Predicting protein structure using hidden Markov models

By Kevin J. Karplus, Kimmen Sjölander, Christian Barrett, Melissa S. Cline, David Haussler, Richard Hughey, Liisa Holm, Christopher Sander. 1997

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

Learning generative models for protein fold families (2011, background): “These statistical patterns are often learned from multiple sequence alignments (MSA) and then encoded using probabilistic graphical models (e.g., [1, 2, 3, 4, 5]).”
Markovian Models for Sequential Data (2004, background): “Recently, HMMs have been applied to a variety of applications outside of speech recognition, such as handwriting recognition [26, 27, 28, 29, 30, 31, 32], pattern recognition in molecular biology [33, 34, 35, 36, 3], and fault-detection [37].”
Profile hidden Markov models (1998, methodology): “At CASP2 last year, HMM-based methods were among the techniques used by several of the most successful prediction groups (Di Francesco et al., 1997; Karplus et al., 1997; Levitt, 1997; Murzin and Bateman, 1997).”
ESyPred3D: Prediction of proteins 3D structures (2002, methodology): “For the target–template alignment step, most of them use PSI-BLAST (Altschul et al., 1997), PileUp (Wisconsin Package Version 9.1, Genetics Computer Group (GCG), Madison, Wisc.), ClustalW (Thompson et al., 1994), 3D-PSSM (Fischer et al., 1999), SAMT99 ( Karplus et al., 1997 ), or also the alignment ”
Finding and Leveraging Structure in Learning Problems (2012, background): “, [109, 132]) and to design new protein sequences (e.”
PANTHER: a library of protein families and subfamilies indexed by function. (2003, methodology): “…using the Henikoff weighting scheme (Henikoff and Henikoff 1994), and given an absolute weight using the formula nseq (1 〈 Pmax〉 ), where nseq is the number of sequences in an alignment and 〈 Pmax 〉 is the average probability for the most common amino acid at each position (Karplus et al. 1997).”
Hidden Markov models for detecting remote protein homologies (1998, methodology): “For example, in the scoring for the CASP-2 contest (Karplus et al., 1997), we had to eliminate by hand some coiled-coil models that scored any helical protein well|the reversedmodel scoring eliminates these problems.”
A Discriminative Framework for Detecting Remote Protein Homologies (2000, methodology): “Considerable recent work has been done in refining HMMs for the purpose of identifying weak protein homologies in this way [34, 5, 14, 24, 33].”
Integrating model simulation tools and cryo‐electron microscopy (2022, methodology): “First, α-helical regions are predicted in the density map and in the protein sequence using a consensus of jufo,(82,83) psipred,(84) and sam.(85,86) Then, an in-house Monte Carlo assembly algorithm is used to place the predicted α helices into α-helical density rods of the density map.”