1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
use super::AtomSerial; use super::{Element, Residue}; use serde::Serialize; use std::str::FromStr; /// Represents an atom in a structural model. /// /// # Field /// /// - `id`: Unique identifier. No two atoms. No two `Atom`s in the same `Model` can have the same `id`. /// - `name`: Atom name. This represents the exact "role" of an atom in a given residue. /// - `residue`: The [`Residue`] this atom belongs to. This can be an amino acid, a nucleotide, water, or a custom molecule. /// - `chain`: The chain identifier /// - `sequence_number`: The position of this atom in the chain /// - `coord`: Cartesian coordinates `x, y, z` /// - `occupancy`: /// - `temperature_factor`: /// - `element`: The [`Element`] /// - `chaege`: The charge on the atom /// /// [`Residue`]: ../residue/struct.Residue.html /// [`Element`]: ../element/enum.Element.html #[derive(Debug, Clone, Serialize)] pub struct Atom { pub id: AtomSerial, pub name: AtomName, pub id1: char, pub residue: Residue, pub chain: char, pub sequence_number: u32, pub insertion_code: char, pub coord: [f32; 3], pub occupancy: f32, pub temperature_factor: f32, pub element: Element, pub charge: i8, // pub is_hetatom: bool, // ! implied } pub struct GenericAtomParser; /// Internally, an `AtomName` is represented as an array of 4 bytes. /// /// For convinience, `FromStr` is implemented for `AtomName`, so you can: /// /// ``` /// use std::str::FromStr; /// use protein_core::structure::AtomName; /// /// let atom = AtomName::from_str("O2").unwrap(); /// assert_eq!(atom, AtomName([b'O', b'2', b' ', b' '])); /// ``` #[derive(Debug, Clone, Serialize, Eq, PartialEq)] pub struct AtomName(pub [u8; 4]); impl AtomName { pub(crate) fn is_n(&self) -> bool { &self.0 == b"N " } pub(crate) fn is_c(&self) -> bool { &self.0 == b"C " } pub(crate) fn is_ca(&self) -> bool { &self.0 == b"CA " } pub(crate) fn is_o(&self) -> bool { &self.0 == b"O " } } #[derive(Debug)] pub enum ParseAtomNameError { LengthGreaterThan4, LengthZero, } impl FromStr for AtomName { type Err = ParseAtomNameError; fn from_str(s: &str) -> Result<Self, ParseAtomNameError> { let s = s.as_bytes(); match s.len() { 1usize => Ok(AtomName([s[0], b' ', b' ', b' '])), 2usize => Ok(AtomName([s[0], s[1], b' ', b' '])), 3usize => Ok(AtomName([s[0], s[1], s[2], b' '])), 4usize => Ok(AtomName([s[0], s[1], s[2], s[3]])), 0usize => Err(ParseAtomNameError::LengthZero), _ => Err(ParseAtomNameError::LengthGreaterThan4), } } } // #[derive(Debug, Clone, Serialize)] // pub enum AtomName { // AminoAcid(AminoAcidAtomName), // Nucleotide(NucleotideAtomName), // WaterO, // Other(String), // } // #[derive(Debug, Clone, Serialize)] // pub enum AminoAcidAtomName { // N, // CA, // C, // O, // Other(String), // } // impl AminoAcidAtomName { // pub fn from_bytes(inp: &[u8]) -> Self { // match inp { // b"N" => Self::N, // b"CA" => Self::CA, // b"C" => Self::C, // b"O" => Self::O, // _ => Self::Other(unsafe { std::str::from_utf8_unchecked(inp).to_owned() }), // } // } // pub fn from_bytes_fixed4(inp: &[u8]) -> Self { // match inp { // b" N " => Self::N, // b" CA " => Self::CA, // b" C " => Self::C, // b" O " => Self::O, // _ => Self::Other(unsafe { std::str::from_utf8_unchecked(inp).trim_start().to_owned() }), // } // } // } // #[derive(Debug, Clone, Serialize)] // pub enum NucleotideAtomName { // OP1, // OP2, // O5, // O4, // O3, // O2, // C5, // C4, // C3, // C2, // C1, // N9, // N7, // N6, // N4, // N3, // N2, // N1, // P, // Other(String), // } // impl NucleotideAtomName { // pub fn from_bytes_uppercase(inp: &[u8]) -> Self { // match inp { // b"OP1" => Self::OP1, // b"OP2" => Self::OP2, // b"O5" => Self::O5, // b"O4" => Self::O4, // b"O3" => Self::O3, // b"O2" => Self::O2, // b"C5" => Self::C5, // b"C4" => Self::C4, // b"C3" => Self::C3, // b"C2" => Self::C2, // b"C1" => Self::C1, // b"N9" => Self::N9, // b"N7" => Self::N7, // b"N6" => Self::N6, // b"N4" => Self::N4, // b"N3" => Self::N3, // b"N2" => Self::N2, // b"N1" => Self::N1, // b"P" => Self::P, // _ => Self::Other(unsafe { std::str::from_utf8_unchecked(inp).to_owned() }), // } // } // pub fn from_bytes_uppercase_fixed4(inp: &[u8]) -> Self { // match inp { // b" OP1" => Self::OP1, // b" OP2" => Self::OP2, // b" O5 " => Self::O5, // b" O4 " => Self::O4, // b" O3 " => Self::O3, // b" O2 " => Self::O2, // b" C5 " => Self::C5, // b" C4 " => Self::C4, // b" C3 " => Self::C3, // b" C2 " => Self::C2, // b" C1 " => Self::C1, // b" N9 " => Self::N9, // b" N7 " => Self::N7, // b" N6 " => Self::N6, // b" N4 " => Self::N4, // b" N3 " => Self::N3, // b" N2 " => Self::N2, // b" N1 " => Self::N1, // b" P " => Self::P, // _ => Self::Other(unsafe { std::str::from_utf8_unchecked(inp).trim_start().to_owned() }), // } // } // }