Widespread aggregation and neurodegenerative diseases are associated with supersaturated proteins

Abstract

The maintenance of protein solubility is a fundamental aspect of cellular homeostasis because protein aggregation is associated with a wide variety of human diseases. Numerous proteins unrelated in sequence and structure, however, can misfold and aggregate, and widespread aggregation can occur in living systems under stress or aging. A crucial question in this context is why only certain proteins appear to aggregate readily in vivo, whereas others do not. We identify here the proteins most vulnerable to aggregation as those whose cellular concentrations are high relative to their solubilities. We find that these supersaturated proteins represent a metastable subproteome involved in pathological aggregation during stress and aging and are overrepresented in biochemical processes associated with neurodegenerative disorders. Consequently, such cellular processes become dysfunctional when the ability to keep intrinsically supersaturated proteins soluble is compromised. Thus, the simultaneous analysis of abundance and solubility can rationalize the diverse cellular pathologies linked to neurodegenerative diseases and aging.

Figure 1. Protein aggregation in vivo can occur through different routes

Proteins may misfold and aggregate as they emerge from the ribosome or when they unfold at least transiently from the native state. The proteins most at risk of aggregation are those whose concentration is high with respect to their solubility. We quantify this risk by defining the supersaturation σ_u and σ_f scores. The supersaturation score σ_u, which measures the tendency of proteins to aggregate from the unfolded state, is based on the Zyggregator score (Tartaglia et al., 2008) (Z_agg) and mRNA expression levels. The supersaturation score σ_f, which measures the tendency of proteins to aggregate from the folded state, is based on the structurally-corrected Zyggregator score (Tartaglia et al., 2008) $(Z_{\mathit{\text{agg}}}^{SC})$ and protein concentration.

Figure 2. Widespread protein aggregation is associated with high supersaturation scores

(a) Summary of the results for the different classes of aggregating proteins analyzed in this work. Results are given in terms of the increases in the supersaturation scores over the average value for the whole proteome or for an experimental lysate (“fold change”). We compared the supersaturation scores σ_f for: (b) the whole proteome and the human “amyloid proteins” in UniProt (UniProt Consortium, 2012), (c) the whole proteome and proteins that co-precipitate in amyloid plaques (Liao et al., 2004), (d) the whole proteome and proteins that co-precipitate in neurofibrillary tangles (Wang et al., 2005), (e) the whole lysate and proteins that co-precipitate in Lewy bodies (Xia et al., 2008), (f) the whole lysate and proteins that co-precipitate in artificial β-sheet protein aggregates (Olzscha et al.), (g) the whole proteome and proteins found to aggregate in C. elegans during aging (David et al., 2010; Reis-Rodrigues et al., 2012). Boxplots extend from the lower to the upper quartiles, with the internal lines refer to the median values. Whiskers range from the lowest to highest value data points within 150% of the interquartile ranges. The statistical significance was assessed by Wilcoxon/Mann-Whitney U test with the Bonferroni-corrected p-values (*p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001).

Figure 3. Biochemical processes associated with neurodegenerative diseases are highly enriched in supersaturated proteins

(a) List of the KEGG pathways (Kanehisa et al., 2010) identified here as significantly enriched (Bonferroni-corrected p-values) in proteins at or above the 95^th percentile of supersaturation (σ_u): (R) ribosome, (OP) oxidative phosphorylation, (PD) Parkinson’s disease, (HD) Huntington’s disease, (AD) Alzheimer’s disease, (CMC) cardiac muscle contraction, (PEcI) pathogenic E. coli infection, (Pr) proteasome; physiological and pathological pathways are shown in blue and red, respectively. (b,c) Test of the robustness of the significance of the enrichment of the KEGG pathways according to their supersaturation scores. Gaussian noise was introduced 100 independent times into the proteome scores at 50 different levels and plotted (1× = no noise) for: (b) physiological pathways, which are robust up to 28× (R), 8.8× (OP), 2.3× (CMC) and 1.2× (Pr), and (c) pathological pathways, which are robust up to 8.2× (PD), 6.2× (HD), 5.5× (AD) and 2.1× (PEcI). Error bars indicate interquartile ranges, green points indicate error levels below the p=0.05 significance (red dashed line) by the Wilcoxon/Mann-Whitney U test.

Figure 4. Supersaturated proteins are common to different neurodegenerative pathways

(a) Comparison of the σ_u scores for the proteome and the set of 76 proteins common among the Alzheimer’s, Parkinson’s, and Huntington’s KEGG pathways (Kanehisa et al., 2010); this set of proteins is denoted as ‘overlap’. (b) Comparison of the scores for the proteins in the Alzheimer’s, Parkinson’s, and Huntington’s pathways. Colors are assigned based on the division of the σ_u scores into deciles from low (green) to high (red).

Figure 5. Proteins that form complexes tend to be more supersaturated than the proteome as a whole

We compared the σ_f scores for: (a) the proteome and proteins involved in complexes, and (b) the nuclear proteome and proteins involved in nuclear complexes. Boxplots extend from the lower to the upper quartiles, with the internal lines refer to the median values. Whiskers range from the lowest to highest value data points within 150% of the interquartile ranges. The statistical significance was assessed by Wilcoxon/Mann-Whitney U test with the Bonferroni-corrected p-values (*p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001).

Figure 6. Supersaturated proteins are over-represented in the KEGG Alzheimer’s disease pathway

The KEGG pathway for Alzheimer’s disease (Kanehisa et al.) is curated from the literature and includes many proteins not directly associated with the disruption of the homeostasis of the Aβ peptide. Those proteins that are part of the overlap (see Fig. 4a) of the Alzheimer’s, Parkinson’s, and Huntington’s disease pathways are shown in bold. Approximately 65% of proteins in the Alzheimer’s pathway have high σ_u scores. Colors are assigned based on the division of the σ_u database into deciles from low (green) to high (red).