Probabilistic framework for integration of mass spectrum and retention time information in small molecule identification.
Ontology highlight
ABSTRACT: Motivation
Identification of small molecules in a biological sample remains a major bottleneck in molecular biology, despite a decade of rapid development of computational approaches for predicting molecular structures using mass spectrometry (MS) data. Recently, there has been increasing interest in utilizing other information sources, such as liquid chromatography (LC) retention time (RT), to improve identifications solely based on MS information, such as precursor mass-per-charge and tandem mass spectrometry (MS2).Results
We put forward a probabilistic modelling framework to integrate MS and RT data of multiple features in an LC-MS experiment. We model the MS measurements and all pairwise retention order information as a Markov random field and use efficient approximate inference for scoring and ranking potential molecular structures. Our experiments show improved identification accuracy by combining MS2 data and retention orders using our approach, thereby outperforming state-of-the-art methods. Furthermore, we demonstrate the benefit of our model when only a subset of LC-MS features has MS2 measurements available besides MS1.Availability and implementation
Software and data are freely available at https://github.com/aalto-ics-kepaco/msms_rt_score_integration.Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Bach E
PROVIDER: S-EPMC8289373 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Machine learning has been extensively applied in small molecule analysis to predict a wide range of molecular properties and processes including mass spectrometry fragmentation or chromatographic retention time. However, current approaches for retention time prediction lack sufficient accuracy due to limited available experimental data. Here we introduce the METLIN small molecule retention time (SMRT) dataset, an experimentally acquired reverse-phase chromatography retention time dataset covering up to 80,038 small molecules. To demonstrate the utility of this dataset, we deployed a deep learning model for retention time prediction applied to small molecule annotation. Results showed that in 70[Formula: see text] of the cases, the correct molecular identity was ranked among the top 3 candidates based on their predicted retention time. We anticipate that this dataset will enable the community to apply machine learning or first principles strategies to generate better models for retention time prediction.
| S-EPMC6925099 | biostudies-literature
Project description:Retention time information is used for metabolite annotation in metabolomic experiments. But its usefulness is hindered by the availability of experimental retention time data in metabolomic databases, and by the lack of reproducibility between different chromatographic methods. Accurate prediction of retention time for a given chromatographic method would be a valuable support for metabolite annotation. We have trained state-of-the-art machine learning regressors using the 80, 038 experimental retention times from the METLIN Small Molecule Retention Tim (SMRT) dataset. The models included deep neural networks, deep kernel learning, several gradient boosting models, and a blending approach. 5, 666 molecular descriptors and 2, 214 fingerprints (MACCS166, Extended Connectivity, and Path Fingerprints fingerprints) were generated with the alvaDesc software. The models were trained using only the descriptors, only the fingerprints, and both types of features simultaneously. Bayesian hyperparameter search was used for parameter tuning. To avoid data-leakage when reporting the performance metrics, nested cross-validation was employed. The best results were obtained by a heavily regularized deep neural network trained with cosine annealing warm restarts and stochastic weight averaging, achieving a mean and median absolute errors of [Formula: see text] and [Formula: see text], respectively. To the best of our knowledge, these are the most accurate predictions published up to date over the SMRT dataset. To project retention times between chromatographic methods, a novel Bayesian meta-learning approach that can learn from just a few molecules is proposed. By applying this projection between the deep neural network retention time predictions and a given chromatographic method, our approach can be integrated into a metabolite annotation workflow to obtain z-scores for the candidate annotations. To this end, it is enough that just as few as 10 molecules of a given experiment have been identified (probably by using pure metabolite standards). The use of z-scores permits considering the uncertainty in the projection when ranking candidates, and not only the accuracy. In this scenario, our results show that in 68% of the cases the correct molecule was among the top three candidates filtered by mass and ranked according to z-scores. This shows the usefulness of this information to support metabolite annotation. Python code is available on GitHub at https://github.com/constantino-garcia/cmmrt.
| S-EPMC9172150 | biostudies-literature
Project description:Somatic mutations are a primary contributor to malignancy in human cells. Accurate detection of mutations is needed to define the clonal composition of tumours whereby clones may have distinct phenotypic properties. Although analysis of mutations over multiple tumour samples from the same patient has the potential to enhance identification of clones, few analytic methods exploit the correlation structure across samples. We posited that incorporating clonal information into joint analysis over multiple samples would improve mutation detection, particularly those with low prevalence. In this paper, we develop a new procedure called MuClone, for detection of mutations across multiple tumour samples of a patient from whole genome or exome sequencing data. In addition to mutation detection, MuClone classifies mutations into biologically meaningful groups and allows us to study clonal dynamics. We show that, on lung and ovarian cancer datasets, MuClone improves somatic mutation detection sensitivity over competing approaches without compromising specificity.
