SEARCH · PubMed Health

Results for “annotation”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources

PubMed2025

Annotation matters: the effect of structural gene annotation on orthology inference.

MOTIVATION: In silico gene annotation, the process of identifying the genes present in a genome, remains a challenging task. As genome assemblies rapidly increase, the corresponding gene models and repertoires often fall short in quality. Despite advances in annotation methods, a lack of community standards means that most published gene annotations result from ad hoc pipelines. As a result, only a few species have nearly complete and accurate gene models. This annotation quality is thought to affect downstream analyses, including orthology inference, often the first step of comparative genomics studies. RESULTS: We show that different annotation methods yield markedly distinct orthology inferences. We compared orthology assignments of gene models obtained by four prominent protein-coding gene model sources: the NCBI Eukaryotic Genome Annotation Pipeline, the Ensembl Gene Annotation System, the UniProt Reference Proteomes, and Augustus 3.4 (an ab initio pipeline). We observe significant discrepancies between sources, namely in the proportion of orthologous genes per genome, the completeness of Hierarchical Orthologous Groups, and the accuracy and recall of the predicted orthologs on a standard orthology benchmark.

Molecular Sequence Annotation↗

PubMed2025

Efficient evidence-based genome annotation with EviAnn.

For many years, machine learning-based ab initio gene finding approaches have been central components of eukaryotic genome annotation pipelines, and they remain so today. The reliance on these approaches was originally sustained by the high cost and low availability of gene expression data, a primary source of evidence for gene annotation along with protein homology. However, innovations in modern sequencing technologies have revolutionized the acquisition of gene expression data, allowing scientists to rely more heavily on this class of evidence. In addition, proteins found in a multitude of well-annotated genomes represent another invaluable resource for gene annotation. Existing annotation packages often underutilize these data sources, which prompted us to develop EviAnn (Evidence-based Annotator), a novel evidence-based eukaryotic gene annotation system. EviAnn takes a strongly data-driven approach, building the exon-intron structure of genes from transcript alignments or protein-sequence homology rather than from purely ab initio gene finding techniques. We show that when provided with the same input data, EviAnn consistently outperforms current state-of-the-art packages including BRAKER3, MAKER2, and FINDER, while utilizing considerably less computer time. Annotation of a mammalian genome can be completed in less than an hour on a single multi-core server. EviAnn is freely available under an open-source license from https://github.com/alekseyzimin/EviAnn_release and from Bioconda as "eviann".

Journal Article↗

PubMed2004

GOtcha: a new method for prediction of protein function assessed by the annotation of seven genomes.

BACKGROUND: The function of a novel gene product is typically predicted by transitive assignment of annotation from similar sequences. We describe a novel method, GOtcha, for predicting gene product function by annotation with Gene Ontology (GO) terms. GOtcha predicts GO term associations with term-specific probability (P-score) measures of confidence. Term-specific probabilities are a novel feature of GOtcha and allow the identification of conflicts or uncertainty in annotation. RESULTS: The GOtcha method was applied to the recently sequenced genome for Plasmodium falciparum and six other genomes. GOtcha was compared quantitatively for retrieval of assigned GO terms against direct transitive assignment from the highest scoring annotated BLAST search hit (TOPBLAST). GOtcha exploits information deep into the 'twilight zone' of similarity search matches, making use of much information that is otherwise discarded by more simplistic approaches. At a P-score cutoff of 50%, GOtcha provided 60% better recovery of annotation terms and 20% higher selectivity than annotation with TOPBLAST at an E-value cutoff of 10(-4). CONCLUSIONS: The GOtcha method is a useful tool for genome annotators. It has identified both errors and omissions in the original Plasmodium falciparum annotation and is being adopted by many other genome sequencing projects.

Animals↗

PubMed2026

Combining Annotation Software to Identify Orthologous Genes (CASIO) Provides a New Dataset of Orthologous Genes for Swallowtail Butterflies.

