Protein Function Prediction Research Articles

Partial order relation-based gene ontology embedding improves protein function prediction.

Protein annotation has long been a challenging task in computational biology. Gene Ontology (GO) has become one of the most popular frameworks to describe protein functions and their relationships. Prediction of a protein annotation with proper GO terms demands high-quality GO term representation learning, which aims to learn a low-dimensional dense vector representation with accompanying semantic meaning for each functional label, also known as embedding. However, existing GO term embedding methods, which mainly take into account ancestral co-occurrence information, have yet to capture the full topological information in the GO-directed acyclic graph (DAG). In this study, we propose a novel GO term representation learning method, PO2Vec, to utilize the partial order relationships to improve the GO term representations. Extensive evaluations show that PO2Vec achieves better outcomes than existing embedding methods in a variety of downstream biological tasks. Based on PO2Vec, we further developed a new protein function prediction method PO2GO, which demonstrates superior performance measured in multiple metrics and annotation specificity as well as few-shot prediction capability in the benchmarks. These results suggest that the high-quality representation of GO structure is critical for diverse biological tasks including computational protein annotation.

A comprehensive computational benchmark for evaluating deep learning-based protein function prediction approaches.

Proteins play an important role in life activities and are the basic units for performing functions. Accurately annotating functions to proteins is crucial for understanding the intricate mechanisms of life and developing effective treatments for complex diseases. Traditional biological experiments struggle to keep pace with the growing number of known proteins. With the development of high-throughput sequencing technology, a wide variety of biological data provides the possibility to accurately predict protein functions by computational methods. Consequently, many computational methods have been proposed. Due to the diversity of application scenarios, it is necessary to conduct a comprehensive evaluation of these computational methods to determine the suitability of each algorithm for specific cases. In this study, we present a comprehensive benchmark, BeProf, to process data and evaluate representative computational methods. We first collect the latest datasets and analyze the data characteristics. Then, we investigate and summarize 17 state-of-the-art computational methods. Finally, we propose a novel comprehensive evaluation metric, design eight application scenarios and evaluate the performance of existing methods on these scenarios. Based on the evaluation, we provide practical recommendations for different scenarios, enabling users to select the most suitable method for their specific needs. All of these servers can be obtained from https://csuligroup.com/BEPROF and https://github.com/CSUBioGroup/BEPROF.

Clinical and Genomic Predictors of Adverse Events in Newly Diagnosed Glioblastoma.

Adverse clinical events cause significant morbidity in patients with GBM (GBM). We examined whether genomic alterations were associated with AE (AE) in patients with GBM. We identified adults with histologically confirmed IDH-wild-type GBM with targeted next-generation sequencing (OncoPanel) at Dana Farber Cancer Institute from 2013 to 2019. Seizure at presentation, lymphopenia, thromboembolic events, pseudoprogression, and early progression (within 6 months of diagnosis) were identified as AE. The biologic function of genetic variants was categorized as loss-of-function (LoF), no change in function, or gain-of-function (GoF) using a somatic tumor mutation knowledge base (OncoKB) and consensus protein function predictions. Associations between functional genomic alterations and AE were examined using univariate logistic regressions and multivariable regressions adjusted for additional clinical predictors. Our study included 470 patients diagnosed with GBM who met the study criteria. We focused on 105 genes that had sequencing data available for ≥ 90% of the patients and were altered in ≥10% of the cohort. Following false-discovery rate (FDR) correction and multivariable adjustment, the TP53, RB1, IGF1R, and DIS3 LoF alterations were associated with lower odds of seizures, while EGFR, SMARCA4, GNA11, BRD4, and TCF3 GoF and SETD2 LoF alterations were associated with higher odds of seizures. For all other AE of interest, no significant associations were found with genomic alterations following FDR correction. Genomic biomarkers based on functional variant analysis of a routine clinical panel may help identify AE in GBM, particularly seizures. Identifying these risk factors could improve the management of patients through better supportive care and consideration of prophylactic therapies.

Insights into the inner workings of transformer models for protein function prediction.

