process pdb before loading it (#17)

* add `process_pdb`

* update test data with haddock-related headers

* update dependencies

Cargo.toml

@@ -31,4 +31,5 @@ kd-tree = "0.6.0"
 clap = { version = "4.5", features = ["derive"] }
 nalgebra = "0.33.0"
 itertools = "0.13.0"
-pdb-handler = "0.1.0"
+pdb-handler = "0.1"
+tempfile = "3.12"

src/structure.rs

@@ -9,7 +9,9 @@ use rand::rngs::StdRng;
 use rand::seq::SliceRandom;
 use rand::SeedableRng;
 use std::fs::File;
-use std::io::Write;
+use std::io::BufReader;
+use std::io::Cursor;
+use std::io::{Read, Write};
 
 #[derive(Clone)]
 pub struct Bead {
@@ -564,11 +566,10 @@ pub fn get_atoms_from_resnumbers(pdb: &PDB, selection: &[isize]) -> Vec<Atom> {
 /// - Any warnings generated during parsing are discarded. If you need to handle warnings,
 ///   consider modifying the function to return them along with the PDB structure.
 pub fn load_pdb(input_pdb: &str) -> Result<PDB, Vec<PDBError>> {
-    // Pad lines before reading the PDB file
-    let padded_reader = pdb_handler::pad_lines(input_pdb);
+    let processed_buf = process_pdb(input_pdb);
 
     let pdb = pdbtbx::open_pdb_raw(
-        padded_reader,
+        processed_buf,
         pdbtbx::Context::None,
         pdbtbx::StrictnessLevel::Loose,
     );
@@ -579,10 +580,53 @@ pub fn load_pdb(input_pdb: &str) -> Result<PDB, Vec<PDBError>> {
     }
 }
 
+/// Processes a PDB file by removing remarks and padding specific lines.
+///
+/// This function performs two operations on the input PDB file:
+/// 1. Removes all lines that start with "REMARK".
+/// 2. Pads lines starting with "ATOM" to a length of 80 characters.
+///
+/// # Arguments
+///
+/// * `input_pdb` - A string slice that holds the path to the input PDB file.
+///
+/// # Returns
+///
+/// A `BufReader<Cursor<Vec<u8>>>` containing the processed PDB content.
+///
+/// # Errors
+///
+/// This function will panic if:
+/// - The input file cannot be read.
+/// - A temporary file cannot be created or written to.
+/// - The `remove_remark` or `pad_lines` functions fail.
+///
+pub fn process_pdb(input_pdb: &str) -> BufReader<Cursor<Vec<u8>>> {
+    // Remove remarks from the PDB file
+    let no_remarks = pdb_handler::remove_remark(input_pdb);
+
+    // Convert the bufreader to a string
+    let mut content = String::new();
+    no_remarks
+        .into_inner()
+        .read_to_string(&mut content)
+        .unwrap();
+
+    let mut temp_file = tempfile::NamedTempFile::new().unwrap();
+
+    // Write the content to the temporary file
+    temp_file.write_all(content.as_bytes()).unwrap();
+    let temp_path = temp_file.path().to_str().unwrap();
+
+    // Pad lines before reading the PDB file
+    pdb_handler::pad_lines(temp_path)
+}
+
 #[cfg(test)]
 mod tests {
 
     use std::env;
+    use std::io::BufRead;
 
     use super::*;
 
@@ -625,4 +669,20 @@ mod tests {
         let pdb = load_pdb(pdb_path.to_str().unwrap()).unwrap();
         assert_eq!(pdb.atoms().count(), 8);
     }
+
+    #[test]
+    fn test_process_pdb() {
+        let processed_buf = process_pdb("tests/data/remark_short_lines.pdb");
+
+        let lines: Vec<String> = processed_buf.lines().map(|l| l.unwrap()).collect();
+
+        // Check that there are no REMARK lines
+        assert!(lines.iter().all(|line| !line.starts_with("REMARK")));
+
+        // Check that all ATOM lines are 80 characters long
+        assert!(lines
+            .iter()
+            .filter(|line| line.starts_with("ATOM"))
+            .all(|line| line.len() == 80));
+    }
 }

