Pad lines before parsing pdb

Cargo.toml

@@ -31,3 +31,4 @@ kd-tree = "0.6.0"
 clap = { version = "4.5", features = ["derive"] }
 nalgebra = "0.33.0"
 itertools = "0.13.0"
+pdb-handler = "0.1.0"

src/interactor.rs

@@ -137,17 +137,14 @@ impl Interactor {
     ///
     /// # Dependencies
     ///
-    /// This method relies on external functions from the `pdbtbx` and `structure` modules:
-    /// - `pdbtbx::open_pdb`
+    /// This method relies on external functions from the `structure` module:
     /// - `structure::get_residues`
     /// - `structure::neighbor_search`
+    /// - `structure::load_pdb`
     ///
     pub fn set_passive_from_active(&mut self) {
-        match pdbtbx::open_pdb(
-            self.structure.clone().unwrap(),
-            pdbtbx::StrictnessLevel::Loose,
-        ) {
-            Ok((pdb, _warnings)) => {
+        match structure::load_pdb(self.structure.clone().unwrap().as_str()) {
+            Ok(pdb) => {
                 let residues = structure::get_residues(
                     &pdb,
                     self.active.iter().map(|x| *x as isize).collect(),
@@ -187,20 +184,17 @@ impl Interactor {
     ///
     /// # Dependencies
     ///
-    /// This method relies on external functions from the `pdbtbx` and `sasa` modules:
-    /// - `pdbtbx::open_pdb`
+    /// This method relies on external functions from the `sasa` and `structure` modules:
     /// - `sasa::calculate_sasa`
+    /// - `structure::load_pdb`
     ///
     /// # Note
     ///
     /// The threshold for considering a residue as "surface" is set to 0.7 relative SASA.
     /// This value may need to be adjusted based on specific requirements.
     pub fn set_surface_as_passive(&mut self) {
-        match pdbtbx::open_pdb(
-            self.structure.clone().unwrap(),
-            pdbtbx::StrictnessLevel::Loose,
-        ) {
-            Ok((pdb, _warnings)) => {
+        match structure::load_pdb(self.structure.clone().unwrap().as_str()) {
+            Ok(pdb) => {
                 let sasa = sasa::calculate_sasa(pdb.clone());
 
                 // Add these neighbors to the passive set
@@ -238,20 +232,17 @@ impl Interactor {
     ///
     /// # Dependencies
     ///
-    /// This method relies on external functions from the `pdbtbx` and `sasa` modules:
-    /// - `pdbtbx::open_pdb`
+    /// This method relies on external functions from the `sasa` and `structure` module:
     /// - `sasa::calculate_sasa`
+    /// - `structure::load_pdb`
     ///
     /// # Note
     ///
     /// The default threshold for considering a residue as "buried" is set to 0.7 relative SASA.
     /// This can be customized by setting the `filter_buried_cutoff` field of the `Interactor`.
     pub fn remove_buried_residues(&mut self) {
-        match pdbtbx::open_pdb(
-            self.structure.clone().unwrap(),
-            pdbtbx::StrictnessLevel::Loose,
-        ) {
-            Ok((pdb, _warnings)) => {
+        match structure::load_pdb(self.structure.clone().unwrap().as_str()) {
+            Ok(pdb) => {
                 let sasa = sasa::calculate_sasa(pdb.clone());
 
                 let sasa_cutoff = self.filter_buried_cutoff.unwrap_or(0.7);

