JACC: Basic Transl. Sci. 1(3), 170–179 (2016). https://doi.org/10.1016/j.jacbts.2016.03.002, https://www.sciencedirect.com/science/article/pii/S2452302X1600036X
Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. CoRR abs/1707.00600 (2017). https://arxiv.org/abs/1707.00600
Yan, V.C., Muller, F.L.: Advantages of the parent nucleoside GS-441524 over Remdesivir for COVID-19 treatment. ACS Med. Chem. Lett. 11(7), 1361–1366 (2020)
Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: a survey. CoRR abs/2110.11334 (2021). https://arxiv.org/abs/2110.11334
Yousefi, H., Mashouri, L., Okpechi, S.C., Alahari, N., Alahari, S.K.: Repurposing existing drugs for the treatment of COVID-19/SARS-CoV-2 infection: a review describing drug mechanisms of action. Biochem. Pharmacol. 183, 114296 (2020)
Acknowledgments
We express our gratitude to Dr. Forbes J. Burkowski, Dr. Vahid Salimi, and Dr. Ali Sharifi Zarchi for their priceless guidance and help in validating the output of the models.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Code and Data Availability
The code repository is available at https://github.com/rohban-lab/Drug-Efficiency-Estimation-with-Confidence-Score.
Raw Cellprofiler features are available at http://hpc.sharif.edu:8080/HRCE/, and normalized well level features at https://doi.org/10.6084/m9.figshare.23723946.v1.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mirzaie, N., Sanian, M.V., Rohban, M.H. (2023). Weakly-Supervised Drug Efficiency Estimation with Confidence Score: Application to COVID-19 Drug Discovery. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14227. Springer, Cham. https://doi.org/10.1007/978-3-031-43993-3_65
Download citation
DOI: https://doi.org/10.1007/978-3-031-43993-3_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43992-6
Online ISBN: 978-3-031-43993-3
eBook Packages: Computer ScienceComputer Science (R0)