| S-EPMC6355807 | biostudies-other
Project description:Current approaches to protein identification rely heavily on database matching of fragmentation spectra or precursor peptide ions. We have developed a method for MALDI TOF-TOF instrumentation that uses peptide masses and their measurement errors to confirm protein identifications from a first pass MS/MS database search. The method uses MS1-level spectral data that have heretofore been ignored by most search engines. This approach uses the distribution of mass errors of peptide matches in the MS1 spectrum to develop a probability model that is independent of the MS/MS database search identifications. Peptide mass matches can come from both precursor ions that have been fragmented as well as those that are tentatively identified by accurate mass alone. This additional corroboration enables us to confirm protein identifications to MS/MS-based scores that are otherwise considered to be only of moderate quality. Straightforward and easily applicable to current proteomic analyses, this tool termed "ProteinProcessor" provides a robust and invaluable addition to current protein identification tools.
| S-EPMC5176252 | biostudies-literature
Project description:MOTIVATION: Time-evolving differential protein-protein interaction (PPI) networks are essential to understand serial activation of differentially regulated (up- or downregulated) cellular processes (DRPs) and their interplays over time. Despite developments in the network inference, current methods are still limited in identifying temporal transition of structures of PPI networks, DRPs associated with the structural transition and the interplays among the DRPs over time. RESULTS: Here, we present a probabilistic model for estimating Time-Evolving differential PPI networks with MultiPle Information (TEMPI). This model describes probabilistic relationships among network structures, time-course gene expression data and Gene Ontology biological processes (GOBPs). By maximizing the likelihood of the probabilistic model, TEMPI estimates jointly the time-evolving differential PPI networks (TDNs) describing temporal transition of PPI network structures together with serial activation of DRPs associated with transiting networks. This joint estimation enables us to interpret the TDNs in terms of temporal transition of the DRPs. To demonstrate the utility of TEMPI, we applied it to two time-course datasets. TEMPI identified the TDNs that correctly delineated temporal transition of DRPs and time-dependent associations between the DRPs. These TDNs provide hypotheses for mechanisms underlying serial activation of key DRPs and their temporal associations. AVAILABILITY AND IMPLEMENTATION: Source code and sample data files are available at http://sbm.postech.ac.kr/tempi/sources.zip. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
| S-EPMC4147907 | biostudies-other
Project description:BACKGROUND:It is important to understand the motor deficits of children with Cerebral Palsy (CP). Our understanding of this motor disorder can be enriched by computational models of motor control. One crucial stage in generating movement involves combining uncertain information from different sources, and deficits in this process could contribute to reduced motor function in children with CP. Healthy adults can integrate previously-learned information (prior) with incoming sensory information (likelihood) in a close-to-optimal way when estimating object location, consistent with the use of Bayesian statistics. However, there are few studies investigating how children with CP perform sensorimotor integration. We compare sensorimotor estimation in children with CP and age-matched controls using a model-based analysis to understand the process. METHODS AND FINDINGS:We examined Bayesian sensorimotor integration in children with CP, aged between 5 and 12 years old, with Gross Motor Function Classification System (GMFCS) levels 1-3 and compared their estimation behavior with age-matched typically-developing (TD) children. We used a simple sensorimotor estimation task which requires participants to combine probabilistic information from different sources: a likelihood distribution (current sensory information) with a prior distribution (learned target information). In order to examine sensorimotor integration, we quantified how participants weighed statistical information from the two sources (prior and likelihood) and compared this to the statistical optimal weighting. We found that the weighing of statistical information in children with CP was as statistically efficient as that of TD children. CONCLUSIONS:We conclude that Bayesian sensorimotor integration is not impaired in children with CP and therefore, does not contribute to their motor deficits. Future research has the potential to enrich our understanding of motor disorders by investigating the stages of motor processing set out by computational models. Therapeutic interventions should exploit the ability of children with CP to use statistical information.
