Prediction of contact maps by GIOHMMs and recurrent neural networks using lateral propagation from all four cardinal corners

By Gianluca Pollastri, Pierre Baldi. 2002

156 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Signal Processing

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 Computational Theory and Mathematics

In Signal Processing

Citations in the corpus

Improved Contact Predictions Using the Recognition of Protein Like Contact Patterns (2014, methodology): “utilize the information, that can be inferred from the structure of a contact map using advanced machine learning methods including deep learning approaches [22-26] or constraint satisfaction of rules describing protein like contacts maps using linear programming [27].”
Evaluation of residue-residue contact predictions in CASP9 (2011, neutral): “Although these numbers are higher than in the last CASP42 (22 and 14, respectively), according to the submitted abstracts, only very few prediction groups used new methods.”
EVA: evaluation of protein structure prediction servers (2003, background): “A number of servers predict contacts directly, using neural networks of different kinds trained on contact maps (10, 11 ).”
Learning to play Go using recursive neural networks (2008, background): “The basic architecture is closely related to an architecture originally proposed for a problem in a completely different area – the prediction of protein contact maps (Pollastri and Baldi, 2002; Baldi and Pollastri, 2003).”
Machine Learning Methods for Protein Structure Prediction (2008, background): “tecture [29] that in principle can use the entire sequence to derive”
SCRATCH: a protein structure and structural feature prediction server (2005, methodology): “CMAPpro : The contact map predictions are included as an attachment to the structural features email message.”
Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks (2014, methodology): “For that purpose we build an artificial neural network based on the 2D-RNN adaptive architecture, previously described in [17,39] and further outlined here in Methods and Additional file.”
Structural bioinformatics A machine learning information retrieval approach to protein fold recognition (2006, unknown): “These structural features for query proteins are predicted using the SCRATCH suite (Pollastri et al., 2001a, b; Pollastri and Baldi, 2002; Cheng et al., 2005; Cheng and Baldi, 2005; http://www.igb.uci.edu/ servers/psss.html).”
The Principled Design of Large-Scale Recursive Neural Network Architectures--DAG-RNNs and the Protein Structure Prediction Problem (2003, result): “…metrics for assessing contact map prediction remain to be developed, we have used here a variety of measures to address some of these problems and to allow comparisons with results published in the literature, especially Fariselli et al. (2001), Pollastri and Baldi (2002), Pollastri et al. (2003).”
Deep learning methods in protein structure prediction (2020, methodology): “2D-BRNN have been applied to predict contact maps [72,124,108,125], multi-class contact maps [29], and distance maps [96].”
Predicting protein residue-residue contacts using deep networks and boosting (2012, methodology): “The features we used for training our residue-residue contact predictors are consistent with those used by many other predictors (Cheng and Baldi, 2007; Li, et al., 2011; Pollastri and Baldi, 2002; Tegge, et al., 2009).”