Enhancement of Proteome Coverage by Ion Mobility Fractionation Coupled to PASEF on a TIMS-QTOF Instrument

Abstract

Trapped ion-mobility spectrometry (TIMS) was used to fractionate ions in the gas phase based on their ion mobility (V s/cm²), followed by parallel accumulation-serial fragmentation (PASEF) using a quadrupole time-of-flight instrument to determine the effect on the depth of proteome coverage. TIMS fractionation (up to four gas-phase fractions) coupled to data-dependent acquisition (DDA)-PASEF resulted in the detection of ∼7000 proteins and over 70,000 peptides overall from 200 ng of human (HeLa) cell lysate per injection using a commercial 25 cm ultra high performance liquid chromatography (UHPLC) column with a 90 min gradient. This result corresponded to ∼19 and 30% increases in protein and peptide identifications, respectively, when compared to a default, single-range TIMS DDA-PASEF analysis. Quantitation precision was not affected by TIMS fractionation as demonstrated by the average and median coefficient of variation values that were less than 4% upon label-free quantitation of technical replicates. TIMS fractionation was utilized to generate a DDA-based spectral library for downstream data-independent acquisition (DIA) analysis of lower sample input using a shorter LC gradient. The TIMS-fractionated library, consisting of over 7600 proteins and 82,000 peptides, enabled the identification of ∼4000 and 6600 proteins from 10 and 200 ng of human (HeLa) cell lysate input, respectively, with a 20 min gradient, single-shot DIA analysis. Data are available in ProteomeXchange: identifier PXD033129.

Keywords: DDA-PASEF; DIA-PASEF; gas-phase fractionation; ion mobility; proteomics; spectral library; timsTOF Pro.

Figure 1.

Optimization of single TIMS range with DDA-PASEF analysis. Comparison of peptide ion density within the default range of 0.6-1.6 1/K0 (A) to the narrowed range of 0.7-1.4 1/K0 (B) for 200ng of HeLa digest. Average protein identification per run, both with and without MBR, with a 45 min gradient (C) and 90 min gradient (D) DDA-PASEF analysis, which shows the effect of narrowing the TIMS ion mobility range. The effect of narrowing the TIMS range on average peptide identification per run, with and without MBR, in both 45 min gradient (E) and 90 min gradient (F) DDA-PASEF analysis. Error bar represents +SD.

Figure 2.

Effect of TIMS fractionation on protein and peptide coverage. Comparison of protein identification in 45 min gradient (A) and 90 min gradient (B) DDA-PASEF analysis of 200ng HeLa digest where 1 fraction represents the optimized full IM range of 0.7-1.4 1/K₀ followed by 2 fractions consisting of 0.7-1.1 1/K₀ and 1.0-1.4 1/K₀; 3 fractions consisting of 0.7-1.0 1/K₀, 0.9-1.2 1/K₀, and 1.1-1.4 1/K₀; 4 fractions consisting of 0.7-0.95 1/K₀, 0.85-1.1 1/K₀, 1.0-1.25 1/K₀, 1.15-1.4 1/K₀. Peptide identification obtained with 45 min gradient (C) and 90 min gradient (D) DDA-PASEF analysis.

Figure 3.

Cumulative protein and peptide identifications from TIMS fractionation compared to technical replicates of a single TIMS range. Protein identification obtained from 45 min gradient (A) and 90 min gradient (B) DDA-PASEF analysis of 200ng HeLa digest showing the cumulative increase based on number of TIMS fractions (solid line, error bars represent ± SD) compared to technical replicates of the optimized single TIMS range (dashed line). Cumulative increase comparison at the peptide level for the same 45 min (C) and 90 min (D) DDA-PASEF analyses.

Figure 4.

Effect of TIMS fractionation on peptide detection and quantitation. Four fraction TIMS DDA-PASEF analysis showing peptide ion density within the 0.7-0.95 1/K₀ (A), 0.85-1.1 1/K₀ (B), 1.0-1.25 1/K₀ (C), and 1.15-1.4 1/K₀ (D). Accurate and reproducible measurement of peptide IM values was observed. Quantitation precision is not affected by multi-range TIMS fractionation as demonstrated by the number of quantifiable proteins at a specific % CV cutoff as well as the overall median and average % CV values obtained upon comparison to single range TIMS DDA-PASEF analysis for 1 Frac (E) compared to 4 Frac (F).

Figure 5.

TIMS fractionation provides complementary coverage and improves bioinformatic analysis. Differences between quantifiable unique IDs are shown in the qualitative Venn Diagram (A). Ingenuity Pathway Analysis reveals several targets within IL10 signaling pathway (B) were only detected in TIMS fractionated data with high quantitation precision (C). This pathway was significantly enriched in TIMS fractionated data (p=0.02, Fisher’s exact test with B-H correction) and NS (p=0.12) with standard DDA acquisition.

Figure 6.

Optimization of 2-range TIMS DDA-PASEF for in-depth quantitative proteomics as well as spectral library building for DIA-PASEF. Two IM-range DDA-PASEF analysis was performed within the ion dense region of 0.8-1.25 1/K₀ at a longer gradient time (150 min) where over 7,300 proteins (A) and 71,000 peptides (B) on average per run were identified. Quantitation precision was maintained for over 7,000 proteins. Overall, a spectral library of 82,241 peptides corresponding to 7,615 proteins was generated for subsequent DIA-PASEF analysis. A shorter gradient time of 20 min was utilized for DIA-PASEF analysis of both 10ng and 200ng HeLa digest, where significant single-shot coverage at the protein (C) and precursor (D) level was obtained.