SeqHub

Cite

How to cite SeqHub

If SeqHub contributed to your research, please cite the references below.

SeqHub

The software platform integrating Tatta Bio’s AI models to support protein and genome analysis.

N. Jha, J. Kravitz, J. West-Roberts, C. Lu, A. P. Camargo, S. Roux, A. Cornman, & Y. Hwang. Gaia: An AI-enabled genomic context–aware platform for protein sequence annotation. Science Advances 11(25) eadv5109 (2025). https://doi.org/10.1126/sciadv.adv5109

FlashPPI

The method behind predicted protein–protein interaction networks.

A. Cornman, M. Tranzillo, N. G. Zulaybar, I. Bouzit, & Y. Hwang. Linear-time prediction of proteome-scale microbial protein interactions. Proceedings of the National Academy of Sciences 123(25) e2610619123 (2026). https://doi.org/10.1073/pnas.2610619123

Intergenic SAE features

The method behind predicted Sparse Autoencoder (SAE) features within intergenic regions using gLM2.

N. G. Zulaybar, M. Tranzillo, R. Silverstein, Y. Hwang, & A. Cornman. Discovery of microbial intergenic features with genomic language modeling and multimodal search. bioRxiv (2026). https://doi.org/10.64898/2026.09.15.751765

Recent citations

See how scientists have used SeqHub in their work.

Pseudomonas vancouverensis as a platform for one-carbon (C1) assimilation and polyhydroxyalkanoate accumulation

Emil C. Ørsted, Meg Walsh, Kevin O’Connor, Daniel C. Volke, Pablo I. Nikel·Metabolic Engineering·2026

From the author

"We used SeqHub (Gaia back then) to look through the genome of the P. vancouverensis strain we work with for potential C1-assimilation genes that the Prokka pipeline might have missed. Being able to upload a full genome, rather than BLASTing individual protein sequences was very useful in this regard. SeqHub did not show any of the usual suspects, pointing us towards that the strain is either piggy-bagging on enzyme promiscuity or that it has a set of unannotated/uncharacterized genes involved in C1-assimilation. We are using SeqHub a lot in the group, since some of the bugs we are working with are either uncharacterized or different from E. coli, so it is nice to have a tool at hand that allows us to predict protein function and compare gene clusters in a fast and intuitive way."
Emil Ørsted Christensen

Genome-Informed Identification of Species-Specific Diagnostic Markers for Listeria Using Pangenome Analysis

Viona Osei, Emmanuel Kuufire, Rejoice Nyarku, Kingsley E. Bentum, Tyric James, Asmaa Elrefaey, Temesgen Samuel, Woubit Abebe·Pathogens·2026

A Novel Pilus System in Candidate Phyla Radiation Bacteria

Luca Troman, Junhyeong Kim, Jayson J. A. Rose, Matthew Johnson, Jillian F. Banfield, Steve Petrovski, Debnath Ghosal·bioRxiv·2026

Pseudoalteromonas is a symbiont of marine invertebrates that exhibits broad patterns of phylosymbiosis

Alejandro De Santiago, Shelby Barnes, Tiago José Pereira, Mirayana Marcellino Barros, Lekeah Durden, Min Khant Han, J Cameron Thrash, Holly M Bik·The ISME Journal·2026

Balancing of immune activation and suppression during phage infection

Iana Fedorova, Yourun Yue, Zirui Gao, Michelle Grunberg, Hao Wang, Junjie Li, Zhiyu Zang, Diego De Nault, Xilin Yang, Joseph P. Gerdt, Yue Feng, Joseph Bondy-Denomy·bioRxiv·2026

Mining Microbial Transcriptomes to Engineer Cell-Based Bacterial Biosensors in Gut-Resident Bacteroidaceae

Joshua Glazier, David Villegas, Sandra McClure, Joyce Ghali, Jay Fuerte-Stone, Mark Mimee·bioRxiv·2026

Join the Community

Become a Seqer and help build the future of biological sequence discovery!

Join Discord