We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent representations inside of transformer models, which were finetuned to Gene Ontology term and Enzyme Commission number prediction, can be inspected too. The approach enabled us to identify amino acids in the sequences that the transformers pay particular attention to, and to show that these relevant sequence parts reflect expectations from biology and chemistry, both in the embedding layer and inside of the model, where we identified transformer heads with a statistically significant correspondence of attribution maps with ground truth sequence annotations (e.g. transmembrane regions, active sites) across many proteins. Source code can be accessed at https://github.com/markuswenzel/xai-proteins.

Functional prediction of proteins from the human gut archaeome.

The human gastrointestinal tract contains diverse microbial communities, including archaea. Among them, Methanobrevibacter smithii represents a highly active and clinically relevant methanogenic archaeon, being involved in gastrointestinal disorders, such as inflammatory bowel disease and obesity. Herein, we present an integrated approach using sequence and structure information to improve the annotation of M. smithii proteins using advanced protein structure prediction and annotation tools, such as AlphaFold2, trRosetta, ProFunc, and DeepFri. Of an initial set of 873 481 archaeal proteins, we found 707 754 proteins exclusively present in the human gut. Having analysed archaeal proteins together with 87 282 994 bacterial proteins, we identified unique archaeal proteins and archaeal-bacterial homologs. We then predicted and characterized functional domains and structures of 73 unique and homologous archaeal protein clusters linked the human gut and M. smithii. We refined annotations based on the predicted structures, extending existing sequence similarity-based annotations. We identified gut-specific archaeal proteins that may be involved in defense mechanisms, virulence, adhesion, and the degradation of toxic substances. Interestingly, we identified potential glycosyltransferases that could be associated with N-linked and O-glycosylation. Additionally, we found preliminary evidence for interdomain horizontal gene transfer between Clostridia species and M. smithii, which includes sporulation Stage V proteins AE and AD. Our study broadens the understanding of archaeal biology, particularly M. smithii, and highlights the importance of considering both sequence and structure for the prediction of protein function.

ProFun-SOM: Protein Function Prediction for Specific Ontology Based on Multiple Sequence Alignment Reconstruction.

Protein function prediction is crucial for understanding species evolution, including viral mutations. Gene ontology (GO) is a standardized representation framework for describing protein functions with annotated terms. Each ontology is a specific functional category containing multiple child ontologies, and the relationships of parent and child ontologies create a directed acyclic graph. Protein functions are categorized using GO, which divides them into three main groups: cellular component ontology, molecular function ontology, and biological process ontology. Therefore, the GO annotation of protein is a hierarchical multilabel classification problem. This hierarchical relationship introduces complexities such as mixed ontology problem, leading to performance bottlenecks in existing computational methods due to label dependency and data sparsity. To overcome bottleneck issues brought by mixed ontology problem, we propose ProFun-SOM, an innovative multilabel classifier that utilizes multiple sequence alignments (MSAs) to accurately annotate gene ontologies. ProFun-SOM enhances the initial MSAs through a reconstruction process and integrates them into a deep learning architecture. It then predicts annotations within the cellular component, molecular function, biological process, and mixed ontologies. Our evaluation results on three datasets (CAFA3, SwissProt, and NetGO2) demonstrate that ProFun-SOM surpasses state-of-the-art methods. This study confirmed that utilizing MSAs of proteins can effectively overcome the two main bottlenecks issues, label dependency and data sparsity, thereby alleviating the root problem, mixed ontology. A freely accessible web server is available at http://bliulab.net/ ProFun-SOM/.

An Effective Computational Method for Predicting Self-Interacting Proteins Based on VGGNet Convolutional Neural Network and Gray-Level Co-occurrence Matrix.

