RT-Transformer: retention time prediction for metabolite annotation to assist in metabolite identification.

MOTIVATION: Liquid chromatography retention times prediction can assist in metabolite identification, which is a critical task and challenge in nontargeted metabolomics. However, different chromatographic conditions may result in different retention times for the same metabolite. Current retention time prediction methods lack sufficient scalability to transfer from one specific chromatographic method to another. RESULTS: Therefore, we present RT-Transformer, a novel deep neural network model coupled with graph attention network and 1D-Transformer, which can predict retention times under any chromatographic methods. First, we obtain a pre-trained model by training RT-Transformer on the large small molecule retention time dataset containing 80 038 molecules, and then transfer the resulting model to different chromatographic methods based on transfer learning. When tested on the small molecule retention time dataset, as other authors did, the average absolute error reached 27.30 after removing not retained molecules. Still, it reached 33.41 when no samples were removed. The pre-trained RT-Transformer was further transferred to 5 datasets corresponding to different chromatographic conditions and fine-tuned. According to the experimental results, RT-Transformer achieves competitive performance compared to state-of-the-art methods. In addition, RT-Transformer was applied to 41 external molecular retention time datasets. Extensive evaluations indicate that RT-Transformer has excellent scalability in predicting retention times for liquid chromatography and improves the accuracy of metabolite identification. AVAILABILITY AND IMPLEMENTATION: The source code for the model is available at https://github.com/01dadada/RT-Transformer. The web server is available at https://huggingface.co/spaces/Xue-Jun/RT-Transformer.

ProSAP: a GUI software tool for statistical analysis and assessment of thermal stability data.

The Cellular Thermal Shift Assay (CETSA) plays an important role in drug-target identification, and statistical analysis is a crucial step significantly affecting conclusion. We put forward ProSAP (Protein Stability Analysis Pod), an open-source, cross-platform and user-friendly software tool, which provides multiple methods for thermal proteome profiling (TPP) analysis, nonparametric analysis (NPA), proteome integral solubility alteration and isothermal shift assay (iTSA). For testing the performance of ProSAP, we processed several datasets and compare the performance of different algorithms. Overall, TPP analysis is more accurate with fewer false positive targets, but NPA methods are flexible and free from parameters. For iTSA, edgeR and DESeq2 identify more true targets than t-test and Limma, but when it comes to ranking, the four methods show not much difference. ProSAP software is available at https://github.com/hcji/ProSAP and https://zenodo.org/record/5763315.

Plant economic strategies in two contrasting forests.

BACKGROUND: Predicting relationships between plant functional traits and environmental effects in their habitats is a central issue in terms of classic ecological theories. Yet, only weak correlation with functional trait composition of local plant communities may occur, implying that some essential information might be ignored. In this study, to address this uncertainty, the objective of the study is to test whether and how the consistency of trait relationships occurs by analyzing broad variation in eight traits related to leaf morphological structure, nutrition status and physiological activity, within a large number of plant species in two distinctive but comparable harsh habitats (high-cold alpine fir forest vs. north-cold boreal coniferous forest). RESULTS: The contrasting and/or consistent relationships between leaf functional traits in the two distinctive climate regions were observed. Higher specific leaf area, photosynthetic rate, and photosynthetic nitrogen use efficiency (PNUE) with lower N concentration occurred in north-cold boreal forest rather than in high-cold alpine forest, indicating the acquisitive vs. conservative resource utilizing strategies in both habitats. The principal component analysis illuminated the divergent distributions of herb and xylophyta groups at both sites. Herbs tend to have a resource acquisition strategy, particularly in boreal forest. The structural equation modeling revealed that leaf density had an indirect effect on PNUE, primarily mediated by leaf structure and photosynthesis. Most of the traits were strongly correlated with each other, highlighting the coordination and/or trade-offs. CONCLUSIONS: We can conclude that the variations in leaf functional traits in north-cold boreal forest were largely distributed in the resource-acquisitive strategy spectrum, a quick investment-return behavior; while those in the high-cold alpine forest tended to be mainly placed at the resource-conservative strategy end. The habitat specificity for the relationships between key functional traits could be a critical determinant of local plant communities. Therefore, elucidating plant economic spectrum derived from variation in major functional traits can provide a fundamental insight into how plants cope with ecological adaptation and evolutionary strategies under environmental changes, particularly in these specific habitats.

