The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold
Open accessPublished version of a preprint
Abstract
The open-source de novo protein-level assembler, Plass ( https://plass.mmseqs.com ), assembles six-frame-translated sequencing reads into protein sequences. It recovers 2–10 times more protein sequences from complex metagenomes and can assemble huge datasets. We assembled two redundancy-filtered reference protein catalogs, 2 billion sequences from 640 soil samples (soil reference protein catalog) and 292 million sequences from 775 marine eukaryotic metatranscriptomes (marine eukaryotic reference catalog), the largest free collections of protein sequences. The protein-level assembler can assemble protein catalogs from raw metagenomic sequencing data, enabling large-scale metagenomics studies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
FLASH: fast length adjustment of short reads to improve genome assemblies
Magoč, T., & Salzberg, S. L. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr507 · Cited by 15,366
Prodigal: prokaryotic gene recognition and translation initiation site identification
Hyatt, D., Chen, G.-L., LoCascio, P. F., Land, M., Larimer, F. W., & Hauser, L. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-119 · Cited by 12,692
Li, D., Liu, C.-M., Luo, R., Sadakane, K., & Lam, T. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv033 · Cited by 10,133
Velvet: Algorithms for de novo short read assembly using de Bruijn graphsPreprint
Zerbino, D. R., & Birney, E. (2008) · Genome Research · doi:10.1101/gr.074492.107 · Cited by 9,587
KEGG: new perspectives on genomes, pathways, diseases and drugs
Kanehisa, M., Furumichi, M., Tanabe, M., Sato, Y., & Morishima, K. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1092 · Cited by 8,865
MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets
Steinegger, M., & Söding, J. (2017) · Nature Biotechnology · doi:10.1038/nbt.3988 · Cited by 4,840
Self-citationmetaSPAdes: a new versatile metagenomic assembler
Nurk, S., Meleshko, D., Korobeynikov, A., & Pevzner, P. A. (2017) · Genome Research · doi:10.1101/gr.213959.116 · Cited by 4,496
Structure and function of the global ocean microbiome
Sunagawa, S., Coelho, L. P., Chaffron, S., Kultima, J. R., Labadie, K., Salazar, G., Djahanschiri, B., Zeller, G., Mende, D. R., Alberti, A., et al. (2015) · Science · doi:10.1126/science.1261359 · Cited by 2,978
Fast Genome-Wide Functional Annotation through Orthology Assignment by eggNOG-Mapper
Huerta-Cepas, J., Forslund, K., Coelho, L. P., Szklarczyk, D., Jensen, L. J., von Mering, C., & Bork, P. (2017) · Molecular Biology and Evolution · doi:10.1093/molbev/msx148 · Cited by 2,709
An integrated catalog of reference genes in the human gut microbiome
MetaHIT Consortium, Li, J., Jia, H., Cai, X., Zhong, H., Feng, Q., Sunagawa, S., Arumugam, M., Kultima, J. R., Prifti, E., et al. (2014) · Nature Biotechnology · doi:10.1038/nbt.2942 · Cited by 2,164
Cited by
Sorted by citations
Items 301–400 of 446
Singh, J., Paliwal, K. K., Singh, J., & Zhou, Y. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.10.16.464622 · Cited by 4
“These methods were trained on extensive protein databases such as Uniref 23 , Uniclust 24 , Pfam 25 , and BFD 26,27 .”
MethodProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy StatePreprint
Wang, X., Yang, H., Kodirov, E., Mukherjee, S. S., Clifton, D. A., & Robertson, N. M. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.07.01.498447 · Cited by 4
“The transformer network is a subnet of ProtBert-BFD [17], a protein language model pretrained on BFD-100 dataset [69, 70].”
