Estimating Dataset Size Requirements for Classifying DNA Microarray Data

By Sayan Mukherjee, Pablo Tamayo, Simon Rogers, Ryan M. Rifkin, Anna Engle, Colin Campbell, Todd R. Golub, Jill P. Mesirov. J. Comput. Biol., 2003

301 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/638ec084ada320715e757b375cacd0aa3a27d30f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Microarray data analysis: from disarray to consolidation and consensus (2006, methodology): “Of course, effective cross-validation requires an adequate sample size, and methods for estimating sample sizes for supervised classification studies have been develope”
Predicting sample size required for classification performance (2012, methodology): “Our proposed method is similar to that discussed in Mukherjee et al. with a couple of differences: 1) we conducted weighted curve fitting to favor future predictions; 2) we calculated the confidence interval for the fitted curve rather than fitting two additional curves for the lower and upper quart”
Pharmacogenomic predictor of sensitivity to preoperative chemotherapy with paclitaxel and fluorouracil, doxorubicin, and cyclophosphamide in breast cancer. (2006, unknown): “The steepness of this “learning curve” may help determine a reasonable sample size for predictor discovery.(21) Figure 2 shows the change in mean AAC as the classifier was developed from 20 to 100 cases in increments of 10.”
Why Is My Classifier Discriminatory? (2018, background): “Empirically, learning curves behave asymptotically as inverse power-law curves for diverse algorithms such as deep neural networks, support vector machines, and nearest-neighbor classifiers, even when model capacity is allowed to grow with n (Hestness et al., 2017; Mukherjee et al., 2003).”
Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis (2018, background): “…trained on a number of choice observations that is large enough to enable a su ﬃ ciently accurately learning of the underlying DGP, several approaches have been introduced in di ﬀ erent contexts and applications (Cho et al., 2015; Figueroa et al., 2012; Mukherjee et al., 2003; Sung et al., 2016).”
Revisiting Neural Scaling Laws in Language and Vision (2022, methodology): “This is, perhaps, the most commonly used model in the literature; see for instance [1, 13, 17, 19, 20, 22, 28, 30, 31].”
Predicting accuracy on large datasets from smaller pilot data (2018, methodology): “The power-law models used in this paper have been investigated many times in prior literature (Haussler et al., 1996; Mukherjee et al., 2003; Figueroa et al., 2012; Beleites et al., 2013; Hajian-Tilaki, 2014; Cho et al., 2015).”
Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022, background): “If some (closely related) data are already available, it has been suggested to inspect the model ’ s learning curve in that data, setting out prediction performance against the amount of used data, to estimate the required total sample size for a speci ﬁ c use case 47,51,52 .”