Machine learning techniques can be applied to MALDI-TOF mass spectral data of drug-treated cells to obtain classification models which assign the mechanism of action of drugs. Here, we present an example application of this concept to the screening of antibacterial drugs that act at the major bacterial target sites such as the ribosome, penicillin-binding proteins, and topoisomerases in a pharmacologically relevant phenotypic setting. We show that antibacterial effects can be identified and classified in a label-free, high-throughput manner using wild-type Escherichia coli and Staphylococcus aureus cells at variable levels of target engagement. This phenotypic approach, which combines mass spectrometry and machine learning, therefore denoted as PhenoMS-ML, may prove useful for the identification and development of novel antibacterial compounds and other pharmacological agents.

Venom and toxin samples derived from animal origins are a rich source of bioactive peptides. A high proportion of bioactive peptides that have been identified in venom contain one or more disulfide bridges, which are thought to stabilize tertiary structure, and therefore influence the peptides' specificity and activity. In this chapter, we describe a label-free mass spectrometry-based screening workflow specifically to detect peptides that contain inter- and intramolecular disulfide bonds, followed by elucidation of their primary structure. This method is based on the determination of the normalized isotope shift (NIS) and the normalized mass defect (NMD) of peptides, two parameters which are heavily influenced by the presence of sulfur in a peptide, where cysteines are the main contributing residues. Using ant defensive secretions as an example, we describe the initial fractionation of the venom on strong cation exchange followed by nanoflow HPLC and mass spectrometry. High resolution zoom scan spectra of high-abundance peptides are acquired, allowing an accurate determination of both monoisotopic and average mass, which are essential for calculation of NMD and NIS. Candidate peptides exhibiting relative low NMD and high NIS values are selected for targeted de novo sequencing. By fine-tuning the collision energy for optimal fragmentation of each selected precursor ions, the full sequence of several novel inter- and intramolecular disulfide bond containing ant defensive peptides can be established.

15Protein mass fingerprinting by MALDI-TOF MS in combination with machine learning ML) permits the identification of response signatures generated in cell cultures upon exposure to well-17 characterized drugs. PhenoMS-ML is capable to identify and classify the mode of action of unknown 18 antibacterial agents in wild-type Escherichia coli and Staphylococcus aureus. It allows the sensitive, 19 specific, and high-throughput identification of drug target mechanisms that are difficult to assess by 20 other methods. 21 Main: 22Compound activity data from assays at isolated target proteins play an important role in 23 pharmacology, toxicology and medicinal chemistry, but their translation into systems of higher 24 complexity such as cell cultures (or patients) is frequently difficult (Brown and Wright 2016). This is 25 caused by pharmacokinetic effects, macromolecular crowding effects in the intracellular environment 26 which are absent in a biochemical buffer, or intracellular presence of competing ligands and 27 substrates, such as ATP (Swinney 2014). Numerous important pharmacological targets are difficult, if 28 not impossible, to study in biochemical systems because of their dependency on a specific 29 environment or unusual substrates. This is particularly evident and problematic in the field of 30 antibacterial drug discovery, where we (Bachelier, Mayer et al. 2006, Schiffmann, Neugebauer et al. 31 2006, Mendgen, Scholz et al. 2010) and many others (Payne, Gwynn et al. 2006) have repeatedly 32 failed to translate potent biochemical inhibitors into antibacterial drug candidates. Undeterred by the 33 efforts put in the identification of novel targets and mode of actions in bacteria, the main target 34 pathways of new and established antibacterial agents remain cell wall synthesis, ribosomal machinery, 35 and nucleic acid processing (Livermore, Blaser et al. 2011). Making things worse, these pathways are 36 notoriously difficult to study in biochemical systems, let alone in high-throughput manner, as would 37 be desirable for compound screenings. 38Considering the numerous difficulties involved in setting up individual assay procedures for these 39 important antibacterial targets, whose results would be a limited predictor for actual in vivo efficacy, 40we reasoned that a phenotypic approach to drug screening is highly desirable. Phenotypic 41 antimicrobial testing is typically performed using growth assays (Silver 2011). However, information 42 obtained from such assays is mostly restricted to a binary 'dead-or-alive' information, and does not 43 provide any further information about the targets, pathways, or modes of action that are involved. It 44 seems advantageous to employ cell-based phenotypic screening methods that yield more information 45 on the target and mode of action involved (Feng, Mitchison et al. 2009). 46 A method that addresses this issue is bacterial cytological profiling as described by the Pogliano 47 group (Nonejuie, Burkart et al. 2013), who identified cellular pathways involved in r...