Application of modern reversed-phase peptide retention prediction algorithms to the Houghten and DeGraw dataset: Peptide helicity and its effect on prediction accuracy

Deep learning approaches for data-independent acquisition proteomics

INTRODUCTION

Data-independent acquisition (DIA) is an emerging technology for large-scale proteomic studies. DIA data analysis methods are evolving rapidly, and deep learning has cut a conspicuous figure in this field.

AREAS COVERED

This review discusses and provides an overview of the deep learning methods that are used for DIA data analysis, including spectral library prediction, feature scoring, and statistical control in peptide-centric analysis, as well as de novo peptide sequencing. Literature searches were performed for articles, including preprints, up to December 2021 from PubMed, Scopus, and Web of Science databases.

EXPERT OPINION

While spectral library prediction has broken through the limitation on proteome coverage of experimental libraries, the statistical burden due to the large query space is the remaining challenge of utilizing proteome-wide predicted libraries. Analysis of post-translational modifications is another promising direction of deep learning-based DIA methods.

DeepLC can predict retention times for peptides that carry as-yet unseen modifications

The inclusion of peptide retention time prediction promises to remove peptide identification ambiguity in complex liquid chromatography-mass spectrometry identification workflows. However, due to the way peptides are encoded in current prediction models, accurate retention times cannot be predicted for modified peptides. This is especially problematic for fledgling open searches, which will benefit from accurate retention time prediction for modified peptides to reduce identification ambiguity. We present DeepLC, a deep learning peptide retention time predictor using peptide encoding based on atomic composition that allows the retention time of (previously unseen) modified peptides to be predicted accurately. We show that DeepLC performs similarly to current state-of-the-art approaches for unmodified peptides and, more importantly, accurately predicts retention times for modifications not seen during training. Moreover, we show that DeepLC's ability to predict retention times for any modification enables potentially incorrect identifications to be flagged in an open search of a wide variety of proteome data.

In silico spectral libraries by deep learning facilitate data-independent acquisition proteomics

Data-independent acquisition (DIA) is an emerging technology for quantitative proteomic analysis of large cohorts of samples. However, sample-specific spectral libraries built by data-dependent acquisition (DDA) experiments are required prior to DIA analysis, which is time-consuming and limits the identification/quantification by DIA to the peptides identified by DDA. Herein, we propose DeepDIA, a deep learning-based approach to generate in silico spectral libraries for DIA analysis. We demonstrate that the quality of in silico libraries predicted by instrument-specific models using DeepDIA is comparable to that of experimental libraries, and outperforms libraries generated by global models. With peptide detectability prediction, in silico libraries can be built directly from protein sequence databases. We further illustrate that DeepDIA can break through the limitation of DDA on peptide/protein detection, and enhance DIA analysis on human serum samples compared to the state-of-the-art protocol using a DDA library. We expect this work expanding the toolbox for DIA proteomics.

Development of a Structure-Based, pH-Dependent Lipophilicity Scale of Amino Acids from Continuum Solvation Calculations

Lipophilicity is a fundamental property to characterize the structure and function of proteins, motivating the development of lipophilicity scales. We report a versatile strategy to derive a pH-adapted scale that relies on theoretical estimates of distribution coefficients from conformational ensembles of amino acids. This is accomplished by using an accurately parametrized version of the IEFPCM/MST continuum solvation model as an effective way to describe the partitioning between n-octanol and water, in conjunction with a formalism that combines partition coefficients of neutral and ionic species of residues and the corresponding p K_a values of ionizable groups. Two weighting schemes are considered to derive solvent-like and protein-like scales, which have been calibrated by comparison with other experimental scales developed in different chemical/biological environments and pH conditions as well as by examining properties such as the retention time of small peptides and the recognition of antigenic peptides. A straightforward extension to nonstandard residues is enabled by this efficient methodological strategy.

Predictive chromatography of peptides and proteins as a complementary tool for proteomics

In the last couple of decades, considerable effort has been focused on developing methods for quantitative and qualitative proteome characterization. The method of choice in this characterization is mass spectrometry used in combination with sample separation. One of the most widely used separation techniques at the front end of a mass spectrometer is high performance liquid chromatography (HPLC). A unique feature of HPLC is its specificity to the amino acid sequence of separated peptides and proteins. This specificity may provide additional information about the peptides or proteins under study which is complementary to the mass spectrometry data. The value of this information for proteomics has been recognized in the past few decades, which has stimulated significant effort in the development and implementation of computational and theoretical models for the prediction of peptide retention time for a given sequence. Here we review the advances in this area and the utility of predicted retention times for proteomic applications.

Quality control in mass spectrometry-based proteomics

Mass spectrometry is a highly complex analytical technique and mass spectrometry-based proteomics experiments can be subject to a large variability, which forms an obstacle to obtaining accurate and reproducible results. Therefore, a comprehensive and systematic approach to quality control is an essential requirement to inspire confidence in the generated results. A typical mass spectrometry experiment consists of multiple different phases including the sample preparation, liquid chromatography, mass spectrometry, and bioinformatics stages. We review potential sources of variability that can impact the results of a mass spectrometry experiment occurring in all of these steps, and we discuss how to monitor and remedy the negative influences on the experimental results. Furthermore, we describe how specialized quality control samples of varying sample complexity can be incorporated into the experimental workflow and how they can be used to rigorously assess detailed aspects of the instrument performance.

Peptide retention time prediction

Most methods for interpreting data from shotgun proteomics experiments are to large degree dependent on being able to predict properties of peptide-ions. Often such predicted properties are limited to molecular mass and fragment spectra, but here we put focus on a perhaps underutilized property, a peptide's chromatographic retention time. We review a couple of different principles of retention time prediction,and their applications within computational proteomics. © 2016 Wiley Periodicals, Inc. Mass Spec Rev 36:615-623, 2017.

RePLiCal: A QconCAT Protein for Retention Time Standardization in Proteomics Studies

This study introduces a new reversed-phase liquid chromatography retention time (RT) standard, RePLiCal (Reversed-phase liquid chromatography calibrant), produced using QconCAT technology. The synthetic protein contains 27 lysine-terminating calibrant peptides, meaning that the same complement of standards can be generated using either Lys-C or trypsin-based digestion protocols. RePLiCal was designed such that each constituent peptide is unique with respect to all eukaryotic proteomes, thereby enabling integration into a wide range of proteomic analyses. RePLiCal has been benchmarked against three commercially available peptide RT standard kits and outperforms all in terms of LC gradient coverage. RePLiCal also provides a higher number of calibrant points for chromatographic retention time standardization and normalization. The standard provides stable RTs over long analysis times and can be readily transferred between different LC gradients and nUHPLC instruments. Moreover, RePLiCal can be used to predict RTs for other peptides in a timely manner. Furthermore, it is shown that RePLiCal can be used effectively to evaluate trapping column performance for nUHPLC instruments using trap-elute configurations, to optimize gradients to maximize peptide and protein identification rates, and to recalibrate the m/z scale of mass spectrometry data post-acquisition.