4.2.6 GRUClassifier - WangLabTHU/GPro GitHub Wiki
hcwang and qxdu edited on Aug 4, 2023, 1 version
GRUClassifier is a binary classifier based on the GRU architecture, which was used in paper [1]; Its most significant advantage is that there is no need to limit the length, only the batch_size parameter needs to be specified. In other words, the sequences within the training set can be completely unequal in length! An exemplary example is as follows[2].
All parameters should be defined during the initialization phase. We have encapsulated the source code, thus all predictive models have unified input and output parameters. There are two types of parameters, one should be defined during the initialization phase (Initialization), and the other should be defined during the training/sampling phase (Training/Predicting).
| params | description | default value |
|---|---|---|
| batch_size | training batch size | 64 |
| length | sequential length of the training dataset | None |
| model_name | parameter that controls the saving path under "./checkpoints" | GRUClassifier |
| epoch | training epochs | 200 |
| patience | earlystopping when the indicators no longer change | 10 |
| log_steps | logging the output/criterias of the model every print_epoch epochs | 10 |
| save_steps | saving the result of model every save_epoch epochs | 20 |
| exp_mode | the processing mode for expression input | direct |
| params | description | default value | flexible stage |
|---|---|---|---|
| dataset | training dataset sequences path, fasta file | None | train() |
| labels | training dataset expression path, txt file, each line an expression corresponding to dataset | None | train() |
| savepath | final model saving path directory | None | train() |
| model_path | model loading directory | None |
predict()/predict_input()
|
| data_path | dataset to be predicted , fasta file | None | predict() |
| inputs | data for predict_input, can be datapath, sequence list or onehot encoded data | None | predict_input() |
| mode | input mode for predict_input, can be "path","data" or "onehot" | "path" | predict_input() |
Caution: predict() function will directly generate samples in checkpoint path, but predict_input() will not generate the file automatically.
A demo for model training/predicting is described below:
from gpro.predictor.others.GRUClassifier import GRUClassifier_language
model = GRUClassifier_language(length=306)
default_root = "your working directory"
dataset = os.path.join(default_root, 'data/seq.txt')
labels = os.path.join(default_root, 'data/exp.txt')
save_path = os.path.join(default_root, 'checkpoints/')
model.train(dataset=dataset,labels=labels,savepath=save_path)
# Predict
model_path = os.path.join(default_root, "checkpoints/GRUClassifier/checkpoint.pth")
data_path = os.path.join(default_root, "data/example.txt")
model.predict(model_path=model_path, data_path=data_path)
# Predict input
res = model.predict_input(model_path=model_path, inputs=data_path)
print(res)[1] Gupta A, Zou J. Feedback GAN for DNA optimizes protein functions[J]. Nature Machine Intelligence, 2019, 1(2): 105-111.
[2] Li, Liu, and Zhang. “An Improved Approach for Text Sentiment Classification Based on a Deep Neural Network via a Sentiment Attention Mechanism”. In: Future Internet 11 (Apr. 2019), p. 96. doi: 10.3390/fi11040096.