SHREC 2025: Protein surface shape retrieval including electrostatic potential
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911157677195264 |
|---|---|
| author | Yacoub, Taher Depenveiller, Camille Tatsuma, Atsushi Barisin, Tin Rusakov, Eugen Gobel, Udo Peng, Yuxu Deng, Shiqiang Kagaya, Yuki Park, Joon Hong Kihara, Daisuke Guerra, Marco Palmieri, Giorgio Ranieri, Andrea Fugacci, Ulderico Biasotti, Silvia He, Ruiwen Benhabiles, Halim Cabani, Adnane Hammoudi, Karim Li, Haotian Huang, Hao Li, Chunyan Tehrani, Alireza Meng, Fanwang Heidar-Zadeh, Farnaz Yang, Tuan-Anh Montes, Matthieu |
| author_facet | Yacoub, Taher Depenveiller, Camille Tatsuma, Atsushi Barisin, Tin Rusakov, Eugen Gobel, Udo Peng, Yuxu Deng, Shiqiang Kagaya, Yuki Park, Joon Hong Kihara, Daisuke Guerra, Marco Palmieri, Giorgio Ranieri, Andrea Fugacci, Ulderico Biasotti, Silvia He, Ruiwen Benhabiles, Halim Cabani, Adnane Hammoudi, Karim Li, Haotian Huang, Hao Li, Chunyan Tehrani, Alireza Meng, Fanwang Heidar-Zadeh, Farnaz Yang, Tuan-Anh Montes, Matthieu |
| contents | This SHREC 2025 track dedicated to protein surface shape retrieval involved 9 participating teams. We evaluated the performance in retrieval of 15 proposed methods on a large dataset of 11,555 protein surfaces with calculated electrostatic potential (a key molecular surface descriptor). The performance in retrieval of the proposed methods was evaluated through different metrics (Accuracy, Balanced accuracy, F1 score, Precision and Recall). The best retrieval performance was achieved by the proposed methods that used the electrostatic potential complementary to molecular surface shape. This observation was also valid for classes with limited data which highlights the importance of taking into account additional molecular surface descriptors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SHREC 2025: Protein surface shape retrieval including electrostatic potential Yacoub, Taher Depenveiller, Camille Tatsuma, Atsushi Barisin, Tin Rusakov, Eugen Gobel, Udo Peng, Yuxu Deng, Shiqiang Kagaya, Yuki Park, Joon Hong Kihara, Daisuke Guerra, Marco Palmieri, Giorgio Ranieri, Andrea Fugacci, Ulderico Biasotti, Silvia He, Ruiwen Benhabiles, Halim Cabani, Adnane Hammoudi, Karim Li, Haotian Huang, Hao Li, Chunyan Tehrani, Alireza Meng, Fanwang Heidar-Zadeh, Farnaz Yang, Tuan-Anh Montes, Matthieu Computer Vision and Pattern Recognition Biomolecules I.3.8; I.5.4; J.3 This SHREC 2025 track dedicated to protein surface shape retrieval involved 9 participating teams. We evaluated the performance in retrieval of 15 proposed methods on a large dataset of 11,555 protein surfaces with calculated electrostatic potential (a key molecular surface descriptor). The performance in retrieval of the proposed methods was evaluated through different metrics (Accuracy, Balanced accuracy, F1 score, Precision and Recall). The best retrieval performance was achieved by the proposed methods that used the electrostatic potential complementary to molecular surface shape. This observation was also valid for classes with limited data which highlights the importance of taking into account additional molecular surface descriptors. |
| title | SHREC 2025: Protein surface shape retrieval including electrostatic potential |
| topic | Computer Vision and Pattern Recognition Biomolecules I.3.8; I.5.4; J.3 |
| url | https://arxiv.org/abs/2509.12976 |