src/main.rs

@@ -178,7 +178,7 @@ fn gen_tbl(input_file: &str) {
 ///
 /// # Arguments
 ///
-/// * `input_pdb` - A string slice that holds the path to the input PDB file.
+/// * `input_file` - A string slice that holds the path to the input PDB file.
 /// * `cutoff` - A reference to a f64 value specifying the distance cutoff (in Angstroms) for determining interfaces.
 ///
 /// # Returns
@@ -213,9 +213,10 @@ fn gen_tbl(input_file: &str) {
 /// - `structure::get_true_interface` and `structure::get_chains_in_contact` for interface analysis.
 /// - `Interactor` struct for representing protein chains and their interactions.
 /// - `Air` struct for generating the AIR table.
-fn true_interface(input_pdb: &str, cutoff: &f64) -> Result<(), Box<dyn Error>> {
-    let pdb = match pdbtbx::open_pdb(input_pdb, pdbtbx::StrictnessLevel::Loose) {
-        Ok((pdb, _warnings)) => pdb,
+fn true_interface(input_file: &str, cutoff: &f64) -> Result<(), Box<dyn Error>> {
+    // Read PDB file
+    let pdb = match structure::load_pdb(input_file) {
+        Ok(pdb) => pdb,
         Err(e) => {
             panic!("Error opening PDB file: {:?}", e);
         }
@@ -307,8 +308,8 @@ fn true_interface(input_pdb: &str, cutoff: &f64) -> Result<(), Box<dyn Error>> {
 /// - `Air` struct for generating the AIR table.
 fn restraint_bodies(input_file: &str) -> Result<(), Box<dyn Error>> {
     // Read PDB file
-    let pdb = match pdbtbx::open_pdb(input_file, pdbtbx::StrictnessLevel::Loose) {
-        Ok((pdb, _warnings)) => pdb,
+    let pdb = match structure::load_pdb(input_file) {
+        Ok(pdb) => pdb,
         Err(e) => {
             panic!("Error opening PDB file: {:?}", e);
         }
@@ -404,8 +405,8 @@ fn restraint_bodies(input_file: &str) -> Result<(), Box<dyn Error>> {
 /// - `pdbtbx` for opening and parsing PDB files.
 /// - `structure::get_true_interface` for identifying interface residues.
 fn list_interface(input_file: &str, cutoff: &f64) -> Result<(), Box<dyn Error>> {
-    let pdb = match pdbtbx::open_pdb(input_file, pdbtbx::StrictnessLevel::Loose) {
-        Ok((pdb, _warnings)) => pdb,
+    let pdb = match structure::load_pdb(input_file) {
+        Ok(pdb) => pdb,
         Err(e) => {
             panic!("Error opening PDB file: {:?}", e);
         }
@@ -430,8 +431,8 @@ fn generate_z_restraints(
     grid_size: &usize,
     grid_spacing: &f64,
 ) -> Result<(), Box<dyn Error>> {
-    let pdb = match pdbtbx::open_pdb(input_file, pdbtbx::StrictnessLevel::Loose) {
-        Ok((pdb, _warnings)) => pdb,
+    let pdb = match structure::load_pdb(input_file) {
+        Ok(pdb) => pdb,
         Err(e) => {
             panic!("Error opening PDB file: {:?}", e);
         }

src/sasa.rs

@@ -564,17 +564,15 @@ pub const REL_ASA: &[(&str, AsaValues)] = &[
 #[cfg(test)]
 mod test {
 
+    use crate::structure;
+
     use super::*;
-    use std::env;
 
     // TODO: Add more tests
 
     #[test]
     fn test_calculate_sasa() {
-        let pdb_path = env::current_dir().unwrap().join("tests/data/complex.pdb");
-        let pdb = pdbtbx::open_pdb(pdb_path.to_str().unwrap(), pdbtbx::StrictnessLevel::Loose)
-            .unwrap()
-            .0;
+        let pdb = structure::load_pdb("tests/data/complex.pdb").unwrap();
         let extended_residues = calculate_sasa(pdb);
 
         assert_eq!(extended_residues.len(), 116);

src/structure.rs

@@ -3,8 +3,8 @@ use std::collections::{HashMap, HashSet};
 use itertools::Itertools;
 use kd_tree::KdTree;
 use nalgebra::Vector3;
-use pdbtbx::Residue;
 use pdbtbx::{Atom, PDB};
+use pdbtbx::{PDBError, Residue};
 use rand::rngs::StdRng;
 use rand::seq::SliceRandom;
 use rand::SeedableRng;
@@ -543,6 +543,42 @@ pub fn get_atoms_from_resnumbers(pdb: &PDB, selection: &[isize]) -> Vec<Atom> {
         .collect()
 }
 
