dna-parser 0.3.0__tar.gz → 0.4.0__tar.gz

{dna_parser-0.3.0 → dna_parser-0.4.0}/Cargo.lock

@@ -1,6 +1,6 @@
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
-version = 3
+version = 4
 
 [[package]]
 name = "ahash"
@@ -54,7 +54,7 @@ checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
 [[package]]
 name = "dna_parser"
-version = "0.3.0"
+version = "0.4.0"
 dependencies = [
  "ahash",
  "indexmap",

{dna_parser-0.3.0 → dna_parser-0.4.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "dna_parser"
-version = "0.3.0"
+version = "0.4.0"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

{dna_parser-0.3.0 → dna_parser-0.4.0}/PKG-INFO

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: dna_parser
-Version: 0.3.0
+Version: 0.4.0
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Dist: numpy >=1.16.0
-Requires-Dist: scipy >=1.3.0
-Requires-Dist: scikit-learn >=1.5.0
+Requires-Dist: numpy>=1.16.0
+Requires-Dist: scipy>=1.3.0
+Requires-Dist: scikit-learn>=1.5.0
+Requires-Dist: needletail>=0.7.0
 Requires-Dist: pytest ; extra == 'dev'
 Requires-Dist: mkdocs ; extra == 'dev'
 Provides-Extra: dev

{dna_parser-0.3.0 → dna_parser-0.4.0}/docs/documentation.md

@@ -486,7 +486,7 @@ print(encodings2)
 
 
 ```python
-dna_parser.zcurve_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs= 1)
+dna_parser.zcurve_encoding(sequences, pad_type= "after", pad_length= -2, window= 1, n_jobs= 1)
 ```
 
 #### Function Arguments
@@ -494,11 +494,12 @@ dna_parser.zcurve_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs=
 * **sequences** (list of str): list of genomic sequences.
 * **pad_type** (str): pad (or trim) "before" or "after" the sequences.
 * **pad_length** (int): -2 to pad according to the longest sequence, -1 to trim to the shortest sequence, any positive number for a fixed length.
+* **window** (int): non-overlapping window size to consider along the sequence for the encoding.
 * **n_jobs** (int): number of threads used to encode the sequences in parallel. 0 to use all CPUs available.
 
 #### Output
 
-**Numpy array with shape (number of sequences, length of sequences, 3).** <br /> The sequences are encoded within a cube. At each nucleotide position the Z-curve encoding gives the disparity between purines (r) and pyrimidines (y), the disparity between nucleotides with an amino (m) and a keto (k) group, and the disparity between nucleotide with weak (w) and strong (s) bonds.
+**Numpy array with shape (number of sequences, (length of sequences/window), 3).** <br /> The sequences are encoded within a cube. At each window position the Z-curve encoding gives the disparity between purines (r) and pyrimidines (y), the disparity between nucleotides with an amino (m) and a keto (k) group, and the disparity between nucleotide with weak (w) and strong (s) bonds.
 
 
 ```python
@@ -521,7 +522,21 @@ print(encoding.shape)
 #  [-1  3 -1]
 #  [-1  3 -1]]]
 #
-#(2, 3, 3)
+#(2, 4, 3)
+
+sequences= ["agtc","acc"]
+encoding= dps.zcurve_encoding(sequences, window=2)
+print(encoding)
+print(encoding.shape)
+
+#Output:
+#[[[ 2  0  0]
+#  [ 0  0  0]]
+#
+# [[ 0  2  0]
+#  [-1  3 -1]]]
+#(2, 2, 3)
+
 ```
 <br/>
 

{dna_parser-0.3.0 → dna_parser-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "dna_parser"
-project.version = "0.3.0"
+project.version = "0.4.0"
 requires-python = ">=3.9"
 classifiers = [
     "Programming Language :: Rust",
@@ -12,7 +12,7 @@ classifiers = [
     "Programming Language :: Python :: Implementation :: PyPy",
 ]
 
-dependencies = ['numpy >= 1.16.0', 'scipy >= 1.3.0',  "scikit-learn >= 1.5.0",]
+dependencies = ['numpy >= 1.16.0', 'scipy >= 1.3.0',  "scikit-learn >= 1.5.0", 'needletail >= 0.7.0' ]
 
