Machine Learning on Signal-to-Noise Ratios Improves Peptide Array Design in SAMDI Mass Spectrometry

Abstract

Emerging peptide array technologies are able to profile molecular activities within cell lysates. However, the structural diversity of peptides leads to inherent differences in peptide signal-to-noise ratios (S/N). These complex effects can lead to potentially unrepresentative signal intensities and can bias subsequent analyses. Within mass spectrometry-based peptide technologies, the relation between a peptide’s amino acid sequence and S/N remains largely nonquantitative. To address this challenge, we present a method to quantify and analyze mass spectrometry S/N of two peptide arrays, and we use this analysis to portray quality of data and to design future arrays for SAMDI mass spectrometry. Our study demonstrates that S/N varies significantly across peptides within peptide arrays, and variation in S/N is attributable to differences of single amino acids. We apply supervised machine learning to predict peptide S/N based on amino acid sequence, and identify specific physical properties of the amino acids that govern variation of this metric. We find low peptide–S/N concordance between arrays, demonstrating that different arrays require individual characterization and that global peptide–S/N relationships are difficult to identify. However, with proper peptide sampling, this study illustrates how machine learning can accurately predict the S/N of a peptide in an array, allowing for the efficient design of arrays through selection of high S/N peptides.

Intelligence Algorithms for Protein Classification by Mass Spectrometry

“…In their experiment, RF and SVM with fine-tuned parameters achieved superior performance in discrimination between original sample from Korea and blended samples with accuracy generally above 95%. Albert Y. Xue [ 58 ] presented a machine-learning based method to address the problem of the large nonquantitative relationships between the peptide's amino acid sequence and peptide signal-to-noise ratios (SNR). Random forest was applied to predict the peptide's SNR by its amino acid sequence with Q-squared value of 0.59, which confirmed that the amino acid sequence could be used to predict SNR values of peptide.…”

Peptide Arrays: Development and Application

“…It is already becoming difficult to fully understand the large data sets that are generated form peptide arrays, and as arrays increase in size, it will be more important to develop and apply complex analytical methods. A recent example from our group demonstrates the role of machine learning for more efficient peptide array design …”

Profiling Protein Tyrosine Phosphatase Specificity with Self-Assembled Monolayers for Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry and Peptide Arrays

“…This reaction product can then be quantitated with matrix-assisted laser desorption/ionization mass spectrometry, which reveals peaks corresponding to both the substrate and product (and any intermediates or additional products). The SAMDI-MS method is compatible with the common 384 and 1536 spot formats and has been used to profile enzymes with peptide arrays. ,,− We also recently demonstrated SAMDI could be used to profile the activity of a PTP on a phosphopeptide array . Becker and co-workers’ recent advance in studying protein–protein interactions using protein arrays and MALDI-MS also demonstrates the power of combining these technologies. , …”

“…The SAMDI-MS method is compatible with the common 384 and 1,536 spot formats and has been used to profile enzymes with peptide arrays. 23, 31, 39–43 We also recently demonstrated SAMDI could be used to profile the activity of a PTP on a phosphopeptide array. 44 Becker and coworkers’ recent advance in studying protein-protein interactions using protein arrays and MALDI-MS also demonstrates the power of combining these technologies.…”