De novo peptide sequencing by deep learning
Ontology highlight
ABSTRACT:
INSTRUMENT(S): LTQ Orbitrap, LTQ Orbitrap Velos, LTQ Orbitrap XL, Orbitrap Fusion, Q Exactive
ORGANISM(S): Escherichia Coli (ncbitaxon:562) Homo Sapiens (ncbitaxon:9606) Saccharomyces Cerevisiae (ncbitaxon:4932) Apis Mellifera (ncbitaxon:7460) Pseudomonas Aeruginosa (ncbitaxon:287) Drosophila Melanogaster (ncbitaxon:7227) Bacillus <bacterium> (ncbitaxon:1386) Vigna Mungo (ncbitaxon:3915) Solanum Lycopersicum (ncbitaxon:4081) Mus Musculus (ncbitaxon:10090) Methanosarcina Mazei (ncbitaxon:2209) Caenorhabditis Elegans (ncbitaxon:6239) Candidatus Endoloripes
SUBMITTER: 
Ming Li
PROVIDER: MSV000081382 | MassIVE | Tue Jul 25 07:26:00 BST 2017
REPOSITORIES: MassIVE
Similar Datasets
Project description:Generating and analyzing overlapping peptides through multienzymatic digestion is an efficient procedure for de novo protein using from bottom-up mass spectrometry (MS). Despite improved instrumentation and software, de novo MS data analysis remains challenging. In recent years, deep learning models have represented a performance breakthrough. Incorporating that technology into de novo protein sequencing workflows require machine-learning models capable of handling highly diverse MS data. In this study, we analyzed the requirements for assembling such generalizable deep learning models by systematically varying the composition and size of the training set. We assessed the generated models' performances using two test sets composed of peptides originating from the multienzyme digestion of samples from various species. The peptide recall values on the test sets showed that the deep learning models generated from a collection of highly N- and C-termini diverse peptides generalized 76% more over the termini-restricted ones. Moreover, expanding the training set's size by adding peptides from the multienzymatic digestion with five proteases of several species samples led to a 2-3 fold generalizability gain. Furthermore, we tested the applicability of these multienzyme deep learning (MEM) models by fully de novo sequencing the heavy and light monomeric chains of five commercial antibodies (mAbs). MEMs extracted over 10000 matching and overlapped peptides across six different proteases mAb samples, achieving a 100% sequence coverage for 8 of the ten polypeptide chains. We foretell that the MEMs' proven improvements to de novo analysis will positively impact several applications, such as analyzing samples of high complexity, unknown nature, or the peptidomics field.
2023-01-16 | PXD037803 | Pride
Project description:De novo peptide sequencing from tandem MS data is the key technology in proteomics for the characterization of proteins, especially for new sequences, such as mAbs. In this study, we propose a deep neural network model, DeepNovo, for de novo peptide sequencing. DeepNovo architecture combines recent advances in convolutional neural networks and recurrent neural networks to learn features of tandem mass spectra, fragment ions, and sequence patterns of peptides. The networks are further integrated with local dynamic programming to solve the complex optimization task of de novo sequencing. We evaluated the method on a wide variety of species and found that DeepNovo considerably outperformed state of the art methods, achieving 7.7-22.9% higher accuracy at the amino acid level and 38.1-64.0% higher accuracy at the peptide level. We further used DeepNovo to automatically reconstruct the complete sequences of antibody light and heavy chains of mouse, achieving 97.5-100% coverage and 97.2-99.5% accuracy, without assisting databases. Moreover, DeepNovo is retrainable to adapt to any sources of data and provides a complete end-to-end training and prediction solution to the de novo sequencing problem. Not only does our study extend the deep learning revolution to a new field, but it also shows an innovative approach in solving optimization problems by using deep learning and dynamic programming.
| S-EPMC5547637 | biostudies-literature
Project description:Unlike for DNA and RNA, accurate and high-throughput sequencing methods for proteins are lacking, hindering the utility of proteomics in applications where the sequences are unknown including variant calling, neoepitope identification, and metaproteomics. We introduce Spectralis, a de novo peptide sequencing method for tandem mass spectrometry. Spectralis leverages several innovations including a convolutional neural network layer connecting peaks in spectra spaced by amino acid masses, proposing fragment ion series classification as a pivotal task for de novo peptide sequencing, and a peptide-spectrum confidence score. On spectra for which database search provided a ground truth, Spectralis surpassed 40% sensitivity at 90% precision, nearly doubling state-of-the-art sensitivity. Application to unidentified spectra confirmed its superiority and showcased its applicability to variant calling. Altogether, these algorithmic innovations and the substantial sensitivity increase in the high-precision range constitute an important step toward broadly applicable peptide sequencing.
