[
Back to Home]
LOMETS (Local Meta-Threading Server, version 3) is a next-generation meta-server approach
to template-based protein structure prediction and structure-based function annotation.
The new program integrates multiple deep learning-based threading methods
(CEthreader, DisCovER, EigenThreader, Hybrid-CEthreader, MapAlign)
and state-of-the-art profile-based programs (FFAS3D, HHpred, HHsearch, MRFsearch, MUSTER, SparksX).
For the first time, LOMETS3 is extended to handling multi-domain proteins by introducing the
domain partition (FUpred and ThreaDom) and
assembly (DEMO) modules.
It also introduces a new module for fast full-length model construction using a gradient-based optimization
program (DeepFold), which is guided by restraints from
deep-learning (DeepPotential) and LOMETS top templates.
Protein functions in LOMETS3 are predicted by the modified COFACTOR method,
which adds the LOMETS3 threading templates associated with structure analogs as templates
in COFACTOR structure-based pipelines.
Large-scaled benchmark tests showed that the overall template-recognition and full-length
model construction accuracy is significantly beyond its predecessors (LOMETS and LOMETS2),
due to the integration of deep-learning and multi-domain threading techniques.
LOMETS3 participated in
CASP14
as 'Zhang-TBM' and was ranked as one of the top methods for automatic protein structure prediction.
A detailed description of the LOMETS3 server can be seen on
the About LOMETS page.
The output model of LOMETS server is given by both PDB format and ModelCIF format
now.
Please contact Wei Zheng for any problems or questions.
The output of the LOMETS server includes (Example output):
- Secondary structure prediction.
- Solvent accessibility prediction.
- Contact-map and distance-map prediction by DeepPotential.
- Domain partition results shown in contact-map (optional).
- Individual domain threading/modeling results by LOMETS (optional).
- The best ten assembled templates from individual domain threading templates (optional).
- The best ten initial threading templates selected from 110 (=11x10) templates.
- Full-length models built by an L-BFGS system (DeepFold) using distance restraints from DeepPotential and LOMETS templates.
- The best ten similar structure identified by TM-align using the first LOMETS model, and the associated functional annotations.
- Functional annotations (Gene Ontology term, Enzyme Commission number, and Ligand Binding residues) derived from top-ranking threading templates.
- Function predictions by a modified COFACTOR method using LOMETS3 threading templates and structure analogs in COFACTOR structure-based pipelines.
[Example output]
[About LOMETS]
[Check Previous Jobs]
[Benchmark datasets]
LOMETS Resource:
References:
-
Wei Zheng, Qiqige Wuyun, Xiaogen Zhou, Yang Li, Peter Freddolino, Yang Zhang.
LOMETS3: Integrating deep-learning and profile-alignment for advanced protein template recognition and function annotation.
Nucleic Acids Research, 50: W454-W464 (2022)
[PDF of manuscript].
-
Wei Zheng, Chengxin Zhang, Qiqige Wuyun, Robin Pearce, Yang Li, Yang Zhang.
LOMETS2: improved meta-threading server for fold-recognition and structure-based
function annotation for distant-homology proteins.
Nucleic Acids Research, 47: W429-W436 (2019)
[PDF of manuscript]
[PDF of Support Information].
- Sitao Wu, Yang Zhang.
LOMETS: A local meta-threading-server for protein structure prediction.
Nucleic Acids Research, 35: 3375-3382 (2007)
[PDF of manuscript].
