De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments

Abstract

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.

Machine learning strategies to tackle data challenges in mass spectrometry-based proteomics

“…The ProteomeTools data consists of ground truth fragment ion intensities, RTs, and in some cases CCS values, that are expected to be largely free of interference due to the construction of the peptide pools. These data have been used to develop several ML tools, including the Prosit deep neural network for fragment ion intensity and RT prediction [4], and several de novo peptide sequencing tools [36], [37], [38], [39]. Additionally, ProteomeTools is often used as a benchmark dataset to evaluate prediction tools, such as the CCS prediction model from Meier et al [11].…”

Benchmarking and integrating human B-cell receptor genomic and antibody proteomic profiling

“…There is also a need to understand how Ab-seq experimental and computational protocols impact the coverage of antibody diversity 34,79,80 . We expect antibody repertoire studies will be facilitated in the future by the advances in both machine learning-based 43,45 and experiment-based 69,70 de novo peptide sequence analysis efforts.…”

“…Since antibodies are so similar to each other yet so diverse, and the proportion of shared clones between individuals is very low 26 , it is more sensible to create a custom reference database from the same individual to ensure higher accuracy 32,34,35,37 . Novel methods have been developed where the peptide sequence can be determined de novo (without reference sequences), but these methods are not yet well-established for antibodies [38][39][40][41][42][43][44][45] . Therefore, the integration of Ab-seq with BCR sequencing technologies holds the promise of connecting the genomic and proteomic levels of the adaptive immune repertoire.…”

Multi-Modal Mass Spectrometry Identifies a Conserved Protective Epitope inS. pyogenesStreptolysin O

“…A novel approach involving cumulative fragment-ion evidence was applied to enhance de novo peptide sequencing and subsequent primary protein structure assembly. Peptide candidates were generated using three deep-learning-based de novo peptide tools: PointNovo (51), CasaNovo (52), and InstaNovo (53). For PointNovo, two in-house multienzyme-trained models (54) were utilized, whereas default models were employed for CasaNovo and InstaNovo.…”