MethodPokharel, S., Pratyush, P., Heinzinger, M., Newman, R. H., & KC, D. B. (2022) · Research Square · doi:10.21203/rs.3.rs-1953874/v1 · Cited by 4
Artificial Intelligence Learns Protein PredictionPreprint
Heinzinger, M., & Rost, B. (2024) · Cold Spring Harbor Perspectives in Biology · doi:10.1101/cshperspect.a041458 · Cited by 4
AlphaFlex: Accuracy modeling of protein multiple conformations via predicted flexible residuesPreprint
Ge, L., Cui, X., Zhao, K., Zhou, X., Zhang, Y., & Zhang, G. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.11.664327 · Cited by 4
Liu, J., Neupane, P., & Cheng, J. (2025) · Communications Biology · doi:10.1038/s42003-025-08960-6 · Cited by 10
Zhou, Y., Liu, W., Liu, Q., Liu, J., Xing, Y., Ma, J., & Zhu, Y. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.08.014 · Cited by 3
“BERT-BFD employs masked language modeling objectives trained on the Big Fantastic Database (BFD), a comprehensive corpus containing 2.122 billion evolutionarily diverse protein sequences that were originally curated [19,21].”
InfluentialCarpeDeam: a de novo metagenome assembler for heavily damaged ancient datasets
Kraft, L., Söding, J., Steinegger, M., Jochheim, A., Sackett, P. W., Fernàndez-Guerra, A., & Renaud, G. (2025) · Genome biology · doi:10.1186/s13059-025-03839-5 · Cited by 4
“Additionally, it is important to note that while protein-level assemblers such as PLASS [65] exist, the highly degraded nature of aDNA, resulting in ultra-short aDNA fragments, presents significant challenges for these tools.”
InfluentialSelf-citationConserved pathway for homarine catabolism in environmental bacteria
Ferrer-González, F. X., Heal, K. R., Sacks, J. S., Romero-Maysonet, Y., Finch, A. H., Carlson, L. T., Coe, L. S. Y., Bartolek, Z., Luthy, C. B., Gaffney, M. P., et al. (2026) · Nature Microbiology · doi:10.1038/s41564-026-02313-7 · Cited by 3
Contact-Assisted Threading in Low-Homology Protein Modeling
Bhattacharya, S., Roche, R., Shuvo, M. H., Moussad, B., & Bhattacharya, D. (2023) · Methods in molecular biology · doi:10.1007/978-1-0716-2974-1_3 · Cited by 3
Ditz, J. C., Wistuba-Hamprecht, J., Maier, T., Fendel, R., Pfeifer, N., & Reuter, B. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad206 · Cited by 3
Le, V. T., Tseng, Y.-H., Liu, Y., Malik, M. S., & Ou, Y. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.136048 · Cited by 4
PepPFN: protein-peptide binding residues prediction via pre-trained module-based Fourier Network
Li, X., Cao, B., Ding, H., Kang, N., & Song, T. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00195 · Cited by 3
Dong, B., Su, H., Xu, D., Hou, C., Liu, Z., Niu, N., & Wang, G. (2024) · Genes · doi:10.3390/genes15101350 · Cited by 3
“Elnaggar et al. [18] pre-trained and proposed the ProtTrans model on the UniRef50, UniRef100 [19], and BFD [20] datasets, which achieved the best performance in protein structure prediction tasks.”
MethodHelsem, S. A., Alfsnes, K., Frye, S. A., Hesselberg Løvestad, A., & Ambur, O. H. (2025) · PLOS One · doi:10.1371/journal.pone.0315160 · Cited by 3
CELL-E: A Text-To-Image Transformer for Protein Localization PredictionPreprint
Khwaja, E., Song, Y. S., & Huang, B. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.05.27.493774 · Cited by 4
“These models are trained on millions of amino acid sequences from databases such as BFD [39], UniRef [40], Pfam [15], and Protein Data Bank [41].”
MethodHuman O-linked Glycosylation Site Prediction Using Pretrained Protein Language ModelPreprint
Pakhrin, S. C., Chauhan, N., Khan, S., Upadhyaya, J., Keller, C., Neuman, L. N., Beck, M. R., & Blanco, E. (2023) · Research Square · doi:10.21203/rs.3.rs-3587524/v1 · Cited by 3
PackDock: a Diffusion Based Side Chain Packing Model for Flexible Protein-Ligand DockingPreprint
Zhang, R., Jiang, X., Cao, D., Yu, J., Chen, M., Fan, Z., Kong, X., Xiong, J., Zhang, Z., Zhang, W., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.01.31.578200 · Cited by 2
“Experimental methods have determined about 100,000 structures over the years [56] , which only cover a small part of the known protein sequence space [57] .”
