Modeling RNA polymerase interaction in mitochondria of chordates

Abstract

Background: In previous work, we introduced a concept, a mathematical model and its computer realization that describe the interaction between bacterial and phage type RNA polymerases, protein factors, DNA and RNA secondary structures during transcription, including transcription initiation and termination. The model accurately reproduces changes of gene transcription level observed in polymerase sigma-subunit knockout and heat shock experiments in plant plastids. The corresponding computer program and a user guide are available at http://lab6.iitp.ru/en/rivals. Here we apply the model to the analysis of transcription and (partially) translation processes in the mitochondria of frog, rat and human. Notably, mitochondria possess only phage-type polymerases. We consider the entire mitochondrial genome so that our model allows RNA polymerases to complete more than one circle on the DNA strand.

Results: Our model of RNA polymerase interaction during transcription initiation and elongation accurately reproduces experimental data obtained for plastids. Moreover, it also reproduces evidence on bulk RNA concentrations and RNA half-lives in the mitochondria of frog, human with or without the MELAS mutation, and rat with normal (euthyroid) or hyposecretion of thyroid hormone (hypothyroid). The transcription characteristics predicted by the model include: (i) the fraction of polymerases terminating at a protein-dependent terminator in both directions (the terminator polarization), (ii) the binding intensities of the regulatory protein factor (mTERF) with the termination site and, (iii) the transcription initiation intensities (initiation frequencies) of all promoters in all five conditions (frog, healthy human, human with MELAS syndrome, healthy rat, and hypothyroid rat with aberrant mtDNA methylation). Using the model, absolute levels of all gene transcription can be inferred from an arbitrary array of the three transcription characteristics, whereas, for selected genes only relative RNA concentrations have been experimentally determined. Conversely, these characteristics and absolute transcription levels can be obtained using relative RNA concentrations and RNA half-lives known from various experimental studies. In this case, the "inverse problem" is solved with multi-objective optimization.

Conclusions: In this study, we demonstrate that our model accurately reproduces all relevant experimental data available for plant plastids, as well as the mitochondria of chordates. Using experimental data, the model is applied to estimate binding intensities of phage-type RNA polymerases to their promoters as well as predicting terminator characteristics, including polarization. In addition, one can predict characteristics of phage-type RNA polymerases and the transcription process that are difficult to measure directly, e.g., the association between the promoter's nucleotide composition and the intensity of polymerase binding. To illustrate the application of our model in functional predictions, we propose a possible mechanism for MELAS syndrome development in human involving a decrease of Phe-tRNA, Val-tRNA and rRNA concentrations in the cell. In addition, we describe how changes in methylation patterns of the mTERF binding site and three promoters in hypothyroid rat correlate with changes in intensities of the mTERF binding and transcription initiations. Finally, we introduce an auxiliary model to describe the interaction between polysomal mRNA and ribonucleases.

Figure 1

Mitochondrial genome of Xenopus laevis. The entire circular DNA is presented sequentially as four rows. Genes in the heavy strand (H-strand) are shown by green arrows, and genes in the light strand (L-strand) – by blue arrows. HSP1, HSP2 are two promoters in the H-strand. LSP1, LSP2A, LSP2B are three promoters in the L-strand. mTERF symbolizes a binding site of the protein factor mTERF acting as transcription terminator.

Figure 2

Mitochondrial genome of Homo sapiens. All symbols are the same as in Figure 1.

Figure 3

Mitochondrial genome of Rattus norvegicus. All symbols are the same as in Figure 1.

Figure 4

LSP1 promoter binding intensities plotted against time for three frog embryos. The LSP1 promoter binding intensities mostly increase in agreement with [19].

Figure 5

Transcription numbers predicted during 9 hours of modeled physical time.A, B, C – frog embryos 1, 2, 3; D – healthy human; E – human with the MELAS phenotype; F – euthyroid rat; G – hypothyroid rat. Genes on the heavy strand are in green, on the light strand – in blue. Shaded are mean values, not shaded – standard errors.