Abstract
Protein inference, the identification of the protein set that is the origin of a given peptide profile, is a fundamental challenge in proteomics. We present DeepPep, a deep-convolutional neural network framework that predicts the protein set from a proteomics mixture, given the sequence universe of possible proteins and a target peptide profile. In its core, DeepPep quantifies the change in probabilistic score of peptide-spectrum matches in the presence or absence of a specific protein, hence selecting as candidate proteins with the largest impact to the peptide profile. Application of the method across datasets argues for its competitive predictive ability (AUC of 0.80±0.18, AUPR of 0.84±0.28) in inferring proteins without need of peptide detectability on which the most competitive methods rely. We find that the convolutional neural network architecture outperforms the traditional artificial neural network architectures without convolution layers in protein inference. We expect that similar deep learning architectures that allow learning nonlinear patterns can be further extended to problems in metagenome profiling and cell type inference. The source code of DeepPep and the benchmark datasets used in this study are available at https://deeppep.github.io/DeepPep/.
Highlights
The accurate identification of proteins in a proteomics sample is a key challenge in life sciences
We here present DeepPep, a deep-convolutional neural network framework that predicts the protein set from a standard proteomics mixture, given all protein sequences and a peptide profile
Our results provide evidence that using sequence-level location information of a peptide in the context of proteome sequence can result in more accurate and robust protein inference
Summary
The accurate identification of proteins in a proteomics sample is a key challenge in life sciences. Proteins are fragmented in small amino acid chains that are called peptides that pass through a mass spectrometer. This results in a specific mass spectrum signature for each peptide, which correlates current intensity with a peptide’s weight and charge. This signature is matched to a peptide database to identify which peptides are present in the sample (peptide identification step). The challenge in protein inference is to infer the proteins (output) that give rise to the peptides observed in the sample. Each peptide has been identified after a database search of the sample mass spectrum, with a certain confidence level, known as the “peptide probability” [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