 [project.optional-dependencies]
 dev = ["pytest","mkdocs"]

{dna_parser-0.3.0 → dna_parser-0.4.0}/python/dna_parser/call_functions.py

@@ -1,4 +1,5 @@
 from .dna_parser import *
+from needletail import parse_fastx_file
 
 
 def onehot_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs= 1):
@@ -17,9 +18,9 @@ def random_seq(length, nb_of_seq, seq_type= "dna", n_jobs= 1):
 
     return random_seq_rust(length, nb_of_seq, seq_type, n_jobs)
 
-def zcurve_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs= 1):
+def zcurve_encoding(sequences, pad_type= "after", pad_length= -2, window=1, n_jobs= 1):
 
-    return zcurve_encoding_rust(sequences, pad_type, pad_length, n_jobs)
+    return zcurve_encoding_rust(sequences, pad_type, pad_length, window, n_jobs)
 
 def chaos_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs= 1):
 
@@ -44,30 +45,33 @@ def atomic_encoding(sequences, pad_type= "after", pad_length= -2, n_jobs= 1):
 def load_fasta(path):
 
     if type(path) is str:
-        return load_fasta_rust(path)
+        return [(seq.id, seq.seq) for seq in parse_fastx_file(path)]
     
     elif type(path) is list:
         
-        sequences= [ seq for current_file in path for seq in load_fasta_rust(current_file)]
+        sequences= [ (seq.id, seq.seq) for file in path for seq in parse_fastx_file(file) ]
         return sequences
+ 
 
 def load_metadata(path):
 
+    
     if type(path) is str:
-        return metadata_from_fasta_rust(path)
+        return [seq.id for seq in parse_fastx_file(path)]
     
     elif type(path) is list:
         
-        sequences= [ seq for current_file in path for seq in metadata_from_fasta_rust(current_file)]
+        sequences= [ seq.id for file in path for seq in parse_fastx_file(file)]
         return sequences
+    
 
         
 def load_sequences(path):
 
     if type(path) is str:
-        return seq_from_fasta_rust(path)
+        return [seq.seq for seq in parse_fastx_file(path)]
     
     elif type(path) is list:
         
-        sequences= [ seq for current_file in path for seq in seq_from_fasta_rust(current_file)]
+        sequences= [ seq.seq for file in path for seq in parse_fastx_file(file)]
         return sequences

{dna_parser-0.3.0 → dna_parser-0.4.0}/src/lib.rs

@@ -4,7 +4,6 @@ pub mod kmers;
 pub mod random_sequence;
 pub mod tfidf;
 pub mod real;
-pub mod fasta_files;
 pub mod utils;
 pub mod cross;
 pub mod zcurve;
@@ -27,7 +26,6 @@ use kmers::*;
 use random_sequence::*;
 use tfidf::*;
 use real::*;
-use fasta_files::*;
 use cross::*;
 use zcurve::*;
 use chaos_game::*;
@@ -47,9 +45,6 @@ fn dna_parser(_py: Python<'_>, m: &Bound<PyModule>)-> PyResult<()> {
     m.add_function(wrap_pyfunction!(make_kmers,m)?)?;
     m.add_function(wrap_pyfunction!(random_seq_rust,m)?)?;
     m.add_function(wrap_pyfunction!(real_encoding_rust,m)?)?;
-    m.add_function(wrap_pyfunction!(load_fasta_rust,m)?)?;
-    m.add_function(wrap_pyfunction!(seq_from_fasta_rust,m)?)?;
-    m.add_function(wrap_pyfunction!(metadata_from_fasta_rust,m)?)?;
     m.add_function(wrap_pyfunction!(cross_encoding_rust,m)?)?;
     m.add_function(wrap_pyfunction!(zcurve_encoding_rust,m)?)?;
     m.add_function(wrap_pyfunction!(chaos_encoding_rust,m)?)?;

{dna_parser-0.3.0 → dna_parser-0.4.0}/src/zcurve.rs

@@ -11,7 +11,7 @@ use std::thread;
 use crate::utils;
 
