On the Relationship of Protein and mRNA Dynamics in Vertebrate Embryonic Development

Abstract

A biochemical explanation of development from the fertilized egg to the adult requires an understanding of the proteins and RNAs expressed over time during embryogenesis. We present a comprehensive characterization of protein and mRNA dynamics across early development in Xenopus. Surprisingly, we find that most protein levels change little and duplicated genes are expressed similarly. While the correlation between protein and mRNA levels is poor, a mass action kinetics model parameterized using protein synthesis and degradation rates regresses protein dynamics to RNA dynamics, corrected for initial protein concentration. This study provides detailed data for absolute levels of ∼10,000 proteins and ∼28,000 transcripts via a convenient web portal, a rich resource for developmental biologists. It underscores the lasting impact of maternal dowry, finds surprisingly few cases where degradation alone drives a change in protein level, and highlights the importance of transcription in shaping the dynamics of the embryonic proteome.

Figure 1. Early Embryonic Stages in X. laevis

(A) mRNA and protein were collected from various stages of development. (B) The dataset combines temporal profiles of 27877 mRNA and 6509 proteins and egg concentration data for 9728 proteins. (C) A histogram of ∼8000 cosine distances between published and new mRNA profiles. Three sample mRNA profiles – Chordin, Tenascin N and Secernin are given as published (solid) and new RNA-Seq data (dashed). (D) A histogram of 35 cosine distances between published and new protein abundance changes. Three proteins quantified via Western blot (solid) and multiplexed proteomics (dashed) with representative cosine distances color coded.

Figure 2. Allo-alleles are Concordant in both Protein and mRNA Expression

(A) Peptides with a single amino-acid difference (red) used to distinguish the allo-alleles. (B) mRNA and protein expression in allo-alleles of DAPL1. (C) Histogram of cosine distance over temporal expression in 164 allo-allele pairs of proteins (left) and 630 pairs of mRNA (right). Median cosine distances are 0.006 and 0.04 respectively. Median Pearson correlations are 0.94 and 0.85 respectively. Cosine distance between protein and mRNA pair of DAPL1 profiles is 0.004 and 0.03 respectively, exemplifying the median discordance as shown by colored triangle positions. Gray histograms show the baseline distribution obtained by randomly re-matching allo-alleles. (D) Scatter plot of cumulative protein concentration for allo-alleles. Overall rank correlation between allo-alleles is 0.50.

Figure 3. Most Proteins Change Little in Level from Egg through Tailbud Stages

(A) K-means clustering of relative protein abundance into nine clusters using cosine distance, labeled by the number of proteins which fall into each cluster represented by the median curve. Thickness of the median line reflects the number of proteins in the cluster. (B) Histogram of protein dynamicity shows that most proteins do not change much within the surveyed period. The insert shows representative examples: flat (gray dashed line) TPI1 the triosephosphate Isomerase 1 is among the flattest possible with Δ = 1.0e-04. RPL11 (black) is at the median of the dynamicity distribution (Δ = 0.0162; 1 degree difference. OCM2 (a calmodulin) and one of the isoforms of hemoglobin zeta (HBZ), a form of alpha globin produced in the yolk sack of mammals are among the most dynamic (Δ = 0.571; 35 degrees difference) proteins. Color code: red for dynamic, black for flat. (C) Highly abundant proteins are generally flat, while low abundance proteins are mostly dynamic. Density plot of protein absolute concentration in the egg against dynamism. Black circles show two TPI1 (triosephosphate isomerase 1) which are very highly abundant (1 and 5 μM in the egg) while flat (Δ = 0.002 and 0.004) and red circles show positions of OCM2 (a calmodulin) and HBZ (hemoglobin zeta)- very dynamic (Δ of 0.47 and 0.52) low abundance genes (2 - 20 pM in the egg).

Figure 4. Temporal Expression of Tissue-specific proteins

(A) Histogram of tissue specificity over all measured proteins with the lowest and the highest 25% quantiles color-coded. Sample unspecific genes are elongation factors and proteosome while specific are myosin and creatine kinase. (B) Fraction of “non-Specific / Specific” proteins found in two most representative clusters.

Figure 5. Discordance of Temporal Patterns in mRNA and Protein Expression

(A) Rank correlation (Spearman) within developmental stage between protein and mRNA temporal patterns for ribo-depleted and poly-A enriched methods of mRNA measurement. (B) Histogram of Pearson correlation between protein and mRNA temporal change patterns. (C) Exemplary mRNA/protein time series. The ordinates represent relative concentration of protein to mRNA. Each plot shows estimated absolute concentration of mRNA and protein. (D) Mutual information between the temporal pattern of expression for mRNA and protein presented as co-clustering into three key trends. Grey scale background reflects the number of genes in each cluster. The left column illustrates that a flat protein pattern may correspond to any mRNA pattern, but if the protein is dynamic, it usually follows respective change in the mRNA concentration – see top of the right column for induction. Criss-cross patterns of anti-correlation are rarely observed – bottom of the right column.

Figure 6. Mass-action Kinetics Equation Results in a Plausible Model of Embryonic Protein Economy

(A) Robust fitting of solution to the equation $\frac{dp}{dt}={\mathrm{K}}_{\mathrm{S}}\mathrm{r}(\mathrm{t})-{\mathrm{K}}_{\mathrm{D}}\mathrm{p}(\mathrm{t})$ is done by searching a combination of synthesis and degradation rates minimizing the mean square difference in protein level (see equation above the plot). Beige stripe shows 95% confidence band for protein dynamics which corresponds to the 95% confidence range in synthesis and degradation rates. This region includes actual protein measurements marked via green discs. The no-degradation model is selected. (B) Venn diagram of models of different complexity. (C) Histograms of half-life (left) and synthesis rate (right). Half-life is given in hours, while synthesis rate in moles of protein synthesized per mole of mRNA per hour. (D) Histogram of Pearson correlation for model-based vs measured protein expression for a model assuming median synthesis and median degradation rates while using the actual initial concentration.

Figure 7. Embryonic protein economy

expressed as gradual replacement of maternal by zygotic protein, integrated over all proteins fitted by our model and extrapolated to the whole embryo.