使用模式匹配策略进行快速和可解释的蛋白质接触地图预测
Aysima Hacisuleyman1, Dirk Fasshauer1
1Department of Computational Biology, University of Lausanne, Quartier Centre, Lausanne, 1015, Switzerland.
Physical biology
|February 10, 2026
概括
一种新的基于模板的模式匹配方法可以有效地预测蛋白质接触地图. 这种方法需要比深度学习或共同进化的方法更少的计算资源,为蛋白质结构预测提供了有价值的替代方案.
科学领域:
- 结构生物学 结构生物学
- 计算生物学 计算生物学
- 生物信息学是一种生物信息学.
背景情况:
- 测序蛋白质和实验确定结构之间的差距正在扩大.
- 目前的方法,如AlphaFold2和同进化分析 (MI,DCA) 有局限性,包括高计算成本和依赖广泛的序列数据.
研究的目的:
- 开发一种计算效率高,可解释的方法来预测蛋白质接触地图.
- 为现有方法提供替代方案,特别是对于具有有限序列同类的蛋白质或需要快速预测的蛋白质.
主要方法:
- 一种基于模板的模式匹配方法,从同类结构中识别保存的结构图案.
- 将残余的空间安排编码为序列模式,并将其与查询序列对齐.
- 使用少量结构模板 (50-500) 和没有GPU的标准硬件.
主要成果:
- 在25个蛋白质域上与实验接触图取得了高相关性 (0.735-0.942).
- 证明了比MI和GREMLIN具有可比准确性的更好的接触覆盖范围.
- 在 7,599 个注释差的序列中,获得了平均 F1 评分为 0.609 ± 0.095 和准确度为 0.954 ± 0.036.
结论:
- 模式匹配方法是基于深度学习和共进化的方法的计算效率高,可解释的替代方案.
- 这种方法对于具有有限序列同类的蛋白质或当快速预测至关重要时特别有价值.
- 该方法成功地预测了蛋白质接触地图,使用保存的结构图案和适度的计算资源.
相关概念视频
Microtubule Associated Proteins (MAPs)
6.0K
Microtubule function and architecture are regulated by an array of specialized proteins called microtubule-associated proteins or MAPs. These proteins are widespread across different organisms and have conserved protein motifs, like the multi-TOG domain for tubulin binding found in the CLASP family of MAPs. Some MAPs are lineage-specific based on their conserved domains. Their functions depend upon the cytoskeletal architecture and cell type they are located within. In-plant cells, a specific...
6.0K
Sign Test for Matched Pairs
425
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
To conduct the sign test, we first calculate the differences in...
425
Contact-dependent Signaling
47.6K
Contact-dependent signaling, as the name suggests, requires that communicating cells be in direct contact with each other. This is achieved either through receptor-ligand interactions or by specialized cytoplasmic channels that allow the flow of small molecules between cells. In animal cells, channels called gap junctions facilitate contact-dependent signaling in certain tissues, whereas, plasmodesmata perform a similar function in plants.
Gap Junctions
In animal cells, gap junctions are formed...
Gap Junctions
In animal cells, gap junctions are formed...
47.6K
Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
Contact Angle
23.7K
When a solid is dipped inside a liquid, the liquid surface becomes curved near the contact. For some solid–liquid interfaces, the liquid is pulled up along the solid, while for others, the liquid surface is convex or depressed near the solid surface. This phenomenon can be explained using the concept of cohesive and adhesive forces.
The adhesive force is the molecular force between molecules of different materials, that is, between the molecules of the solid and the liquid. The cohesive...
The adhesive force is the molecular force between molecules of different materials, that is, between the molecules of the solid and the liquid. The cohesive...
23.7K
Predicting Molecular Geometry
46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K