BackgroundAIPAMPDS: an AI platform for antimicrobial peptide design and screeningPreprint
Li, Y., Gao, L., Wenqian, Z., Wang, Z., Xu, X., Ji, J., Zhang, Y., Liu, Y., Zhang, L., Yang, Y., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.03.24.644774 · Cited by 3
Zhai, S., Zhao, H., Wang, J., Lin, S., Liu, T., Jiang, D., Liu, H., Kang, Y., Yao, X., & Hou, T. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.08.647699 · Cited by 3
Biasing Conformational Sampling in AlphaFold 3 and Boltz-2 via Pair Representation ScalingPreprint
Suzuki, S., & Amagasa, T. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.01.23.701250 · Cited by 3
Shoombuatong, W., Ahmed, S., Mahmud, S. H., & Schaduangrat, N. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108440 · Cited by 2
Ma, L., Zhou, W., Bai, Y., Fang, M., Xiao, M., & Li, J. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3559571 · Cited by 2
Zhu, L., Chen, W., & Yang, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127991 · Cited by 2
Predicting RNA Structure Utilizing Attention from Pretrained Language Models
Papazoglou, I., Chatzigoulas, A., Tsekenis, G., & Cournia, Z. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02094 · Cited by 4
Wu, W., Wang, C., Chen, L., Yin, M., Zhu, Y., Fu, K., Ye, J., Xiong, H., & Wang, Z. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737138 · Cited by 7
“Through pre-training on databases containing hundreds of millions of such protein sequences ( e.g. , UniRef [78], BFD [73, 74]), pLMs enable effective modeling and prediction of protein structures and functions [36].”
Alphappimi: a comprehensive deep learning framework for predicting PPI-modulator interactions
Liu, D., Song, T., Wang, S., Li, X., Han, P., Wang, J., & Wang, S. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01077-2 · Cited by 2
“The ProtTrans model (24 layers, 32 heads per layer) was pre-trained on over 45 million protein sequences from BFD [62, 63] and UniRef50 [61], generating 1024-dimen-sional embeddings that capture complementary evolutionary patterns.”
Song, S., Lu, M., Su, Y., & Liu, T. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108846 · Cited by 2
Enhancing protein immunogenicity prediction via uncertainty weighted deep ensemble
Qayyum, A. B. A., Rahmati, A. H., Qian, X., & Yoon, B.-J. (2026) · Oxford Open Immunology · doi:10.1093/oxfimm/iqag008 · Cited by 2
“ProtTrans: This work investigates scaling protein language models using both autoregressive (Transformer-XL [62], XLNet [63]) and auto-encoding models (BERT [64], ALBERT [65], ELECTRA [66], T5 [57]) trained on UniRef and BFD datasets [59, 67].”
Scoring protein sequence alignments using deep learning
Shrestha, B., & Adhikari, B. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac210 · Cited by 2
Application of Computational Techniques in Antibody Fc-Fused Molecule Design for Therapeutics
Ng, C. L., Lim, T. S., & Choong, Y. S. (2023) · Molecular Biotechnology · doi:10.1007/s12033-023-00885-x · Cited by 2
“…Kalign [54] Sequence assembly The merging of gene/protein fragments to reconstruct the original sequence or create new sequence ABySS [55]; Plass [56]; SPAdes [57] Visualization Graphical presentation of i.e. protein structures; genomic and assembly data; alignment and phylogeny ChimeraX [58];…”
Improving Protein Secondary Structure Prediction by Deep Language Models and Transformer Networks
Wu, T., Cheng, W., & Cheng, J. J. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-4196-5_3 · Cited by 2
Inferring context-specific site variation with evotuned protein language models
Lytras, S., Strange, A. P., Ito, J., & Sato, K. (2026) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqag018 · Cited by 3
“All type A sequences, unique on the amino acid level, were downloaded, leading to a total of 33 657 sequences (retrieved on the 11 th of April 2024).”
