Muhamed-Kheir commited on
Commit
87019ba
·
verified ·
1 Parent(s): af876ca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -7
README.md CHANGED
@@ -1,14 +1,71 @@
1
  ---
2
- title: FtsI Classifier
3
- emoji: 🐢
4
- colorFrom: yellow
5
- colorTo: green
6
  sdk: gradio
7
  sdk_version: 6.1.0
8
  app_file: app.py
9
  pinned: false
10
- license: other
11
- short_description: Predict classe of ftsI
12
  ---
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: FtsI Kmer Unique
3
+ emoji: 📈
4
+ colorFrom: gray
5
+ colorTo: red
6
  sdk: gradio
7
  sdk_version: 6.1.0
8
  app_file: app.py
9
  pinned: false
10
+ license: mit
11
+ short_description: Finding unique k-mer signatures among groups of sequences
12
  ---
13
 
14
+ # Genomic Classification of Beta-Lactam Resistance
15
+
16
+ This repository provides a Python implementation of a genomic classification framework based on k-mer analysis of gene sequences (ftsI / penA) to predict beta-lactam susceptibility categories.
17
+
18
+ ## Description
19
+
20
+ The method identifies group-specific k-mers from allele sequences and uses them to classify isolates into resistance categories. The approach is designed to capture genomic patterns beyond predefined mutation rules.
21
+
22
+ This framework was developed and applied to:
23
+ - *Haemophilus influenzae* (ftsI gene)
24
+ - *Neisseria meningitidis* (penA gene)
25
+
26
+ ## Files
27
+
28
+ - `app.py` — main application (Gradio interface)
29
+ - `kmer_unique.py` — core k-mer extraction and filtering functions
30
+ - `requirements.txt` — Python dependencies
31
+
32
+ ## Requirements
33
+
34
+ Python ≥ 3.9
35
+
36
+ Install dependencies:
37
+
38
+ ```bash
39
+ pip install -r requirements.txt
40
+ ## Usage
41
+
42
+ ### Hugging Face interface
43
+
44
+ Run the app directly via the Hugging Face Space interface.
45
+
46
+ ## Input
47
+
48
+ - FASTA file containing gene sequences (ftsI or penA)
49
+ - Sequences grouped by phenotype or category
50
+
51
+ ## Output
52
+
53
+ - Predicted resistance category per sequence
54
+ - Identification of group-specific k-mer signatures
55
+
56
+ ## Method overview
57
+
58
+ 1. Extraction of k-mers from sequences
59
+ 2. Identification of unique k-mers per category
60
+ 3. Filtering based on frequency thresholds
61
+ 4. Classification of sequences based on k-mer matches
62
+
63
+ ## Citation
64
+
65
+ If you use this code, please cite:
66
+
67
+ [Your manuscript reference]
68
+
69
+ ## DOI
70
+
71
+ DOI: (to be added after Zenodo deposition)