Predicting Self-interacting proteins (SIPs) is a crucial area of research in predicting protein functions, as well as in understanding gene-disease and disease-drug associations. These interactions are integral to numerous cellular processes and play pivotal roles within cells. However, traditional methods for identifying SIPs through biological experiments are often expensive, time-consuming, and have long cycles. Therefore, the development of effective computational methods for accurately predicting SIPs is not only necessary but also presents a significant challenge. In this research, we introduce a novel computational prediction technique, VGGNGLCM, which leverages protein sequence data. This method integrates the VGGNet deep convolutional neural network (VGGN) with the Gray-Level Co-occurrence Matrix (GLCM) to detect Self-interacting proteins associations. Specifically, we initially utilized Position Specific Scoring Matrix (PSSM) to capture protein evolutionary information and integrated key features from PSSM using GLCM. We then employed VGGNet as a predictive classifier, leveraging its capabilities for powerful learning and classification prediction. Subsequently, the extracted features were input into the VGGNet deep convolutional neural network to identify Self-interacting proteins. To evaluate the performance of the VGGNGLCM model, we conducted experiments using yeast and human datasets, achieving average accuracies of 95.68% and 97.72% respectively. Additionally, we compared the prediction performance of the VGGNet classifier with that of the Convolutional Neural Network (CNN) and the state-of-the-art Support Vector Machine (SVM) using the same feature extraction method. We also compared the prediction ability of VGGNGLCM with other existing approaches. The comparison results further demonstrate the superior performance of VGGNGLCM over other prediction models in this domain. The experimental verification further strengthens the evidence that VGGNGLCM is effective and robust compared to existing methods. It also highlights the high accuracy and robustness of the VGGNGLCM model in predicting Self-interacting proteins (SIPs). Consequently, we believe that the VGGNGLCM method serves as a valuable computational tool and can catalyze extensive bioinformatics research related to SIPs prediction.

When Protein Structure Embedding Meets Large Language Models.

Protein structure analysis is essential in various bioinformatics domains such as drug discovery, disease diagnosis, and evolutionary studies. Within structural biology, the classification of protein structures is pivotal, employing machine learning algorithms to categorize structures based on data from databases like the Protein Data Bank (PDB). To predict protein functions, embeddings based on protein sequences have been employed. Creating numerical embeddings that preserve vital information while considering protein structure and sequence presents several challenges. The existing literature lacks a comprehensive and effective approach that combines structural and sequence-based features to achieve efficient protein classification. While large language models (LLMs) have exhibited promising outcomes for protein function prediction, their focus primarily lies on protein sequences, disregarding the 3D structures of proteins. The quality of embeddings heavily relies on how well the geometry of the embedding space aligns with the underlying data structure, posing a critical research question. Traditionally, Euclidean space has served as a widely utilized framework for embeddings. In this study, we propose a novel method for designing numerical embeddings in Euclidean space for proteins by leveraging 3D structure information, specifically employing the concept of contact maps. These embeddings are synergistically combined with features extracted from LLMs and traditional feature engineering techniques to enhance the performance of embeddings in supervised protein analysis. Experimental results on benchmark datasets, including PDB Bind and STCRDAB, demonstrate the superior performance of the proposed method for protein function prediction.

A comprehensive framework for advanced protein classification and function prediction using synergistic approaches: Integrating bispectral analysis, machine learning, and deep learning

Proteins are fundamental components of diverse cellular systems and play crucial roles in a variety of disease processes. Consequently, it is crucial to comprehend their structure, function, and intricate interconnections. Classifying proteins into families or groups with comparable structural and functional characteristics is a crucial aspect of this comprehension. This classification is crucial for evolutionary research, predicting protein function, and identifying potential therapeutic targets. Sequence alignment and structure-based alignment are frequently ineffective techniques for identifying protein families.This study addresses the need for a more efficient and accurate technique for feature extraction and protein classification. The research proposes a novel method that integrates bispectrum characteristics, deep learning techniques, and machine learning algorithms to overcome the limitations of conventional methods. The proposed method uses numbers to represent protein sequences, utilizes bispectrum analysis, uses different topologies for convolutional neural networks to pull out features, and chooses robust features to classify protein families. The goal is to outperform existing methods for identifying protein families, thereby enhancing classification metrics. The materials consist of numerous protein datasets, whereas the methods incorporate bispectrum characteristics and deep learning strategies. The results of this study demonstrate that the proposed method for identifying protein families is superior to conventional approaches. Significantly enhanced quality metrics demonstrated the efficacy of the combined bispectrum and deep learning approaches. These findings have the potential to advance the field of protein biology and facilitate pharmaceutical innovation. In conclusion, this study presents a novel method that employs bispectrum characteristics and deep learning techniques to improve the precision and efficiency of protein family identification. The demonstrated advancements in classification metrics demonstrate this method’s applicability to numerous scientific disciplines. This furthers our understanding of protein function and its implications for disease and treatment.