Shiono, D., & Yoshidome, T. (2022) · Journal of the Physical Society of Japan · doi:10.7566/jpsj.91.064804 · Cited by 2
Near-complete protein structural modelling of the minimal genomePreprint
Greener, J. G., Desai, N., Kandathil, S. M., & Jones, D. T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06623 · Cited by 3
“HHblits [32] searches were carried out against the 2018_08 version of the UniClust30 database, the BFD database [33], and our custom pipeline [34] that uses sequences from the EBI MGnify database [35].”
MethodA Deep Semi-Supervised Framework for Accurate Modelling of Orphan SequencesPreprint
Moffat, L., & Jones, D. T. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.07.13.201459 · Cited by 2
“Given the speed at which sequence databases are growing 1,59 this is not unreasonable, but unlikely to be within reach in the near future.”
BackgroundPredicting direct physical interactions in multimeric proteins with deep learningPreprint
Gao, M., An, D. N., Parks, J. M., & Skolnick, J. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.11.09.467949 · Cited by 2
“We used different sets of sequence libraries[53-56] and Protein Data Bank (PDB)[57] releases to generate appropriate input features for different test sets, as described below.”
MethodTMvisDB: resource for transmembrane protein annotation and 3D visualizationPreprint
Marquet, C., Grekova, A., Houri, L., Bernhofer, M., Soto, L. F. J., Karl, T., Heinzinger, M., Dallago, C., & Rost, B. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.11.30.518551 · Cited by 2
“Similarly to structure predictors advancing rapidly [14-17], methods to quickly and reliably search and cluster the exploding sequence space (>2.4 billion in metagenomic databases) are continuously improving [18-20].”
InfluentialZhu, Y., & Yu, D. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.05.30.542787 · Cited by 2
“ESM2, ProtTrans, and ESM-MSA are both unsupervised attention networks with 36, 24, and 12 layers, respectively, and separately trained on Uniref50 [48], UniClust30 & Uniref50, and BFD (Big Fantastic Database) [49] & Uniref50, respectively, where “&” means that two databases are both used to train a transformer.”
MethodGenome-scale annotation of protein binding sites via language model and geometric deep learning
(2023) · doi:10.1101/2023.11.02.565344 · Cited by 2
“In addition to the pre-computed residue features (ProtTrans embedding and structural properties by DSSP), a comprehensive, end-to-end geometric featurizer is employed to extract the geometric node features including distance, direction and angle, as well as geometric edge features between residues…”
MethodProtein domain embeddings for fast and accurate similarity searchPreprint
Iovino, B. G., Tang, H., & Ye, Y. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.27.567555 · Cited by 2
Strain-resolved de-novo metagenomic assembly of viral genomes and microbial 16S rRNAsPreprint
Jochheim, A., Jochheim, F. A., Kolodyazhnaya, A., Morice, É., Steinegger, M., & Söding, J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.29.587318 · Cited by 2
Self-citationImproving AlphaFold3 by Engineering MSA and Template InputsPreprint
Neupane, P., Liu, J., & Cheng, J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.22.720119 · Cited by 4
“It first generates default MSAs following the paradigm used in the default AF3, where the target sequence is searched against both general-purpose protein databases (UniRef30 [27], UniRef90 [28]) and metagenomic databases (BFD [29, 30, 31], MGnify [32]) using HHblits [33] and JackHMMER [34].”
Ahmad, S., Schaduangrat, N., Chumnanpuen, P., Mahmud, S., Goh, M. K. O., & Shoombuatong, W. (2025) · PLoS ONE · doi:10.1371/journal.pone.0333614 · Cited by 1
“Since PLMs are pre-trained on extensive protein databases such as BFD [23,24], UniRef [25], and Pfam [26], which collectively contain over a billion protein sequences, they can extract comprehensive and valuable information.”
