Foldseek: fast and accurate protein structure search
By Michel van Kempen, Stephanie S. Kim, Charlotte Tumescheit, Milot Mirdita, J. Soeding, Martin Steinegger. 2022
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Erik Nijkamp
- Yoshua Bengio
- Regina Barzilay
- Tommi S. Jaakkola
- Ruslan Salakhutdinov
- Sergey Levine
- Percy Liang
- Mohit Bansal
Citations in the corpus
- Learning inverse folding from millions of predicted structures (2022, methodology): “To achieve that a rigorous structural hold-out, we additionally use foldseek (van Kempen et al., 2022) for pairwise TMalign between the test set the train set.”
- Protein Representation Learning by Geometric Structure Pretraining (2022, methodology): “Results are evaluated with the scripts and predictions provided in (van Kempen et al., 2022).”
- SaProt: Protein Language Modeling with Structure-aware Vocabulary (2024, background): “The initial goal of Foldseek (van Kempen et al., 2022) is to facilitate fast and accurate protein structure searches.”
- SE(3) diffusion model with application to protein backbone generation (2023, methodology): “We use FoldSeek (van Kempen et al., 2022) to search for similar structures and report the highest TM-scores of samples to any chain in PDB, which we refer to as pdbTM.”
- The prospects and opportunities of protein structure prediction with AI (2022, background): “Prediction databases can also be searched with structure-aware algorithms, potentially leading to more sensitive protein classification 5 .”
- ProGen2: Exploring the Boundaries of Protein Language Models (2022, methodology): “Similarity of predicted structures to observed proteins in the PDB was measured by calculating the TMscore (Zhang & Skolnick, 2004) using Foldseek (van Kempen et al., 2022).”
- DALI shines a light on remote homologs: One hundred discoveries (2022, background): “…by the sudden availability of a plethora of structural models, tools for fast and efficient structural comparison are more needed than ever (Aderinwale et al., 2022; Bordin et al., 2022; van Kempen et al., 2002), and in this context, the DALI algorithm is one of the most sensitive (Holm, 2019).”