DNA length in protein-DNA complexes

Last updated on Sun Feb 11 22:55:10 2024.

How to re-use this work

If you use these figures in your own work, please cite this website: https://doi.org/10.5281/zenodo.3470119

Structures of protein-DNA complexes by experimental method

All figures are interactive (you can zoom in, and hovering over elements will show more information).

# Load required packages
library(magrittr)
library(jsonlite)
library(dplyr)
library(forcats)
library(stringr)
library(ggplot2)
library(plotly)
library(here)

# Query the PDB for all DNA molecules in crystal structures of protein-DNA
# complexes
pdb_query <- 'https://www.ebi.ac.uk/pdbe/search/pdb/select?q=molecule_type:%22DNA%22%20AND%20assembly_composition:%22DNA/protein%20complex%22&fl=pdb_id,molecule_sequence,experimental_method&rows=1000000&wt=json'

pdb_data <- pdb_query %>% 
    fromJSON() %>% 
    .$response %>% 
    .$docs %>% 
    as_tibble() %>% 
    distinct(pdb_id, .keep_all = TRUE) %>% 
    filter(experimental_method %in% c("X-ray diffraction",
                                      "Electron Microscopy",
                                      "Solution NMR")) %>% 
    mutate(dna_length = str_length(molecule_sequence),
           experimental_method = as_factor(as.character(experimental_method)))

# Summary statistics
protein_dna_cplx_structures <- ggplot(data = pdb_data) +
    geom_bar(mapping = aes(x = experimental_method)) +
    theme_bw() +
    xlab("") +
    ylab("Number of PDB entries") +
    ggtitle("Structures of protein-DNA complexes")
ggplotly(protein_dna_cplx_structures)

Download figure in SVG format

DNA length in crystal structures of protein-DNA complexes

Entire distribution

dna_length_xtal <- pdb_data %>% 
    filter(experimental_method == "X-ray diffraction") %>% 
    ggplot() +
    geom_histogram(mapping = aes(x = dna_length), binwidth = 1) +
    theme_bw() +
    ggtitle("DNA length in crystal structures of protein-DNA complexes") +
    xlab("DNA length (bp)") +
    ylab("Number of crystal structures")
ggplotly(dna_length_xtal)

Download figure in SVG format

0-150 bp range

dna_length_xtal_150 <- pdb_data %>% 
    filter(experimental_method == "X-ray diffraction" & dna_length < 151) %>% 
    ggplot() +
    geom_histogram(mapping = aes(x = dna_length), binwidth = 1) +
    theme_bw() +
    ggtitle("DNA length in crystal structures of protein-DNA complexes (0-150 bp)") +
    xlab("DNA length (bp)") +
    ylab("Number of crystal structures")
ggplotly(dna_length_xtal_150)

Download figure in SVG format

DNA length in cryo-EM structures of protein-DNA complexes

dna_length_cryoem <- pdb_data %>% 
    filter(experimental_method == "Electron Microscopy") %>% 
    ggplot() +
    geom_histogram(mapping = aes(x = dna_length), binwidth = 1) +
    theme_bw() +
    ggtitle("DNA length in cryo-EM structures of protein-DNA complexes") +
    xlab("DNA length (bp)") +
    ylab("Number of cryo-EM structures")
ggplotly(dna_length_cryoem)

Download figure in SVG format

DNA length in NMR structures of protein-DNA complexes

dna_length_nmr <- pdb_data %>% 
    filter(experimental_method == "Solution NMR") %>% 
    ggplot() +
    geom_histogram(mapping = aes(x = dna_length), binwidth = 1) +
    theme_bw() +
    ggtitle("DNA length in NMR structures of protein-DNA complexes") +
    xlab("DNA length (bp)") +
    ylab("Number of NMR structures")
ggplotly(dna_length_nmr)

Download figure in SVG format

Dataset

The histograms presented above are derived from the following dataset:

# Format table for display
pdb_table <- pdb_data %>% 
    arrange(desc(dna_length)) %>% 
    select(`PDB code` = pdb_id,
           `DNA length` = dna_length)
pdb_table

Download raw dataset in JSON format