Explainable multiscale representation learning for anticancer peptide prediction
Zhang, Y., Mao, X., Liu, Y., Li, W., Zhou, Z., Xu, Y., Wu, J., Zou, Q., & Xu, L. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.113827 · Cited by 1
Song, S., Su, Y., Guo, Q., & Liu, T. (2026) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2026.109307 · Cited by 1
Ankh‐Score Produces Better Sequence Alignments Than AlphaFold3
Malec, J., Rusen, K., Golding, G. B., & Ilie, L. (2026) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.70143 · Cited by 1
“PLMs are trained on vast unlabelled sequence databases, such as UniProt [6] or BFD [7], to provide contextual representations for amino acid residues in the form of high-dimensional vectors, called embeddings, that capture functional and evolutionary patterns, helping to create state- of- the-art…”
Microbial N 2 O Reduction in Sulfidic Waters: Implications for Proterozoic Oceans
Buessecker, S., Klos, A. S., Quan, M. E., Finch, A. H., Sobol, M. S., Evans, G. N., Anbar, A. D., Kaçar, B., & Dekas, A. (2026) · Geobiology · doi:10.1111/gbi.70056 · Cited by 1
“High-quality reads were directly assembled to protein sequences with Plass (Steinegger et al. 2019) in default configuration, resulting in a minimum of 1.8 million sequences per sample.”
InfluentialApplication of Protein Language Models to low-N Engineering of metalloproteinase inhibitors
Buxton, E. K., Patel, R., Toumaian, M. R., & Raeeszadeh‐Sarmazdeh, M. (2021) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00048 · Cited by 1
“The model was first pre-trained on a dataset of 2.1B noisy, redundant, and shorter protein sequences from BFD and then it was fine-tuned on 45M less noisy, less redundant, and longer sequences from Uniref50.”
BackgroundDe Novo Design of Target-Specific Ligands Using BERT-Pretrained Transformer
Zheng, Y., Lu, F., Zou, J., Hua, H., Lu, X., & Min, X. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8549-4_26 · Cited by 1
Liu, T., Song, C., & Wang, C. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2024063 · Cited by 1
“(7) The ProtBERT and ProtT5 models are based on two auto-encoder transformer structures, trained on data from the BFD [37] and UniRef databases.”
MethodFujita, H., Nomura, A., Endo, T., & Sekijima, M. (2023) · Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE) · doi:10.1109/csce60160.2023.00351 · Cited by 1
“However, the number of proteins whose three-dimensional structures have been experimentally determined is approximately 1/10,000th of the total number of known amino acid sequences of proteins [6]–[8].”
BackgroundTransAnnot—a fast transcriptome annotation pipeline
Zelenskaia, M., Arangasamy, Y., Mirdita, M., Söding, J., & Raghavan, V. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbae152 · Cited by 1
“However, PLASS has not yet been extensively benchmarked for transcriptome assembly and requires a minimum read length of > ¼ 100 nt .”
MethodInfluentialSelf-citationLi, J., Lu, Y., Wang, X., & Chang, Z. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821766 · Cited by 1
Wang, R., Yang, X., Pang, C., & Wei, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3539313 · Cited by 1
“Here, we used a BERT-based model ProtBERT-big fantastic database (BFD) [30] which was pre-trained on the BFD [31], a database consisting of 2.1 billion unlabeled protein data, in a self-supervised manner to obtain semantic knowledge from a large corpus of protein sequences.”
InfluentialThe grand biological universe: A comprehensive geometric construction of genome space
Yu, H., Sun, N., Ren, R., Zhou, T., Guan, M., Zhao, L., & Yau, S. S. ‐. (2025) · The Innovation · doi:10.1016/j.xinn.2025.100937 · Cited by 1
“7 While the concept of searching has enhanced the computational efficiency of alignment methods, these methods heavily depend on large databases and often analyze sequences in fragments rather than understanding their overall structure.”
