Proteome rearrangements after auditory learning: high-resolution profiling of synapse-enriched protein fractions from mouse brain

Abstract

Learning and memory processes are accompanied by rearrangements of synaptic protein networks. While various studies have demonstrated the regulation of individual synaptic proteins during these processes, much less is known about the complex regulation of synaptic proteomes. Recently, we reported that auditory discrimination learning in mice is associated with a relative down-regulation of proteins involved in the structural organization of synapses in various brain regions. Aiming at the identification of biological processes and signaling pathways involved in auditory memory formation, here, a label-free quantification approach was utilized to identify regulated synaptic junctional proteins and phosphoproteins in the auditory cortex, frontal cortex, hippocampus, and striatum of mice 24 h after the learning experiment. Twenty proteins, including postsynaptic scaffolds, actin-remodeling proteins, and RNA-binding proteins, were regulated in at least three brain regions pointing to common, cross-regional mechanisms. Most of the detected synaptic proteome changes were, however, restricted to individual brain regions. For example, several members of the Septin family of cytoskeletal proteins were up-regulated only in the hippocampus, while Septin-9 was down-regulated in the hippocampus, the frontal cortex, and the striatum. Meta analyses utilizing several databases were employed to identify underlying cellular functions and biological pathways. Data are available via ProteomeExchange with identifier PXD003089. How does the protein composition of synapses change in different brain areas upon auditory learning? We unravel discrete proteome changes in mouse auditory cortex, frontal cortex, hippocampus, and striatum functionally implicated in the learning process. We identify not only common but also area-specific biological pathways and cellular processes modulated 24 h after training, indicating individual contributions of the regions to memory processing.

Keywords: auditory learning; chemical synapse; label-free quantification; learning and memory; phosphoproteomics; quantitative mass spectrometry.

Figure 1

Four brain regions implicated in FM‐tone discrimination learning were analyzed. The rodent auditory cortex (AC) was shown to be critical for FMTD learning (Ohl et al. 1999). The AC is connected with a number of cortical and subcortical structures (Budinger and Scheich 2009), including strong efferent fibers toward the striatum (STR) and the entorhinal cortex, which feeds directly to the hippocampus (HIP). The connection between AC and the frontal cortex (FC) is reciprocal. The projection from AC to the STR is differentially modulated by FMTD learning (Schulz et al. 2016). Strengths of connections are roughly indicated by the thickness of arrows.

Figure 2

FMTD training‐induced synaptic proteome changes. Proteome analysis was performed on SJ‐enriched samples from the auditory cortex (AC), frontal cortex (FC), hippocampus (HIP), and striatum (STR) of mice of set 1a 24 h after FMTD training (AV) as compared to naïve controls (NV). Left part of each panel: Volcano plots showing the relative abundance ratios (AV/NV) of all identified and quantified proteins. Dashed horizontal and vertical lines indicate the statistical significance thresholds (−10logP ≥ 13) and the protein fold‐change thresholds (AV/NV ratios ≤ 1/1.5 or ≥ 1.5), respectively. AV/NV ratios meeting these criteria are represented by data points in the upper left and upper right subareas; the numbers of these data points and the total numbers of data points are given below the plots. Right part of each panel: Heat map clusters of significantly training‐regulated proteins are shown for NV and AV mice (numbers above the heat maps indicate individual experimental animals; note: because of losses during SJ preparation and/or nanoLC‐mass spectrometry MS/MS, the numbers of individual animal data sets were diminished for AC to n = 4 per group and for FC to n = 5 in the AV group). Hierarchical clustering is generated using the neighbor joining algorithm with an Euclidean distance similarity measurement of the log2 ratios of the abundance of each sample relative to the average abundance. High‐resolution heat maps including cluster analyses are available from synprot (http://www.synprot.de/high-resolution_synaptic_proteome/).

Figure 3

Cross‐regional and region‐specific proteome and phosphoproteome changes. The numbers of significantly regulated SJ‐enriched proteins of the analyzed brain regions after FMTD training are compared in a Venn diagram. Numbers refer to proteins with training‐induced abundance changes in SJ‐enriched protein fractions and numbers in parentheses to proteins with changed phosphorylation patterns upon FMTD training. Venn analysis was performed with the mathematical software package ‘DanteR’ (Pacific Northwest National Laboratory/http://omics.pnl.gov) using data from Tables S3 and S4. AC, auditory cortex; FC, frontal cortex; HIP, hippocampus; STR, striatum.

Figure 4

Assignment of FMTD training‐regulated SJ‐enriched proteins to structural and functional elements and processes. (a) Numbers of proteins regulated in their abundance as listed in Table S3. (b) Numbers of proteins with phosphopeptide changes as listed in Table S4. AC, auditory cortex; FC, frontal cortex; HIP, hippocampus; STR, striatum.

Figure 5

Representation of biological functions and pathways in the identified protein data sets by single enrichment analysis (SEA) utilizing GeneCodis as a tool (see Table S6). The analysis was performed for each examined brain region with the combined data on protein and phosphopeptide abundances (Tables S3 and S4). Annotation databases such as Gene Ontology (GO) (http://geneontology.org/) assign proteins and genes to their ‘biological functions’ or ‘biological pathways’. The SEA tests for significantly represented biological pathways within a given list of proteins. The significance is determined by comparing the frequency of representation of a given pathway in that list with the expected random frequency. The network was calculated by in‐house scripts and visualized with the tool Gephi (http://gephi.github.io/). Only GO terms with at least three proteins in at least one of the brain regions were taken into account. Nodes are depicted as circles. Each node represents a GO term, the color indicates the brain region (green: auditory cortex; blue: frontal cortex; magenta: hippocampus; red: striatum). The size of a given node visualizes the number of proteins that it has in common with other nodes. Additionally, the number and strengths of connections (indicated by line width) indicate the number of proteins that a particular node shares with other nodes. Numbers and strengths of connections, in turn, determine the distance of nodes, thus clustering closely related nodes. If nodes represent the same GO term and include identical sets of proteins, but derive from different brain regions, they were merged into one node (indicated by respective colors).