RNA


BIOINFORMATICSBIOINFORMATICS

Mining biochemical information: Lessons taught by the ribosome


MICHELLE  WHIRL-CARRILLO  a1, IRENE S.  GABASHVILI  a1, MICHAEL  BADA  a1, D. REY  BANATAO  a1 and RUSS B.  ALTMAN  a1 c1
a1 Stanford Medical Informatics, Stanford University, Stanford, California 94305-5479, USA

Abstract

The publication of the crystal structures of the ribosome offers an opportunity to retrospectively evaluate the information content of hundreds of qualitative biochemical and biophysical studies of these structures. We assessed the correspondence between more than 2,500 experimental proximity measurements and the distances observed in the ribosomal crystals. Although detailed experimental procedures and protocols are unique in almost each analyzed paper, the data can be grouped into subsets with similar patterns and analyzed in an integrative fashion. We found that, for crosslinking, footprinting, and cleavage data, the corresponding distances observed in crystal structures generally did not exceed the maximum values expected (from the estimated length of the agent and maximal anticipated deviations from the conformations found in crystals). However, the distribution of distances had heavier tails than those typically assumed when building three-dimensional models, and the fraction of incompatible distances was greater than expected. Some of these incompatibilities can be attributed to the experimental methods used. In addition, the accuracy of these procedures appears to be sensitive to the different reactivities, flexibilities, and interactions among the components. These findings demonstrate the necessity of a very careful analysis of data used for structural modeling and consideration of all possible parameters that could potentially influence the quality of measurements. We conclude that experimental proximity measurements can provide useful distance information for structural modeling, but with a broad distribution of inferred distance ranges. We also conclude that development of automated modeling approaches would benefit from better annotations of experimental data for detection and interpretation of their significance.

(Received June 29 2001)
(Revised July 20 2001)
(Accepted December 11 2001)


Key Words: bacterial ribosome; cleavage; crosslinking; crystal structure; footprinting; proximity measures; ribosomal proteins; ribosomal RNA.

Correspondence:
c1 Reprint requests to: Russ B. Altman, Stanford Medical Informatics, Stanford University, 251 Campus Drive, MSOB x-215, Stanford, California 94305-5479, USA; e-mail: altman@smi.stanford.edu.