Prediction of Protein–Peptide Binding Sites Using PepBCL
Wang, R., Nakai, K., & Wei, L. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4623-6_16 · Cited by 1
Type IV minor pilin ComN predicted the USS-receptor in Pasteurellaceae
Helsem, S. A., Alfsnes, K., Frye, S. A., Løvestad, A. H., & Ambur, O. H. (2025) · Frontiers in Microbiology · doi:10.3389/fmicb.2025.1647523 · Cited by 1
“…differences between the local and AF3 web server 5 outputs and were able to reconcile these differences by locally running the jackhmmer, using v. 3.4 (Potter et al., 2018) and MSA search on the BFD database (Steinegger et al., 2019; Steinegger and Söding, 2018) using the parameter incdomE 0.01.”
InfluentialImproved Protein Real-Valued Distance Prediction Using Deep Residual Dense Network (DRDN)
Geethu, S., & Vimina, E. R. (2022) · The Protein Journal · doi:10.1007/s10930-022-10067-4 · Cited by 1
“The HHblits algorithm is applied to the BFD database in the second phase.”
MethodCamargo, A. P., de Souza, R. S. C., José, J., Gerhardt, I. R., Dante, R. A., Mukherjee, S., Huntemann, M., Kyrpides, N. C., Carazzolle, M. F., & Arruda, P. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.07.30.454538 · Cited by 1
“To improve the recovery of the protein sequence space encompassed by these 20 microbiomes, we performed protein-level assembly directly from sequence reads [17].”
MethodStatistical methods for biological sequence analysis for DNA binding motifs and protein contacts
Roth, C. (2021) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-8835 · Cited by 1
MsPBRsP: Multi-Scale Protein Binding Residues Prediction Using Language ModelPreprint
Li, Y., Lu, S., Nan, X., Zhang, S., & Zhou, Q. (2023) · SSRN Electronic Journal · doi:10.1101/2023.02.26.528265 · Cited by 1
“The other way is similar to word embedding in natural language processing (NLP) and employing a pre-trained BERT model [61] named ProtTrans [59] which is trained on a super huge datasets Big Fantastic Database (BFD) [62, 63].”
MethodOpinion piece/Book chapter: Artificial Intelligence learns protein predictionPreprint
Heinzinger, M., & Rost, B. (2023) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/n7wfp · Cited by 1
Human O -linked Glycosylation Site Prediction Using Pretrained Protein Language ModelPreprint
Pakhrin, S. C., Chauhan, N., Khan, S., Upadhyaya, J., Keller, C., Neuman, L. N., Beck, M. R., & Blanco, E. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.23.563673 · Cited by 1
Bloomfield, S. J., Zomer, A., & Mather, A. E. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.25.586564 · Cited by 1
TemBERTure: Advancing protein thermostability prediction with Deep Learning and attention mechanismsPreprint
Rodella, C., Lazaridi, S., & Lemmin, T. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.28.587204 · Cited by 2
Murphy, D., Mesdaghi, S., Rodríguez, F. S., Simpkin, A. J., Elliott, L. G., & Rigden, D. J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.13.589297 · Cited by 1
“The options “use_turbo” and “use_ptm” (pTM network) were unselected [33], mmseqs was used for the MSA generation step [87,88], with all other options and parameters the default.”
MethodTowards Unraveling Biomolecular Conformational Landscapes with a Generative Foundation ModelPreprint
The OpenComplex Team, & Ye, Q. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.05.01.651643 · Cited by 3
WAChRs are excitatory opsins sensitive to indoor lightingPreprint
Tose, A. J., Nava, A. A., McGrath, S. N., Mardinly, A. R., & Naka, A. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.12.675947 · Cited by 2
Coche-Miranda, J., Arros, P., Canales, N., Berríos-Pastén, C., Lagos, R., Orlando, J., Chávez, F. P., & Marcoleta, A. E. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.30.679653 · Cited by 1
“81 of these clusters also contained 3,502 Antarctic proteins (PLASS DB or Meta DB).”