+/// Loads a PDB (Protein Data Bank) file from a file path.
+///
+/// This function takes a PDB file content as a string, pads the lines,
+/// and then attempts to parse it into a PDB structure using the pdbtbx library.
+///
+/// # Arguments
+///
+/// * `input_pdb` - A string slice containing the file path of a PDB file.
+///
+/// # Returns
+///
+/// * `Result<PDB, Vec<PDBError>>` - On success, returns the parsed PDB structure.
+///   On failure, returns a vector of PDBError describing what went wrong during parsing.
+///
+/// # Notes
+///
+/// - This function uses `pdb_handler::pad_lines` to preprocess the input string.
+/// - The PDB is parsed with `pdbtbx::StrictnessLevel::Loose` to allow for some flexibility in the input format.
+/// - 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 pdb = pdbtbx::open_pdb_raw(
+        padded_reader,
+        pdbtbx::Context::None,
+        pdbtbx::StrictnessLevel::Loose,
+    );
+
+    match pdb {
+        Ok((pdb, _)) => Ok(pdb),
+        Err(e) => Err(e),
+    }
+}
+
 #[cfg(test)]
 mod tests {
 
@@ -552,11 +588,7 @@ mod tests {
 
     #[test]
     fn test_get_true_interface() {
-        let pdb_path = env::current_dir().unwrap().join("tests/data/complex.pdb");
-
-        let pdb = pdbtbx::open_pdb(pdb_path.to_str().unwrap(), pdbtbx::StrictnessLevel::Loose)
-            .unwrap()
-            .0;
+        let pdb = load_pdb("tests/data/complex.pdb").unwrap();
 
         let observed_true_interface = get_true_interface(&pdb, 5.0);
 
@@ -575,4 +607,22 @@ mod tests {
 
         assert_eq!(observed_true_interface, expected_true_interface);
     }
+
+    #[test]
+    fn test_load_pdb_short_lines() {
+        let pdb_path = env::current_dir()
+            .unwrap()
+            .join("tests/data/leu_short_lines.pdb");
+        let pdb = load_pdb(pdb_path.to_str().unwrap()).unwrap();
+        assert_eq!(pdb.atoms().count(), 8);
+    }
+
+    #[test]
+    fn test_load_pdb_normal_lines() {
+        let pdb_path = env::current_dir()
+            .unwrap()
+            .join("tests/data/leu_normal_lines.pdb");
+        let pdb = load_pdb(pdb_path.to_str().unwrap()).unwrap();
+        assert_eq!(pdb.atoms().count(), 8);
+    }
 }

tests/data/leu_normal_lines.pdb

@@ -0,0 +1,8 @@
+ATOM      1  N   LEU A 929      26.117  -5.693  15.769  1.00 29.81      A    N
+ATOM      2  CA  LEU A 929      27.153  -4.857  15.061  1.00 29.93      A    C
+ATOM      3  C   LEU A 929      26.486  -3.835  14.143  1.00 29.74      A    C
+ATOM      4  O   LEU A 929      26.790  -2.625  14.181  1.00 29.50      A    O
+ATOM      5  CB  LEU A 929      28.096  -5.742  14.248  1.00 30.37      A    C
+ATOM      6  CG  LEU A 929      29.617  -5.471  14.154  1.00 28.52      A    C
+ATOM      7  CD1 LEU A 929      30.109  -5.719  12.711  1.00 27.72      A    C
+ATOM      8  CD2 LEU A 929      30.111  -4.134  14.702  1.00 25.22      A    C

tests/data/leu_short_lines.pdb

@@ -0,0 +1,8 @@
+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