Bottom - Index of papers - Previous - Next - Paper in HTML - Abstract - CUBIC
| Title: | Neural networks for protein structure prediction: |
| Author: | Burkhard Rost |
| Quote: |
Neural networks have been applied to many pattern classification problems. Here, I reviewed applications to the problem of predicting protein structure from protein sequence. Initially, methods were designed as a ‘quick and dirty’ demonstration that artificial intelligence-based machines could solve real-life problems. At that stage, biologists typically reached higher levels of accuracy when using their expertise than computer scientists when using their machines. However, more thourough investigations enabled to include the information used by experts into neural network-based tools. Now, some tools are - on average - as accurate as the best experts; and experts using such tools often arrive at even more accurate predictions. Thus, several neural network-based methods have eventually contributed significantly to advancing the field of bio-informatics, and some are clearly influencing molecular biology.
Key words: prediction of protein structure and function; neural network applications; extraction of information learned by neural networks
List of outstanding questions: (xx) to add after consultation of editor
Top -
Index of papers -
Paper in HTML -
Abstract -
Paper as PDF -
Appendix -
CUBIC