Skip to article frontmatterSkip to article content

Prediction

Overview

You need to decompress the example data.zip file in your preferred folder, e.g., drutai/.

There are three required files.

We display 5 relations between small molecules and targets to predict their possible interactions.

1
2
3
4
5
6
sm	target
148124	C1KC03
84093	P03901
5757	Q8N0U8
5743	O00238
84093	A0A0H2UXE9

Python

We access Drutai by defining the following parameters.

params = {
    'br_fpn': '../../data/drutai/example_data/br_sm_target.txt',
    'smile_fpn': '../../data/drutai/example_data/br_smile.txt',
    'method': 'LSTMCNN',
    'fasta_fp': '../../data/drutai/example_data/',
    'model_fp': '../../data/drutai/lstmcnn',
    'sv_fpn': '../../data/drutai/example_data/pred.drutai',
}
Command
Output log
import drutai

drutai.predict.sm_target_interaction(
    br_fpn=params['br_fpn'],
    smile_fpn=params['smile_fpn'],
    fasta_fp=params['fasta_fp'],
    method=params['method'],
    model_fp=params['model_fp'],
    sv_fpn=params['sv_fpn'],
)

CLI

Drutai can also be used in shell. To know how to use, please type

drutai -h

It shows the usage of different parameters.

-m, --method,
    A deep learning method. It can be any below.
    AlexNet | BiRNN | RNN | Seq2Seq |
    CNN | ConvMixer64 | DSConv | LSTMCNN |
    MobileNet | ResNet18 | ResNet50 | SEResNet |
-br, --br_fpn, binary relations between small molecules and protein targets
-d, --smile_fpn, map between small molecule IDs and their smile strings
-t, --fasta_fp, protein target fasta file paths
-mf, --model_fp, a model path
-o, --sv_fpn, outputting drutai predictions

You can run it using the following code.

Command
Output log
drutai -m LSTMCNN -br ./data/drutai/example_data/br_sm_target.txt -d ./data/drutai/example_data/br_smile.txt -t ./data/drutai/example_data/ -mf ./data/drutai/lstmcnn -o ./data/drutai/out.drutai
deepsmirud -m LSTMCNN -br ./data/input/br_sm_mirna.txt -d ./data/input/br_smile.txt -t ./data/input/ -mf ./data/model/lstmcnn -o ./data/out.deepsmirud
References
  1. Sun, J., Xu, M., Ru, J., James-Bott, A., Xiong, D., Wang, X., & Cribbs, A. P. (2023). Small molecule-mediated targeting of microRNAs for drug discovery: Experiments, computational techniques, and disease implications. European Journal of Medicinal Chemistry, 115500. https://doi.org/10.1016/j.ejmech.2023.115500
Tutorial
Model