Mass spectrometry-based proteomics focuses on identifying the peptide that generates a tandem mass spectrum. Traditional methods rely on protein databases but are often limited or inapplicable in certain contexts. De novo peptide sequencing, which assigns peptide sequences to spectra without prior information, is valuable for diverse biological applications; however, owing to a lack of accuracy, it remains challenging to apply. Here we introduce InstaNovo, a transformer model that translates fragment ion peaks into peptide sequences. We demonstrate that InstaNovo outperforms state-of-the-art methods and showcase its utility in several applications. We also introduce InstaNovo+, a diffusion model that improves performance through iterative refinement of predicted sequences. Using these models, we achieve improved therapeutic sequencing coverage, discover novel peptides and detect unreported organisms in diverse datasets, thereby expanding the scope and detection rate of proteomics searches. Our models unlock opportunities across domains such as direct protein sequencing, immunopeptidomics and exploration of the dark proteome.

Snake venoms represent a danger to human health, but also a gold mine of bioactive proteins that can be harnessed for drug discovery purposes. The evolution of snakes and their venom has been studied for decades, particularly via traditional morphological and basic genetic methods alongside venom proteomics. However, while the field of genomics has matured rapidly over the past 2 decades, owing to the development of next-generation sequencing technologies, snake genomics remains in its infancy. Here, we provide an overview of the state of the art in snake genomics and discuss its potential implications for studying venom evolution and toxinology. On the basis of current knowledge, gene duplication and positive selection are key mechanisms in the neofunctionalization of snake venom proteins. This makes snake venoms important evolutionary drivers that explain the remarkable venom diversification and adaptive variation observed in these reptiles. Gene duplication and neofunctionalization have also generated a large number of repeat sequences in snake genomes that pose a significant challenge to DNA sequencing, resulting in the need for substantial computational resources and longer sequencing read length for high-quality genome assembly. Fortunately, owing to constantly improving sequencing technologies and computational tools, we are now able to explore the molecular mechanisms of snake venom evolution in unprecedented detail. Such novel insights have the potential to affect the design and development of antivenoms and possibly other drugs, as well as provide new fundamental knowledge on snake biology and evolution.

Each year, snakebite envenoming claims thousands of lives and causes severe injury to victims across sub-Saharan Africa, many of whom depend on antivenoms derived from animal plasma as their sole treatment option ¹ . Traditional antivenoms are expensive, can cause adverse immunological reactions, offer limited efficacy against local tissue damage and are often ineffective against all medically relevant snake species ² . There is thus an urgent unmet medical need for innovation in snakebite envenoming therapy. However, developing broad-spectrum treatments is highly challenging owing to the vast diversity of venomous snakes and the complex and variable composition of their venoms ³ . Here we addressed this challenge by immunizing an alpaca and a llama with the venoms of 18 different snakes, including mambas, cobras and a rinkhals, constructing phage display libraries, and identifying high-affinity broadly neutralizing nanobodies. We combined eight of these nanobodies into a defined oligoclonal mixture, resulting in an experimental polyvalent recombinant antivenom that was capable of neutralizing seven toxin families or subfamilies. This antivenom effectively prevented venom-induced lethality in vivo across 17 African elapid snake species and markedly reduced venom-induced dermonecrosis for all tested cytotoxic venoms. The recombinant antivenom performed better than a currently used plasma-derived antivenom and therefore shows considerable promise for comprehensive, continent-wide protection against snakebites by all medically relevant African elapids.

Bottom-up mass spectrometry-based proteomics is challenged by the task of identifying the peptide that generates a tandem mass spectrum. Traditional methods that rely on known peptide sequence databases are limited and may not be applicable in certain contexts. De novo peptide sequencing, which assigns peptide sequences to the spectra without prior information, is valuable for various biological applications; yet, due to a lack of accuracy, it remains challenging to apply this approach in many situations. Here, we introduce InstaNovo, a transformer neural network with the ability to translate fragment ion peaks into the sequence of amino acids that make up the studied peptide(s). The model was trained on 28 million labelled spectra matched to 742k human peptides from the ProteomeTools project. We demonstrate that InstaNovo outperforms current state-of-the-art methods on benchmark datasets and showcase its utility in several applications. Building upon human intuition, we also introduce InstaNovo+, a multinomial diffusion model that further improves performance by iterative refinement of predicted sequences. Using these models, we could de novo sequence antibody-based therapeutics with unprecedented coverage, discover novel peptides, and detect unreported organisms in different datasets, thereby expanding the scope and detection rate of proteomics searches. Finally, we could experimentally validate tryptic and non-tryptic peptides with targeted proteomics, demonstrating the fidelity of our predictions. Our models unlock a plethora of opportunities across different scientific domains, such as direct protein sequencing, immunopeptidomics, and exploration of the dark proteome.

Snake venom metalloproteinases (SVMPs) and snake venom serine proteinases (SVSPs) are among the most abundant enzymes in many snake venoms, particularly among viperids. These proteinases are responsible for some of the clinical manifestations classically seen in viperid envenomings, including hemorrhage, necrosis, and coagulopathies. The objective of this study was to investigate the enzymatic activities of these proteins using a high-throughput peptide library to screen for the proteinase targets of the venoms of five viperid (Echis carinatus, Bothrops asper, Daboia russelii, Bitis arietans, Bitis gabonica) and one elapid (Naja nigricollis) species of high medical importance. The proteinase activities of these venoms were each tested against 360 peptide substrates, yielding 2160 activity profiles. A nonlinear regression model that accurately described the observed enzymatic activities was fitted to the experimental data, allowing for the comparison of cleavage rates across species. In this study, previously unknown protein targets of snake venom proteinases were identified, potentially implicating novel human and animal proteins that may be involved in the pathophysiology of viper envenomings. The functional relevance of these targets was further evaluated and discussed. These new findings may contribute to our understanding of the clinical manifestations and underlying biochemical mechanisms of snakebite envenoming by viperid species.

Positional proteomics methodologies have transformed protease research, and have brought mass spectrometry (MS)-based degradomics studies to the forefront of protease characterization and system-wide interrogation of protease signaling. Considerable advancements in both sensitivity and throughput of liquid chromatography (LC)-MS/MS instrumentation enable the generation of enormous positional proteomics datasets of natural and protein termini and neo-termini of cleaved protease substrates. However, concomitant progress has not been observed to the same extent in data analysis and post-processing steps, arguably constituting the largest bottleneck in positional proteomics workflows. Here, we present a computational tool, CLIPPER 2.0, that builds on prior algorithms developed for MS-based protein termini analysis, facilitating peptide-level annotation and data analysis. CLIPPER 2.0 can be used with several sample preparation workflows and proteomics search algorithms and enables fast and automated database information retrieval, statistical and network analysis, as well as visualization of terminomic datasets. We demonstrate the applicability of our tool by analyzing GluC and MMP9 cleavages in HeLa lysates. CLIPPER 2.0 is available at https://github.com/UadKLab/CLIPPER-2.0.