Prediction of Liquid Chromatographic Retention Time with Graph Neural Networks to Assist in Small Molecule Identification.

The predicted liquid chromatographic retention times (RTs) of small molecules are not accurate enough for wide adoption in structural identification. In this study, we used the graph neural network to predict the retention time (GNN-RT) from structures of small molecules directly without the requirement of molecular descriptors. The predicted accuracy of GNN-RT was compared with random forests (RFs), Bayesian ridge regression, convolutional neural network (CNN), and a deep-learning regression model (DLM) on a METLIN small molecule retention time (SMRT) dataset. GNN-RT achieved the highest predicting accuracy with a mean relative error of 4.9% and a median relative error of 3.2%. Furthermore, the SMRT-trained GNN-RT model can be transferred to the same type of chromatographic systems easily. The predicted RT is valuable for structural identification in complementary to tandem mass spectra and can be used to assist in the identification of compounds. The results indicate that GNN-RT is a promising method to predict the RT for liquid chromatography and improve the accuracy of structural identification for small molecules.

Predicting a Molecular Fingerprint from an Electron Ionization Mass Spectrum with Deep Neural Networks.

Electron ionization-mass spectrometry (EI-MS) hyphenated to gas chromatography (GC) is the workhorse for analyzing volatile compounds in complex samples. The spectral matching method can only identify compounds within the spectral database. In response, we present a deep-learning-based approach (DeepEI) for structure elucidation of an unknown compound with its EI-MS spectrum. DeepEI employs deep neural networks to predict molecular fingerprints from an EI-MS spectrum and searches the molecular structure database with the predicted fingerprints. We evaluated DeepEI with MassBank spectra, and the results indicate DeepEI is an effective identification method. In addition, DeepEI can work cooperatively with database spectral matching and NEIMS (fingerprint to spectrum method) to improve identification accuracy.

Deep MS/MS-Aided Structural-Similarity Scoring for Unknown Metabolite Identification.

Tandem mass spectrometry (MS/MS) is the workhorse for structural annotation of metabolites, because it can provide abundance of structural information. Currently, metabolite identification mainly relies on querying experimental spectra against public or in-house spectral databases. The identification is severely limited by the available spectra in the databases. Although, the metabolome consists of a huge number of different functional metabolites, the whole metabolome derives from a limited number of initial metabolites via bioreactions. In each bioreaction, the reactant and the product often change some substructures but are still structurally related. These structurally related metabolites often have related MS/MS spectra, which provide the possibility to identify unknown metabolites through known ones. However, it is challenging to explore the internal relationship between MS/MS spectra and structural similarity. In this study, we present the deep-learning-based approach for MS/MS-aided structural-similarity scoring (DeepMASS), which can score the structural similarity of unknown metabolite against the known one with MS/MS spectra and deep neural networks. We evaluated DeepMASS with leave-one-out cross-validation on MS/MS spectra of 662 compounds in KEGG and an external test on the biomarkers from male infertility study measured on Shimadzu LC-ESI-IT-TOF and Bruker Compact LC-ESI-QTOF. Results show that the identification of unknown compound is valid if its structure-related metabolite is available in the database. It provides an effective approach to extend the identification range of metabolites for existing MS/MS databases.

Enhancing coverage in LC-MS-based untargeted metabolomics by a new sample preparation procedure using mixed-mode solid-phase extraction and two derivatizations.

It is a challenge to expand the metabolome coverage of liquid chromatography (LC)-electrospray ionization (ESI) mass spectrometry (MS) based untargeted metabolomics analysis. The limited coverage is attributed to the weak signal of hydroxyl and carboxyl groups in ESI-MS and the limited capacity of LC separation for metabolites with a wide range of polarities. Here a new sample preparation procedure is proposed to solve these problems. Mixed-mode (reversed-phase and anion-exchange) solid-phase extraction sorbents were used to separate metabolites into hydrophilic amine, hydrophobic amine/alcohol, and organic acid groups. Then, alcohols and carboxylic acids in separated groups were tagged with pyridine with use of two derivatization systems for signal enhancement. Finally, hydrophilic amines were analyzed by LC-MS with a hydrophilic interaction LC column, and the two hydrophobic compound groups were analyzed by LC-MS with a C18 column. From the results for standard samples, the detection limits of the new method are lower than those of the classic solvent extraction-protein precipitation method by 3.3-70 times for five amino acids and by 65-1141 times for five fatty acids. Moreover, the detection limit of this new method is 125 ng mL-1 for cholesterol, which has no signal with the classic method even at 10 µg mL-1. In seminal plasma samples, 110 more metabolites were identified by this new method than by the traditional solvent extraction-protein precipitation method in positive-mode ESI (new method vs traditional method, 65 vs 22 identified by comparing MS/MS spectra with those of standards, 203 vs 136 identified by searching MS spectra in a published database). Among them, 53 carboxylic acids and 21 alcohols were identified only by the new method, and more hydrophilic amine metabolites, such as amino acids and nucleosides, were identified by the new method than by the classic method. Finally, in application to the study of male infertility, more potential biomarkers of oligoasthenoteratospermic infertility were found with the new method (46 potential biomarkers) than with the classic method (19 potential biomarkers) and previously reported methods (10-30 potential biomarkers). Thus, it is demonstrated that this new sample preparation method expands the detection coverage of LC-MS-based untargeted metabolomics methods and has application potential in biological research.

