Structural bioinformatics A machine learning information retrieval approach to protein fold recognition

By Jianlin Cheng, Pierre Baldi. 2006

234 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, 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 Computational Theory and Mathematics

1. Yang Zhang
2. Jianlin Cheng
3. Taeho C. Jo
4. Badri Adhikari
5. Jie Hou
6. Sitao Wu
7. Yaoqi Zhou
8. Sheng Wang

In Molecular Biology

1. Jianlin Cheng
2. Yang Zhang
3. Jinbo Xu
4. Sheng Wang
5. Badri Adhikari
6. Jie Hou
7. Sitao Wu
8. Yaoqi Zhou

Citations in the corpus

• DeepSF: deep convolutional neural network for mapping protein sequences to folds (2017, methodology): “To work around the problem, another kind of machine learning methods (Cheng and Baldi, 2006; Jo and Cheng, 2014; Jo et al., 2015) converts a multi-fold classification problem into a binary classification problem to predict if a target protein and a template protein share the same fold based on their”
• MUSTER: Improving protein sequence profile–profile alignments by using multiple sources of structure information (2008, methodology): “4–6 There have been a number of threading algorithms in literature based on various approaches, for example the sequence profile–profile alignment,7–14 structural profile alignment,15–17 hidden Markov models,18–20 machine learning,21,22 and pair-wise potentials with optimal searching.”
• SP5: Improving Protein Fold Recognition by Using Torsion Angle Profiles and Profile-Based Gap Penalty Model (2008, methodology): “[48], respectively.”
• Machine Learning Methods for Protein Structure Prediction (2008, background): “More recently, a general machine learning framework has been proposed to improve both the sensitivity and specificity of fold recognition based on pairwise similarity features between query and template proteins [88].”
• CMsearch: simultaneous exploration of protein sequence space and structure space improves not only protein homology detection but also protein structure prediction (2016, methodology): “These methods can either rely on sequences only or employ structure features as well, where the latter is also called threading (Cheng and Baldi, 2006; Jo et al., 2015; Karplus et al., 1998; Wang et al., 2012a,b; Wu and Zhang, 2008).”
• Evaluating the absolute quality of a single protein model using structural features and support vector machines (2009, unknown): “42.”
• Improving protein fold recognition by random forest (2014, methodology): “Recognizing a known structure that is similar to the unknown structure (i.e. fold recognition) is an important step of the template-based protein structure modeling approach that uses the known structure as a template to construct a structural model for the target protein [4,5].”
• A new taxonomy-based protein fold recognition approach based on autocross-covariance transformation (2009, methodology): “methods The taxonomic fold recognition methods construct classifiers to discriminate the correct folds of proteins while the threading methods, such as RAPTOR (Xu, 2005; Xu et al., 2003), HHPred (Soding et al., 2005), FOLDPro (Cheng and Baldi, 2006) and SP3/SP5 (Zhang et al., 2008), use the sequence”
• Progress and challenges in protein structure prediction. (2008, methodology): “Numerous algorithms have been developed during the past 15 years for the purpose of identifying structure templates from the PDB, which use techniques including sequence profile–profile alignments (PPAs) [10–13], structural profile alignments [14], hidden Markov models (HMMs) [15,16 ], machine learn”