DIPS-Plus: The enhanced database of interacting protein structures for interface prediction (2021-06-06T00:00:00.000000Z)

TL;DR

It is demonstrated 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.

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.

Authors

Alex Morehead

3 papers

Chen Chen

1 papers

A. Sedova

1 papers

TL;DR

Abstract

Authors

References76 items

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

Protein complex prediction with AlphaFold-Multimer

flDPnn: Accurate intrinsic disorder prediction with putative propensities of disorder functions

Highly accurate protein structure prediction with AlphaFold

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

Protein interaction interface region prediction by geometric deep learning

MSA Transformer

ATOM3D: Tasks On Molecules in Three Dimensions

Installation and Setup

Deep Learning of High-Order Interactions for Protein Interface Prediction

Array programming with NumPy

Introduction to Anaconda and Python: Installation and setup

Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning

PyTorch: An Imperative Style, High-Performance Deep Learning Library

DeepSVM-fold: protein fold recognition by combining support vector machines and pairwise sequence similarity scores generated by deep learning networks

Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks.

DNSS2: improved ab initio protein secondary structure prediction using advanced deep learning architectures

Machine Learning With Python

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

Correlations between secondary structure- and protein-protein interface-mimicry: the interface mimicry hypothesis.

HH-suite3 for fast remote homology detection and deep protein annotation

Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold

BIPSPI: a method for the prediction of partner-specific protein–protein interfaces

End-to-End Learning on 3D Protein Structure for Interface Prediction

Worldwide Protein Data Bank validation information: usage and trends

Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets.

Protein Interface Prediction using Graph Convolutional Networks

Network analysis and in silico prediction of protein-protein interactions with applications in drug discovery.

Quantum-chemical insights from deep tensor neural networks

Mastering the game of Go with deep neural networks and tree search

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Updates to the Integrated Protein-Protein Interaction Benchmarks: Docking Benchmark Version 5 and Affinity Benchmark Version 2.

PDB-wide collection of binding data: current status of the PDBbind database

A series of PDB-related databanks for everyday needs

PAIRpred: Partner‐specific prediction of interacting residues from sequence and structure

Protein-ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment

Building a Framework for Predictive Science

Partner-Aware Prediction of Interacting Residues in Protein-Protein Complexes from Sequence Data

HMMER web server: interactive sequence similarity searching

Scikit-learn: Machine Learning in Python

The RCSB Protein Data Bank: redesigned web site and web services

Sequence-based identification of interface residues by an integrative profile combining hydrophobic and evolutionary information

Modeling the temporal interplay of molecular signaling and gene expression by using dynamic nested effects models

Biopython: freely available Python tools for computational molecular biology and bioinformatics

Prediction of Protein–Protein Interaction Sites in Sequences and 3D Structures by Random Forests

PSAIA – Protein Structure and Interaction Analyzer

Reaching for high-hanging fruit in drug discovery at protein–protein interfaces

Flexible protein-protein docking.

An amino acid has two sides: A new 2D measure provides a different view of solvent exposure

Using Bayesian Networks to Analyze Expression Data

Main-chain conformational features at different conformations of the side-chains in proteins.

Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids

Reduced surface: an efficient way to compute molecular surfaces.

Conservation and prediction of solvent accessibility in protein families

Hidden Markov models in computational biology. Applications to protein modeling.

DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Prediction (Supplementary Data), Zenodo

Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Biomolecular Structures and Interaction Networks

Foldseek: fast and accurate protein structure search

s41597-023-02409-3 hypothesis

The quality and validation of structures from structural genomics.

Supplementary information Predicting protein-protein interface residues using local surface structural similarity

pandas: a Foundational Python Library for Data Analysis and Statistics

Characterization of Protein–Protein Interfaces

Python Programming Language

Biological Sequence Analysis Probabilistic Models Of Proteins And Nucleic Acids

Pymol: An open-source molecular graphics tool. CCP4 Newsl

Others may do so and should contact the original authors about incorporating fixes/extensions

to correct labeling errors, add new instances, delete instances)? If so, please describe how often

were individuals in question told that their data would be retained for a fixed period of time and then deleted)? If so, please describe these limits and explain how they will be enforced

If and when the dataset is updated after its initial release, we will keep older versions of it around for consistency

Did you describe any potential participant risks, with links to Institutional Review Board (IRB) approvals, if applicable?

Since DIPS-Plus was released on

Jianlin Cheng's email address is chengji@missouri.edu. Is there an erratum? If so, please provide a link or other access point

The pandas development team. pandas-dev/pandas: Pandas. Version latest

The PyMOL Molecular Graphics System, Version 1.8"