With the massive increase in genomic resources, it is becoming increasingly popular to analyse thousands of loci across many species. However, many of the available genomes are not annotated, which hinders an efficient search for orthologous protein-coding genes. Here, we aim to develop a semi-automated pipeline and compare four genomic annotation methods (BRAKER2, BUSCO, Miniprot and Scipio). Our results highlight the importance of integrating multiple annotation tools to optimise ortholog detection and improve genomic studies. Each annotation method showed different strengths. BRAKER2 annotated a substantial number of genes. BUSCO, despite limitations inherent to its reference database, identified a higher number of orthologs. Miniprot exhibited notable flexibility in accommodating diverse protein datasets, whereas Scipio successfully recovered a considerable set of genes that were not detected by the other tools. The combination of these tools allowed for more comprehensive ortholog detection. Taking advantage of this pipeline, we developed a comprehensive dataset of orthologous genes for swallowtail butterflies (Lepidoptera: Papilionidae), called Papilionidae_odb, which will facilitate future studies, especially for a non-model group with abundant genomic data and few transcriptomic resources. We tested Papilionidae_odb by inferring a robust phylogenetic framework for Leptocircini using 142 complete genomes, which improved branch support for some phylogenetic relationships, although challenges remained in resolving relationships within certain species groups, likely due to rapid radiations. Our results highlight the complementary nature of the annotation methods and suggest that combining these tools can yield more accurate results in genomic research. This approach was implemented in a Snakemake workflow called CASIO (Combining Annotation Software to Identify Orthologous genes) and can easily be applied to other non-model groups to improve genomic datasets in diverse taxa where transcriptomic resources are still limited.

Animals↗

PubMed2026

ORFannotate: reproducible coding sequence annotation of transcriptome assemblies.

SUMMARY: Accurate annotation of coding sequences and translational features within transcript models is essential for interpreting assembled transcriptomes and their functional potential. Existing open reading frame (ORF) prediction tools typically operate on transcript FASTA files and do not reintegrate coding sequence (CDS) information back into transcript models, limiting their utility in long-read sequencing workflows where GTF/GFF annotations are the primary output. We present ORFannotate, a lightweight, GTF-native Python command-line tool that predicts ORFs from transcript annotations and reinserts precise, exon-aware CDS and UTR features into the original GTF/GFF file. In addition, ORFannotate provides biologically informative translational context by annotating Kozak sequence strength, detecting non-overlapping upstream ORFs (uORFs) with coding probabilities, characterising 5' and 3' untranslated regions (UTRs), and predicting nonsense-mediated decay (NMD) susceptibility. All annotations are consolidated in a transcript-level summary to support downstream analysis. By generating GTF files with accurate CDS annotations, ORFannotate facilitates reproducible analysis of both long- and short-read transcriptomes and integrates seamlessly with visualization tools, genome browsers, and comparative transcript analysis workflows. ORFannotate is fast, scalable and provides a practical solution for transcriptome annotation beyond coding potential prediction alone. AVAILABILITY AND IMPLEMENTATION: ORFannotate is implemented in Python and freely available under the GNU General Public License v3 (GPL-3.0) at: https://github.com/egustavsson/ORFannotate (DOI: https://doi.org/10.5281/zenodo.16812866).

Open Reading Frames↗

PubMed2026

Long-read transcriptomics corrects Trichomonas vaginalis intron annotations and refines transcript-end features.

BACKGROUND: Trichomonas vaginalis causes the most prevalent non-viral sexually transmitted infection worldwide. Despite its large genome (181.5 Mb; 36,310 predicted protein-coding genes in NYU_TvagG3_2), intron annotations remain limited and inconsistently validated. A recent short-read RNA-seq study reported 63 putative active introns, but short reads can misassign splice boundaries and cannot resolve complete transcript structures. METHODS: We integrated Oxford Nanopore direct RNA sequencing (DRS), ONT cDNA long-read sequencing, and Illumina RNA-seq to refine intron annotations, transcript-end features, and UTR boundaries in T. vaginalis. Candidate introns were validated by targeted PCR and Sanger sequencing, and representative splicing events were further assessed using public SRA datasets. RESULTS: Starting from 31 historically annotated introns, motif-guided long-read screening and orthogonal validation identified 17 additional validated introns, increasing the curated set to 48 confirmed introns. Among these 17 events, three were previously unrecognized in the current NYU_TvagG3_2 reference annotation. We also corrected five reported loci, including two false-positive introns, two splice-coordinate misannotations, and one gene-sequence error. DRS further supported transcript termination site mapping, UAAA polyadenylation-signal profiling relative to poly(A) addition sites, and single-molecule poly(A)-tail estimation. StringTie mixed-mode assemblies provided updated UTR boundaries for intron-bearing transcripts and transcripts without curated introns. CONCLUSIONS: This study provides a rigorously validated, long-read-refined resource of intron annotations, UTR boundaries, and UAAA-guided transcript-end features for T. vaginalis, together with a reproducible workflow for non-model protists. These refinements improve the current reference annotation and support future studies of functional genomics, parasite biology, pathogenesis, and diagnostic development.

