PLUS: Predicting cancer metastasis potential based on positive and unlabeled learning

• Published in: PLoS computational biology Vol. 18; no. 3; p. e1009956
• Main Authors: Zhou, Junyi, Lu, Xiaoyu, Chang, Wennan, Wan, Changlin, Lu, Xiongbin, Zhang, Chi, Cao, Sha
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.03.2022; Public Library of Science (PLoS)
• Subjects: Algorithms; Breast cancer; Cancer; Classification; Computer applications; Datasets; Decision making; Diagnosis; Feature selection; Forecasts and trends; Gene expression; Gene sequencing; Genomes; Head & neck cancer; Humans; Labels; Learning; Lymphatic system; Machine learning; Medical prognosis; Medicine and Health Sciences; Metastases; Metastasis; MicroRNAs; Neoplasms; Patients; Power; Transcriptomics; Tumors; United States

Metastatic cancer accounts for over 90% of all cancer deaths, and evaluations of metastasis potential are vital for minimizing the metastasis-associated mortality and achieving optimal clinical decision-making. Computational assessment of metastasis potential based on large-scale transcriptomic canc...