| S-EPMC10762064 | biostudies-literature
Project description:MOTIVATION:De novo peptide sequencing based on tandem mass spectrometry data is the key technology of shotgun proteomics for identifying peptides without any database and assembling unknown proteins. However, owing to the low ion coverage in tandem mass spectra, the order of certain consecutive amino acids cannot be determined if all of their supporting fragment ions are missing, which results in the low precision of de novo sequencing. RESULTS:In order to solve this problem, we developed pNovo 3, which used a learning-to-rank framework to distinguish similar peptide candidates for each spectrum. Three metrics for measuring the similarity between each experimental spectrum and its corresponding theoretical spectrum were used as important features, in which the theoretical spectra can be precisely predicted by the pDeep algorithm using deep learning. On seven benchmark datasets from six diverse species, pNovo 3 recalled 29-102% more correct spectra, and the precision was 11-89% higher than three other state-of-the-art de novo sequencing algorithms. Furthermore, compared with the newly developed DeepNovo, which also used the deep learning approach, pNovo 3 still identified 21-50% more spectra on the nine datasets used in the study of DeepNovo. In summary, the deep learning and learning-to-rank techniques implemented in pNovo 3 significantly improve the precision of de novo sequencing, and such machine learning framework is worth extending to other related research fields to distinguish the similar sequences. AVAILABILITY AND IMPLEMENTATION:pNovo 3 can be freely downloaded from http://pfind.ict.ac.cn/software/pNovo/index.html. SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
| S-EPMC6612832 | biostudies-other
Project description:This work introduces a method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties. We demonstrate how this model can execute a range of tasks such as generating analogues to a query structure and generating compounds predicted to be active against a biological target. As a proof of principle, the model is first trained to generate molecules that do not contain sulphur. As a second example, the model is trained to generate analogues to the drug Celecoxib, a technique that could be used for scaffold hopping or library expansion starting from a single molecule. Finally, when tuning the model towards generating compounds predicted to be active against the dopamine receptor type 2, the model generates structures of which more than 95% are predicted to be active, including experimentally confirmed actives that have not been included in either the generative model nor the activity prediction model. Graphical abstract .
| S-EPMC5583141 | biostudies-other
Project description:A benchmark set of bottom-up proteomics data for training deep learning networks. It has data from 51 organisms and includes nearly 1 million peptides.
2018-06-13 | PXD010000 | Pride
Project description:Proliferation of drug-resistant diseases raises the challenge of searching for new, more efficient antibiotics. Currently, some of the most effective antibiotics (i.e., Vancomycin and Daptomycin) are cyclic peptides produced by non-ribosomal biosynthetic pathways. The isolation and sequencing of cyclic peptide antibiotics, unlike the same activity with linear peptides, is time-consuming and error-prone. The dominant technique for sequencing cyclic peptides is nuclear magnetic resonance (NMR)-based and requires large amounts (milligrams) of purified materials that, for most compounds, are not possible to obtain. Given these facts, there is a need for new tools to sequence cyclic non-ribosomal peptides (NRPs) using picograms of material. Since nearly all cyclic NRPs are produced along with related analogs, we develop a mass spectrometry approach for sequencing all related peptides at once (in contrast to the existing approach that analyzes individual peptides). Our results suggest that instead of attempting to isolate and NMR-sequence the most abundant compound, one should acquire spectra of many related compounds and sequence all of them simultaneously using tandem mass spectrometry. We illustrate applications of this approach by sequencing new variants of cyclic peptide antibiotics from Bacillus brevis, as well as sequencing a previously unknown family of cyclic NRPs produced by marine bacteria. Supplementary Material is available online at www.liebertonline.com/cmb.
| S-EPMC3216106 | biostudies-literature
Project description:We have devised and implemented a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). On the basis of deep and reinforcement learning (RL) approaches, ReLeaSE integrates two deep neural networks-generative and predictive-that are trained separately but are used jointly to generate novel targeted chemical libraries. ReLeaSE uses simple representation of molecules by their simplified molecular-input line-entry system (SMILES) strings only. Generative models are trained with a stack-augmented memory network to produce chemically feasible SMILES strings, and predictive models are derived to forecast the desired properties of the de novo-generated compounds. In the first phase of the method, generative and predictive models are trained separately with a supervised learning algorithm. In the second phase, both models are trained jointly with the RL approach to bias the generation of new chemical structures toward those with the desired physical and/or biological properties. In the proof-of-concept study, we have used the ReLeaSE method to design chemical libraries with a bias toward structural complexity or toward compounds with maximal, minimal, or specific range of physical properties, such as melting point or hydrophobicity, or toward compounds with inhibitory activity against Janus protein kinase 2. The approach proposed herein can find a general use for generating targeted chemical libraries of novel compounds optimized for either a single desired property or multiple properties.
| S-EPMC6059760 | biostudies-literature
Project description:Testing datasets and pre-trained model for DeepNovo, a deep learning-based tool for de novo sequencing of DIA data.
2018-05-16 | MSV000082368 | MassIVE
Project description:Here, we combine comparative regulatory genomics with machine learning to investigate enhancer logic in melanoma. Through epigenomics profiling of 26 melanoma cell lines across six species, we examine the conservation of the two main melanoma states and underlying master regulators. By training a deep neural network on topic models derived from the human lines, we were able to classify not only human melanoma enhancers, but also regulatory regions in the other species. The deep learning model revealed important genomic features (i.e. TF binding motifs) for the different melanoma states, how they co-occur within melanoma enhancers, and where they are placed with respect to the central enhancer nucleosome. This in-depth analysis of the melanoma enhancer code allowed us to propose a mechanistic model of TF binding in MEL melanoma enhancers. Finally, by exploiting the deep layers of our model, we are able to identify causal mutations for melanoma enhancer loss and gain through evolution, not only affecting enhancer accessibility but also activity.
2020-04-22 | GSE142238 | GEO