To re-tune or not to re-tune: Comments on the flexible criterion

To tune or not to tune the number of trees in random forest?

The number of trees T in the random forest (RF) algorithm for supervised learning has to be set by the user. It is controversial whether T should simply be set to the largest computationally manageable value or whether a smaller T may in some cases be better. While the principle underlying bagging is that"more trees are better", in practice the classification error rate sometimes reaches a mini...

To tune or not to tune: Detecting orbital variability in Oligo-Miocene climate records

Transposable Elements Re-Wire and Fine-Tune the Transcriptome

What good are transposable elements (TEs)? Although their activity can be harmful to host genomes and can cause disease, they nevertheless represent an important source of genetic variation that has helped shape genomes. In this review, we examine the impact of TEs, collectively referred to as the mobilome, on the transcriptome. We explore how TEs-particularly retrotransposons-contribute to tra...

Re: Playing the old piano: another tune for endocrine therapy.

In 1896, George Thomas Beatson, a gentleman farmer and surgeon, reported his experience in treating three young women who had locally advanced breast cancer by removing their ovaries (1). All three of these women experienced a reduction in the size of their breast cancers; this result introduced the era of endocrine treatment for cancer. Beatson postulated that “there is some ovarian influence ...

To Re(label), or Not To Re(label)

One of the most popular uses of crowdsourcing is to provide training data for supervised machine learning algorithms. Since human annotators often make errors, requesters commonly ask multiple workers to label each example. But is this strategy always the most cost effective use of crowdsourced workers? We argue “No” — often classifiers can achieve higher accuracies when trained with noisy “uni...