In silico identification software (ISIS): a machine learning approach to tandem mass spectral identification of lipids.
Ontology highlight
ABSTRACT: Motivation
Liquid chromatography-mass spectrometry-based metabolomics has gained importance in the life sciences, yet it is not supported by software tools for high throughput identification of metabolites based on their fragmentation spectra. An algorithm (ISIS: in silico identification software) and its implementation are presented and show great promise in generating in silico spectra of lipids for the purpose of structural identification. Instead of using chemical reaction rate equations or rules-based fragmentation libraries, the algorithm uses machine learning to find accurate bond cleavage rates in a mass spectrometer employing collision-induced dissociation tandem mass spectrometry.Results
A preliminary test of the algorithm with 45 lipids from a subset of lipid classes shows both high sensitivity and specificity.
SUBMITTER: Kangas LJ
PROVIDER: S-EPMC3381961 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Tandem mass spectral libraries (MS/MS) are usually built by acquiring experimentally measured mass spectra from chemical reference compounds. We here show the versatility of in-silico or computer generated tandem mass spectra that are directly obtained from compound structures. We use the freely available LipidBlast development software to generate 15 000 MS/MS spectra of the glucuronosyldiacylglycerol (GlcADG) lipid class, recently discovered for the first time in plants. The generation of such an in-silico MS/MS library for positive and negative ionization mode took 5 h development time, including the validation of the obtained mass spectra. Such libraries allow for high-throughput annotations of previously unknown glycolipids. The publicly available LipidBlast templates are universally applicable for the development of MS/MS libraries for novel lipid classes.
| S-EPMC4238643 | biostudies-other
Project description:MotivationUntargeted mass spectrometry (MS/MS) is a powerful method for detecting metabolites in biological samples. However, fast and accurate identification of the metabolites' structures from MS/MS spectra is still a great challenge.ResultsWe present a new analysis method, called SubFragment-Matching (SF-Matching) that is based on the hypothesis that molecules with similar structural features will exhibit similar fragmentation patterns. We combine information on fragmentation patterns of molecules with shared substructures and then use random forest models to predict whether a given structure can yield a certain fragmentation pattern. These models can then be used to score candidate molecules for a given mass spectrum. For rapid identification, we pre-compute such scores for common biological molecular structure databases. Using benchmarking datasets, we find that our method has similar performance to CSI: FingerID and those very high accuracies can be achieved by combining our method with CSI: FingerID. Rarefaction analysis of the training dataset shows that the performance of our method will increase as more experimental data become available.Availability and implementationSF-Matching is available from http://www.bork.embl.de/Docu/sf_matching.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC7703789 | biostudies-literature
Project description:Lipid identification from data produced with high-throughput technologies is essential to the elucidation of the roles played by lipids in cellular function and disease. Software tools for identifying lipids from tandem mass (MS/MS) spectra have been developed, but they are often costly or lack the sophistication of their proteomics counterparts. We have developed Greazy, an open source tool for the automated identification of phospholipids from MS/MS spectra, that utilizes methods similar to those developed for proteomics. From user-supplied parameters, Greazy builds a phospholipid search space and associated theoretical MS/MS spectra. Experimental spectra are scored against search space lipids with similar precursor masses using a peak score based on the hypergeometric distribution and an intensity score utilizing the percentage of total ion intensity residing in matching peaks. The LipidLama component filters the results via mixture modeling and density estimation. We assess Greazy's performance against the NIST 2014 metabolomics library, observing high accuracy in a search of multiple lipid classes. We compare Greazy/LipidLama against the commercial lipid identification software LipidSearch and show that the two platforms differ considerably in the sets of identified spectra while showing good agreement on those spectra identified by both. Lastly, we demonstrate the utility of Greazy/LipidLama with different instruments. We searched data from replicates of alveolar type 2 epithelial cells obtained with an Orbitrap and from human serum replicates generated on a quadrupole-time-of-flight (Q-TOF). These findings substantiate the application of proteomics derived methods to the identification of lipids. The software is available from the ProteoWizard repository: http://tiny.cc/bumbershoot-vc12-bin64 .