TarMet: a reactive GUI tool for efficient and confident quantification of MS based targeted metabolic and stable isotope tracer analysis.

INTRODUCTION: Untargeted and targeted analyses are two classes of metabolic study. Both strategies have been advanced by high resolution mass spectrometers coupled with chromatography, which have the advantages of high mass sensitivity and accuracy. State-of-art methods for mass spectrometric data sets do not always quantify metabolites of interest in a targeted assay efficiently and accurately. OBJECTIVES: TarMet can quantify targeted metabolites as well as their isotopologues through a reactive and user-friendly graphical user interface. METHODS: TarMet accepts vendor-neutral data files (NetCDF, mzXML and mzML) as inputs. Then it extracts ion chromatograms, detects peak position and bounds and confirms the metabolites via the isotope patterns. It can integrate peak areas for all isotopologues automatically. RESULTS: TarMet detects more isotopologues and quantify them better than state-of-art methods, and it can process isotope tracer assay well. CONCLUSION: TarMet is a better tool for targeted metabolic and stable isotope tracer analyses.

KPIC2: An Effective Framework for Mass Spectrometry-Based Metabolomics Using Pure Ion Chromatograms.

Distilling accurate quantitation information on metabolites from liquid chromatography coupled with mass spectrometry (LC-MS) data sets is crucial for further statistical analysis and biomarker identification. However, it is still challenging due to the complexity of biological systems. The concept of pure ion chromatograms (PICs) is an effective way of extracting meaningful ions, but few toolboxes provide a full processing workflow for LC-MS data sets based on PICs. In this study, an integrated framework, KPIC2, has been developed for metabolomics studies, which can detect pure ions accurately, align PICs across samples, group PICs to identify isotope and potential adducts, fill missing peaks and do multivariate pattern recognition. To evaluate its performance, MM48, metabolomics quantitation, and Soybean seeds data sets have been analyzed using KPIC2, XCMS, and MZmine2. KPIC2 can extract more true ions with fewer detecting features, have good quantification ability on a metabolomics quantitation data set, and achieve satisfactory classification on a soybean seeds data set through kernel-based OPLS-DA and random forest. It is implemented in R programming language, and the software, user guide, as well as example scripts and data sets are available as an open source package at https://github.com/hcji/KPIC2 .

Tungsten Inert Gas Welding of 6061-T6 Aluminum Alloy Frame: Finite Element Simulation and Experiment.

In order to address the irregularity of the welding path in aluminum alloy frame joints, this study conducted a numerical simulation of free-path welding. It focuses on the application of the TIG (tungsten inert gas) welding process in aluminum alloy welding, specifically at the intersecting line nodes of welded bicycle frames. The welding simulation was performed on a 6061-T6 aluminum alloy frame. Using a custom heat source subroutine written in Fortran language and integrated into the ABAQUS environment, a detailed numerical simulation study was conducted. The distribution of key fields during the welding process, such as temperature, equivalent stress, and post-weld deformation, were carefully analyzed. Building upon this analysis, the thin-walled TIG welding process was optimized using the response surface method, resulting in the identification of the best welding parameters: a welding current of 240 A, a welding voltage of 20 V, and a welding speed of 11 mm/s. These optimal parameters were successfully implemented in actual welding production, yielding excellent welding results in terms of forming quality. Through experimentation, it was confirmed that the welded parts were completely formed under the optimized process parameters and met the required product standards. Consequently, this research provides valuable theoretical and technical guidance for aluminum alloy bicycle frame welding.

