Solving the protein sequence metric problem.

By W. Atchley, Jieping Zhao, Andrew D. Fernandes, Tanja Drüke. Proceedings of the National Academy of Sciences of the United States of America, 2005

460 citations recorded by the source corpus.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/d4452cb86ab6dc79e50f4fcf5bd0821d453a0e89

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

Citations in the corpus

SuSPect: Enhanced Prediction of Single Amino Acid Variant (SAV) Phenotype Using Network Features (2014, unknown): “[55] from the 494 amino acid indices in the Amino Acid Index [56].”
Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions (2017, methodology): “The inputs to these networks include information extracted from PSSM derived with PSI-BLAST, predicted solvent accessibility, predicted secondary structure, and Atchley factors [100].”
Deep learning in bioinformatics (2016, background): “In addition, extracted features from sequences such as a position specific scoring matrices (PSSM) [78], physicochemical properties [79, 80], Atchley factors [81] and one-dimensional structural properties [82, 83] are often used as inputs for deep learning algorithms to alleviate difficulties from c”
Modern Hopfield Networks and Attention for Immune Repertoire Classification (2020, methodology): “Each amino acid of each k-mer is represented by 5 features, the so-called Atchley factors (Atchley et al., 2005).”
HLA class I binding prediction via convolutional neural networks (2017, background): “Each of the 15 dimensions on their own have no explicit physic-ochemical interpretation, unlike in Atchley factors [Atchley et al ., 2005] or Kidera factors [Kidera et al ., 1985].”
Radiation and Dual Checkpoint Blockade Activates Non-Redundant Immune Mechanisms in Cancer (2015, unknown): “Based on previously described methods 15,16 , Atchley factors were used to reduce a linear sequence of amino acids into analyzable numeric features of distinct amino acid properties.”
A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction (2014, methodology): “We selected the input pro.les from three kinds of features: the amino acid residues themselves (RES), the PSSM information (PSSM), and the Atchley factors (FAC) [26].”
Predicting protein residue-residue contacts using deep networks and boosting (2012, background): “The Acthely factors are scaled representations of five numerical values which characterize a residue by electrostatic charge, codon diversity, volume, polarity and secondary structure (Atchley, et al., 2005).”