| S-EPMC4996967 | biostudies-literature
Project description:Current tandem mass spectral libraries for lipid annotations in metabolomics are limited in size and diversity. We provide a freely available computer-generated tandem mass spectral library of 212,516 spectra covering 119,200 compounds from 26 lipid compound classes, including phospholipids, glycerolipids, bacterial lipoglycans and plant glycolipids. We show platform independence by using tandem mass spectra from 40 different mass spectrometer types including low-resolution and high-resolution instruments.
| S-EPMC3731409 | biostudies-literature
Project description:Shotgun proteomics experiments are dependent upon database search engines to identify peptides from tandem mass spectra. Many of these algorithms score potential identifications by evaluating the number of fragment ions matched between each peptide sequence and an observed spectrum. These systems, however, generally do not distinguish between matching an intense peak and matching a minor peak. We have developed a statistical model to score peptide matches that is based upon the multivariate hypergeometric distribution. This scorer, part of the "MyriMatch" database search engine, places greater emphasis on matching intense peaks. The probability that the best match for each spectrum has occurred by random chance can be employed to separate correct matches from random ones. We evaluated this software on data sets from three different laboratories employing three different ion trap instruments. Employing a novel system for testing discrimination, we demonstrate that stratifying peaks into multiple intensity classes improves the discrimination of scoring. We compare MyriMatch results to those of Sequest and X!Tandem, revealing that it is capable of higher discrimination than either of these algorithms. When minimal peak filtering is employed, performance plummets for a scoring model that does not stratify matched peaks by intensity. On the other hand, we find that MyriMatch discrimination improves as more peaks are retained in each spectrum. MyriMatch also scales well to tandem mass spectra from high-resolution mass analyzers. These findings may indicate limitations for existing database search scorers that count matched peaks without differentiating them by intensity. This software and source code is available under Mozilla Public License at this URL: http://www.mc.vanderbilt.edu/msrc/bioinformatics/.
| S-EPMC2525619 | biostudies-literature
Project description:Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal space. Specifically, the training acts on the spectral domain and seeks to modify the eigenvalues and eigenvectors of transfer operators in direct space. The proposed method is ductile and can be tailored to return either linear or non-linear classifiers. Adjusting the eigenvalues, when freezing the eigenvectors entries, yields performances that are superior to those attained with standard methods restricted to operate with an identical number of free parameters. To recover a feed-forward architecture in direct space, we have postulated a nested indentation of the eigenvectors. Different non-orthogonal basis could be employed to export the spectral learning to other frameworks, as e.g. reservoir computing.
| S-EPMC7910623 | biostudies-literature
Project description:Fatty acid esters of hydroxy fatty acids (FAHFAs) are a family of recently discovered lipids with important physiological functions in mammals and plants. However, low detection sensitivity in negative ionization mode mass spectrometry makes low-abundance FAHFA challenging to analyze. A 2-dimethylaminoethylamine (DMED) based chemical derivatization strategy was recently reported to improve the MS sensitivity of FAHFAs by labeling FAHFAs with a positively ionizable tertiary amine group. To facilitate reliable, high-throughput, and automatic annotation of these compounds, a DMED-FAHFA in silico library containing 4290 high-resolution tandem mass spectra covering 264 different FAHFA classes was developed. The construction of the library was based on the heuristic information from MS/MS fragmentation patterns of DMED-FAHFA authentic standards, and then, the patterns were applied to computer-generated DMED-FAHFAs. The developed DMED-FAHFA in silico library was demonstrated to be compatible with library search software NIST MS Search and the LC-MS/MS data processing tool MS-DIAL to guarantee high-throughput and automatic annotations. Applying the in silico library in Arabidopsis thaliana samples for profiling FAHFAs by high-resolution LC-MS/MS enabled the annotation of 19 DMED-FAHFAs from 16 families, including 3 novel compounds. Using the in silico library largely decreased the false-positive annotation rate in comparison to low-resolution LC-MS/MS. The developed library, MS/MS spectra, and development templates are freely available for commercial and noncommercial use at https://zenodo.org/record/3606905.
