Sequence determinants of compaction in intrinsically disordered proteins

Abstract

Intrinsically disordered proteins (IDPs), which lack folded structure and are disordered under nondenaturing conditions, have been shown to perform important functions in a large number of cellular processes. These proteins have interesting structural properties that deviate from the random-coil-like behavior exhibited by chemically denatured proteins. In particular, IDPs are often observed to exhibit significant compaction. In this study, we have analyzed the hydrodynamic radii of a number of IDPs to investigate the sequence determinants of this compaction. Net charge and proline content are observed to be strongly correlated with increased hydrodynamic radii, suggesting that these are the dominant contributors to compaction. Hydrophobicity and secondary structure, on the other hand, appear to have negligible effects on compaction, which implies that the determinants of structure in folded and intrinsically disordered proteins are profoundly different. Finally, we observe that polyhistidine tags seem to increase IDP compaction, which suggests that these tags have significant perturbing effects and thus should be removed before any structural characterizations of IDPs. Using the relationships observed in this analysis, we have developed a sequence-based predictor of hydrodynamic radius for IDPs that shows substantial improvement over a simple model based upon chain length alone.

Figure 1

Number of residues versus R_h for 20 folded (solid squares), 27 chemically denatured (solid circles), and 32 intrinsically disordered (open diamonds) proteins.

Figure 2

(A) Correlation (r_aa) between the fractional content of each amino acid from each protein and R_rel. (B) Same as A, except that histidine residues present in a polyhistidine tag are considered separately (asterisk). Error bars were calculated with a bootstrapping procedure (see Methods). W and C are not shown because the number of these residues in the data set was very low.

Figure 3

Comparisons of R_rel for all proteins in the IDP data set to the fraction of polyhistidine tag residues (A), fraction of proline residues (B), absolute net charge (C), mean hydrophobicity (D), predicted fraction of helical residues (E), and predicted fraction of extended residues (F).

Figure 4

Number of residues versus R_h values measured with SEC (open circles) and PFG NMR (solid squares). The best-fit power-law scaling lines (Eq. 2) are shown for SEC measurements (upper line) and PFG NMR measurements (lower line).

Figure 5

Differences between experimentally determined R_h and $R_{\text{h}}^{\text{IDP}}$ predicted with the simple power-law model (solid bars) and the new sequence-based model (open bars) for all 32 IDPs in the data set.