 
-fn zcurve_after(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 2]>>) {
+fn zcurve_after(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 2]>>, window: usize) {
 
 
     let mut r= 0;
@@ -20,71 +20,70 @@ fn zcurve_after(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[us
     let mut k= 0;
     let mut w= 0;
     let mut s= 0;
-    
 
-    for item in array.axis_iter_mut(Axis(0)).zip_longest(sequence.chars()) {
+    for item in array.axis_iter_mut(Axis(0)).zip_longest(sequence.chars().chunks(window).into_iter()) {
 
-        let nucleotide: char;
         let mut col: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 1]>>;
 
-        if item.is_both() {
-            let (option_col,char) = item.left_and_right();
-            col= option_col.unwrap();
-            nucleotide= char.unwrap().to_ascii_lowercase();
-        }
-
-        else if !item.is_left() {
+        if item.is_left() {
             break
         }
 
-        else {
+        else if item.is_right() {
             col= item.left().unwrap();
-            nucleotide= ' ';
-        }
-        
-        if nucleotide == 'a' || nucleotide == 'g' {
-            r += 1;
             col[0]= r-y;
-        }
-
-        else if  nucleotide == 'c' || nucleotide == 't' || nucleotide == 'u'{
-            y += 1;
-            col[0]= r-y;
-        }
-
-        else {
-            col[0]= r-y;
-        }
-
-        if nucleotide == 'a' || nucleotide == 'c' {
-            m += 1;
             col[1]= m-k;
-            
+            col[2]= w-s;
         }
 
-        else if nucleotide == 't' || nucleotide == 'u'|| nucleotide == 'g' {
-            k += 1;
-            col[1]= m-k;
-        }
-
-        else {
-            col[1]= m-k;
-        }
+        else  {
+            let (option_col,nt_chunk) = item.left_and_right();
+            col= option_col.unwrap();
+            
+            for mut nucleotide in nt_chunk.unwrap() {
+                nucleotide= nucleotide.to_ascii_lowercase();
 
-        if nucleotide == 'a' || nucleotide == 't' || nucleotide == 'u' {
-            w += 1;
-            col[2]= w-s
+                if nucleotide == 'a' || nucleotide == 'g' {
+                    r += 1;
+                    col[0]= r-y;
+                }
+        
+                else if  nucleotide == 'c' || nucleotide == 't' || nucleotide == 'u'{
+                    y += 1;
+                    col[0]= r-y;
+                }
+        
+                if nucleotide == 'a' || nucleotide == 'c' {
+                    m += 1;
+                    col[1]= m-k;
+                    
+                }
+        
+                else if nucleotide == 't' || nucleotide == 'u'|| nucleotide == 'g' {
+                    k += 1;
+                    col[1]= m-k;
+                }
+        
+                if nucleotide == 'a' || nucleotide == 't' || nucleotide == 'u' {
+                    w += 1;
+                    col[2]= w-s
+                }
+        
+                else if nucleotide == 'g' || nucleotide == 'c' {
+                    s += 1;
+                    col[2]= w-s
+        
+                }
+        
+                col[0]= r-y;
+                col[1]= m-k;
+                col[2]= w-s;
+                
+            }
         }
 
-        else if nucleotide == 'g' || nucleotide == 'c' {
-            s += 1;
-            col[2]= w-s
-
-        }
 
-        else {
-            col[2]= w-s
-        }
+    
 
 
     }
@@ -93,7 +92,7 @@ fn zcurve_after(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[us
 
 }
 
-fn zcurve_before(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 2]>>) {
+fn zcurve_before(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 2]>>, window: usize) {
 
 
     let mut r= 0;
@@ -107,61 +106,61 @@ fn zcurve_before(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[u
     let array_rev = array.axis_iter_mut(Axis(0)).rev();
     let sequence_rev: Vec<char>= sequence.chars().rev().collect();
 
-    let zip_tup= array_rev.zip(sequence_rev).rev();
-
-    for (mut col, charac) in zip_tup {
-
-        let nucleotide= charac.to_ascii_lowercase();
-        
-        if nucleotide == 'a' || nucleotide == 'g' {
-            r += 1;
-            col[0]= r-y;
-        }
+    let zip_tup= array_rev.zip(sequence_rev.chunks(window)).rev();
 
