DIPS-Plus: The enhanced database of interacting protein structures for interface prediction

Alex Morehead; Chen Chen; Ada Sedova; Jianlin Cheng

doi:10.1038/s41597-023-02409-3

DIPS-Plus: The enhanced database of interacting protein structures for interface prediction

Alex Morehead, Chen Chen, Ada Sedova, Jianlin Cheng

Molecular Biophysics

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

In this work, we expand on a dataset recently introduced for protein interface prediction (PIP), the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42,112 complexes for machine learning of protein interfaces. While the original DIPS dataset contains only the Cartesian coordinates for atoms contained in the protein complex along with their types, DIPS-Plus contains multiple residue-level features including surface proximities, half-sphere amino acid compositions, and new profile hidden Markov model (HMM)-based sequence features for each amino acid, providing researchers a curated feature bank for training protein interface prediction methods. We demonstrate through rigorous benchmarks that training an existing state-of-the-art (SOTA) model for PIP on DIPS-Plus yields new SOTA results, surpassing the performance of some of the latest models trained on residue-level and atom-level encodings of protein complexes to date.

Original language	English
Article number	509
Journal	Scientific Data
Volume	10
Issue number	1
DOIs	https://doi.org/10.1038/s41597-023-02409-3
State	Published - Dec 2023

Funding

This project is partially supported by three NSF grants (DBI 2308699, DBI 1759934, and IIS 1763246), one NIH grant (GM093123), three DOE grants (DE-SC0020400, DE-AR0001213, and DE-SC0021303), and the computing allocation on the Andes compute cluster provided by Oak Ridge Leadership Computing Facility (Project ID: BIF132). In particular, this research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.

Funders	Funder number
Oak Ridge National Laboratory	BIF132
National Science Foundation	DBI 1759934, DBI 2308699, IIS 1763246
National Institutes of Health	GM093123
U.S. Department of Energy	DE-AC05-00OR22725, DE-AR0001213, DE-SC0020400, DE-SC0021303
Office of Science

Access to Document

10.1038/s41597-023-02409-3

Cite this

@article{abc1efc573ac4722a583df34d581e62c,

title = "DIPS-Plus: The enhanced database of interacting protein structures for interface prediction",

abstract = "In this work, we expand on a dataset recently introduced for protein interface prediction (PIP), the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42,112 complexes for machine learning of protein interfaces. While the original DIPS dataset contains only the Cartesian coordinates for atoms contained in the protein complex along with their types, DIPS-Plus contains multiple residue-level features including surface proximities, half-sphere amino acid compositions, and new profile hidden Markov model (HMM)-based sequence features for each amino acid, providing researchers a curated feature bank for training protein interface prediction methods. We demonstrate through rigorous benchmarks that training an existing state-of-the-art (SOTA) model for PIP on DIPS-Plus yields new SOTA results, surpassing the performance of some of the latest models trained on residue-level and atom-level encodings of protein complexes to date.",

author = "Alex Morehead and Chen Chen and Ada Sedova and Jianlin Cheng",

note = "Publisher Copyright: {\textcopyright} 2023, Springer Nature Limited.",

year = "2023",

month = dec,

doi = "10.1038/s41597-023-02409-3",

language = "English",

volume = "10",

journal = "Scientific Data",

issn = "2052-4463",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - DIPS-Plus

T2 - The enhanced database of interacting protein structures for interface prediction

AU - Morehead, Alex

AU - Chen, Chen

AU - Sedova, Ada

AU - Cheng, Jianlin

PY - 2023/12

Y1 - 2023/12

N2 - In this work, we expand on a dataset recently introduced for protein interface prediction (PIP), the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42,112 complexes for machine learning of protein interfaces. While the original DIPS dataset contains only the Cartesian coordinates for atoms contained in the protein complex along with their types, DIPS-Plus contains multiple residue-level features including surface proximities, half-sphere amino acid compositions, and new profile hidden Markov model (HMM)-based sequence features for each amino acid, providing researchers a curated feature bank for training protein interface prediction methods. We demonstrate through rigorous benchmarks that training an existing state-of-the-art (SOTA) model for PIP on DIPS-Plus yields new SOTA results, surpassing the performance of some of the latest models trained on residue-level and atom-level encodings of protein complexes to date.

AB - In this work, we expand on a dataset recently introduced for protein interface prediction (PIP), the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42,112 complexes for machine learning of protein interfaces. While the original DIPS dataset contains only the Cartesian coordinates for atoms contained in the protein complex along with their types, DIPS-Plus contains multiple residue-level features including surface proximities, half-sphere amino acid compositions, and new profile hidden Markov model (HMM)-based sequence features for each amino acid, providing researchers a curated feature bank for training protein interface prediction methods. We demonstrate through rigorous benchmarks that training an existing state-of-the-art (SOTA) model for PIP on DIPS-Plus yields new SOTA results, surpassing the performance of some of the latest models trained on residue-level and atom-level encodings of protein complexes to date.

UR - http://www.scopus.com/inward/record.url?scp=85166591254&partnerID=8YFLogxK

U2 - 10.1038/s41597-023-02409-3

DO - 10.1038/s41597-023-02409-3

M3 - Article

C2 - 37537186

AN - SCOPUS:85166591254

SN - 2052-4463

VL - 10

JO - Scientific Data

JF - Scientific Data

IS - 1

M1 - 509

ER -

DIPS-Plus: The enhanced database of interacting protein structures for interface prediction

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this