Trichomonas vaginalis↗

PubMed2025

Leveraging functional annotations to map rare variants associated with Alzheimer disease with gruyere.

Increased availability of whole-genome sequencing (WGS) has facilitated the study of rare variants (RVs) in complex diseases. Multiple RV association tests are available to study the relationship between genotype and phenotype, but most do not fully leverage the availability of variant-level functional annotations. We propose genome-wide rare variant enrichment evaluation (gruyere), an empirical Bayesian framework that complements existing methods by learning global, trait-specific weights for functional annotations to improve variant prioritization. We apply gruyere to WGS data from the Alzheimer's Disease Sequencing Project to identify Alzheimer disease (AD)-associated genes and annotations. Growing evidence suggests that the disruption of microglial regulation is a key contributor to AD risk, yet existing methods have not examined rare non-coding effects that incorporate such cell-type-specific information. To address this gap, we (1) define per-gene non-coding RV test sets using predicted enhancer and promoter regions in microglia and other brain cell types (oligodendrocytes, astrocytes, and neurons) and (2) include cell-type-specific variant effect predictions (VEPs) as functional annotations. gruyere identifies 13 significant genetic associations not detected by other RV methods, four of which remain significant in omnibus tests. We find that deep-learning-based VEPs for splicing, transcription factor binding, and chromatin state are highly predictive of functional non-coding RVs. Our study establishes a robust framework incorporating functional annotations, coding RVs, and cell-type-associated non-coding RVs to perform genome-wide association tests, uncovering AD-relevant genes and annotations.

Alzheimer Disease↗

PubMed2026

scATAnno: Automated Cell Type Annotation for Single-cell ATAC-seq Data.

Recent advances in single-cell epigenomic techniques have increased the demand for single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) analysis. One key analytical task is to determine cell type identity based on epigenetic data. Here, we introduce scATAnno, a Python package designed to automatically annotate scATAC-seq data using large-scale scATAC-seq reference atlases. This workflow generates reference atlases from publicly available datasets, enabling accurate cell type annotation by integrating query data with reference atlases without the use of single-cell RNA sequencing (scRNA-seq) data. To enhance annotation accuracy, we incorporated k-nearest neighbors (KNN)-based and weighted distance-based uncertainty scores to effectively detect cell populations within the query data that are distinct from all cell types in the reference data. We compared and benchmarked scATAnno against five other published cell annotation approaches, demonstrating its superior performance across multiple datasets and metrics. We further showcased the utility of scATAnno across multiple datasets, including peripheral blood mononuclear cells (PBMCs), triple-negative breast cancer (TNBC), and basal cell carcinoma (BCC), and demonstrated that scATAnno accurately annotates cell types across diverse biological conditions. Overall, scATAnno is a useful tool for scATAC-seq reference atlas construction and cell type annotation and can facilitate the interpretation of new scATAC-seq datasets in complex biological systems. scATAnno is publicly available at https://scatanno-main.readthedocs.io/.

Single-Cell Analysis↗

PubMed2025

Deep learning-based annotation of plant abiotic stress resistance genes for crops.

The declining costs of DNA sequencing have expanded genomic data, crucial for understanding plant abiotic stress responses and crop improvement. However, accurate gene annotation remains challenging. To address this limitation, we propose the PASRGA, a deep learning approach that leverages transfer learning and contrastive learning to annotate genes related to drought, salt, cold, and UV resistance. PASRGA achieves high F1-scores, area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), and Matthews correlation coefficient (MCC) in annotating stress resistance genes, significantly outperforming the general protein annotation model CLEAN, the plant phosphatase gene annotation model PF-NET, the top-ranked model in the CAFA5 challenge NetGO 4.0, and four traditional machine learning methods. Its effectiveness was further validated with a salt stress treatment experiment in Eutrema salsugineum. To facilitate crop breeding practices, we utilized PASRGA to annotate the genomes of 17 major crops. To improve accessibility and utility, we incorporated both manually curated and PASRGA-predicted gene data, together with the PASRGA tool, into the PlantASRG database (https://bioinfor.nefu.edu.cn/PlantASRG/). This comprehensive resource aims to support crop breeding initiatives and ensure food security.

