BagReg: Protein inference through machine learning

Mining Statistically Significant Patterns with High Utility

Statistically significant pattern mining (SSPM) is to mine patterns with significance based on hypothesis test. Under the constraint of statistical significance, our study aims to introduce a new preference relation into high utility patterns and to discover high utility and significant patterns (HUSPs) from transaction datasets, which has never been considered in existing SSPM problems. Our approach can be divided into two parts, HUSP-Mining and HUSP-Test. HUSP-Mining looks for HUSP candidates and HUSP-Test tests their significance. HUSP-Mining is not outputting all high utility itemsets (HUIs) as HUSP candidates; it is established based on candidate length and testable support requirements which can remove many insignificant HUIs early in the mining process; compared with the traditional HUIs mining algorithm, it can get candidates in a short time without losing the real HUSPs. HUSP-Test is to draw significant patterns from the results of HUSP-Mining based on Fisher’s test. We propose an iterative multiple testing procedure, which can alternately and efficiently reject a hypothesis and safely ignore the hypotheses that have less utility than the rejected hypothesis. HUSP-Test controls Family-wise Error Rate (FWER) under a user-defined threshold by correcting the test level which can find more HUSPs than standard Bonferroni’s control. Substantial experiments on real datasets show that our algorithm can draw HUSPs efficiently from transaction datasets with strong mathematical guarantee.

MetaLP: An integrative linear programming method for protein inference in metaproteomics

Metaproteomics based on high-throughput tandem mass spectrometry (MS/MS) plays a crucial role in characterizing microbiome functions. The acquired MS/MS data is searched against a protein sequence database to identify peptides, which are then used to infer a list of proteins present in a metaproteome sample. While the problem of protein inference has been well-studied for proteomics of single organisms, it remains a major challenge for metaproteomics of complex microbial communities because of the large number of degenerate peptides shared among homologous proteins in different organisms. This challenge calls for improved discrimination of true protein identifications from false protein identifications given a set of unique and degenerate peptides identified in metaproteomics. MetaLP was developed here for protein inference in metaproteomics using an integrative linear programming method. Taxonomic abundance information extracted from metagenomics shotgun sequencing or 16s rRNA gene amplicon sequencing, was incorporated as prior information in MetaLP. Benchmarking with mock, human gut, soil, and marine microbial communities demonstrated significantly higher numbers of protein identifications by MetaLP than ProteinLP, PeptideProphet, DeepPep, PIPQ, and Sipros Ensemble. In conclusion, MetaLP could substantially improve protein inference for complex metaproteomes by incorporating taxonomic abundance information in a linear programming model.

DeepPep: Deep proteome inference from peptide profiles

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/.

The accurate identification of proteins in a proteomics sample, called the protein inference problem, is a fundamental challenge in biomedical sciences. Current approaches are based on applications of traditional neural networks, linear optimization and Bayesian techniques. 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. Comparison to leading methods shows that DeepPep has most robust performance with various instruments and datasets. 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. We conclude that Deep Learning on protein sequence leads to superior platforms for protein inference that can be further refined with additional features and extended for far reaching applications.