Prediction Of Retention Times Research Articles

Equivalent carbon number-based targeted odd-chain fatty acyl lipidomics reveals triacylglycerol profiling in clinical colon cancer

Odd-chain FAs (OCFAs) are present in very low level at nearly 1% of total FAs in human plasma, and thus, their functions were usually ignored. Recent epidemiological studies have shown that OCFAs are inversely associated with a variety of disease risks. However, the contribution of OCFAs incorporated into complex lipids remains elusive. Here, we developed a targeted odd-chain fatty acyl-containing lipidomics method based on equivalent carbon number and retention time prediction. The method displayed good reproducibility and robustness as shown by peak width at half height within 0.7 min and coefficient of variation under 20%. A total number of 776 lipid species with odd-chain fatty acyl residues could be detected in the ESI mode of reverse-phase LC-MS, of which 309 lipids were further validated using multiple reaction monitoring transitions. Using this method, we quantified odd-chain fatty acyl-containing lipidome in tissues from 12 colon cancer patients, revealing the remodeling of triacylglycerol. The dynamics of odd-chain fatty acyl lipids were further consolidated by the association with genomic and proteomic features of altered catabolism of branched-chain amino acids and triacylglycerol endogenous synthesis in colon cancer. This lipidomics approach will be applicable for screening of dysregulated odd-chain fatty acyl lipids, which enriches and improves the methods for diagnosis and prognosis evaluation of cancer using lipidomics.

Retention time prediction for chromatographic enantioseparation by quantile geometry-enhanced graph neural network

The enantioseparation of chiral molecules is a crucial and challenging task in the field of experimental chemistry, often requiring extensive trial and error with different experimental settings. To overcome this challenge, here we show a research framework that employs machine learning techniques to predict retention times of enantiomers and facilitate chromatographic enantioseparation. A documentary dataset of chiral molecular retention times in high-performance liquid chromatography (CMRT dataset) is established to handle the challenge of data acquisition. A quantile geometry-enhanced graph neural network is proposed to learn the molecular structure-retention time relationship, which shows a satisfactory predictive ability for enantiomers. The domain knowledge of chromatography is incorporated into the machine learning model to achieve multi-column prediction, which paves the way for chromatographic enantioseparation prediction by calculating the separation probability. The proposed research framework works well in retention time prediction and chromatographic enantioseparation facilitation, which sheds light on the application of machine learning techniques to the experimental scene and improves the efficiency of experimenters to speed up scientific discovery.

Predicting the retention time of Synthetic Cannabinoids using a combinatorial QSAR approach

BackgroundAbuse of Synthetic Cannabinoids (SCs) has become a serious threat to public health. Due to the various structural and chemical group modified by criminals, their detection is a major challenge in forensic toxicological identification. Therefore, rapid and efficient identification of SCs is important for forensic toxicology and drug bans. The prediction of an analyte's retention time in liquid chromatography is an important index for the qualitative analysis of compounds and can provide informatics solutions for the interpretation of chromatographic data. MethodsIn this study, experimental data from high-resolution mass spectrometry (HRMS) are used to construct a regression model for predicting the retention time of SCs using machine learning methods. The prediction ability of the model is improved by adopting a strategy that combines different descriptors in different independent machine-learning methods. ResultsThe best model was obtained with a method that combined Substructure Fingerprint Count and Finger printer features and the support vector regression (SVR) method, as it exhibited an R2 value of 0.81 for the validation set and 0.83 for the test set. In addition, 4 new SCs were predicted by the optimized model, with a prediction error within 3%. ConclusionsOur study provides a model that can predict the retention time of compounds and it can be used as a filter to reduce false-positive candidates when used in combination with LC-HRMS, especially in the absence of reference standards. This can improve the confidence of identification in non-targeted analysis and the reliability of identifying unknown substances.

Retention Database for Prediction, Simulation, and Optimization of GC Separations.

This work presents an open source database with suitable retention parameters for prediction and simulation of GC separations and gives a short introduction to three common retention models. Useful computer simulations play an important role to save resources and time in method development in GC. Thermodynamic retention parameters for the ABC model and the K-centric model are determined by isothermal measurements. This standardized procedure of measurements and calculations, presented in this work, have a useful benefit for all chromatographers, analytical chemists, and method developers because it can be used in their own laboratories to simplify the method development. The main benefits as simulations of temperature-programed GC separations are demonstrated and compared to measurements. The observed deviations of predicted retention times are in most cases less than 1%. The database includes more than 900 entries with a large range of compounds such as VOCs, PAHs, FAMEs, PCBs, or allergenic fragrances over 20 different GC columns.