Crops, Agricultural↗

PubMed2023

Functional Annotation Routines Used by ABRF Bioinformatics Core Facilities - Observations, Comparisons, and Considerations.

The functional annotation of gene lists is a common analysis routine required for most genomics experiments, and bioinformatics core facilities must support these analyses. In contrast to methods such as the quantitation of RNA-Seq reads or differential expression analysis, our research group noted a lack of consensus in our preferred approaches to functional annotation. To investigate this observation, we selected 4 experiments that represent a range of experimental designs encountered by our cores and analyzed those data with 6 tools used by members of the Association of Biomolecular Resource Facilities (ABRF) Genomic Bioinformatics Research Group (GBIRG). To facilitate comparisons between tools, we focused on a single biological result for each experiment. These results were represented by a gene set, and we analyzed these gene sets with each tool considered in our study to map the result to the annotation categories presented by each tool. In most cases, each tool produces data that would facilitate identification of the selected biological result for each experiment. For the exceptions, Fisher's exact test parameters could be adjusted to detect the result. Because Fisher's exact test is used by many functional annotation tools, we investigated input parameters and demonstrate that, while background set size is unlikely to have a significant impact on the results, the numbers of differentially expressed genes in an annotation category and the total number of differentially expressed genes under consideration are both critical parameters that may need to be modified during analyses. In addition, we note that differences in the annotation categories tested by each tool, as well as the composition of those categories, can have a significant impact on results.

Computational Biology↗

PubMed2003

Reevaluating human gene annotation: a second-generation analysis of chromosome 22.

We report a second-generation gene annotation of human chromosome 22. Using expressed sequence databases, comparative sequence analysis, and experimental verification, we have extended genes, fused previously fragmented structures, and identified new genes. The total length in exons of annotation was increased by 74% over our previously published annotation and includes 546 protein-coding genes and 234 pseudogenes. Thirty-two potential protein-coding annotations are partial copies of other genes, and may represent duplications on an evolutionary path to change or loss of function. We also identified 31 non-protein-coding transcripts, including 16 possible antisense RNAs. By extrapolation, we estimate the human genome contains 29,000-36,000 protein-coding genes, 21,300 pseudogenes, and 1500 antisense RNAs. We suggest that our revised annotation criteria provide a paradigm for future annotation of the human genome.

Animals↗

PubMed2026

A novel deep learning-driven framework for improving lncRNA comprehensive annotation with LncADeep 2.0.

MOTIVATION: Long non-coding RNAs (lncRNAs) have emerged as crucial players in diverse physiological and pathological processes, yet the biological mechanisms of the vast majority of lncRNAs remain elusive. To fill this gap, it is necessary to improve the accuracy of lncRNA identification and functional annotation. RESULTS: Here, we introduce LncADeep 2.0, an integrated deep learning framework designed to meet these needs. In the identification module, LncADeep 2.0 incorporated novel peptide features along with sequence and structural information, demonstrating superior performance over our previous LncADeep and other existing tools on both annotated transcripts from GENCODE and RNA-seq data. For functional annotation, LncADeep 2.0 leveraged lncRNA-centric interaction networks and gene ontology terms through the transfer learning strategy to achieve robust annotation performance with limited functional data. Compared to LncADeep, LncADeep 2.0 could accurately elucidate the general functions of given lncRNA sequences, predict tissue- or cell-type-specific functions from bulk and single-cell RNA-seq data, and establish connections between tumor-associated lncRNAs and genomic markers. Overall, LncADeep 2.0 stands out as an efficient and reliable tool for lncRNA identification and functional annotation across a wide spectrum of biological processes. AVAILABILITY AND IMPLEMENTATION: LncADeep 2.0 is available for use at https://github.com/Jefferson-Chou/LncADeep2 and https://doi.org/10.5281/zenodo.17164767.