| S-EPMC8168918 | biostudies-literature
Project description:Most shotgun proteomics data analysis workflows are based on the assumption that each fragment ion spectrum is explained by a single species of peptide ion isolated by the mass spectrometer; however, in reality mass spectrometers often isolate more than one peptide ion within the window of isolation that contribute to additional peptide fragment peaks in many spectra. We present a new tool called reSpect, implemented in the Trans-Proteomic Pipeline (TPP), which enables an iterative workflow whereby fragment ion peaks explained by a peptide ion identified in one round of sequence searching or spectral library search are attenuated based on the confidence of the identification, and then the altered spectrum is subjected to further rounds of searching. The reSpect tool is not implemented as a search engine, but rather as a post-search engine processing step where only fragment ion intensities are altered. This enables the application of any search engine combination in the iterations that follow. Thus, reSpect is compatible with all other protein sequence database search engines as well as peptide spectral library search engines that are supported by the TPP. We show that while some datasets are highly amenable to chimeric spectrum identification and lead to additional peptide identification boosts of over 30% with as many as four different peptide ions identified per spectrum, datasets with narrow precursor ion selection only benefit from such processing at the level of a few percent. We demonstrate a technique that facilitates the determination of the degree to which a dataset would benefit from chimeric spectrum analysis. The reSpect tool is free and open source, provided within the TPP and available at the TPP website. Graphical Abstract ᅟ.
| S-EPMC4750398 | biostudies-literature
Project description:MotivationCompound structure identification is using increasingly more sophisticated computational tools, among which machine learning tools are a recent addition that quickly gains in importance. These tools, of which the method titled Compound Structure Identification:Input Output Kernel Regression (CSI:IOKR) is an excellent example, have been used to elucidate compound structure from mass spectral (MS) data with significant accuracy, confidence and speed. They have, however, largely focused on data coming from liquid chromatography coupled to tandem mass spectrometry (LC-MS). Gas chromatography coupled to mass spectrometry (GC-MS) is an alternative which offers several advantages as compared to LC-MS, including higher data reproducibility. Of special importance is the substantial compound coverage offered by GC-MS, further expanded by derivatization procedures, such as silylation, which can improve the volatility, thermal stability and chromatographic peak shape of semi-volatile analytes. Despite these advantages and the increasing size of compound databases and MS libraries, GC-MS data have not yet been used by machine learning approaches to compound structure identification.ResultsThis study presents a successful application of the CSI:IOKR machine learning method for the identification of environmental contaminants from GC-MS spectra. We use CSI:IOKR as an alternative to exhaustive search of MS libraries, independent of instrumental platform and data processing software. We use a comprehensive dataset of GC-MS spectra of trimethylsilyl derivatives and their molecular structures, derived from a large commercially available MS library, to train a model that maps between spectra and molecular structures. We test the learned model on a different dataset of GC-MS spectra of trimethylsilyl derivatives of environmental contaminants, generated in-house and made publicly available. The results show that 37% (resp. 50%) of the tested compounds are correctly ranked among the top 10 (resp. 20) candidate compounds suggested by the model. Even though spectral comparisons with reference standards or de novo structural elucidations are neccessary to validate the predictions, machine learning provides efficient candidate prioritization and reduction of the time spent for compound annotation.
| S-EPMC9476372 | biostudies-literature
Project description:Acquisition and processing of informative tandem mass spectra (MS2) is crucial for numerous applications, including library-based (tentative) identification, feature prioritization, and prediction of chemical and toxicological characteristics. However, for environmentally relevant compounds, approaches to automatically assess the quality of the MS2 spectra are missing. This work focused on developing a machine learning-based approach to automatically evaluate the diagnostic information of MS2 spectra (e.g., number, distribution, and intensity of diagnostic fragments) of environmentally relevant compounds analyzed with electrospray ionization. For this, approximately 1400 MS2 spectra of 204 environmental contaminants, acquired with different collision energies using liquid chromatography coupled to high-resolution mass spectrometry, were used to train a random forest classifier to distinguish between spectra providing good or poor diagnostic information. Prior to training, validation, and testing, spectra were manually labeled based on criteria such as number, intensity, range of fragments present, molecular ion intensity, and noise levels. Subsequently, feature engineering and selection were applied to retrieve relevant variables from raw MS2 spectra as inputs for the classifier. The optimal set of features based on model performances was selected and used to train a final model, which showed an accuracy of 84%, a precision of 88%, and a recall of 75%. Results show that the combination of selected features and the machine learning model used here can effectively distinguish between MS2 spectra providing good or poor diagnostic information according to the defined criteria. The developed model has the potential to improve a broad range of applications that rely on MS2 data.
| S-EPMC10603772 | biostudies-literature