Unsupervised machine learning reveals risk stratifying glioblastoma tumor cells
A goal of cancer research is to reveal cell subsets linked to continuous clinical outcomes to generate new therapeutic and biomarker hypotheses. We introduce a machine learning algorithm, Risk Assessment Population IDentification (RAPID), that is unsupervised and automated, identifies phenotypically...
Main Authors: | Nalin Leelatian, Justine Sinnaeve, Akshitkumar M Mistry, Sierra M Barone, Asa A Brockman, Kirsten E Diggins, Allison R Greenplate, Kyle D Weaver, Reid C Thompson, Lola B Chambless, Bret C Mobley, Rebecca A Ihrie, Jonathan M Irish |
---|---|
Format: | Article |
Language: | English |
Published: |
eLife Sciences Publications Ltd
2020-06-01
|
Series: | eLife |
Subjects: | |
Online Access: | https://elifesciences.org/articles/56879 |
Similar Items
-
661 Five immunotypic signatures identified in human glioblastoma correlate with tumor contact with the lateral ventricle, immune suppression, and patient outcome
by: Akshitkumar Mistry, et al.
Published: (2020-11-01) -
Glioblastoma Distance From the Subventricular Neural Stem Cell Niche Does Not Correlate With Survival
by: Akshitkumar M. Mistry, et al.
Published: (2020-12-01) -
Mutation Status and Epithelial Differentiation Stratify Recurrence Risk in Chordoid Meningioma—A Multicenter Study with High Prognostic Relevance
by: Maria-Magdalena Georgescu, et al.
Published: (2020-01-01) -
A Rare Case of Obturator Nerve Schwannoma Resembling Ovarian Malignancy: Learning from our Lesson
by: Suwanit Therasakvichaya, et al.
Published: (2018-10-01) -
Intelligent facial expression recognition with unsupervised facial point detection and evolutionary feature optimization
by: Mistry, Kamlesh
Published: (2016)