RNA, Long Noncoding↗

PubMed2026

AniAnn's: alignment-free annotation of tandem repeat arrays using fast average nucleotide identity estimates.

MOTIVATION: Satellite DNA has long posed challenges for genome assembly and analysis due to its low sequence complexity and poor mappability. These large heterochromatic arrays of tandem repeats are ubiquitous across eukaryotic genomes, yet remain understudied. Current methods for annotating satellite regions, and other classes of tandem repeat arrays, are limited in their ability to annotate divergent or novel sequences. RESULTS: In this work, we introduce AniAnn's, an algorithm for annotating large blocks of tandemly repeating DNAs. AniAnn's exploits the high Average Nucleotide Identity (ANI) shared between repeat units of the same array to quickly and accurately infer the boundaries of such arrays. We show that AniAnn's improves the annotation of satellites and other tandem repeats within a variety of plant and animal genomes, while requiring only a fraction of the runtime compared to previous approaches. We conclude by exploring several use cases of AniAnn's as a lightweight method for masking repeats prior to whole-genome alignment as well as the de novo annotation and classification of satellite repeats. AVAILABILITY: AniAnn's is open source software and available at github.com/marbl/anianns.

Algorithms↗

PubMed2026

Microbiome Datahub: an open-access platform integrating environmental metadata, taxonomy, and functional annotation for comprehensive metagenome-assembled genome datasets.

BACKGROUND: Metagenome-assembled genomes (MAGs) provide crucial insights into the genomic diversity of uncultured microbes. However, MAG datasets deposited in public repositories such as INSDC are often difficult to reuse due to heterogeneous quality, inconsistent taxonomic and functional annotations, and insufficiently curated environmental metadata. While secondary MAG databases such as MGnify, IMG/M, and SPIRE provide standardized resources, they reconstruct MAGs de novo from public metagenomic reads and therefore do not represent the original MAGs reported in publications. RESULTS: To address this gap, we developed Microbiome Datahub, an open-access platform that systematically aggregates and re-annotates original MAGs from INSDC. We collected 214,427 MAGs, predicted genes by DFAST, performed quality assessment with CheckM, standardized taxonomic assignments with GTDB-Tk, inferred 27 phenotypic traits using Bac2Feature, assigned proteins to MBGD ortholog clusters and KEGG Orthology IDs using PZLAST, and annotated environmental metadata with the Metagenome and Microbes Environmental Ontology. Across these MAGs, the average completeness was 80.5% and contamination 1.8%; notably, the most frequent values were >95% completeness and <1% contamination, indicating that the majority of MAGs are of high quality. Comparative analyses showed that Microbiome Datahub provides phylogenetically and environmentally diverse MAGs: while the majority originated from vertebrate gut environments, a substantial number were also recovered from other habitats such as groundwater, including nearly 10,000 MAGs from the Patescibacteria. Inference of 27 phenotypic traits, including optimum growth temperature, further revealed ecological differentiation across phyla. Protein clustering revealed 56 million identity 40% clusters, with the majority unique compared with MGnify and GlobDB, and ~19% of proteins unassigned to MBGD ortholog clusters, underscoring their novelty. CONCLUSIONS: Microbiome Datahub integrates MAG genome sequences, gene and protein predictions, quality metrics, environmental and taxonomic annotations, ortholog cluster assignments, and phenotype predictions, all accessible via a web interface, API, and bulk downloads. By combining original MAGs with curated metadata and functional annotations, Microbiome Datahub constitutes a comprehensive and reusable resource that will accelerate microbiome and microbial genomics research. Video Abstract.

Metagenome↗

PubMed2025

Expanding kinetoplastid genome annotation through protein structure comparison.

