Ryan Rifkin

TL;DR: It is demonstrated that medulloblastomas are molecularly distinct from other brain tumours including primitive neuroectodermal tumours, atypical teratoid/rhabdoid tumours (AT/RTs) and malignant gliomas, and it is shown that the clinical outcome of children with medullOBlastomas is highly predictable on the basis of the gene expression profiles of their tumours at diagnosis.

TL;DR: The results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

TL;DR: It is argued that a simple "one-vs-all" scheme is as accurate as any other approach, assuming that the underlying binary classifiers are well-tuned regularized classifiers such as support vector machines.

TL;DR: Conditions for generalization in terms of a precise stability property of the learning process are provided: when the training set is perturbed by deleting one example, the learned hypothesis does not change much.

TL;DR: This work obtained 190 samples from 14 tumor classes and generated a combined expression dataset containing 16063 genes for each of those samples, and performed multi-class classification by combining the outputs of binary classifiers.