Updated MS²PIP web server supports cutting-edge proteomics applications.

Interest in the use of machine learning for peptide fragmentation spectrum prediction has been strongly on the rise over the past years, especially for applications in challenging proteomics identification workflows such as immunopeptidomics and the full-proteome identification of data independent acquisition spectra. Since its inception, the MS²PIP peptide spectrum predictor has been widely used for various downstream applications, mostly thanks to its accuracy, ease-of-use, and broad applicability. We here present a thoroughly updated version of the MS²PIP web server, which includes new and more performant prediction models for both tryptic- and non-tryptic peptides, for immunopeptides, and for CID-fragmented TMT-labeled peptides. Additionally, we have also added new functionality to greatly facilitate the generation of proteome-wide predicted spectral libraries, requiring only a FASTA protein file as input. These libraries also include retention time predictions from DeepLC. Moreover, we now provide pre-built and ready-to-download spectral libraries for various model organisms in multiple DIA-compatible spectral library formats. Besides upgrading the back-end models, the user experience on the MS²PIP web server is thus also greatly enhanced, extending its applicability to new domains, including immunopeptidomics and MS3-based TMT quantification experiments. MS²PIP is freely available at https://iomics.ugent.be/ms2pip/.

Recent advances of data‐independent acquisition mass spectrometry‐based proteomics

Recent advances of data‐independent acquisition mass spectrometry‐based proteomics

Improved LC–MS identification of short homologous peptides using sequence-specific retention time predictors

Peptides are an important group of compounds contributing to the desired, as well as the undesired taste of a food product. Their taste impressions can include aspects of sweetness, bitterness, savoury, umami and many other impressions depending on the amino acids present as well as their sequence. Identification of short peptides in foods is challenging. We developed a method to assign identities to short peptides including homologous structures, i.e. peptides containing the same amino acids with a different sequence order, by accurate prediction of the retention times during reversed phase separation. To train the method, a large set of well-defined short peptides with systematic variations in the amino acid sequence was prepared by a novel synthesis strategy called ‘swapped-sequence synthesis’. Additionally, several proteins were enzymatically digested to yield short peptides. Experimental retention times were determined after reversed phase separation and peptide MS2 data was acquired using a high-resolution mass spectrometer operated in data-dependent acquisition mode (DDA). A support vector regression model was trained using a combination of existing sequence-independent peptide descriptors and a newly derived set of selected amino acid index derived sequence-specific peptide (ASP) descriptors. The model was trained and validated using the experimental retention times of the 713 small food-relevant peptides prepared. Whilst selecting the most useful ASP descriptors for our model, special attention was given to predict the retention time differences between homologous peptide structures. Inclusion of ASP descriptors greatly improved the ability to accurately predict retention times, including retention time differences between 157 homologous peptide pairs. The final prediction model had a goodness-of-fit (Q2) of 0.94; moreover for 93% of the short peptides, the elution order was correctly predicted.Graphical abstract

A transformer architecture for retention time prediction in liquid chromatography mass spectrometry-based proteomics.

Accurate retention time (RT) prediction is important for spectral library-based analysis in data-independent acquisition mass spectrometry-based proteomics. The deep learning approach has demonstrated superior performance over traditional machine learning methods for this purpose. The transformer architecture is a recent development in deep learning that delivers state-of-the-art performance in many fields such as natural language processing, computer vision, and biology. We assess the performance of the transformer architecture for RT prediction using datasets from five deep learning models Prosit, DeepDIA, AutoRT, DeepPhospho, and AlphaPeptDeep. The experimental results on holdout datasets and independent datasets exhibit state-of-the-art performance of the transformer architecture. The software and evaluation datasets are publicly available for future development in the field.

