Read a pdcBD PQR coordinate file.

read.pdcBD(file, maxlines = 50000, multi = FALSE, rm.insert = FALSE,
         rm.alt = TRUE, verbose = TRUE)

Arguments

file

the name of the pdcBD PQR file to be read.

maxlines

the maximum number of lines to read before giving up with large files. Default is 50,000 lines.

multi

logical, if TRUE multiple ATOM records are read for all models in multi-model files.

rm.insert

logical, if TRUE PDB insert records are ignored.

rm.alt

logical, if TRUE PDB alternate records are ignored.

verbose

print details of the reading process.

Details

maxlines may require increasing for some large multi-model files. The preferred means of reading such data is via binary DCD format trajectory files (see the read.dcd function).

Value

Returns a list of class "pdb" with the following components:

atom

a character matrix containing all atomic coordinate ATOM data, with a row per ATOM and a column per record type. See below for details of the record type naming convention (useful for accessing columns).

het

a character matrix containing atomic coordinate records for atoms within “non-standard” HET groups (see atom).

helix

‘start’, ‘end’ and ‘length’ of H type sse, where start and end are residue numbers “resno”.

sheet

‘start’, ‘end’ and ‘length’ of E type sse, where start and end are residue numbers “resno”.

seqres

sequence from SEQRES field.

xyz

a numeric vector of ATOM coordinate data.

calpha

logical vector with length equal to nrow(atom) with TRUE values indicating a C-alpha “elety”.

References

Grant, B.J. et al. (2006) Bioinformatics 22, 2695--2696.

For a description of PDB format (version3.3) see:
http://www.wwpdb.org/documentation/format33/v3.3.html.

Author

Barry Grant

Note

For both atom and het list components the column names can be used as a convenient means of data access, namely: Atom serial number “eleno” , Atom type “elety”, Alternate location indicator “alt”, Residue name “resid”, Chain identifier “chain”, Residue sequence number “resno”, Code for insertion of residues “insert”, Orthogonal coordinates “x”, Orthogonal coordinates “y”, Orthogonal coordinates “z”, Occupancy “o”, and Temperature factor “b”. See examples for further details.