Targeted metabolite profiling and de novo transcriptome sequencing reveal the key terpene synthase genes in medicinally important plant, Couroupita guianensis Aubl

AbstractThe Lecythidaceae family tree, Couroupita guianensis Aubl, popularly known as Nagpushpa, is a widely cultivated ornamental tree with several uses in traditional medicine. The tree is revered as highly sacred in Indian traditional culture due to its uniquely shaped, fragrant flowers. Considering the significance, we were prompted to carry out the metabolite and transcriptome analysis of Nagapushpa. The flower, petals, stamen, stem and leaf of C. guianensis were metabolically profiled, and it was discovered that the flower tissue contained the highest terpenoid reservoir. A number of terpenoid pathway transcripts were also found in the flower tissue after transcriptome profiling. KEGG pathway mapping was carried out to correlate transcript sequences with the biosynthesis of different types of terpenes. We were able to clone three full-length terpene synthase gene candidates, i.e. monoterpene ocimene synthase, diterpene ent-kaurene synthase and sesquiterpene farnesene synthase. The transcript expression of selected terpene synthase genes was also verified in flower tissue. These cloned sequences were used for in silico structural investigations and protein function prediction at the level of 3D structure. The data presented in this study provide a comprehensive resource for the metabolic and transcriptomic profiles of C. guianensis. The study paves the way towards the elucidation of terpene biosynthetic pathway in C. guianensis and heterologous production of useful terpenoids in the future.

In silico protein function prediction: the rise of machine learning-based approaches.

Proteins function as integral actors in essential life processes, rendering the realm of protein research a fundamental domain that possesses the potential to propel advancements in pharmaceuticals and disease investigation. Within the context of protein research, an imperious demand arises to uncover protein functionalities and untangle intricate mechanistic underpinnings. Due to the exorbitant costs and limited throughput inherent in experimental investigations, computational models offer a promising alternative to accelerate protein function annotation. In recent years, protein pre-training models have exhibited noteworthy advancement across multiple prediction tasks. This advancement highlights a notable prospect for effectively tackling the intricate downstream task associated with protein function prediction. In this review, we elucidate the historical evolution and research paradigms of computational methods for predicting protein function. Subsequently, we summarize the progress in protein and molecule representation as well as feature extraction techniques. Furthermore, we assess the performance of machine learning-based algorithms across various objectives in protein function prediction, thereby offering a comprehensive perspective on the progress within this field.

THPLM: a sequence-based deep learning framework for protein stability changes prediction upon point variations using pretrained protein language model.

Quantitative determination of protein thermodynamic stability is a critical step in protein and drug design. Reliable prediction of protein stability changes caused by point variations contributes to developing-related fields. Over the past decades, dozens of structure-based and sequence-based methods have been proposed, showing good prediction performance. Despite the impressive progress, it is necessary to explore wild-type and variant protein representations to address the problem of how to represent the protein stability change in view of global sequence. With the development of structure prediction using learning-based methods, protein language models (PLMs) have shown accurate and high-quality predictions of protein structure. Because PLM captures the atomic-level structural information, it can help to understand how single-point variations cause functional changes. Here, we proposed THPLM, a sequence-based deep learning model for stability change prediction using Meta's ESM-2. With ESM-2 and a simple convolutional neural network, THPLM achieved comparable or even better performance than most methods, including sequence-based and structure-based methods. Furthermore, the experimental results indicate that the PLM's ability to generate representations of sequence can effectively improve the ability of protein function prediction. The source code of THPLM and the testing data can be accessible through the following links: https://github.com/FPPGroup/THPLM.

Deep generative models of LDLR protein structure to predict variant pathogenicity

The complex structure and function of low density lipoprotein receptor (LDLR) makes classification of protein-coding missense variants challenging. Deep generative models, including Evolutionary model of Variant Effect (EVE), Evolutionary Scale Modeling (ESM), and AlphaFold 2 (AF2), have enabled significant progress in the prediction of protein structure and function. ESM and EVE directly estimate the likelihood of a variant sequence but are purely data-driven and challenging to interpret. AF2 predicts LDLR structures, but variant effects are explicitly modeled by estimating changes in stability. We tested the effectiveness of these models for predicting variant pathogenicity compared to established methods. AF2 produced two distinct conformations based on a novel hinge mechanism. Within ESM’s hidden space, benign and pathogenic variants had different distributions. In EVE, these distributions were similar. EVE and ESM were comparable to Polyphen-2, SIFT, REVEL, and Primate AI for predicting binary classifications in ClinVar. However, they were more strongly correlated with experimental measures of LDL uptake. AF2 poorly performed in these tasks. Using the UK Biobank to compare association with clinical phenotypes, ESM and EVE were more strongly associated with serum LDL-C than Polyphen-2. ESM was able to identify variants with more extreme LDL-C levels than EVE and had a significantly stronger association with atherosclerotic cardiovascular disease. In conclusion, AF2 predicted LDLR structures do not accurately model variant pathogenicity. ESM and EVE are competitive with prior scoring methods for prediction based on binary classifications in ClinVar but are superior based on correlations with experimental assays and clinical phenotypes.