A rapid and sensitive single-cell proteomic method based on fast liquid-chromatography separation, retention time prediction and MS1-only acquisition

Single-cell analysis has received much attention in recent years for elucidating the widely existing cellular heterogeneity in biological systems. However, the ability to measure the proteome in single cells is still far behind that of transcriptomics due to the lack of sensitive and high-throughput mass spectrometry methods. Herein, we report an integrated strategy termed “SCP-MS1” that combines fast liquid chromatography (LC) separation, deep learning-based retention time (RT) prediction and MS1-only acquisition for rapid and sensitive single-cell proteome analysis. In SCP-MS1, the peptides were identified via four-dimensional MS1 feature (m/z, RT, charge and FAIMS CV) matching, therefore relieving MS acquisition from the time consuming and information losing MS2 step and making this method particularly compatible with fast LC separation. By completely omitting the MS2 step, all the MS analysis time was utilized for MS1 acquisition in SCP-MS1 and therefore led to 65%–138% increased MS1 feature collection. Unlike “match between run” methods that still needed MS2 information for RT alignment, SCP-MS1 used deep learning-based RT prediction to transfer the measured RTs in long gradient bulk analyses to short gradient single cell analyses, which was the key step to enhance both identification scale and matching accuracy. Using this strategy, more than 2000 proteins were obtained from 0.2 ng of peptides with a 14-min active gradient at a false discovery rate (FDR) of 0.8%. Comparing with the DDA method, improved quantitative performance was also observed for SCP-MS1 with approximately 50% decreased median coefficient of variation of quantified proteins. For single-cell analysis, 1715 ± 204 and 1604 ± 224 proteins were quantified in single 293T and HeLa cells, respectively. Finally, SCP-MS1 was applied to single-cell proteome analysis of sorafenib resistant and non-resistant HepG2 cells and revealed clear cellular heterogeneity in the resistant population that may be masked in bulk studies.

Quantitative Structure Retention-Relationship Modeling: Towards an Innovative General-Purpose Strategy.

Reversed-Phase Liquid Chromatography (RPLC) is a common liquid chromatographic mode used for the control of pharmaceutical compounds during their drug life cycle. Nevertheless, determining the optimal chromatographic conditions that enable this separation is time consuming and requires a lot of lab work. Quantitative Structure Retention Relationship models (QSRR) are helpful for doing this job with minimal time and cost expenditures by predicting retention times of known compounds without performing experiments. In the current work, several QSRR models were built and compared for their adequacy in predicting the retention times. The regression models were based on a combination of linear and non-linear algorithms such as Multiple Linear Regression, Support Vector Regression, Least Absolute Shrinkage and Selection Operator, Random Forest, and Gradient Boosted Regression. Models were built for five pH conditions, i.e., at pH 2.7, 3.5, 6.5, and 8.0. In the end, the model predictions were combined using stacking and the performances of all models were compared. The k-nearest neighbor-based application domain filter was established to assess the reliability of the prediction for further compound prioritization. Altogether, this study can be insightful for analytical chemists working with RPLC to begin with the computational prediction modeling such as QSRR to predict the separation of small molecules.

Identifying antimicrobials and their metabolites in wastewater and surface water with effect-directed analysis

This study aimed to identify antimicrobial contaminants in the aquatic environment with effect-directed analysis. Wastewater influent, effluent, and surface water (up- and downstream of the discharge location) were sampled at two study sites. The samples were enriched, subjected to high-resolution fractionation, and the resulting 80 fractions were tested in an antibiotics bioassay. The resulting bioactive fractions guided the suspect and nontargeted identification strategy in the high-resolution mass spectrometry data that was recorded in parallel. Chemical features were annotated with reference databases, assessed on annotation quality, and assigned identification confidence levels. To identify antibiotic metabolites, Phase I metabolites were predicted in silico for over 500 antibiotics and included as a suspect list. Predicted retention times and fragmentation patterns reduced the number of annotations to consider for confirmation testing. Overall, the bioactivity of three fractions could be explained by the identified antibiotics (clarithromycin and azithromycin) and an antibiotic metabolite (14-OH(R) clarithromycin), explaining 78% of the bioactivity measured at one study site. The applied identification strategy successfully identified antibiotic metabolites in the aquatic environment, emphasizing the need to include the toxic effects of bioactive metabolites in environmental risk assessments.

Retention time prediction for small samples based on integrating molecular representations and adaptive network

Retention time (RT) can provide orthogonal information different from that of mass spectrometry and contribute to identifying compounds. Many machine learning methods have been developed and applied to RT prediction. In application, the training data size is usually small in most chromatography systems. To enhance the performance of RT prediction, this study proposes a RT prediction method based on multi-data combinations and adaptive neural network (MDC-ANN). MDC-ANN establishes the RT prediction model for the target chromatographic system through transfer learning and a base deep learning model trained on a big dataset. It selects the optimal molecular representation combination from the multiple input candidates and automatically determines the neural network structure according to the determined input combination. MDC-ANN was compared with two new efficient deep learning methods, three transferring methods and four popular machine learning methods on 14 small datasets and showed advantages in MAE, MedAE, MRE and R2 in most cases. The experiment results illustrated that integrating multiple molecular representations can provide more information, improve the performance of RT prediction and contribute to compound annotation, different chromatographic systems may use different molecular representation combinations to obtain good RT prediction performance. Hence, MDC-ANN which automatically determines the best combination of molecular representations for a specific system is promising for predicting RTs accurately in real applications.

