Bayesian prediction of tissue-regulated splicing using RNA sequence and cellular context
By Hui Yuan Xiong, Yoseph Barash, Brendan J. Frey. 2011
101 citations recorded by the source corpus.
Subfields: Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Molecular Biology
- Brendan J. Frey
- Nitish Srivastava
- Leo J. Lee
- Hui Yuan Xiong
- Benjamin J. Blencowe
- Yoseph Barash
- Adrian R. Krainer
- Quaid D. Morris
Citations in the corpus
- A Bayesian encourages dropout (2014, background): “See, for example, (Neal, 1996; Xiong et al., 2011), which assigned Gaussian distribution to the weight matrices W s.”
- Artificial intelligence in oncology (2020, background): “Early studies adopted a naive Bayesian model, 55 but the advent of deep learning allowed the development of more complex models that have provided better predictive accuracy.”
- Deep Learning and Its Applications in Biomedicine (2018, methodology): “Frey et al. formulated the assembly of a splicing code as a statistical inference problem [158], and proposed a Bayesian method to predict tissue-regulated splicing using RNA sequences and cellular context.”
- Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights (2014, background): “The Monte Carlo approach [21] achieves state-of-the-art performance for small MNNs [26], but does not scale well [25].”
- The human splicing code reveals new insights into the genetic determinants of disease (2014, methodology): “Unlike existing methods (3, 11, 12), our computational model was derived using human data, incorporates over 300 new sequence features, and outputs realvalued absoluteC values for individual tissues, rather than categorical C values for tissue differences (13).”
- Dropout: a simple way to prevent neural networks from overfitting (2014, methodology): “Results were averaged across the same 5 folds used by Xiong et al. (2011).”
- Deep learning of the tissue-regulated splicing code (2014, methodology): “Our architecture uses hidden variables that jointly represent features in genomic sequences and tissue types when making predictions.”