Early detection of dark-affected plant mechanical responses using enhanced electrical signals.

BACKGROUND: Mechanical damage to plants triggers local and systemic electrical signals that are eventually decoded into plant defense responses. These responses are constantly affected by other environmental stimuli in nature, for instance, light fluctuation. In recent years, studies on decoding plant electrical signals powered by various machine learning models are increasing in a sense of early prediction or detection of different environmental stresses that threaten plant growth or crop yields. However, the main bottleneck is the low-throughput nature of plant electrical signals, making it challenging to obtain a substantial amount of training data. Consequently, training these models with small datasets often leads to unsatisfactory performance. RESULTS: In the present work, we set out to decode wound-induced electrical signals (also termed slow wave potentials, SWPs) from plants that are deprived of light to different extents. Using non-invasive electrophysiology, we separately collected sets of local and distal SWPs from the treated plants. Then, we proposed a workflow based on few-shot learning to automatically identify SWPs. This workflow incorporates data preprocessing, feature extraction, data augmentation and classifier training. We established the integral and the first-order derivative as features for efficiently classifying SWPs. We then proposed an Adversarial Autoencoder (AAE) structure to augment the SWP samples. Combining them, the Random Forest classifier allowed remarkable classification accuracies of 0.99 for both local and systemic SWPs. In addition, in comparison to two other reported methods, our proposed AAE structure enabled better classification results using our tested features and classifiers. CONCLUSIONS: The results of this study establish new features for efficiently classifying wound-induced electrical signals, which allow for distinguishing dark-affected local and systemic plant wound responses. We also propose a new data augmentation structure to generate virtual plant electrical signals. The methods proposed in this study could be further applied to build models for crop plants using electrical signals as inputs, and also to process other small-scale signals.

Effects of C and Al Alloying on Constitutive Model Parameters and Hot Deformation Behavior of Medium-Mn Steels.

Single-pass isothermal hot compression tests on four medium-Mn steels with different C and Al contents were conducted using a Gleeble-3500 thermal simulation machine at varying deformation temperatures (900-1150 °C) and strain rates (0.01-5 s-1). Based on friction correction theory, the friction of the test stress-strain data was corrected. On this basis, the Arrhenius constitutive model of experimental steels considering Al content and strain compensation and hot processing maps of different experimental steels at a strain of 0.9 were established. Moreover, the effects of C and Al contents on constitutive model parameters and hot processing performance were analyzed. The results revealed that the increase in C content changed the trend of the thermal deformation activation energy Q with the true strain. The Q value of 2C7Mn3Al increased by about 50 KJ/mol compared with 7Mn3Al at a true strain greater than 0.4. In contrast, increasing the Al content from 0 to 1.14 wt.% decreased the activation energy of thermal deformation in the true strain range of 0.4-0.9. Continuing to increase to 3.30 wt.% increased the Q of 7Mn3Al over 7Mn by about 65 KJ/mol over the full strain range. In comparison, 7Mn1Al exhibited the best hot processing performance under the deformation temperature of 975-1125 °C and strain rate of 0.2-5 s-1. This is due to the addition of C element reduces the δ-ferrite volume fraction, which leads to the precipitation of κ-carbides and causes the formation of microcracks; an increase in Al content from 0 to 1.14 wt.% reduces the austenite stability and improves the hot workability, but a continued increase in the content up to 3.30 wt.% results in the emergence of δ-ferrite in the microstructure, which slows down the austenite DRX and not conducive to the hot processing performance.

High-throughput drug target discovery using a fully automated proteomics sample preparation platform.

Drug development is plagued by inefficiency and high costs due to issues such as inadequate drug efficacy and unexpected toxicity. Mass spectrometry (MS)-based proteomics, particularly isobaric quantitative proteomics, offers a solution to unveil resistance mechanisms and unforeseen side effects related to off-targeting pathways. Thermal proteome profiling (TPP) has gained popularity for drug target identification at the proteome scale. However, it involves experiments with multiple temperature points, resulting in numerous samples and considerable variability in large-scale TPP analysis. We propose a high-throughput drug target discovery workflow that integrates single-temperature TPP, a fully automated proteomics sample preparation platform (autoSISPROT), and data independent acquisition (DIA) quantification. The autoSISPROT platform enables the simultaneous processing of 96 samples in less than 2.5 hours, achieving protein digestion, desalting, and optional TMT labeling (requires an additional 1 hour) with 96-channel all-in-tip operations. The results demonstrated excellent sample preparation performance with >94% digestion efficiency, >98% TMT labeling efficiency, and >0.9 intra- and inter-batch Pearson correlation coefficients. By automatically processing 87 samples, we identified both known targets and potential off-targets of 20 kinase inhibitors, affording over a 10-fold improvement in throughput compared to classical TPP. This fully automated workflow offers a high-throughput solution for proteomics sample preparation and drug target/off-target identification.

