DLEB paper is published in Nucleic Acids Research.
Wy, Suyeon, et al. "DLEB: a web application for building deep learning models in biological research." Nucleic Acids Research (2022).
Deep Learning Editor for Biologists (DLEB) consists of two parts: (i) a client-side web interface for easily designing deep learning models and
(ii) server-side module for generating the corresponding Python code for running in their machines directly.
In the client-side web interface, users can design deep learning models by using a user-friendly and easy-to-use WYSIWYG (What You See Is What You Get) interface. DLEB also provides diverse template models and recommends models in a step-by-step fashion for users who do not have sufficient knowledge of model structures.
After the user designs the deep learning model with the specification of training parameters is done, the model is implemented and corresponding Python code is generated in the server-side module. The generated Python code consists of many useful parts, such as the implementation of designed deep learning models, the code for preprocessing input biological data, model training, and monitoring, which allow users to run the code and examine the training process in their machines directly without any additional tasks. The Python codes for the designed deep learning models implement based on Tensorflow2 and Keras libraries.
DLEB also provides various example biological datasets for training and testing the built models.
DLEB will serve as a highly valuable platform for easily applying deep learning to solve many important biological problems.
What are you looking for?
Model Design
You can freely design your own deep learning models without programming knowledge or skills.
Just build the brilliant model structures. DLEB will write scripts for the models.
Model Recommendation
You can find proper deep learning models for your studies even if you do not have enough knowledge of models.
Just tell us which data you have and what you want to do with models.
Data Download
You can get various example biological data that researchers have used in the several previous deep learning studies, for training and testing your deep learning models.