InfluentialGardon, H., Tabuteau, S., Irlinger, F., Dugat‐Bony, É., Barbe, V., Callon, C., Gendre, J. C., Cruaud, C., Delbès, C., Gavory, F., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.15.694182 · Cited by 1
A dive into the coral microbiome
Gourlé, H. (2020) · Epsilon Open Archive (Sveriges lantbruksuniversitet biblioteket (Swedish University of Agricultural Sciences))
Margelevičius, M. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.06.22.449457
“If insufficient sequences appear in the search results, HHblits is used to search the BFD metagenomic protein database of MSAs [35], filtered to 30% sequence identity.”
MethodInfluential(2021) · PeerJ · doi:10.7287/peerj.12198v0.1/reviews/2
“The databases can be updated with new genomes or individual gene sequences ( e.g., created via metagenome assembly with PLASS (Steinegger, Mirdita, and Söding 2019)).”
Faculty Opinions recommendation of Highly accurate protein structure prediction with AlphaFold.
Arulanandam, A. J. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.740477161.793587548
Zhang, W., & Zhai, R. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.740510745.793587739
Faculty Opinions recommendation of Highly accurate protein structure prediction with AlphaFold.
Chakraborty, S. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.740477161.793587538
Gutiérrez, J., & Hablützel, P. I. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.07.27.501711
“One particularly 312 interesting addition would be the huge protein catalog MERC assembled from 313 metatranscriptome datasets derived from the TARA OCEAN expedition [63], which could be 314 mined for high level representations of the largely unknown sequence space [64] with distant 315 homologies to diverse metabolic…”
BackgroundToward enhancing drug discovery and development research using AlphaFold
Tomii, K. (2022) · Translational and Regulatory Sciences · doi:10.33611/trs.2022-007
FrameRate: learning the coding potential of unassembled metagenomic readsPreprint
Liu-Wei, W., Aubrey, W., Clare, A. J., Hoehndorf, R., Creevey, C. J., & Dimonaco, N. J. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.09.16.508314
“Another such tool, Plass [Steinegger et al., 2019], specifically aims to partly circumvent genome assembly and gain protein-level insight directly from DNA sequencing reads.”
MethodAN ANALYSIS OF PROTEIN STRUCTURE PREDICTION WITH HELP OF ARTIFICIAL INTELLIGENCE
Bhadoriya, A. (2022) · International Journal of Engineering Applied Sciences and Technology · doi:10.33564/ijeast.2022.v07i04.027
Jochheim, A. (2022) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-9608
Protein tertiary structure prediction and refinement using deep learning
Wu, T. (2022) · MOspace Institutional Repository (University of Missouri) · doi:10.32469/10355/94100
Integrated de novo gene prediction and peptide assembly of metagenomic sequencing data
Thippabhotla, S., Liu, B., Podgorny, A., Yooseph, S., Yang, Y., Zhang, J., & Zhong, C. (2023) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqad023
“The first strategy corresponded to the assembly of FGS (42) or MPD (46) predicted reads using PLASS (49).”
BackgroundMethodInfluentialCELL-E: zero-shot sequence-to-image synthesis for protein localization predictionPreprint
Khwaja, E., Song, Y. S., & Huang, B. (2023) · Research Square · doi:10.21203/rs.3.rs-2963881/v1
“These models are trained on millions of amino acid sequences from databases such as BFD [37], UniRef [38], Pfam [39], and Protein Data Bank [ 40].”
MethodRecent advances in estimating protein structure model accuracy
Liu, D., Cui, X., Wang, H.-D., & Zhang, G. (2023) · Acta Physica Sinica · doi:10.7498/aps.72.20231071
Deep learning based secreted protein prediction
Liu, C., Wang, B., Zhang, X., & Zhang, F. (2023) · International Conference on Advanced Algorithms and Signal Image Processing (AASIP) · doi:10.1117/12.3006157
“In this study, we utilized the pre-trained Bert model ProtBert-Big Fantastic Database (BFD) [12] , which is based on the generic domain Bert pre-training [13] using a large corpus of untagged protein data from BFD.”