-        else if  nucleotide == 'c' || nucleotide == 't' || nucleotide == 'u'{
-            y += 1;
-            col[0]= r-y;
-        }
+    for (mut col, nt_chunk) in zip_tup {
 
-        else {
-            col[0]= r-y;
-        }
+        for nt in nt_chunk {
 
-        if nucleotide == 'a' || nucleotide == 'c' {
-            m += 1;
-            col[1]= m-k;
-            
-        }
+            let nucleotide= nt.to_ascii_lowercase();
+        
+            if nucleotide == 'a' || nucleotide == 'g' {
+                r += 1;
+                col[0]= r-y;
+            }
+
+            else if  nucleotide == 'c' || nucleotide == 't' || nucleotide == 'u'{
+                y += 1;
+                col[0]= r-y;
+            }
+
+            else {
+                col[0]= r-y;
+            }
+
+            if nucleotide == 'a' || nucleotide == 'c' {
+                m += 1;
+                col[1]= m-k;
+                
+            }
 
-        else if nucleotide == 't' || nucleotide == 'u'|| nucleotide == 'g' {
-            k += 1;
-            col[1]= m-k;
-        }
+            else if nucleotide == 't' || nucleotide == 'u'|| nucleotide == 'g' {
+                k += 1;
+                col[1]= m-k;
+            }
 
-        else {
-            col[1]= m-k;
-        }
+            else {
+                col[1]= m-k;
+            }
 
-        if nucleotide == 'a' || nucleotide == 't' || nucleotide == 'u' {
-            w += 1;
-            col[2]= w-s
-        }
+            if nucleotide == 'a' || nucleotide == 't' || nucleotide == 'u' {
+                w += 1;
+                col[2]= w-s
+            }
 
-        else if nucleotide == 'g' || nucleotide == 'c' {
-            s += 1;
-            col[2]= w-s
+            else if nucleotide == 'g' || nucleotide == 'c' {
+                s += 1;
+                col[2]= w-s
 
-        }
+            }
 
-        else {
-            col[2]= w-s
+            else {
+                col[2]= w-s
+            }
         }
 
-
     }
 
-
-
 }
 
 
@@ -171,14 +170,14 @@ fn zcurve_before(sequence: &str, mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[u
 /// Returns the onehot encodings in a Vec for the sequences passed to this fucntion.
 ///
 /// this function parse the type and length of padding for the encoding 
-fn encode_chunks(chunk: &[String], mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 3]>> , pad_type: &str ) {
+fn encode_chunks(chunk: &[String], mut array: ArrayBase<ViewRepr<&mut i64>, Dim<[usize; 3]>> , pad_type: &str , window: usize) {
 
 
     if pad_type== "after" {
 
         for (seq, sub_array) in chunk.iter().zip(array.axis_iter_mut(Axis(0))) {
 
-            zcurve_after(seq, sub_array);
+            zcurve_after(seq, sub_array, window);
             
         }
     }
@@ -187,7 +186,7 @@ fn encode_chunks(chunk: &[String], mut array: ArrayBase<ViewRepr<&mut i64>, Dim<
         
         for (seq, sub_array) in chunk.iter().zip(array.axis_iter_mut(Axis(0))) {
 
-            zcurve_before(seq, sub_array); 
+            zcurve_before(seq, sub_array, window); 
             
         }
     }
@@ -206,7 +205,7 @@ fn encode_chunks(chunk: &[String], mut array: ArrayBase<ViewRepr<&mut i64>, Dim<
 ///
 /// This function splits the sequences to encode and distributes them to different threads. 
 /// the usize is used to keep the order of sequences and the Vec<Array2<i8>> represent the onehot encodings of the genomic sequences
-fn multithreads(sequences: Vec<String>, pad_type: &str, mut array: Array3<i64>, nb_cpus: usize) -> Array3<i64> {
+fn multithreads(sequences: Vec<String>, pad_type: &str, mut array: Array3<i64>, window: usize, nb_cpus: usize) -> Array3<i64> {
 
