Predicting the effects of mutations on the kinetic rate constants of protein-protein interactions is central to both the modeling of complex diseases and the design of effective peptide drug inhibitors. However, while most studies have concentrated on the determination of association rate constants, dissociation rates have received less attention. In this work we take a novel approach by relating the changes in dissociation rates upon mutation to the energetics and architecture of hotspots and hotregions, by performing alanine scans pre- and post-mutation. From these scans, we design a set of descriptors that capture the change in hotspot energy and distribution. The method is benchmarked on 713 kinetically characterized mutations from the SKEMPI database. Our investigations show that, with the use of hotspot descriptors, energies from single-point alanine mutations may be used for the estimation of off-rate mutations to any residue type and also multi-point mutations. A number of machine learning models are built from a combination of molecular and hotspot descriptors, with the best models achieving a Pearson's Correlation Coefficient of 0.79 with experimental off-rates and a Matthew's Correlation Coefficient of 0.6 in the detection of rare stabilizing mutations. Using specialized feature selection models we identify descriptors that are highly specific and, conversely, broadly important to predicting the effects of different classes of mutations, interface regions and complexes. Our results also indicate that the distribution of the critical stability regions across protein-protein interfaces is a function of complex size more strongly than interface area. In addition, mutations at the rim are critical for the stability of small complexes, but consistently harder to characterize. The relationship between hotregion size and the dissociation rate is also investigated and, using hotspot descriptors which model cooperative effects within hotregions, we show how the contribution of hotregions of different sizes, changes under different cooperative effects.

(A) Shows PCC between experimental ΔΔG with the respective Δlog10(koff) and Δlog10(kon) for single-point alanine, single-point non-alanine, multi-point and all 713 mutations. (B) Shows PCC between Int_HS_Energy with the respective ΔΔG, Δlog10(koff) and Δlog10(kon) for single-point alanine, single-point non-alanine, multi-point and all 713 mutations. Experimental values for the 713 mutations used here are extracted from SKEMPI [41] and are presented in Dataset S1.

Mutation Stability Prediction

  Overview

The Mutation Stability Prediction (MSP) task involves classifying whether mutations in the SKEMPI 2.0 database (J. Jankauskaite, B. Jiménez-García et al., 2019) are stabilizing or not using the provided protein structures. Each mutation in the MSP task includes a PDB file with the residue of interest transformed to the specified mutant amino acid as well as the native PDB file. A total of 4148 mutant structures accompanied by their… See the full description on the dataset page: https://huggingface.co/datasets/vector-institute/atom3d-msp.

Protein–protein interactions (PPIs) play a significant role in nearly all cellular and biological activities. Data-driven machine learning models have demonstrated great power in PPIs. However, the design of efficient molecular featurization poses a great challenge for all learning models for PPIs. Here, we propose persistent spectral (PerSpect) based PPI representation and featurization, and PerSpect-based ensemble learning (PerSpect-EL) models for PPI binding affinity prediction, for the first time. In our model, a sequence of Hodge (or combinatorial) Laplacian (HL) matrices at various different scales are generated from a specially designed filtration process. PerSpect attributes, which are statistical and combinatorial properties of spectrum information from these HL matrices, are used as features for PPI characterization. Each PerSpect attribute is input into a 1D convolutional neural network (CNN), and these CNN networks are stacked together in our PerSpect-based ensemble learning models. We systematically test our model on the two most commonly used datasets, i.e. SKEMPI and AB-Bind. It has been found that our model can achieve state-of-the-art results and outperform all existing models to the best of our knowledge.

Pearson's Correlation Coefficient (PCC) of hotspot descriptors with experimental Δlog10(koff) for the 713 off-rate mutations in SKEMPI.

PPIRef is a dataset of 3D structures of protein-protein interfaces. See the GitHub repository for more details.