An automated toxicity based prioritization framework for fast chemical characterization in non-targeted analysis

Identification of environmental pollutants with harmful effects is commonly conducted by non-targeted analysis (NTA) using liquid chromatography coupled with high-resolution mass spectrometry. Prioritization of possible candidates is important yet challenging because of the large number of candidates from MS acquisitions. We aimed to prioritize candidates to the exposure potential of organic chemicals by their toxicity and identification evidence in the matrix. We have developed an R package application, “NTAprioritization.R”, for fast prioritization of suspect lists. In this workflow, the identification levels of candidates were first rated according to spectral matching and retention time prediction. The toxicity levels were rated according to candidates’ toxicity of different endpoints or ToxPi score. Finally, the various levels of candidates were identified as Tier 1 – 5 descending in priority. For validation, we used this workflow to identify pollutants in a sludge water sample spiked with 28 environmental pollutants. The workflow reduced the candidate list of over 6,982 candidates to a final list of 2,779 compounds and prioritized them to 5 tiers (Tier 1 – 5), including 21 out of 28 spiked standards. Overall, this study shows the added value of an automated prioritization R package for the fast screening of environmental pollutants based on the NTA method.

Identification of Alternative Splicing in Proteomes of Human Melanoma Cell Lines without RNA Sequencing Data.

Alternative splicing is one of the main regulation pathways in living cells beyond simple changes in the level of protein expression. Most of the approaches proposed in proteomics for the identification of specific splicing isoforms require a preliminary deep transcriptomic analysis of the sample under study, which is not always available, especially in the case of the re-analysis of previously acquired data. Herein, we developed new algorithms for the identification and validation of protein splice isoforms in proteomic data in the absence of RNA sequencing of the samples under study. The bioinformatic approaches were tested on the results of proteome analysis of human melanoma cell lines, obtained earlier by high-resolution liquid chromatography and mass spectrometry (LC-MS). A search for alternative splicing events for each of the cell lines studied was performed against the database generated from all known transcripts (RefSeq) and the one composed of peptide sequences, which included all biologically possible combinations of exons. The identifications were filtered using the prediction of both retention times and relative intensities of fragment ions in the corresponding mass spectra. The fragmentation mass spectra corresponding to the discovered alternative splicing events were additionally examined for artifacts. Selected splicing events were further validated at the mRNA level by quantitative PCR.

Improving SWATH-MS analysis by deep-learning.

Data-independent acquisition (DIA) of tandem mass spectrometry spectra has emerged as a promising technology to improve coverage and quantification of proteins in complex mixtures. The success of DIA experiments is dependent on the quality of spectral libraries used for data base searching. Frequently, these libraries need to be generated by labor and time intensive data dependent acquisition (DDA) experiments. Recently, several algorithms have been published that allow the generation of theoretical libraries by an efficient prediction of retention time and intensity of the fragment ions. Sequential windowed acquisition of all theoretical fragment ion spectra mass spectrometry (SWATH-MS) is a DIA method that can be applied at an unprecedented speed, but the fragmentation spectra suffer from a lower quality than data acquired on Orbitrap instruments. To reliably generate theoretical libraries that can be used in SWATH experiments, we developed deep-learning for SWATH analysis (dpSWATH), to improve the sensitivity and specificity of data generated by Q-TOF mass spectrometers. The theoretical library built by dpSWATH allowed us to increase the identification rate of proteins compared to traditional or library-free methods. Based on our analysis we conclude that dpSWATH is a superior prediction framework for SWATH-MS measurements than other algorithms based on Orbitrap data.