Kinetoplastids belong to the Discoba supergroup, an early divergent eukaryotic clade. Although the amount of genomic information on these parasites has grown substantially, assigning gene functions through traditional sequence-based homology methods remains challenging. Recently, significant advancements have been made in in-silico protein structure prediction and algorithms for rapid and precise large-scale protein structure comparisons. In this work, we developed a protein structure-based homology search pipeline (ASC, Annotation by Structural Comparisons) and applied it to transfer biological information to all kinetoplastid proteins available in TriTrypDB, the reference database for this lineage. Our pipeline enabled the assignment of structural similarity to a substantial portion of kinetoplastid proteins, improving current knowledge through annotation transfer. Additionally, we identified structural homologs for representatives of 6,700 uncharacterized proteins across 33 kinetoplastid species, proteins that could not be annotated using existing sequence-based tools and databases. As a result, this approach allowed us to infer potential biological information for a considerable number of kinetoplastid proteins. Among these, we identified structural homologs to ubiquitous eukaryotic proteins that are challenging to detect in kinetoplastid genomes through standard genome annotation pipelines. The results (KASC, Kinetoplastid Annotation by Structural Comparison) are openly accessible to the community at kasc.fcien.edu.uy through a user-friendly, gene-by-gene interface that enables visual inspection of the data.

Kinetoplastida↗

PubMed2026

Large-scale benchmarking of prokaryotic annotation tools across thousands of species.

BACKGROUND: Genome annotation is an important step in deriving functional meaning from prokaryotic sequencing data, yet systematic evaluations guiding tool selection are lacking. We present the first large-scale investigation of four prominent open-source annotation tools (Prokka, Bakta, EggNOG-mapper, and PGAP) across 156,033 diverse genomes. This includes Escherichia coli strains for baseline performance, thousands of archaea and bacteria genomes, as well as frameshifted and metagenome-assembled genomes. RESULTS: Bakta excels in annotating high-quality bacterial genomes, while PGAP was better for archaeal genomes and challenging bacterial assemblies, including metagenome-assembled, fragmented, or contaminated samples. For Gene Ontology annotation, PGAP consistently provides broader term coverage, whereas EggNOG-mapper offers more terms per feature. CONCLUSIONS: Our findings highlight tool-specific strengths crucial for selecting optimal solutions based on genome quality, taxonomy, and origin (e.g. MAGs). This study provides an evidence-based guide for users and informs future tool development.

Molecular Sequence Annotation↗

PubMed2002

Apollo: a sequence annotation editor.

The well-established inaccuracy of purely computational methods for annotating genome sequences necessitates an interactive tool to allow biological experts to refine these approximations by viewing and independently evaluating the data supporting each annotation. Apollo was developed to meet this need, enabling curators to inspect genome annotations closely and edit them. FlyBase biologists successfully used Apollo to annotate the Drosophila melanogaster genome and it is increasingly being used as a starting point for the development of customized annotation editing tools for other genome projects.

Animals↗

PubMed2026

DeepMASS v.2: An enhanced deep learning platform for large-scale discovery and structural annotation of unknown plant metabolites.

Determining the structures of unknown metabolites remains a fundamental bottleneck in plant metabolomics, as the vast chemical diversity of plant secondary metabolites far exceeds the coverage of existing spectral libraries. Here, we present DeepMASS v.2, a substantially enhanced platform for annotating unknown metabolites from liquid chromatography-tandem mass spectrometry data, designed to address this challenge at scale. DeepMASS v.2 leverages a semantic spectral representation model trained on millions of spectra from GNPS, NIST, and in-house resources. By integrating Spec2Vec-based embeddings with HNSW (hierarchical navigable small world) graph retrieval and a unified chemical space defined by molecular fingerprints, DeepMASS v.2 identifies structurally related neighbors of unknown spectra and ranks candidate structures according to their proximity to the predicted structural neighborhoods within chemical space. Benchmarking against Critical Assessment of Small Molecule Identification datasets and a curated natural product collection demonstrated that DeepMASS v.2 outperforms state-of-the-art in silico annotation tools, including SIRIUS, CFM-ID, MetFrag, and MS-Finder. Importantly, DeepMASS v.2 maintains strong performance for metabolites absent from spectral libraries, highlighting its capacity to annotate genuinely unknown compounds. Application of DeepMASS v.2 to large-scale plant metabolomics datasets demonstrated its ability to expand accessible metabolome coverage. Implemented as an intuitive web platform, DeepMASS v.2 provides the community with a scalable, interpretable, and high-throughput solution for structural annotation, enabling more comprehensive characterization of plant chemical diversity and accelerating natural product discovery in molecular plant science. The DeepMASS v.2 web server is publicly available at http://deepmass.cn.

Metabolomics↗