Statistical analysis and modeling of mass spectrometry (MS) data have a long and rich history with several modern MS-based applications using statistical and chemometric methods. Recently, machine learning (ML) has experienced a renaissance due to advents in computational hardware and the development of new algorithms for artificial neural networks (ANN) and deep learning architectures. Moreover, recent successes of new ANN and deep learning architectures in several areas of science, engineering, and society have further strengthened the ML field. Importantly, modern ML methods and architectures have enabled new approaches for tasks related to MS that are now widely adopted in several popular MS-based subdisciplines, such as mass spectrometry imaging and proteomics. Herein, we aim to provide an introductory summary of the practical aspects of ML methodology relevant to MS. Additionally, we seek to provide an up-to-date review of the most recent developments in ML integration with MS-based techniques while also providing critical insights into the future direction of the field.

Lignin is an aromatic biopolymer that may yield valuable chemicals currently obtained solely from petroleum. However, extraction of lignin by using traditional methods, such as organosolv extraction, produces very complex mixtures. Molecular level characterization of the major components is essential to be able to rationally tailor methodology for the conversion of these mixtures to transportation fuel and valuable chemicals. In this study, high performance liquid chromatography/high resolution tandem mass spectrometry (HPLC/MSⁿ) was used to obtain molecular weight, elemental composition and structural information for the major components in an organosolv lignin sample. HPLC/MSⁿ coupled with hydroxide-doped electrospray ionization was used to identify the structures of the major components by using a Thermo Scientific linear quadrupole ion trap-Fourier transform ion cyclotron resonance hybrid mass spectrometer (LQIT/FT-ICR). The results reported here demonstrate that the major products of organosolv extraction are low molecular weight compounds, including monomeric and dimeric lignin units, with various functionalities.

With limited current biomass utilization as a renewable resource, it is important to develop a method to convert biomass into materials to replace fossil fuel products. In this article, lignin and carbohydrate derived monomers, including 4-methylcatechol, 5-hydroxymethylfurfural (HMF), and furfural, were used to prepare bisphenol–furan type polyphenols. Epoxy networks were synthesized from different polyphenol monomers via glycidylation and curing steps under identical reaction conditions. The structures of bisphenol–furan trinuclear compounds, epoxide precursors, and cured epoxy polymer networks were characterized by nuclear magnetic resonance spectroscopy (NMR), Fourier transform infrared spectroscopy (FTIR) and high resolution mass spectrometry (MS). Differential scanning calorimetry (DSC), thermogravimetric analysis (TGA), and dynamic mechanical analysis (DMA) were conducted to test the thermo-mechanical properties of the resulting networks. These polymer materials exhibited an excellent glassy modulus (9.6 GPa), glass transition temperature (T_g) (110 °C), and thermal stability. The density and water absorption of the materials were measured. This work provides synthesis routes to highly bio-based epoxy thermosets, which paves the way towards preparing moldable polymers from wood via biorefinery products.