Analyzing protein-protein interactions from affinity purification-mass spectrometry data with SAINT

Abstract

Significance Analysis of INTeractome (SAINT) is a software package for scoring protein-protein interactions based on label-free quantitative proteomics data (e.g., spectral count or intensity) in affinity purification-mass spectrometry (AP-MS) experiments. SAINT allows bench scientists to select bona fide interactions and remove nonspecific interactions in an unbiased manner. However, there is no 'one-size-fits-all' statistical model for every dataset, since the experimental design varies across studies. Key variables include the number of baits, the number of biological replicates per bait, and control purifications. Here we give a detailed account of input data format, control data, selection of high-confidence interactions, and visualization of filtered data. We explain additional options for customizing the statistical model for optimal filtering in specific datasets. We also discuss a graphical user interface of SAINT in connection to the LIMS system ProHits, which can be installed as a virtual machine on Mac OS X or Windows computers.

Figure 1

Choosing the appropriate version and optional arguments in SAINT.

Figure 2

Illustration of input data in the TIP49 dataset.

Figure 3

Importing the SAINT result files into Cytoscape for the analysis of the TIP49 dataset.

Figure 4

The network visualization of the TIP49 dataset in Cytoscape.

Figure 5

Select samples to analyze using the ProHits interface.

Figure 6

Define controls and samples and select parameters for file preparation.

Figure 7

Select SAINT options and initiate analysis within ProHits.

Figure 8

Tracking of the SAINT analysis parameters in ProHits.

Figure 9

Graphical user interface to explore SAINT results.

Figure 10

Automated Cytoscape generation of SAINT results from ProHits.

Figure 11

Comparison of probabilities using different options in the TIP49 dataset.

Figure 12

Ideal design of an AP-MS experiment with negative controls and biological replicates. Hypothetical experiment involving the purification of four different baits (colored circles) and a negative control (grey circle). Each of the biological replicate experiments is performed for each of the baits in a single batch. Different biological replicates are performed on batches of cells harvested at different times, and for which purification and proteolysis is done on different days. Notice the randomization of the loading order of the samples on the mass spectrometer to help preventing bias (e.g. carry-over).