Effects of Different Pre-Heating Welding Methods on the Temperature Field, Residual Stress and Deformation of a Q345C Steel Butt-Welded Joint.

Heavy plate welding has been widely used in the construction of large projects and structures, in which the residual stress and deformation caused by the welding process are the key problems to address to reduce the stability and safety of the whole structure. Strengthening before welding is an important method to reduce the temperature gradient, control the residual stress and reduce the deformation of welds. Based on the ABAQUS software, the thermal elastoplastic finite element method (FEM) was used to simulate the welding thermal cycle, residual stress and deformation of low-alloy, high-strength steel joints. Based on the finite element simulation, the influences of flame heating and ceramic heating on the temperature field, residual stress distribution and deformation of a Q345C steel butt-welded joint were studied. The results showed that the thermal cycle of the ceramic sheet before welding had little influence on the whole weldment, but had great influence on the residual stress of the weldment. The results show that the maximum temperature and residual stress of the welded parts are obviously weakened under the heating of ceramic pieces, and the residual stress of the selected feature points is reduced by 5.88%, and the maximum temperature of the thermal cycle curve is reduced by 22.67%. At the same time, it was concluded that the weld shapes of the two were basically the same, but the weld seams heated by ceramic pieces had a better weld quality and microstructures through comparing the macro- and micro-structures between the welded parts heated by ceramic pieces and the simulated weld. Heating before welding, therefore, is an effective method to obtain a high weld quality with less residual stress and deformation.

A Comprehensive Comparative Analysis of Deep Learning Based Feature Representations for Molecular Taste Prediction.

Taste determination in small molecules is critical in food chemistry but traditional experimental methods can be time-consuming. Consequently, computational techniques have emerged as valuable tools for this task. In this study, we explore taste prediction using various molecular feature representations and assess the performance of different machine learning algorithms on a dataset comprising 2601 molecules. The results reveal that GNN-based models outperform other approaches in taste prediction. Moreover, consensus models that combine diverse molecular representations demonstrate improved performance. Among these, the molecular fingerprints + GNN consensus model emerges as the top performer, highlighting the complementary strengths of GNNs and molecular fingerprints. These findings have significant implications for food chemistry research and related fields. By leveraging these computational approaches, taste prediction can be expedited, leading to advancements in understanding the relationship between molecular structure and taste perception in various food components and related compounds.

Effect of Free Cross-Linking Rate on the Molding of Bulk SiOC Ceramics.

Polymer-derived ceramics (PDCs) have many advantages in ceramic molding and ceramic properties, but because of the obvious volume shrinkage in the process of precursor transformation into ceramics, it is easy for defects to appear in the forming process of bulk PDCs. Herein, theoretical analyses and experimental studies were carried out to improve the quality of sintered samples and realize the parametric design of raw materials. Firstly, based on the HPSO/D4Vi cross-linking system, the mathematical model of the free cross-linking ratio was established, and the theoretical value was calculated. After that, the samples with different free cross-linking rates were heated at 450 °C and 650 °C for different holding times. It was found that the free cross-linking ratio (α) had a significant impact on the weight loss of the samples. When the difference of the α value was 10%, the difference of the samples' weight loss ratio could reach 30%. Finally, the morphology of sintered products with different α values was analyzed, and it was found that obvious defects will occur when the free cross-linking ratio is too high or low; when this value is 40.8%, dense and crack-free bulk ceramics can be obtained. According to analysis of the chemical reaction and cross-linking network density during sintering, the appropriate value of the free cross-linking ratio and reasonable control of the cross-linking network are beneficial for reducing the loss of the main chain element and C element, alleviating the sintering stress, and thus obtaining qualified pressureless sintered bulk ceramic samples.

Ultra-fast and accurate electron ionization mass spectrum matching for compound identification with million-scale in-silico library.

