MS-DIAL: data-independent MS/MS deconvolution for comprehensive metabolome analysis

Abstract

Data-independent acquisition (DIA) in liquid chromatography (LC) coupled to tandem mass spectrometry (MS/MS) provides comprehensive untargeted acquisition of molecular data. We provide an open-source software pipeline, which we call MS-DIAL, for DIA-based identification and quantification of small molecules by mass spectral deconvolution. For a reversed-phase LC-MS/MS analysis of nine algal strains, MS-DIAL using an enriched LipidBlast library identified 1,023 lipid compounds, highlighting the chemotaxonomic relationships between the algal strains.

Figure 1. Main workflow of MS-DIAL program

(a) MS vendor format or mzML is converted to ABF binary format for rapid data retrieval. (b) Peak spotting (two-dimensional peak detection, see main text) is performed to determine precursor ions for MS/MS spectra. The detected precursor ions are described as spots. The blue color range describes the isolation window of precursor ions. The focused spot is also depicted as the following procedures. (c) The MS²Dec deconvolution process includes chromatogram extractions (drawn by regular line on the left panel), model peak constructions (drawn by bold line on the left panel), and mass spectrum reconstructions (right panel). (d) The MSP format is utilized for matching experimental mass spectra against mass spectral libraries such as MassBank or LipidBlast. The compound identification is performed by the weighted similarity score of retention time, accurate mass, isotope ratio, and MS/MS spectra.

Figure 2. A deconvolution example with respect to SWATH acquisition with HILIC positive ion mode

Two pharmaceutical agents, metoclopramide and norcocaine, were detected in untargeted metabolomics screens and co-eluted within 1.8-s peak top difference. The MS/MS ion traces with respect to these two metabolites are also shown in the top-right panel of precursor ion traces. The middle panels show raw MS/MS spectra of metoclopramide (left) and norcocaine (right), respectively. The spectrum of metoclopramide dominates and masks that of norcocaine, making its detection highly difficult. The bottom panels show the deconvoluted MS/MS spectrum and spectra matching results of metoclopramide (left) and norcocaine (right) yielding dot-product scores of 0.80 and 0.86, respectively.

Figure 3. System validation for lipid profiling, lipid coverage and chemotaxonomic relationship of nine algal species

(a) The experimental and predicted retention times of 254 (training) and 1,808 (validation) lipids were plotted along X-axis and Y-axis, respectively. Prediction was performed by using PLS-R on 464 properties from the PaDEL-descriptor suite. The R square, Q square, and standard deviation of the validation set were 0.9935, 0.9939, and 0.14 min, respectively. (b) Comparison of mass spectra in positive (left) and negative (right) ion modes in commonly identified lipids between SWATH (data-independent) and the traditional data-dependent (DDA) methods. The blue histogram shows the spectra similarity between the deconvoluted- and DDA spectra. The red histogram shows the similarity between the centroid (non-deconvoluted)- and DDA spectra. (c) Venn diagram of lipid coverages between SWATH and DDA methods. The top panel is the result of nine algal species at 10 ms (SWATH) and 50 ms (DDA) accumulation times in both ionization modes for product ion scanning. The bottom panel is the result of Chlamydomonas reinhardtii that the accumulation time of SWATH was 10 ms and 30 ms in positive- and negative ion modes, respectively. (d) Hierarchical clustering analysis for nine algal species and 1,023 binary variables. The top and bottom trees are from the classical taxonomies and chemotaxonomies, respectively. The yellow and blue colors between these trees show ‘included’ and ‘not included’ in each algae. UTEX 2341 is currently annotated as Chlorella minutissima. Chlamydomonas reinhardtii and Dunaliella salina are distinguished in Family levels as Chlamydomonadaceae and Dunaliellaceae, respectively.