Sequence classification using deep learning
SECLAF is a complete amino acid and DNA sequence analysis framework. SECLAF allows you to train and test deep neural networks for multi-label classification of biological sequences, and is free and open source. This is an online demonstration of SECLAF, performing Gene Ontology and UniProt family classification. more...
SECLAF is an open-source application for training deep neural networks on biological sequence data. This online version allows you to try out models pre-trained with SECLAF on your own collections of sequences.
The input should be a list of amino acid (protein) sequences. It can be either a simple text file, containing one sequence per row, or a FASTA file. The maximum allowed number of sequences per file is 1000, and the file size may be at most 16 MB.
You can then choose a pretrained model (neural network) from a list. SECLAF will run the selected model on these sequences to classify them.
Technical details: SECLAF is a free and open source neural network training, testing and inference framework designed to help bioinformaticians with evaluating models on multi-label sequence classification tasks. This is a website where you can try out some example models trained with SECLAF. The toolchain is run on a GPU in our high-performance server computer. 10 requests are allowed per day per user.
Please cite us if you use SECLAF.
Here you can download the offline version of SECLAF.
Prerequisites: Linux, Python, CUDA 8.0 with cuDNN 5.1. Several packages (numpy, tensorflow-gpu, etc.) need to be installed with pip. A state-of-the-art GPU is highly recommended.
Pretrained models for Gene Ontology and Uniprot families classification are available here. (See the examples folder in seclaf.zip).
Balazs Szalkai, Vince Grolmusz: Near Perfect Protein Multi-Label Classification with Deep Neural Networks, Methods (2017), https://doi.org/10.1016/j.ymeth.2017.06.034
Balazs Szalkai, Vince Grolmusz: SECLAF: A Webserver and Deep Neural Network Design Tool for Biological Sequence Classification, arXiv preprint arXiv:1708.04103
You can use this service only if you accept the following terms: We do not guarantee anything about this service. We do not state anything about the usability of this service, and we do not state that the results that we may return can be used for any purpose. We cannot guarantee that this service will be available in the future, and we cannot guarantee that your query would generate any output at all.
Privacy: We will not give out your data to anyone, and, regularly, only you can retrieve the results to your query using the unique webpage identifier generated for you. However, we cannot guarantee that others do not intercept the traffic between you and our server. Therefore, do not use our webserver for proprietary data analysis, we cannot guarantee the data integrity and safety for you.
|SUPPORTED THROUGH THE NEW NATIONAL EXCELLENCE PROGRAM OF THE MINISTRY OF HUMAN CAPACITIES|