Deep Multiple Drug Classification Data

This repository contains the data used to train and to test the models from the DeepMDC repository. It also includes the supplementary material of the related article.

Suplementary Material

Training and Test Data

All genomic data provided here is from Klebsiella pneumoniae and was retrieved from this article (Training and Test 1) and this project (Test 2).

Meropenem

Training Samples: k_pneumoniae_meropenem.tar.xz

Class	n
R	775
S	715
I (S)	60
Total	1550

Test 1 Samples: k_pneumoniae_meropenem_test1.tar.xz

Class	n
R	77
S	72
I (S)	6
Total	155

Test 2 Samples: k_pneumoniae_meropenem_test2.tar.xz

Class	n
R	51
S	46
I (S)	3
Total	100

---

Gentamicin

Training Samples: k_pneumoniae_gentamicin.tar.xz

Class	n
R	975
S	858
I (S)	117
Total	1950

Test 1 Samples: k_pneumoniae_gentamicin_test1.tar.xz

Class	n
R	97
S	86
I (S)	12
Total	195

Test 2 Samples: k_pneumoniae_gentamicin_test2.tar.xz

Class	n
R	42
S	68
I (S)	3
Total	113

---

Ceftazidime

Training Samples: k_pneumoniae_ceftazidime.tar.xz

Class	n
R	1470
S	287
I (S)	38
Total	1795

Test 1 Samples: k_pneumoniae_ceftazidime_test1.tar.xz

Class	n
R	147
S	29
I (S)	4
Total	180

Test 2 Samples: k_pneumoniae_ceftazidime_test2.tar.xz

Class	n
R	80
S	18
I (S)	7
Total	105

---

Cefepime

Training Samples: k_pneumoniae_cefepime.tar.xz

Class	n
R	1030
S	519
I (S)	186
Total	1735

Test 1 Samples: k_pneumoniae_cefepime_test1.tar.xz

Class	n
R	103
S	51
I (S)	19
Total	173

Test 2 Samples: k_pneumoniae_cefepime_test2.tar.xz

Class	n
R	75
S	9
I (S)	10
Total	94

JSONs

This folder contains all ORFs extracted from the data directory, stored in JSON format along with their respective annotations generated using Bakta. This data (all_ORFs.json.xz) were used to retrieve biological information from the generated models.