{"title":"使用微流体液滴平台的无标记机器学习预测肿瘤球体化疗。","authors":"Caroline Parent, Hasti Honari, Tiziana Tocci, Franck Simon, Sakina Zaidi, Audric Jan, Vivian Aubert, Olivier Delattre, Hervé Isambert, Claire Wilhelm, Jean-Louis Viovy","doi":"10.1002/smsc.202500173","DOIUrl":null,"url":null,"abstract":"<p><p>An integrated approach is proposed to rapidly evaluate the effects of anticancer treatments in 3D models, combining a droplet-based microfluidic platform for spheroid formation and single-spheroid chemotherapy application, label-free morphological analysis, and machine learning to assess treatment response. Morphological features of spheroids, such as size and color intensity, are extracted and selected using the multivariate information-based inductive causation algorithm, and used to train a neural network for spheroid classification into viability classes, derived from metabolic assays performed within the same platform as a benchmark. The model is tested on Ewing sarcoma cell lines and patient-derived xenograft (PDX) cells, demonstrating robust performance across datasets. It accurately predicts spheroid viability, used to generate dose-response curves and to determine half maximal inhibitory concentration (IC50) values comparable to traditional biochemical assays. Notably, a model trained on cell line spheroids successfully classifies PDX spheroids, highlighting its adaptability. Compared to convolutional neural network-based approaches, this method works with smaller training datasets and provides greater interpretability by identifying key morphological features. The droplet platform further reduces cell requirements, while single-spheroid confinement enhances classification quality. Overall, this label-free experimental and analytical platform is confirmed as a scalable, efficient, and dynamic tool for drug screening.</p>","PeriodicalId":29791,"journal":{"name":"Small Science","volume":"5 9","pages":"2500173"},"PeriodicalIF":8.3000,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12412520/pdf/","citationCount":"0","resultStr":"{\"title\":\"Label-Free Machine Learning Prediction of Chemotherapy on Tumor Spheroids Using a Microfluidics Droplet Platform.\",\"authors\":\"Caroline Parent, Hasti Honari, Tiziana Tocci, Franck Simon, Sakina Zaidi, Audric Jan, Vivian Aubert, Olivier Delattre, Hervé Isambert, Claire Wilhelm, Jean-Louis Viovy\",\"doi\":\"10.1002/smsc.202500173\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>An integrated approach is proposed to rapidly evaluate the effects of anticancer treatments in 3D models, combining a droplet-based microfluidic platform for spheroid formation and single-spheroid chemotherapy application, label-free morphological analysis, and machine learning to assess treatment response. Morphological features of spheroids, such as size and color intensity, are extracted and selected using the multivariate information-based inductive causation algorithm, and used to train a neural network for spheroid classification into viability classes, derived from metabolic assays performed within the same platform as a benchmark. The model is tested on Ewing sarcoma cell lines and patient-derived xenograft (PDX) cells, demonstrating robust performance across datasets. It accurately predicts spheroid viability, used to generate dose-response curves and to determine half maximal inhibitory concentration (IC50) values comparable to traditional biochemical assays. Notably, a model trained on cell line spheroids successfully classifies PDX spheroids, highlighting its adaptability. Compared to convolutional neural network-based approaches, this method works with smaller training datasets and provides greater interpretability by identifying key morphological features. The droplet platform further reduces cell requirements, while single-spheroid confinement enhances classification quality. Overall, this label-free experimental and analytical platform is confirmed as a scalable, efficient, and dynamic tool for drug screening.</p>\",\"PeriodicalId\":29791,\"journal\":{\"name\":\"Small Science\",\"volume\":\"5 9\",\"pages\":\"2500173\"},\"PeriodicalIF\":8.3000,\"publicationDate\":\"2025-07-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12412520/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Small Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1002/smsc.202500173\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/9/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Small Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1002/smsc.202500173","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/9/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
Label-Free Machine Learning Prediction of Chemotherapy on Tumor Spheroids Using a Microfluidics Droplet Platform.
An integrated approach is proposed to rapidly evaluate the effects of anticancer treatments in 3D models, combining a droplet-based microfluidic platform for spheroid formation and single-spheroid chemotherapy application, label-free morphological analysis, and machine learning to assess treatment response. Morphological features of spheroids, such as size and color intensity, are extracted and selected using the multivariate information-based inductive causation algorithm, and used to train a neural network for spheroid classification into viability classes, derived from metabolic assays performed within the same platform as a benchmark. The model is tested on Ewing sarcoma cell lines and patient-derived xenograft (PDX) cells, demonstrating robust performance across datasets. It accurately predicts spheroid viability, used to generate dose-response curves and to determine half maximal inhibitory concentration (IC50) values comparable to traditional biochemical assays. Notably, a model trained on cell line spheroids successfully classifies PDX spheroids, highlighting its adaptability. Compared to convolutional neural network-based approaches, this method works with smaller training datasets and provides greater interpretability by identifying key morphological features. The droplet platform further reduces cell requirements, while single-spheroid confinement enhances classification quality. Overall, this label-free experimental and analytical platform is confirmed as a scalable, efficient, and dynamic tool for drug screening.
期刊介绍:
Small Science is a premium multidisciplinary open access journal dedicated to publishing impactful research from all areas of nanoscience and nanotechnology. It features interdisciplinary original research and focused review articles on relevant topics. The journal covers design, characterization, mechanism, technology, and application of micro-/nanoscale structures and systems in various fields including physics, chemistry, materials science, engineering, environmental science, life science, biology, and medicine. It welcomes innovative interdisciplinary research and its readership includes professionals from academia and industry in fields such as chemistry, physics, materials science, biology, engineering, and environmental and analytical science. Small Science is indexed and abstracted in CAS, DOAJ, Clarivate Analytics, ProQuest Central, Publicly Available Content Database, Science Database, SCOPUS, and Web of Science.