Predicting the secondary structure of globular proteins using neural network models.

By Ning Qian, Terrence J. Sejnowski. 1988

How researchers see this paper

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

Citations in the corpus

Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction (2014, background): “…models (Schmidler et al., 2000; Chu et al., 2004; van der Maaten et al., 2011), or combination of neural network and graphical models, like conditional neural ﬁelds (CNF) which integrate a windows-based neural network with conditional random ﬁeld (CRF) (Peng et al., 2009; Wang et al., 2011).”
On the momentum term in gradient descent learning algorithms (1999, background): “It is interesting to note that in most simulations of connectionist learning algorithms, the p values were indeed chosen to be close to 1, typically around 0.9 (for examples see Rumelhart et al., 1986; Qian and Sejnowski, 1988, 1989 ).”
Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction (2017, background): “…to the protein secondary structure problem have a rich history: the use of neural networks for secondary structure prediction was pi-oneered by Qian and Sejnowski in 1988, and subsequent attempts using both recurrent (Sønderby & Winther, 2014; Li & Yu, 2016) and convolutional (Li & Yu, 2016;…”
A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models (2005, methodology): “NNs models are used to predict protein structures by Qian and Sejnowski (1988). Shang et al. (2000) used NNs and Regression to detect antibiotic-resistant pathogen infections in the US hospitals. The results obtained by Shang et al. are mixed; Regression model worked better for smaller test sets, ho”
A simple and fast secondary structure prediction method using hidden neural networks (2005, background): “Qian and Sejnowski (1988) introduced one of the earliest artificial neural network (NN)-based methods.”
Predicting Protein Secondary and Supersecondary Structure (2005, background): “Similar to [QS88], the output of this first level neural network is fed to a structureto-structure network.”
Prediction of proteasome cleavage motifs by neural networks. (2002, methodology): “Each amino acid is represented using 21 binary positions (conventional sparse encoding: Qian and Sejnowski, 1988; Hertz et al., 1991) in 21 input neurons.”
Artificial neural networks for computer-based molecular design. (1998, methodology): “A conventional three-layer bp-network and a data set of sequence pro®les instead of single sequences led to a higher prediction accuracy compared to the original work of Qian and Sejnowski (1988).”
A Unified Multitask Architecture for Predicting Local Protein Properties (2012, methodology): “Since the advent of the first automated secondary structure prediction method 22 years ago [5], dozens of subsequent methods have been described in the scientific literature.”
Predicting subcellular localization of proteins based on their N-terminal amino acid sequence. (2000, methodology): “First layer networks are implemented using the HOW package, (Brunak et al., 1991) with a logarithmic error function and sparsely encoded sliding windows for input data encoding (Qian & Sejnowski, 1988; Brunak et al., 1991).”
Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks (2014, methodology): “In the absence of a reliable solution to the protein structure prediction problem, some research groups have focused on solving simplified problems such as the prediction of protein structural features [12-14].”
Conditional models for contextual human motion recognition (2006, methodology): “CRFs and MEMMs are also related to ‘sliding window’ methods [ 37 ] that predict each state label of a sequence independently by classifying it based on a window of observations (forward and backward in time) centered at the current state.”