Spectrum matching is the most common method for compound identification in mass spectrometry (MS). However, some challenges limit its efficiency, including the coverage of spectral libraries, the accuracy, and the speed of matching. In this study, a million-scale in-silico EI-MS library is established. Furthermore, an ultra-fast and accurate spectrum matching (FastEI) method is proposed to substantially improve accuracy using Word2vec spectral embedding and boost the speed using the hierarchical navigable small-world graph (HNSW). It achieves 80.4% recall@10 accuracy (88.3% with 5 Da mass filter) with a speedup of two orders of magnitude compared with the weighted cosine similarity method (WCS). When FastEI is applied to identify the molecules beyond NIST 2017 library, it achieves 50% recall@1 accuracy. FastEI is packaged as a standalone and user-friendly software for common users with limited computational backgrounds. Overall, FastEI combined with a million-scale in-silico library facilitates compound identification as an accurate and ultra-fast tool.

Target deconvolution with matrix-augmented pooling strategy reveals cell-specific drug-protein interactions.

Target deconvolution is a crucial but costly and time-consuming task that hinders large-scale profiling for drug discovery. We present a matrix-augmented pooling strategy (MAPS) which mixes multiple drugs into samples with optimized permutation and delineates targets of each drug simultaneously with mathematical processing. We validated this strategy with thermal proteome profiling (TPP) testing of 15 drugs concurrently, increasing experimental throughput by 60x while maintaining high sensitivity and specificity. Benefiting from the lower cost and higher throughput of MAPS, we performed target deconvolution of the 15 drugs across 5 cell lines. Our profiling revealed that drug-target interactions can differ vastly in targets and binding affinity across cell lines. We further validated BRAF and CSNK2A2 as potential off-targets of bafetinib and abemaciclib, respectively. This work represents the largest thermal profiling of structurally diverse drugs across multiple cell lines to date.

Multi-Objective Optimization of Process Parameters in 6016 Aluminum Alloy Hot Stamping Using Taguchi-Grey Relational Analysis.

The hot stamping technology of aluminum alloy is of great significance for realizing the light weight of the automobile body, and the proper process parameters are important conditions to obtain excellent aluminum alloy parts. In this paper, the thermal deformation behavior of 6016 aluminum alloy at a high temperature is experimentally studied to provide a theoretical basis for a finite element model. With the help of blank stamping finite element software, a numerical model of a 6016 aluminum alloy automobile windshield beam during hot stamping was established. The finite element model was verified by a forming experiment. Then, the effect of the process parameters, including blank holder force, die gap, forming temperature, friction coefficient, and stamping speed on aluminum alloy formability were investigated using Taguchi design, grey relational analysis (GRA), and analysis of variance (ANOVA). Stamping tests were arranged at temperatures between 480 and 570 °C, blank holder force between 20 and 50 kN, stamping speed between 50 and 200 mm/s, die gap between 1.05 t and 1.20 t (t is the thickness of the sheet), and friction coefficient between 0.15 and 0.60. It was found that the significant factors affecting the forming quality of the hot-stamped parts were blank holder force and stamping speed, with influence significance of 28.64% and 34.09%, respectively. The optimal parameters for hot stamping of the automobile windshield beam by the above analysis are that the die gap is 1.05 t, the blank temperature is 540 °C, the coefficient of friction is 0.15, stamping speed is 200 mm/s, and blank holder force is 50 kN. The optimized maximum thickening rate is 4.87% and the maximum thinning rate is 9.00%. The optimization method used in this paper and the results of the process parameter optimization provide reference values for the optimization of hot stamping forming.

Mechanical Properties and Fracture Behavior of a TC4 Titanium Alloy Sheet.

TC4 titanium alloy has excellent comprehensive properties. Due to its light weight, high specific strength, and good corrosion resistance, it is widely used in aerospace, military defense, and other fields. Given that titanium alloy components are often fractured by impact loads during service, studying the fracture behavior and damage mechanism of TC4 titanium alloy is of great significance. In this study, the Johnson-Cook failure model parameters of TC4 titanium alloy were obtained via tensile tests at room temperature. The mechanical behavior of TC4 titanium alloy during the tensile process was determined by simulating the sheet tensile process with the finite element software ABAQUS. The macroscopic and microscopic morphologies of tensile fracture were analyzed to study the deformation mechanism of the TC4 titanium alloy sheet. The results provide a theoretical basis for predicting the fracture behavior of TC4 titanium alloy under tensile stress.