VoroMQA: Assessment of protein structure quality using interatomic contact areas

By Kliment Olechnovic, Č. Venclovas. 2017

178 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO) (2019, methodology): “” 32 All these methods clearly out-perform the “ Baseline Potential ” based on a full-atomic statistical potential of mean force as has been reported earlier 4 (Table 2).”
IntFOLD: an integrated web resource for high performance protein structure and function prediction (2019, positive): “Each IntFOLD5 model was considered individually using 6 pure-single model methods (CDA (20), SSA (20), ProQ2 (4), ProQ2D (39), ProQ3D (39) and VoroMQA (40)), and four alternative quasi-single model methods (DBA (20), MF5s (20), MFcQs (20) and ResQ (41)).”
Learning from Protein Structure with Geometric Vector Perceptrons (2020, methodology): “…the CNN methods 3DCNN (Derevyanko et al., 2018) and Ornate (Pag`es et al., 2019), the GNN method GraphQA (Baldas-sarre et al., 2020), and three methods that use sequential representations—VoroMQA (Olechnoviˇc & Venclovas, 2017), SBROD (Karasikov et al., 2019), and ProQ3D (Uziela et al., 2017).”
Estimation of model accuracy in CASP13 (2019, methodology): “Each model was considered individually using six previously described pure-single model methods: CDA, 56 SSA, 56 ProQ2, 57 ProQ2D, 52 ProQ3D 52 and VoroMQA.”
Deep convolutional networks for quality assessment of protein folds (2018, methodology): “This database provides a 5-tiered classiﬁcation of all structures in the PDB according to the following criteria: architecture (A-group), possible homology (X-group), homology (H-group), topology (T-group), and family (F-group).”
Protein model quality assessment using 3D oriented convolutional neural networks (2018, methodology): “Among the single model methods, one can distinguish simple methods such as VoroMQA (5) or RWplus (6), which rely on a single type of structural features (contact area or pairwise atomic distances, respectively).”
Protein Docking Model Evaluation by Graph Neural Networks (2020, unknown): “To assess the quality of structure models, considering multi-body (atom or residue) interactions (55-58) have been proven to be an effective approach.”
ProteinGCN: Protein model quality assessment using Graph Convolutional Networks (2020, background): “• VoroMQA [23]: It estimates protein quality by contsructing a Voronoi tesselation for the set of atoms in the protein model and then uses the derived inter-atomic contact areas to produce scores at atomic, residue and global levels.”
GraphQA: protein model quality assessment using graph convolutional networks (2020, methodology): “VoroMQA and RWplus (Olechnovi ˇ c & Venclovas, 2017; Zhang & Zhang, 2010) are two statistical potential methods that represent an alternative to the other machine-learning based methods.”