Assessing rejection-related disease in kidney transplant biopsies based on archetypal analysis of molecular phenotypes

ABSTRACT: Molecular phenotyping of biopsies affords opportunities for increased precision and improved disease classification to address the limitations of conventional histologic diagnostic systems. We applied archetypal analysis, an unsupervised method similar to cluster analysis, to microarray data from 1208 prospectively collected kidney transplant biopsies from 13 centers. Seven machine learning-generated cross-validated classifier scores per biopsy were used as input for the archetypal analysis. Six archetypes representing extreme phenotypes were generated: no rejection; T cell-mediated rejection (TCMR); three phenotypes associated with antibody-mediated rejection (ABMR) - early-stage, fully-developed, and late-stage; and mixed rejection (TCMR plus early-stage ABMR). Each biopsy was assigned s

ORGANISM(S): Homo sapiens

SUBMITTER: Jessica Chang 

PROVIDER: E-GEOD-98320 | biostudies-arrayexpress |

REPOSITORIES: biostudies-arrayexpress