DeepSec: a deep learning framework for secreted protein discovery in human body fluids

Abstract

Motivation: Human proteins that are secreted into different body fluids from various cells and tissues can be promising disease indicators. Modern proteomics research empowered by both qualitative and quantitative profiling techniques has made great progress in protein discovery in various human fluids. However, due to the large number of proteins and diverse modifications present in the fluids, as well as the existing technical limits of major proteomics platforms (e.g. mass spectrometry), large discrepancies are often generated from different experimental studies. As a result, a comprehensive proteomics landscape across major human fluids are not well determined.

Results: To bridge this gap, we have developed a deep learning framework, named DeepSec, to identify secreted proteins in 12 types of human body fluids. DeepSec adopts an end-to-end sequence-based approach, where a Convolutional Neural Network is built to learn the abstract sequence features followed by a Bidirectional Gated Recurrent Unit with fully connected layer for protein classification. DeepSec has demonstrated promising performances with average area under the ROC curves of 0.85-0.94 on testing datasets in each type of fluids, which outperforms existing state-of-the-art methods available mostly on blood proteins. As an illustration of how to apply DeepSec in biomarker discovery research, we conducted a case study on kidney cancer by using genomics data from the cancer genome atlas and have identified 104 possible marker proteins.

Availability: DeepSec is available at https://bmbl.bmi.osumc.edu/deepsec/.

Supplementary information: Supplementary data are available at Bioinformatics online.

Fig. 1.

The distribution of 12 types of body fluids that are analyzed in this study

Fig. 2.

The architecture of DeepSec which supports input as PSI-profiles based on protein sequences, feature extraction through CNN, classification based on BGRU with fully connected dense layer, and the outputs as the probability of being secreted protein

Fig. 3.

The forwards and backwards GRU capturing possible long-range dependencies between the input sequence and the predicted class

Fig. 4.

Results of predicted human proteins secreted in 12 body fluids by screening against all human proteins reported in Swiss-Prot. The orange bar depicts number of predicted proteins against all human proteins in Swiss-Prot and blue bar depicts the experimental identified proteins

Fig. 5.

The ROC curves for body-fluid protein prediction differentiation of DeepSec versus other models in 12 kinds of body fluids on testing datasets

Fig. 6.

The ROC curves of various model architectures. (a) Evaluation on testing dataset. (b) Evaluation on all datasets

Fig. 7.

The significant differential expression between kidney cancer and control samples, including up- and down-regulated results