Unknown

Dataset Information

0

Transferability of Geometric Patterns from Protein Self-Interactions to Protein-Ligand Interactions.


ABSTRACT: There is significant interest in developing machine learning methods to model protein-ligand interactions but a scarcity of experimentally resolved protein-ligand structures to learn from. Protein self-contacts are a much larger source of structural data that could be leveraged, but currently it is not well understood how this data source differs from the target domain. Here, we characterize the 3D geometric patterns of protein self-contacts as probability distributions. We then present a flexible statistical framework to assess the transferability of these patterns to protein-ligand contacts. We observe that the level of transferability from protein self-contacts to protein-ligand contacts depends on contact type, with many contact types exhibiting high transferability. We then demonstrate the potential of leveraging information from these geometric patterns to aid in ligand pose-selection problems in protein-ligand docking. We publicly release our extracted data on geometric interaction patterns to enable further exploration of this problem.

SUBMITTER: Koehl A 

PROVIDER: S-EPMC8669734 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

altmetric image

Publications

Transferability of Geometric Patterns from Protein Self-Interactions to Protein-Ligand Interactions.

Koehl Antoine A   Jagota Milind M   Erdmann-Pham Dan D DD   Fung Alexander A   Song Yun S YS  

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing 20220101


There is significant interest in developing machine learning methods to model protein-ligand interactions but a scarcity of experimentally resolved protein-ligand structures to learn from. Protein self-contacts are a much larger source of structural data that could be leveraged, but currently it is not well understood how this data source differs from the target domain. Here, we characterize the 3D geometric patterns of protein self-contacts as probability distributions. We then present a flexib  ...[more]

Similar Datasets

| S-EPMC2637420 | biostudies-literature
| S-EPMC6525250 | biostudies-literature
| S-EPMC4434174 | biostudies-literature
| S-EPMC10997877 | biostudies-literature
| S-EPMC3365113 | biostudies-literature
| S-EPMC4071618 | biostudies-literature
| S-EPMC10835705 | biostudies-literature
| S-EPMC8515190 | biostudies-literature
| S-EPMC2442010 | biostudies-literature
| S-EPMC4154455 | biostudies-literature