Protein secondary structure prediction with a neural network

Journal Article · Sun Jan 01 00:00:00 EST 1989 · Proceedings of the National Academy of Sciences of the United States of America; (United States)

DOI:https://doi.org/10.1073/pnas.86.1.152· OSTI ID:5954329

Holley, L H; Karplus, M ^[1]

---

1. Harvard Univ., Cambridge, MA (United States)

A method is presented for protein secondary structure prediction based on a neural network. A training phase was used to teach the network to recognize the relation between secondary structure and amino acid sequences on a sample set of 48 proteins of known structure. On a separate test set of 14 proteins of known structure, the method achieved a maximum overall predictive accuracy of 63% for three states: helix, sheet, and coil. A numerical measure of helix and sheet tendency for each residue was obtained from the calculations. When predictions were filtered to include only the strongest 31% of predictions, the predictive accuracy rose to 79%.

• OSTI ID: 5954329
• Journal Information: Proceedings of the National Academy of Sciences of the United States of America; (United States), Vol. 86; ISSN 0027-8424
• Country of Publication: United States
• Language: English

Related Subjects

37 INORGANIC
ORGANIC
PHYSICAL AND ANALYTICAL CHEMISTRY
PROTEINS
MOLECULAR STRUCTURE
AMINO ACID SEQUENCE
CONFORMATIONAL CHANGES
HELICAL CONFIGURATION
MATHEMATICAL MODELS
NEURAL NETWORKS
THEORETICAL DATA
CONFIGURATION
DATA
INFORMATION
NUMERICAL DATA
ORGANIC COMPOUNDS
400201* - Chemical & Physicochemical Properties