Struct2GO: protein function prediction based on Graph pooling algorithm and AlphaFold2 structure information.

In recent years, there has been a breakthrough in protein structure prediction, and the AlphaFold2 model of the DeepMind team has improved the accuracy of protein structure prediction to the atomic level. Currently, deep learning-based protein function prediction models usually extract features from protein sequences and combine them with protein-protein interaction networks to achieve good results. However, for newly sequenced proteins that are not in the protein-protein interaction network, such models cannot make effective predictions. To address this, this paper proposes the Struct2GO model, which combines protein structure and sequence data to enhance the precision of protein function prediction and the generality of the model. We obtain amino acid residue embeddings in protein structure through graph representation learning, utilize the graph pooling algorithm based on a self-attention mechanism to obtain the whole graph structure features, and fuse them with sequence features obtained from the protein language model. The results demonstrate that compared with the traditional protein sequence-based function prediction model, the Struct2GO model achieves better results. https://github.com/lyjps/Struct2GO. Supplementary data are available at Bioinformatics online.

An Overview of Protein Function Prediction Methods: A Deep Learning Perspective

Abstract: Predicting the function of proteins is a major challenge in the scientific community, particularly in the post-genomic era. Traditional methods of determining protein functions, such as experiments, are accurate but can be resource-intensive and time-consuming. The development of Next Generation Sequencing (NGS) techniques has led to the production of a large number of new protein sequences, which has increased the gap between available raw sequences and verified annotated sequences. To address this gap, automated protein function prediction (AFP) techniques have been developed as a faster and more cost-effective alternative, aiming to maintain the same accuracy level. : Several automatic computational methods for protein function prediction have recently been developed and proposed. This paper reviews the best-performing AFP methods presented in the last decade and analyzes their improvements over time to identify the most promising strategies for future methods. : Identifying the most effective method for predicting protein function is still a challenge. The Critical Assessment of Functional Annotation (CAFA) has established an international standard for evaluating and comparing the performance of various protein function prediction methods. In this study, we analyze the best-performing methods identified in recent editions of CAFA. These methods are divided into five categories based on their principles of operation: sequence-based, structure-based, combined-based, ML-based and embeddings-based. : After conducting a comprehensive analysis of the various protein function prediction methods, we observe that there has been a steady improvement in the accuracy of predictions over time, mainly due to the implementation of machine learning techniques. The present trend suggests that all the bestperforming methods will use machine learning to improve their accuracy in the future. : We highlight the positive impact that the use of machine learning (ML) has had on protein function prediction. Most recent methods developed in this area use ML, demonstrating its importance in analyzing biological information and making predictions. Despite these improvements in accuracy, there is still a significant gap compared with experimental evidence. The use of new approaches based on Deep Learning (DL) techniques will probably be necessary to close this gap, and while significant progress has been made in this area, there is still more work to be done to fully realize the potential of DL.

Protein Function Prediction With Functional and Topological Knowledge of Gene Ontology.

Gene Ontology (GO) is a widely used bioinformatics resource for describing biological processes, molecular functions, and cellular components of proteins. It covers more than 5000 terms hierarchically organized into a directed acyclic graph and known functional annotations. Automatically annotating protein functions by using GO-based computational models has been an area of active research for a long time. However, due to the limited functional annotation information and complex topological structures of GO, existing models cannot effectively capture the knowledge representation of GO. To solve this issue, we present a method that fuses the functional and topological knowledge of GO to guide protein function prediction. This method employs a multi-view GCN model to extract a variety of GO representations from functional information, topological structure, and their combinations. To dynamically learn the significance weights of these representations, it adopts an attention mechanism to learn the final knowledge representation of GO. Furthermore, it uses a pre-trained language model (i.e., ESM-1b) to efficiently learn biological features for each protein sequence. Finally, it obtains all predicted scores by calculating the dot product of sequence features and GO representation. Our method outperforms other state-of-the-art methods, as demonstrated by the experimental results on datasets from three different species, namely Yeast, Human and Arabidopsis. Our proposed method's code can be accessed at: https://github.com/Candyperfect/Master.