File description

1. ppi_6A.zip stores the PPIRef dataset: .pdb files with all 6A-distance interfaces from PDB as of Jan 2024.
2. ppi_6A_stats.zip stores the statistics about the ppi_6A dataset. This includes the indexes for fast search with MMseqs2 and iDist, as well as a .csv file with main statistics for all interfaces.
3. ppi_10A.zip: .pdb files with all 10A-distance interfaces from PDB downloaded in June 2024.
4. ppi_10A_stats.zip stores the statistics about the ppi_10A dataset. This includes iDist embeddings, as well as a .csv file with main statistics for all interfaces.
5. pdb_redo_ppi_10A.zip: .pdb files with all 10A-distance interfaces from PDB-REDO downloaded in June 2024.
6. pdb_redo_ppi_10A_stats.zip stores the statistics about the pdb_redo_ppi_10A dataset. This includes iDist embeddings, as well as a .csv file with main statistics for all interfaces.
7. skempi2.zip stores PPI interfaces from the SKEMPI v2.0 dataset

How to use

It is recommended to download and extract the files in the PPIRef/ppiref/data/ppiref directory. This can be done automatically via the ppiref package. For example, to download and extract the ppi_6A.zip archive run:
from ppiref.utils.misc import download_from_zenodo
download_from_zenodo('ppi_6A.zip')

Protein hotspot residues are key sites that mediate protein-protein interactions. Accurate identification of these residues is essential for understanding the mechanism from protein to function and for designing drug targets. Current research has mostly focused on using machine learning methods to predict hot spots from known interface residues, which artificially extract the corresponding features of amino acid residues from sequence, structure, evolution, energy, and other information to train and test machine learning models. The process is cumbersome, time-consuming and laborious to some extent. This paper proposes a novel idea that develops a pre-trained protein sequence embedding model combined with a one-dimensional convolutional neural network, called Embed-1dCNN, to predict protein hotspot residues. In order to obtain large data samples, this work integrates and extracts data from the datasets of ASEdb, BID, SKEMPI and dbMPIKT to generate a new dataset, and adopts the SMOTE algorithm to expand positive samples to form the training set. The experimental results show that the method achieves an F1 score of 0.82 on the test set. Compared with other hot spot prediction methods, our model achieved better prediction performance.

Protein hotspot residues are key sites that mediate protein-protein interactions. Accurate identification of these residues is essential for understanding the mechanism from protein to function and for designing drug targets. Current research has mostly focused on using machine learning methods to predict hot spots from known interface residues, which artificially extract the corresponding features of amino acid residues from sequence, structure, evolution, energy, and other information to train and test machine learning models. The process is cumbersome, time-consuming and laborious to some extent. This paper proposes a novel idea that develops a pre-trained protein sequence embedding model combined with a one-dimensional convolutional neural network, called Embed-1dCNN, to predict protein hotspot residues. In order to obtain large data samples, this work integrates and extracts data from the datasets of ASEdb, BID, SKEMPI and dbMPIKT to generate a new dataset, and adopts the SMOTE algorithm to expand positive samples to form the training set. The experimental results show that the method achieves an F1 score of 0.82 on the test set. Compared with other hot spot prediction methods, our model achieved better prediction performance.

Protein hotspot residues are key sites that mediate protein-protein interactions. Accurate identification of these residues is essential for understanding the mechanism from protein to function and for designing drug targets. Current research has mostly focused on using machine learning methods to predict hot spots from known interface residues, which artificially extract the corresponding features of amino acid residues from sequence, structure, evolution, energy, and other information to train and test machine learning models. The process is cumbersome, time-consuming and laborious to some extent. This paper proposes a novel idea that develops a pre-trained protein sequence embedding model combined with a one-dimensional convolutional neural network, called Embed-1dCNN, to predict protein hotspot residues. In order to obtain large data samples, this work integrates and extracts data from the datasets of ASEdb, BID, SKEMPI and dbMPIKT to generate a new dataset, and adopts the SMOTE algorithm to expand positive samples to form the training set. The experimental results show that the method achieves an F1 score of 0.82 on the test set. Compared with other hot spot prediction methods, our model achieved better prediction performance.