| S-EPMC5706703 | biostudies-literature
Project description:In order to successfully reproduce, plants must sense changes in their environment and flower at the correct time. Many plants utilize day length and vernalization, a mechanism for verifying that winter has occurred, to determine when to flower. Our study used available temperature and day length data from different climates to provide a general understanding how this information processing of environmental signals could have evolved in plants. For climates where temperature fluctuation correlations decayed exponentially, a simple stochastic model characterizing vernalization was able to reconstruct the switch-like behavior of the core flowering regulatory genes. For these and other climates, artificial neural networks were used to predict flowering gene expression patterns. For temperate plants, long-term cold temperature and short-term day length measurements were sufficient to produce robust flowering time decisions from the neural networks. Additionally, evolutionary simulations on neural networks confirmed that the combined signal of temperature and day length achieved the highest fitness relative to neural networks with access to only one of those inputs. We suggest that winter temperature memory is a well-adapted strategy for plants' detection of seasonal changes, and absolute day length is useful for the subsequent triggering of flowering.
| S-EPMC7511014 | biostudies-literature
Project description:A large number of metabolites are found in each plant, most of which have not yet been identified. Development of a methodology is required to deal systematically with unknown metabolites, and to elucidate their biological roles in an integrated 'omics' framework. Here we report the development of a 'metabolite annotation' procedure. The metabolite annotation is a process by which structures and functions are inferred for metabolites. Tomato (Solanum lycopersicum cv. Micro-Tom) was used as a model for this study using LC-FTICR-MS. Collected mass spectral features, together with predicted molecular formulae and putative structures, were provided as metabolite annotations for 869 metabolites. Comparison with public databases suggests that 494 metabolites are novel. A grading system was introduced to describe the evidence supporting the annotations. Based on the comprehensive characterization of tomato fruit metabolites, we identified chemical building blocks that are frequently found in tomato fruit tissues, and predicted novel metabolic pathways for flavonoids and glycoalkaloids. These results demonstrate that metabolite annotation facilitates the systematic analysis of unknown metabolites and biological interpretation of their relationships, which provide a basis for integrating metabolite information into the system-level study of plant biology.
| S-EPMC2440531 | biostudies-literature
Project description:The prefrontal cortex (PFC) plays a prominent role in performing flexible cognitive functions and working memory, yet the underlying computational principle remains poorly understood. Here, we trained a rate-based recurrent neural network (RNN) to explore how the context rules are encoded, maintained across seconds-long mnemonic delay, and subsequently used in a context-dependent decision-making task. The trained networks replicated key experimentally observed features in the PFC of rodent and monkey experiments, such as mixed selectivity, neuronal sequential activity, and rotation dynamics. To uncover the high-dimensional neural dynamical system, we further proposed a geometric framework to quantify and visualize population coding and sensory integration in a temporally defined manner. We employed dynamic epoch-wise principal component analysis (PCA) to define multiple task-specific subspaces and task-related axes, and computed the angles between task-related axes and these subspaces. In low-dimensional neural representations, the trained RNN first encoded the context cues in a cue-specific subspace, and then maintained the cue information with a stable low-activity state persisting during the delay epoch, and further formed line attractors for sensor integration through low-dimensional neural trajectories to guide decision-making. We demonstrated via intensive computer simulations that the geometric manifolds encoding the context information were robust to varying degrees of weight perturbation in both space and time. Overall, our analysis framework provides clear geometric interpretations and quantification of information coding, maintenance, and integration, yielding new insight into the computational mechanisms of context-dependent computation.
| S-EPMC8367843 | biostudies-literature
Project description:Intermittency are a common and challenging problem in demand forecasting. We introduce a new, unified framework for building probabilistic forecasting models for intermittent demand time series, which incorporates and allows to generalize existing methods in several directions. Our framework is based on extensions of well-established model-based methods to discrete-time renewal processes, which can parsimoniously account for patterns such as aging, clustering and quasi-periodicity in demand arrivals. The connection to discrete-time renewal processes allows not only for a principled extension of Croston-type models, but additionally for a natural inclusion of neural network based models-by replacing exponential smoothing with a recurrent neural network. We also demonstrate that modeling continuous-time demand arrivals, i.e., with a temporal point process, is possible via a trivial extension of our framework. This leads to more flexible modeling in scenarios where data of individual purchase orders are directly available with granular timestamps. Complementing this theoretical advancement, we demonstrate the efficacy of our framework for forecasting practice via an extensive empirical study on standard intermittent demand data sets, in which we report predictive accuracy in a variety of scenarios.
| S-EPMC8629246 | biostudies-literature