ProS-GNN: Predicting effects of mutations on protein stability using graph neural networks

EFG-CS: Predicting chemical shifts from amino acid sequences with protein structure prediction using machine learning and deep learning models

Nuclear magnetic resonance (NMR) crystallography is one of the main methods in structural biology for analyzing protein stereochemistry and structure. The chemical shift of the resonance frequency reflects the effect of the protons in a molecule producing distinct NMR signals in different chemical environments. Apprehending chemical shifts from NMR signals can be challenging since having an NMR structure does not necessarily provide all the required chemical shift information, making predictive models essential for accurately deducing chemical shifts, either from protein structures or, more ideally, directly from amino acid sequences. Here, we present EFG-CS, a web server that specializes in chemical shift prediction. EFG-CS employs a machine learning-based transfer prediction model for backbone atom chemical shift prediction, using ESMFold-predicted protein structures. Additionally, ESG-CS incorporates a graph neural network-based model to provide comprehensive side-chain atom chemical shift predictions. Our method demonstrated reliable performance in backbone atom prediction, achieving comparable accuracy levels with root mean square errors (RMSE) of 0.30 ppm for H, 0.22 ppm for Hα, 0.89 ppm for C, 0.89 ppm for Cα, 0.84 ppm for Cβ, and 1.69 ppm for N. Moreover, our approach also showed predictive capabilities in side-chain atom chemical shift prediction achieving RMSE values of 0.71 ppm for Hβ, 0.74-1.15 ppm for Hδ, and 0.58-0.94 ppm for Hγ, solely utilizing amino acid sequences without homology or feature curation. This work shows for the first time that generative AI protein models can predict NMR shifts nearly comparable to experimental models. This web server is freely available at https://biosig.lab.uq.edu.au/efg_cs, and the chemical shift prediction results can be downloaded in tabular format and visualized in 3D format.

Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations

Engineering stabilized proteins is a fundamental challenge in the development of industrial and pharmaceutical biotechnologies. We present Stability Oracle: a structure-based graph-transformer framework that achieves SOTA performance on accurately identifying thermodynamically stabilizing mutations. Our framework introduces several innovations to overcome well-known challenges in data scarcity and bias, generalization, and computation time, such as: Thermodynamic Permutations for data augmentation, structural amino acid embeddings to model a mutation with a single structure, a protein structure-specific attention-bias mechanism that makes transformers a viable alternative to graph neural networks. We provide training/test splits that mitigate data leakage and ensure proper model evaluation. Furthermore, to examine our data engineering contributions, we fine-tune ESM2 representations (Prostata-IFML) and achieve SOTA for sequence-based models. Notably, Stability Oracle outperforms Prostata-IFML even though it was pretrained on 2000X less proteins and has 548X less parameters. Our framework establishes a path for fine-tuning structure-based transformers to virtually any phenotype, a necessary task for accelerating the development of protein-based biotechnologies.

Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset

Protein stability plays a crucial role in a variety of applications, such as food processing, therapeutics, and the identification of pathogenic mutations. Engineering campaigns commonly seek to improve protein stability, and there is a strong interest in streamlining these processes to enable rapid optimization of highly stabilized proteins with fewer iterations. In this work, we explore utilizing a mega-scale dataset to develop a protein language model optimized for stability prediction. ESMtherm is trained on the folding stability of 528k natural and de novo sequences derived from 461 protein domains and can accommodate deletions, insertions, and multiple-point mutations. We show that a protein language model can be fine-tuned to predict folding stability. ESMtherm performs reasonably on small protein domains and generalizes to sequences distal from the training set. Lastly, we discuss our model's limitations compared to other state-of-the-art methods in generalizing to larger protein scaffolds. Our results highlight the need for large-scale stability measurements on a diverse dataset that mirrors the distribution of sequence lengths commonly observed in nature.

Mining channel-regulated peptides from animal venom by integrating sequence semantics and structural information

Channel-regulated peptides (CRPs) derived from animal venom hold great promise as potential drug candidates for numerous diseases associated with channel proteins. However, discovering and identifying CRPs using traditional bio-experimental methods is a time-consuming and laborious process. While there were a few computational studies on CRPs, they were limited to specific channel proteins, relied heavily on complex feature engineering, and lacked the incorporation of multi-source information. To address these problems, we proposed a novel deep learning model, called DeepCRPs, based on graph neural networks for systematically mining CRPs from animal venom. By combining the sequence semantic and structural information, the classification performance of four CRPs was significantly enhanced, reaching an accuracy of 0.92. This performance surpassed baseline models with accuracies ranging from 0.77 to 0.89. Furthermore, we employed advanced interpretable techniques to explore sequence and structural determinants relevant to the classification of CRPs, yielding potentially valuable bio-function interpretations. Comprehensive experimental results demonstrated the precision and interpretive capability of DeepCRPs, making it an accurate and bio-explainable suit for the identification and categorization of CRPs. Our research will contribute to the discovery and development of toxin peptides targeting channel proteins. The source data and code are freely available at https://github.com/liyigerry/DeepCRPs.