Exploring the variable space of shallow machine learning models for reversed-phase retention time prediction

Peptide retention time (RT) prediction algorithms are tools to study and identify the physicochemical properties that drive the peptide-sorbent interaction. Traditional RT algorithms use multiple linear regression with manually curated parameters to determine the degree of direct contribution for each parameter and improvements to RT prediction accuracies relied on superior feature engineering. Deep learning led to a significant increase in RT prediction accuracy and automated feature engineering via chaining multiple learning modules. However, the significance and the identity of these extracted variables are not well understood due to the inherent complexity when interpreting “relationships-of-relationships” found in deep learning variables. To achieve both accuracy and interpretability simultaneously, we isolated individual modules used in deep learning and the isolated modules are the shallow learners employed for RT prediction in this work. Using a shallow convolutional neural network (CNN) and gated recurrent unit (GRU), we find that the spatial features obtained via the CNN correlate with real-world physicochemical properties namely cross-collisional sections (CCS) and variations of assessable surface area (ASA). Furthermore, we determined that the discovered parameters are “micro-coefficients” that contribute to the “macro-coefficient” – hydrophobicity. Manually embedding CCS and the variations of ASA to the GRU model yielded an R2 = 0.981 using only 525 variables and can represent 88% of the ∼110,000 tryptic peptides used in our dataset. This work highlights the feature discovery process of our shallow learners can achieve beyond traditional RT models in performance and have better interpretability when compared with the deep learning RT algorithms found in the literature.

水道水中農薬のGC/MSスクリーニング分析におけるクロマトグラム解析の誤差要因の分析

In order to adopt "screening analysis" in drinking water quality testing, which performs qualitative and quantitative analysis based on information registered in a database without measuring standard materials at the time of each testing, a validation test was conducted to evaluate the difference on the chromatogram data analysis by analysts. In the validation test, chromatograms of 6 water samples were analyzed using the same database and software by 16 analysts in 13 laboratories. Peak identification was performed based on Retention time (RT), (qualifier and target ion) QT ratio, and degree of matching of mass spectra, and if necessary, peak shapes in water samples were compared with those in calibration curve samples. Large differences were observed in the detection of pesticides among the analysts. There were two main reasons for the disagreement. The first is that the judgement of peak detection at low concentrations near the quantification limit of each pesticide, particularly below the concentration at three times of quantification limit, differed depending on the analyst. The other reason was that some analysts made clear misidentifications and identified wrong peaks close to the predicted retention time, despite the QT ratio and mass spectrum didn't match that in the database. In addition, there were some cases where the quantified values were reported by misidentifying the peaks of degradation products and metabolites, even when the peak detection was correctly judged. In order to use screening analysis practically by drinking water quality testing laboratories, it is important to conduct a validation test like this study in advance to use screening analysis and to coordinate criteria for peak identification and quantification among data analysts.

Mass Spectrometric Methods for Non-Targeted Screening of Metabolites: A Future Perspective for the Identification of Unknown Compounds in Plant Extracts

Phyto products are widely used in natural products, such as medicines, cosmetics or as so-called “superfoods”. However, the exact metabolite composition of these products is still unknown, due to the time-consuming process of metabolite identification. Non-target screening by LC-HRMS/MS could be a technique to overcome these problems with its capacity to identify compounds based on their retention time, accurate mass and fragmentation pattern. In particular, the use of computational tools, such as deconvolution algorithms, retention time prediction, in silico fragmentation and sophisticated search algorithms, for comparison of spectra similarity with mass spectral databases facilitate researchers to conduct a more exhaustive profiling of metabolic contents. This review aims to provide an overview of various techniques and tools for non-target screening of phyto samples using LC-HRMS/MS.

A strategy for screening and identification of new amino acid-conjugated bile acids with high coverage by liquid chromatography-mass spectrometry

Bile acids (BAs) are a class of vital gut microbiota-host cometabolites, and they play an important role in maintaining gut microbiota-host metabolic homeostasis. Very recently, a new mechanism of BA anabolic metabolism mediated by gut microbiota (BA-amino acid conjugation) has been revealed, which provides a perspective for the research on BA metabolism and gut metabolome. In this study, we established a polarity-switching multiple reaction monitoring mass spectrometry-based screening method to mine amino acid-conjugated bile acids (AA-BAs) derived from host-gut microbiota co-metabolism. In addition, a retention time-based annotation strategy was further proposed to identify the AA-BA isomers and epimers. Using the developed methods, we successfully screened 118 AA-BA conjugates from mouse and human feces, 28 of them were confirmed by standards, and 62 putatively identified based on their predicted retention times. Moreover, we observed that the levels of most AA-BAs were significantly downregulated in the feces of chronic sleep deprivation mice, suggesting that the AA-BA metabolism was closely related to the physiological state of the host.

Graph Neural Networks for Improved Retention Time Predictions

In this extended special feature to celebrate the 35th anniversary edition of LCGC Europe, leading figures from the separation science community explore contemporary trends in separation science and identify possible future developments.