imPlatelet classifier: image-converted RNA biomarker profiles enable blood-based cancer diagnostics
| Autor: | Krzysztof Pastuszak, Myron G. Best, Sjors G J G In 't Veld, Thomas Wurdinger, Anna Supernat, Tomasz Stokowy, Anna J. Żaczek, Anna Łojkowska, Jacek Jassem, Sylwia Łapińska-Szumczyk, Robert Różański |
|---|---|
| Přispěvatelé: | Laboratory Medicine, Neurosurgery, CCA - Imaging and biomarkers |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Cancer Research Lung Neoplasms image-based classification tumor‐educated platelets 03 medical and health sciences 0302 clinical medicine Carcinoma Non-Small-Cell Lung image‐based classification Genetics medicine Humans Liquid biopsy Lung cancer Research Articles RC254-282 Ovarian Neoplasms liquid biopsy business.industry Neoplasms. Tumors. Oncology. Including cancer and carcinogens Cancer RNA sequencing Pattern recognition General Medicine medicine.disease tumor-educated platelets Biomarker (cell) 030104 developmental biology Oncology 030220 oncology & carcinogenesis RNA Molecular Medicine Sample collection Artificial intelligence Sarcoma Ovarian cancer business Classifier (UML) Biomarkers Research Article |
| Zdroj: | Molecular oncology, 15(10), 2688-2701. Elsevier Molecular Oncology Pastuszak, K, Supernat, A, Best, M G, in 't Veld, S G J G, Łapińska-Szumczyk, S, Łojkowska, A, Różański, R, Żaczek, A J, Jassem, J, Würdinger, T & Stokowy, T 2021, ' imPlatelet classifier: image-converted RNA biomarker profiles enable blood-based cancer diagnostics ', Molecular oncology, vol. 15, no. 10, pp. 2688-2701 . https://doi.org/10.1002/1878-0261.13014 Molecular Oncology, Vol 15, Iss 10, Pp 2688-2701 (2021) |
| ISSN: | 1574-7891 2688-2701 |
| DOI: | 10.1002/1878-0261.13014 |
| Popis: | Liquid biopsies offer a minimally invasive sample collection, outperforming traditional biopsies employed for cancer evaluation. The widely used material is blood, which is the source of tumor‐educated platelets. Here, we developed the imPlatelet classifier, which converts RNA‐sequenced platelet data into images in which each pixel corresponds to the expression level of a certain gene. Biological knowledge from the Kyoto Encyclopedia of Genes and Genomes was also implemented to improve accuracy. Images obtained from samples can then be compared against standard images for specific cancers to determine a diagnosis. We tested imPlatelet on a cohort of 401 non‐small cell lung cancer patients, 62 sarcoma patients, and 28 ovarian cancer patients. imPlatelet provided excellent discrimination between lung cancer cases and healthy controls, with accuracy equal to 1 in the independent dataset. When discriminating between noncancer cases and sarcoma or ovarian cancer patients, accuracy equaled 0.91 or 0.95, respectively, in the independent datasets. According to our knowledge, this is the first study implementing an image‐based deep‐learning approach combined with biological knowledge to classify human samples. The performance of imPlatelet considerably exceeds previously published methods and our own alternative attempts of sample discrimination. We show that the deep‐learning image‐based classifier accurately identifies cancer, even when a limited number of samples are available. To our knowledge, this is the first report that uses a deep neural network to analyze RNA‐sequencing data in liquid biopsies. imPlatelet method shows superior performance, detecting cases even in the early stage ovarian cancer. It shows remarkable potential in healthy individuals' indication. We believe that similar approach could be applied to sequencing data of tissues or single cells. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text