DeepUEP: Prediction of Urine Excretory Proteins Using Deep Learning

Abstract

Urine excretory proteins are among the most commonly used biomarkers in body fluids. Computational identification of urine excretory proteins can provide very useful information for identifying targeted disease biomarkers in urine by linking transcriptome or proteomics data. There are few methods based on conventional machine learning algorithms for predicting urine excretory proteins, and most of these methods strongly depend on the extraction of features from urine excretory proteins. An end-to-end model for urine excretory protein prediction, called DeepUEP, is presented using deep neural networks relying on only amino acid sequence information. The model achieves good performance and outperforms existing methods on training and testing sets. By comparing known urinary protein biomarkers with the results of the model, we find that the model can achieve a true-positive rate of over 80% for urinary protein biomarkers that have been detected in more than one study. We also combine our model with transcriptome and proteomics data from lung cancer patients to predict the potential urinary protein biomarkers of lung cancer. A web server is developed for the prediction of urine excretory proteins, and it can be accessed at the following URL: http://www.csbg-jlu.info/DeepUEP/. We believe that our prediction model and web server are useful for biomedical researchers who are interested in identifying urinary protein biomarkers, especially for candidate proteins in transcriptome or proteomics analyses of diseased tissues.

DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer

“…For protein sequences less than 1000 in length, the number 0 is filled after the sequence; as for the protein sequences more than 1000 in length, 500 aa from N-terminus and C-terminus of the protein sequence are preserved, respectively. This method of cutting the amino acid sequence has been used in many cases of secreted protein prediction [11,12]. We then transform the PSSM described in [21] by the Sigmoid function 1/(1 + exp(−x)), where x represents a single entry of the PSSM.…”

“…Despite these models achieving promising performances, they generally suffered from some limitations such as manual intervention in the feature selection procedures. Recently, deep learning (DL) with neural network models, such as convolutional neural network (CNN), long short-term memory (LSTM) and gated recurrent unit (GRU), have been used for body-fluid protein prediction [11][12][13]. Du et al proposed a DL model, named DeepUEP, which consists of a CNN module, a recurrent neural network (RNN) with LSTM and an attention module to predict the urine excretory proteins [12].…”

“…Recently, deep learning (DL) with neural network models, such as convolutional neural network (CNN), long short-term memory (LSTM) and gated recurrent unit (GRU), have been used for body-fluid protein prediction [11][12][13]. Du et al proposed a DL model, named DeepUEP, which consists of a CNN module, a recurrent neural network (RNN) with LSTM and an attention module to predict the urine excretory proteins [12]. In addition, they proposed a DL model based on the capsule network and Transformer architecture, SecProCT, to predict secretory proteins in blood and saliva [13].…”