tests/data/complex.pdb

@@ -1,3 +1,48 @@
+REMARK FILENAME="emscoring_1.pdb"
+REMARK ===============================================================
+REMARK HADDOCK stats for emscoring_1.pdb
+REMARK ===============================================================
+REMARK HADDOCK score: -54.1511
+REMARK ===============================================================
+REMARK initial structure 1 - ../0_topoaa/complexyrrk72_y_haddock.pdb
+REMARK ===============================================================
+REMARK            total,bonds,angles,improper,dihe,vdw,elec,air,cdih,coup,rdcs,vean,dani,xpcs,rg
+REMARK energies: -106.18, 0, 0, 0, 0, -30.4344, -75.7457, 0, 0, 0, 0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK            bonds,angles,impropers,dihe,air,cdih,coup,rdcs,vean,dani,xpcs
+REMARK rms-dev.: 0,0,0,0,0,0,0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK               air,cdih,coup,rdcs,vean,dani,xpcs
+REMARK               >0.3,>5,>1,>0,>5,>0.2,>0.2
+REMARK violations.: 0, 0, 0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK                        CVpartition#,violations,rms
+REMARK AIRs cross-validation: 0, 0, 0
+REMARK ===============================================================
+REMARK NCS energy: 0
+REMARK ===============================================================
+REMARK Symmetry energy: 0
+REMARK ===============================================================
+REMARK Membrane restraining energy: 0
+REMARK ===============================================================
+REMARK Local cross-correlation:  0.0000
+REMARK ===============================================================
+REMARK Desolvation energy: -8.56748
+REMARK Internal energy free molecules: -4515.85
+REMARK Internal energy complex: -4364.86
+REMARK Binding energy: 36.2429
+REMARK ===============================================================
+REMARK buried surface area: 802.679
+REMARK ===============================================================
+REMARK Total HADDOCK score without restraints: -54.1511
+REMARK ===============================================================
+REMARK water - chain-A: 0 0 0
+REMARK water - chain-B: 0 0 0
+REMARK ===============================================================
+REMARK water - water: 0 0 0
+REMARK ===============================================================
+REMARK DATE:22-Aug-2024  15:23:46       created by user: unknown
+REMARK VERSION:1.3U
 ATOM      1  N   LEU A 929      26.117  -5.693  15.769  1.00 29.81           N
 ATOM      2  CA  LEU A 929      27.153  -4.857  15.061  1.00 29.93           C
 ATOM      3  C   LEU A 929      26.486  -3.835  14.143  1.00 29.74           C

tests/data/remark_short_lines.pdb

@@ -0,0 +1,53 @@
+REMARK FILENAME="emscoring_1.pdb"
+REMARK ===============================================================
+REMARK HADDOCK stats for emscoring_1.pdb
+REMARK ===============================================================
+REMARK HADDOCK score: -54.1511
+REMARK ===============================================================
+REMARK initial structure 1 - ../0_topoaa/complexyrrk72_y_haddock.pdb
+REMARK ===============================================================
+REMARK            total,bonds,angles,improper,dihe,vdw,elec,air,cdih,coup,rdcs,vean,dani,xpcs,rg
+REMARK energies: -106.18, 0, 0, 0, 0, -30.4344, -75.7457, 0, 0, 0, 0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK            bonds,angles,impropers,dihe,air,cdih,coup,rdcs,vean,dani,xpcs
+REMARK rms-dev.: 0,0,0,0,0,0,0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK               air,cdih,coup,rdcs,vean,dani,xpcs
+REMARK               >0.3,>5,>1,>0,>5,>0.2,>0.2
+REMARK violations.: 0, 0, 0, 0, 0, 0, 0
+REMARK ===============================================================
+REMARK                        CVpartition#,violations,rms
+REMARK AIRs cross-validation: 0, 0, 0
+REMARK ===============================================================
+REMARK NCS energy: 0
+REMARK ===============================================================
+REMARK Symmetry energy: 0
+REMARK ===============================================================
+REMARK Membrane restraining energy: 0
+REMARK ===============================================================
+REMARK Local cross-correlation:  0.0000
+REMARK ===============================================================
+REMARK Desolvation energy: -8.56748
+REMARK Internal energy free molecules: -4515.85
+REMARK Internal energy complex: -4364.86
+REMARK Binding energy: 36.2429
+REMARK ===============================================================
+REMARK buried surface area: 802.679
+REMARK ===============================================================
+REMARK Total HADDOCK score without restraints: -54.1511
+REMARK ===============================================================
+REMARK water - chain-A: 0 0 0
+REMARK water - chain-B: 0 0 0
+REMARK ===============================================================
+REMARK water - water: 0 0 0
+REMARK ===============================================================
+REMARK DATE:22-Aug-2024  15:23:46       created by user: unknown
+REMARK VERSION:1.3U
+ATOM      1  N   LEU A 929      26.117  -5.693  15.769  1.00 29.81      A
+ATOM      2  CA  LEU A 929      27.153  -4.857  15.061  1.00 29.93      A
+ATOM      3  C   LEU A 929      26.486  -3.835  14.143  1.00 29.74      A
+ATOM      4  O   LEU A 929      26.790  -2.625  14.181  1.00 29.50      A
+ATOM      5  CB  LEU A 929      28.096  -5.742  14.248  1.00 30.37      A
+ATOM      6  CG  LEU A 929      29.617  -5.471  14.154  1.00 28.52      A
+ATOM      7  CD1 LEU A 929      30.109  -5.719  12.711  1.00 27.72      A
+ATOM      8  CD2 LEU A 929      30.111  -4.134  14.702  1.00 25.22      A