     //determine size of chunks based on number of threads and add 1 to be sure 
     //to have a number of chunks equal to nb of cpus and not superior
@@ -222,7 +221,7 @@ fn multithreads(sequences: Vec<String>, pad_type: &str, mut array: Array3<i64>,
 
             s.spawn( move || {
                 
-                encode_chunks(chunk_seq, array_slice, pad_type );
+                encode_chunks(chunk_seq, array_slice, pad_type, window );
                 
             });
 
@@ -248,17 +247,18 @@ fn multithreads(sequences: Vec<String>, pad_type: &str, mut array: Array3<i64>,
 /// * `n_jobs` - number of threads to use. 0 to use every cpu
 #[allow(unused_must_use)]
 #[pyfunction]
-pub fn zcurve_encoding_rust<'pyt>(py:  Python <'pyt>, sequences_py: &Bound<'pyt, PyList>, pad_type: &str, pad_length: i128, n_jobs: i16 ) ->  Bound<'pyt, PyArray3<i64>> {
+pub fn zcurve_encoding_rust<'pyt>(py:  Python <'pyt>, sequences_py: &Bound<'pyt, PyList>, pad_type: &str, pad_length: i128, window: usize, n_jobs: i16 ) ->  Bound<'pyt, PyArray3<i64>> {
 
     let sequences: Vec<String> = sequences_py.extract().expect("Error unpacking Python object to Rust");
 
-    let vec_length= utils::get_length(&sequences, pad_length);
+    let mut vec_length= utils::get_length(&sequences, pad_length);
+    vec_length= vec_length.div_ceil(window);
     let cpu_to_use= utils::check_nb_cpus(n_jobs);
 
     let mut final_array= Array3::<i64>::zeros((sequences.len(), vec_length, 3));
 
 
-    final_array= py.allow_threads(move || multithreads(sequences, pad_type, final_array, cpu_to_use));
+    final_array= py.allow_threads(move || multithreads(sequences, pad_type, final_array, window, cpu_to_use));
 
     final_array.to_pyarray(py)
 

{dna_parser-0.3.0 → dna_parser-0.4.0}/tests/test_fasta.py

@@ -4,9 +4,9 @@ import numpy
 
 def test_load_fasta():
     
-    expected= [ (">sequence1", "acgtatgcgtcgtc"),
-    (">sequence2","cccgtga---gtcgat"),
-    (">sequence3","xgtcgycaaatcg-?")]
+    expected= [ ("sequence1", "acgtatgcgtcgtc"),
+    ("sequence2","cccgtga---gtcgat"),
+    ("sequence3","xgtcgycaaatcg-?")]
 
     results= load_fasta("tests/seq_test.fasta")
 
@@ -29,7 +29,7 @@ def test_seq_from_fasta():
 
 def test_seq_metadata_fasta():
 
-    expected= [">sequence1", ">sequence2", ">sequence3"]
+    expected= ["sequence1", "sequence2", "sequence3"]
 
     results= load_metadata("tests/seq_test.fasta")
 
@@ -38,8 +38,8 @@ def test_seq_metadata_fasta():
 def test_list_of_paths():
     paths= ["tests/seq_test.fasta","tests/seq_test.fasta","tests/seq_test.fasta"]
 
-    fasta_expected= [ (">sequence1", "acgtatgcgtcgtc"), (">sequence2","cccgtga---gtcgat"), (">sequence3","xgtcgycaaatcg-?")]*3
-    metadata_expected= [">sequence1", ">sequence2", ">sequence3"]*3
+    fasta_expected= [ ("sequence1", "acgtatgcgtcgtc"), ("sequence2","cccgtga---gtcgat"), ("sequence3","xgtcgycaaatcg-?")]*3
+    metadata_expected= ["sequence1", "sequence2", "sequence3"]*3
     sequences_expected= ["acgtatgcgtcgtc", "cccgtga---gtcgat", "xgtcgycaaatcg-?"]*3
     
     fasta= load_fasta(paths)

{dna_parser-0.3.0 → dna_parser-0.4.0}/tests/test_zcurve.py

@@ -64,4 +64,35 @@ def test_unexpected_char():
 
     for index, x in numpy.ndenumerate(test_matrix):
         
