Abstract
Background: The diagnosis and prognosis of pathological conditions, such as age-related macular degeneration (AMD) and cancer still need improvement. AMD is primarily caused due to the dysfunction of retinal pigment epithelium (RPE), whereas endothelial cells (ECs) play one of the major roles in angiogenesis; an important process which occurs in malignant progression of cancer. Several reports suggested the augmented release of nano-vesicles under pathological conditions, including from RPE as well as cancer-associated ECs, which take part in various biological processes, including intercellular communication in disease progression. Importantly, these nano-vesicles are around 30-1000 nm and carry the fingerprint of their initiating parent cells (IPCs). Therefore, these nano-vesicles could be utilized as the diagnostic tool for AMD and cancer, respectively. However, the analysis of nano-vesicles for biomarker study is confounded by their extensive heterogeneous nature.
Methods: To confront this challenge, we utilized artificial intelligence (AI) based machine learning (ML) algorithms such as support vector machine (SVM) and decision tree model on the dataset of nano-vesicles from RPE and ECs cell lines with low dimensionality.
Results: Overall, Gaussian SVM demonstrated the highest prediction accuracy of the IPCs of nano-vesicles, among all the chosen SVM classifiers. Additionally, the bagged tree showed the highest prediction among the chosen decision tree-based classifiers.
Conclusion: Therefore, the overall bagged tree showed the best performance for the prediction of IPCs of nanovesicles, suggesting the applicability of AI-based prediction approach in diagnosis and prognosis of pathological conditions, including non-invasive liquid biopsy via various biofluids-derived nano-vesicles.
Keywords: Nano-vesicles, exosome, diagnosis, initiating parent cells, machine learning, artificial intelligence.
[http://dx.doi.org/10.2147/OPTH.S2151] [PMID: 19668732]
[http://dx.doi.org/10.1371/journal.pone.0004160] [PMID: 19129916]
[http://dx.doi.org/10.1021/pr400751k] [PMID: 24400796]
[http://dx.doi.org/10.1016/j.biopha.2018.02.067] [PMID: 29494958]
[http://dx.doi.org/10.1007/s11095-008-9661-9] [PMID: 18626751]
[http://dx.doi.org/10.2147/vhrm.2006.2.3.213] [PMID: 17326328]
[http://dx.doi.org/10.1161/01.RES.0000259593.07661.1e] [PMID: 17395884]
[http://dx.doi.org/10.1186/s12929-017-0357-5] [PMID: 28750629]
[http://dx.doi.org/10.7150/ijbs.15514] [PMID: 27994512]
[http://dx.doi.org/10.1186/s12943-019-0963-9] [PMID: 30925917]
[http://dx.doi.org/10.1021/la2038763] [PMID: 22017459]
[http://dx.doi.org/10.3390/genes4020152] [PMID: 24705158]
[http://dx.doi.org/10.3402/jev.v5.32945] [PMID: 27802845]
[http://dx.doi.org/10.1038/s41598-018-34753-5] [PMID: 30401894]
[http://dx.doi.org/10.1016/j.compind.2018.11.004]
[http://dx.doi.org/10.1021/acsnano.7b05503] [PMID: 29019651]
[http://dx.doi.org/10.1021/acs.jpcb.8b01646] [PMID: 29771528]
[http://dx.doi.org/10.1007/BF00994018]
[http://dx.doi.org/10.1007/BF00116251]
[http://dx.doi.org/10.1007/BF00058655]
[http://dx.doi.org/10.1084/jem.183.3.1161] [PMID: 8642258]
[http://dx.doi.org/10.3233/THC-151071] [PMID: 26409558]
[http://dx.doi.org/10.1186/s13578-019-0282-2] [PMID: 30815248]
[http://dx.doi.org/10.1186/s12964-019-0390-y] [PMID: 31291956]
[http://dx.doi.org/10.3390/ijms18061153] [PMID: 28555055]
[http://dx.doi.org/10.1021/acs.langmuir.5b01402] [PMID: 25970769]
[http://dx.doi.org/10.1186/s12951-018-0433-3] [PMID: 30612562]
[http://dx.doi.org/10.1039/C7LC00592J] [PMID: 28832692]