MethodInvestigação metagenômica dos microbiomas de plantas adaptadas à limitação nutricional
Camargo, A. P. D. C. B. D. R. (2021) · doi:10.47749/t/unicamp.2021.1238926
Population dynamics, interactions and evolution of marine microbes using genomic approaches
Latorre, F. (2023) · UPCommons institutional repository (Universitat Politècnica de Catalunya) · doi:10.5821/dissertation-2117-396974
Umbrella toxin particles produced by Streptomyces block mycelial growth of competing speciesPreprint
Zhao, Q., Bertolli, S. K., Park, Y., Tan, Y., Cutler, K. J., Srinivas, P., Asfahl, K. L., Garcia, C. F., Gallagher, L. A., Li, Y., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.09.570830
Genome-scale annotation of protein binding sites via language model and geometric deep learningPreprint
Yuan, Q., Tian, C., & Yang, Y. (2024) · eLife · doi:10.7554/elife.93695.1
EdtClust: A fast homologous protein sequences clustering method based on edit distance
Xiang, Y., Gu, J., & Zhou, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385950
PackDock: a Diffusion Based Side Chain Packing Model for Flexible Protein-Ligand DockingPreprint
Zheng, M., Zhang, R., Jiang, X., Cao, D., Yu, J., Chen, M., Fan, Z., Kong, X., Xiong, J., Zhang, Z., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4128729/v1
Genome-scale annotation of protein binding sites via language model and geometric deep learning
Yuan, Q., Tian, C., & Yang, Y. (2024) · doi:10.7554/elife.93695.2
Álvarez-Carreño, C., Huynh, A. T., Petrov, A. S., Orengo, C. A., & Williams, L. D. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.02.587612
CarpeDeam: A De Novo Metagenome Assembler for Heavily Damaged Ancient DatasetsPreprint
Kraft, L., Söding, J., Steinegger, M., Jochheim, A., Sackett, P. W., Fernàndez-Guerra, A., & Renaud, G. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.09.607291
Self-citationCRULoc: A protein subcellular localization prediction model based on BiGRU and CNN
Lu, Y. (2024) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat62382.2024.10695442
“These models learn high-quality representations of proteins through self-supervised learning [6] from protein databases containing large amounts of unlabeled sequences, such as Uniprot [7] and metagenomic databases like the Big Fantastic Database [8] (BFD) [9].”
BackgroundMethodPackDock is a Flexible Protein-Ligand Docking Approach with Diffusion-Based Side Chain PackingPreprint
Zheng, M., Zhang, R., Jiang, X., Cao, D., Wang, Z., Yu, J., Chen, M., Fan, Z., Kong, X., Xiong, J., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-5429173/v1
Metadata
- Authors
- Steinegger, M., Mirdita, M., & Söding, J.
- Affiliations
- Seoul National University (KR)
- Max Planck Institute for Biophysical Chemistry (DE)
- Corresponding author
- Steinegger, Martin
- Söding, Johannes
- Venue
- Nature Methods
- Published
- 2019-06-24
- Volume
- 16
- Issue
- 7
- Pages
- 603-606
- ISSN
- 1548-7091 (ISSN-L)
- 1548-7105
- OpenAlex
- W2949342052
- Cited by
- 445
- References
- 31
- Citations by year
- 2026: 38 · 2025: 78 · 2024: 101 · 2023: 78 · 2022: 71 · 2021: 50 · 2020: 23 · 2019: 6
- FWCI
- 12.42
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Nature Methods (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Seoul National University Open Repository (Seoul National University) (submittedVersion)
- Funders
- Materials and Energy Research Center
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Physical Sciences › Environmental Science › Ecology › Environmental DNA in Biodiversity Studies
- Physical Sciences › Environmental Science › Ecology › Microbial Community Ecology and Physiology
- Keywords
- metagenomics, metatranscriptomics, soil metagenome
- MeSH terms
- Amino Acid Sequence, Codon, Proteins, Open Reading Frames, Metagenomics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