-        assert x
+        assert x
+
+def test_window():
+    expected= numpy.array([ [0,0,2], [0,0,2], [1,-1,1]]) 
+    results= zcurve_encoding([DNA_SEQUENCES[1]], window= 2)[0]
+
+    test_matrix= results == expected
+
+    for index, x in numpy.ndenumerate(test_matrix):
+        
+        assert x
+
+def test_window():
+    expected= numpy.array([ [0,0,2], [0,0,2], [1,-1,1]]) 
+    results= zcurve_encoding([DNA_SEQUENCES[1]], window= 2)[0]
+
+    test_matrix= results == expected
+
+    for index, x in numpy.ndenumerate(test_matrix):
+        
+        assert x
+    
+def before_test_window():
+    expected= numpy.array([ [0,0,0],[0,0,0],[0,0,2], [0,0,2], [1,-1,1]]) 
+    results= zcurve_encoding([DNA_SEQUENCES[1]],pad_length=10, pad_type="before",window= 2)[0]
+
+    test_matrix= results == expected
+
+    for index, x in numpy.ndenumerate(test_matrix):
+        
+        assert x
+

dna_parser-0.3.0/src/fasta_files.rs

@@ -1,126 +0,0 @@
-use std::fs::File;
-use pyo3::prelude::*;
-use std::io::{prelude::*, BufReader};
-
-//implement a struct for fasta file?
-
-/// Returns a Vec of string where each string is one of the genomic sequences in the fasta file
-/// The order in which the sequences appear in the fasta file is conserved
-///
-/// # Arguments
-/// * `file_path` - path to the fasta file
-#[pyfunction]
-pub fn seq_from_fasta_rust(file_path: &str) ->  Vec<String> {
-   
-    let f = File::open(file_path).expect("Unable to open file");
-    let f = BufReader::new(f);
-
-    let mut sequences = Vec::new();
-    let mut seq= String::from("");
-
-    for line in f.lines(){
-
-        let line = line.expect("Unable to read line");
-
-        if line.starts_with('>') {
-            
-            if !seq.is_empty() {
-
-                sequences.push(seq);
-                seq= String::from("");
-            }
-        }
-
-        else {
-
-            seq.push_str(line.trim());
-
-        }
-
-    }
-
-    if !seq.is_empty() {
-        sequences.push(seq);
-    }
-
-    sequences
-
-}
-
-/// Returns a Vec of string where each string is the metadata for one genomic sequence
-/// The order in which the sequences metadata appear in the fasta file is conserved
-///
-/// # Arguments
-/// * `file_path` - path to the fasta file
-#[pyfunction]
-pub fn metadata_from_fasta_rust(file_path: &str) ->  Vec<String> {
-
-    let f = File::open(file_path).expect("Unable to open file");
-    let f = BufReader::new(f);
-
-    let mut metadata = Vec::new();
-
-    for line in f.lines() {
-
-        let line = line.expect("Unable to read line");
-
-        if line.starts_with('>') {
-
-            metadata.push(line)
-        }
-    }
-
-    metadata 
-}
-
-
-/// Returns a Vec of tuples each containing 2 strings. The first string is the metadata and the second one is the associated genomic sequence
-/// The order in which the metadatas and sequences appear in the fasta file is conserved
-///
-/// # Arguments
-/// * `file_path` - path to the fasta files
-#[pyfunction]
-pub fn load_fasta_rust(file_path: &str) ->  Vec<(String,String)>  {
-
-    let f = File::open(file_path).expect("Unable to open file");
-    let reader = BufReader::new(f);
-
-    let mut metadata_and_seq = Vec::new();
-    let mut metadata= String::from("");
-    let mut seq= String::from("");
-
-    for line in reader.lines() {
-
-        let line = line.expect("Unable to read line");
-
-        if line.starts_with('>') {
-
-            if !seq.is_empty() {
-
-                metadata_and_seq.push((metadata, seq));
-                seq= String::from("");
-            }
-
-            metadata= line;
-        }
-
-        else {
-
-            seq.push_str(line.trim())
-
-        }
-
-    }
-
-    if !seq.is_empty() {
-
-        metadata_and_seq.push((metadata, seq));
-    }
-
-    metadata_and_seq
-
-
-}
-
-// ################  test implementation generator load seq #############
-