See also

atom.select, write.pdb, read.dcd, read.fasta.pdb, read.fasta

Examples

# \donttest{ # PDB server connection required - testing excluded # Read a PDB file pdb <- read.pdb( "1bg2" )
#> Note: Accessing on-line PDB file
#> Warning: /var/folders/xf/qznxnpf91vb1wm4xwgnbt0xr0000gn/T//Rtmp4WslmZ/1bg2.pdb exists. Skipping download
# Print data for the first atom pdb$atom[1,]
#> type eleno elety alt resid chain resno insert x y z o b #> 1 ATOM 1 N <NA> ASP A 3 <NA> 43.743 -2.106 39.408 1 100 #> segid elesy charge #> 1 <NA> N <NA>
# Look at the first het atom pdb$het[1,]
#> NULL
# Print some coordinate data pdb$atom[1:20, c("x","y","z")]
#> x y z #> 1 43.743 -2.106 39.408 #> 2 45.053 -2.661 39.856 #> 3 45.305 -2.401 41.340 #> 4 46.119 -3.083 41.957 #> 5 46.204 -2.067 39.034 #> 6 45.912 -2.039 37.542 #> 7 45.455 -3.066 36.993 #> 8 46.136 -0.978 36.920 #> 9 44.627 -1.402 41.903 #> 10 44.791 -1.079 43.319 #> 11 44.313 -2.242 44.183 #> 12 45.079 -2.800 44.969 #> 13 44.015 0.191 43.679 #> 14 44.010 0.584 45.160 #> 15 45.430 0.779 45.663 #> 16 43.202 1.850 45.351 #> 17 43.039 -2.590 44.037 #> 18 42.451 -3.691 44.790 #> 19 41.508 -4.495 43.904 #> 20 41.084 -5.588 44.275
# Print C-alpha coordinates (can also use 'atom.select') ##pdb$xyz[pdb$calpha, c("resid","x","y","z")] # Print SSE data (for helix and sheet) pdb$helix
#> $start #> #> 20 58 67 91 107 176 197 256 277 281 306 #> #> $end #> #> 25 65 74 95 122 191 203 269 279 288 321 #> #> $chain #> [1] "A" "A" "A" "A" "A" "A" "A" "A" "A" "A" "A" #> #> $type #> [1] "1" "1" "1" "1" "1" "1" "1" "1" "5" "1" "5" #>
pdb$sheet$start
#> #> 50 8 295 79 222 205 126 171 32 38 44 135 141 155 163
# Print SEQRES data pdb$seqres
#> A A A A A A A A A A A A A #> "MET" "ALA" "ASP" "LEU" "ALA" "GLU" "CYS" "ASN" "ILE" "LYS" "VAL" "MET" "CYS" #> A A A A A A A A A A A A A #> "ARG" "PHE" "ARG" "PRO" "LEU" "ASN" "GLU" "SER" "GLU" "VAL" "ASN" "ARG" "GLY" #> A A A A A A A A A A A A A #> "ASP" "LYS" "TYR" "ILE" "ALA" "LYS" "PHE" "GLN" "GLY" "GLU" "ASP" "THR" "VAL" #> A A A A A A A A A A A A A #> "VAL" "ILE" "ALA" "SER" "LYS" "PRO" "TYR" "ALA" "PHE" "ASP" "ARG" "VAL" "PHE" #> A A A A A A A A A A A A A #> "GLN" "SER" "SER" "THR" "SER" "GLN" "GLU" "GLN" "VAL" "TYR" "ASN" "ASP" "CYS" #> A A A A A A A A A A A A A #> "ALA" "LYS" "LYS" "ILE" "VAL" "LYS" "ASP" "VAL" "LEU" "GLU" "GLY" "TYR" "ASN" #> A A A A A A A A A A A A A #> "GLY" "THR" "ILE" "PHE" "ALA" "TYR" "GLY" "GLN" "THR" "SER" "SER" "GLY" "LYS" #> A A A A A A A A A A A A A #> "THR" "HIS" "THR" "MET" "GLU" "GLY" "LYS" "LEU" "HIS" "ASP" "PRO" "GLU" "GLY" #> A A A A A A A A A A A A A #> "MET" "GLY" "ILE" "ILE" "PRO" "ARG" "ILE" "VAL" "GLN" "ASP" "ILE" "PHE" "ASN" #> A A A A A A A A A A A A A #> "TYR" "ILE" "TYR" "SER" "MET" "ASP" "GLU" "ASN" "LEU" "GLU" "PHE" "HIS" "ILE" #> A A A A A A A A A A A A A #> "LYS" "VAL" "SER" "TYR" "PHE" "GLU" "ILE" "TYR" "LEU" "ASP" "LYS" "ILE" "ARG" #> A A A A A A A A A A A A A #> "ASP" "LEU" "LEU" "ASP" "VAL" "SER" "LYS" "THR" "ASN" "LEU" "SER" "VAL" "HIS" #> A A A A A A A A A A A A A #> "GLU" "ASP" "LYS" "ASN" "ARG" "VAL" "PRO" "TYR" "VAL" "LYS" "GLY" "CYS" "THR" #> A A A A A A A A A A A A A #> "GLU" "ARG" "PHE" "VAL" "CYS" "SER" "PRO" "ASP" "GLU" "VAL" "MET" "ASP" "THR" #> A A A A A A A A A A A A A #> "ILE" "ASP" "GLU" "GLY" "LYS" "SER" "ASN" "ARG" "HIS" "VAL" "ALA" "VAL" "THR" #> A A A A A A A A A A A A A #> "ASN" "MET" "ASN" "GLU" "HIS" "SER" "SER" "ARG" "SER" "HIS" "SER" "ILE" "PHE" #> A A A A A A A A A A A A A #> "LEU" "ILE" "ASN" "VAL" "LYS" "GLN" "GLU" "ASN" "THR" "GLN" "THR" "GLU" "GLN" #> A A A A A A A A A A A A A #> "LYS" "LEU" "SER" "GLY" "LYS" "LEU" "TYR" "LEU" "VAL" "ASP" "LEU" "ALA" "GLY" #> A A A A A A A A A A A A A #> "SER" "GLU" "LYS" "VAL" "SER" "LYS" "THR" "GLY" "ALA" "GLU" "GLY" "ALA" "VAL" #> A A A A A A A A A A A A A #> "LEU" "ASP" "GLU" "ALA" "LYS" "ASN" "ILE" "ASN" "LYS" "SER" "LEU" "SER" "ALA" #> A A A A A A A A A A A A A #> "LEU" "GLY" "ASN" "VAL" "ILE" "SER" "ALA" "LEU" "ALA" "GLU" "GLY" "SER" "THR" #> A A A A A A A A A A A A A #> "TYR" "VAL" "PRO" "TYR" "ARG" "ASP" "SER" "LYS" "MET" "THR" "ARG" "ILE" "LEU" #> A A A A A A A A A A A A A #> "GLN" "ASP" "SER" "LEU" "GLY" "GLY" "ASN" "CYS" "ARG" "THR" "THR" "ILE" "VAL" #> A A A A A A A A A A A A A #> "ILE" "CYS" "CYS" "SER" "PRO" "SER" "SER" "TYR" "ASN" "GLU" "SER" "GLU" "THR" #> A A A A A A A A A A A A A #> "LYS" "SER" "THR" "LEU" "LEU" "PHE" "GLY" "GLN" "ARG" "ALA" "LYS" "THR" "ILE"
# Renumber residues nums <- as.numeric(pdb$atom[,"resno"]) pdb$atom[,"resno"] <- nums - (nums[1] - 1) # Write out renumbered PDB file #write.pdb(pdb=pdb,file="eg.pdb") # }