Empirical validation of ProteinMPNN's efficiency in enhancing protein fitness

Introduction: Protein engineering, which aims to improve the properties and functions of proteins, holds great research significance and application value. However, current models that predict the effects of amino acid substitutions often perform poorly when evaluated for precision. Recent research has shown that ProteinMPNN, a large-scale pre-training sequence design model based on protein structure, performs exceptionally well. It is capable of designing mutants with structures similar to the original protein. When applied to the field of protein engineering, the diverse designs for mutation positions generated by this model can be viewed as a more precise mutation range. Methods: We collected three biological experimental datasets and compared the design results of ProteinMPNN for wild-type proteins with the experimental datasets to verify the ability of ProteinMPNN in improving protein fitness. Results: The validation on biological experimental datasets shows that ProteinMPNN has the ability to design mutation types with higher fitness in single and multi-point mutations. We have verified the high accuracy of ProteinMPNN in protein engineering tasks from both positive and negative perspectives. Discussion: Our research indicates that using large-scale pre trained models to design protein mutants provides a new approach for protein engineering, providing strong support for guiding biological experiments and applications in biotechnology.

Graph Neural Network Model for Prediction of Non-Small Cell Lung Cancer Lymph Node Metastasis Using Protein-Protein Interaction Network and 18F-FDG PET/CT Radiomics

The image texture features obtained from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) images of non-small cell lung cancer (NSCLC) have revealed tumor heterogeneity. A combination of genomic data and radiomics may improve the prediction of tumor prognosis. This study aimed to predict NSCLC metastasis using a graph neural network (GNN) obtained by combining a protein-protein interaction (PPI) network based on gene expression data and image texture features. 18F-FDG PET/CT images and RNA sequencing data of 93 patients with NSCLC were acquired from The Cancer Imaging Archive. Image texture features were extracted from 18F-FDG PET/CT images and area under the curve receiver operating characteristic curve (AUC) of each image feature was calculated. Weighted gene co-expression network analysis (WGCNA) was used to construct gene modules, followed by functional enrichment analysis and identification of differentially expressed genes. The PPI of each gene module and genes belonging to metastasis-related processes were converted via a graph attention network. Images and genomic features were concatenated. The GNN model using PPI modules from WGCNA and metastasis-related functions combined with image texture features was evaluated quantitatively. Fifty-five image texture features were extracted from 18F-FDG PET/CT, and radiomic features were selected based on AUC (n = 10). Eighty-six gene modules were clustered by WGCNA. Genes (n = 19) enriched in the metastasis-related pathways were filtered using DEG analysis. The accuracy of the PPI network, derived from WGCNA modules and metastasis-related genes, improved from 0.4795 to 0.5830 (p < 2.75 × 10-12). Integrating PPI of four metastasis-related genes with 18F-FDG PET/CT image features in a GNN model elevated its accuracy over a without image feature model to 0.8545 (95% CI = 0.8401-0.8689, p-value < 0.02). This model demonstrated significant enhancement compared to the model using PPI and 18F-FDG PET/CT derived from WGCNA (p-value < 0.02), underscoring the critical role of metastasis-related genes in prediction model. The enhanced predictive capability of the lymph node metastasis prediction GNN model for NSCLC, achieved through the integration of comprehensive image features with genomic data, demonstrates promise for clinical implementation.

PROSTATA: a framework for protein stability assessment using transformers

MOTIVATION

Accurate prediction of change in protein stability due to point mutations is an attractive goal that remains unachieved. Despite the high interest in this area, little consideration has been given to the transformer architecture, which is dominant in many fields of machine learning.

RESULTS

In this work, we introduce PROSTATA, a predictive model built in a knowledge-transfer fashion on a new curated dataset. PROSTATA demonstrates advantage over existing solutions based on neural networks. We show that the large improvement margin is due to both the architecture of the model and the quality of the new training dataset. This work opens up opportunities to develop new lightweight and accurate models for protein stability assessment.

AVAILABILITY AND IMPLEMENTATION

PROSTATA is available at https://github.com/AIRI-Institute/PROSTATA and https://prostata.airi.net.