QTL mapping and candidate gene analysis of low‐temperature tolerance at the germination stage of soybean

AbstractWhen soybean seeds encounter low temperature during germination, the vigour and germination of soybean seeds are affected, which leads to a lack of seedlings and weak seedlings, resulting in yield reduction. In‐depth analysis of the genetic mechanism of soybean seed germination tolerance to low‐temperature stress and the cultivation of soybean‐tolerant varieties is the key to resisting low‐temperature stress at the germination stage. In the present study, a chromosome segment substitution line (CSSL) population constructed by wild soybean ZYD00006 and cultivated soybean SN14 was used to map three quantitative trait loci (QTLs). Five candidate genes were obtained by gene annotation, GO enrichment analysis and protein function prediction. The candidate genes were subjected to bioinformatics analysis, qRT‐PCR analysis, trypsin activity analysis and soluble protein content analysis. The results showed that the secondary and tertiary structures of the Glyma.09G162700 proteins were mutated. Within 0–72 h, the expression of Glyma.09G162700 in the two materials with different tolerances was consistent, and the change in trypsin activity was consistent with the change in protein expression. Through haplotype analysis, Glyma.09G162700 produced two haplotypes at −2420 bp. The germination rate (GR) and relative germination rate (RGR) of the two haplotypes were significantly different, indicating that the two haplotypes have wide applicability in soybean resources. In summary, Glyma.09G162700 may be a candidate gene for low‐temperature tolerance at the germination stage of soybean. These results provide an important theoretical basis and marker information for analysing the mechanism of low‐temperature tolerance in soybean germination stage and cultivating low‐temperature‐tolerant varieties.

HNetGO: protein function prediction via heterogeneous network transformer.

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

Enhanced protein function prediction by fusion embedding based on protein language models

Natural language models can accomplish non-natural language tasks such as protein prediction, but the actual prediction effect is low and occupies large computational resources. In this paper, a fusion embedding model is proposed to improve the prediction effect of the model and reduce the computational cost of the model by fusing information of different dimensions. The paper is validated by the downstream task of protein function prediction, which provides a reference for solving practical tasks using fusion embedding methods.

Incorporating physics to overcome data scarcity in predictive modeling of protein function: A case study of BK channels.

Machine learning has played transformative roles in numerous chemical and biophysical problems such as protein folding where large amount of data exists. Nonetheless, many important problems remain challenging for data-driven machine learning approaches due to the limitation of data scarcity. One approach to overcome data scarcity is to incorporate physical principles such as through molecular modeling and simulation. Here, we focus on the big potassium (BK) channels that play important roles in cardiovascular and neural systems. Many mutants of BK channel are associated with various neurological and cardiovascular diseases, but the molecular effects are unknown. The voltage gating properties of BK channels have been characterized for 473 site-specific mutations experimentally over the last three decades; yet, these functional data by themselves remain far too sparse to derive a predictive model of BK channel voltage gating. Using physics-based modeling, we quantify the energetic effects of all single mutations on both open and closed states of the channel. Together with dynamic properties derived from atomistic simulations, these physical descriptors allow the training of random forest models that could reproduce unseen experimentally measured shifts in gating voltage, ∆V1/2, with a RMSE ~ 32 mV and correlation coefficient of R ~ 0.7. Importantly, the model appears capable of uncovering nontrivial physical principles underlying the gating of the channel, including a central role of hydrophobic gating. The model was further evaluated using four novel mutations of L235 and V236 on the S5 helix, mutations of which are predicted to have opposing effects on V1/2 and suggest a key role of S5 in mediating voltage sensor-pore coupling. The measured ∆V1/2 agree quantitatively with prediction for all four mutations, with a high correlation of R = 0.92 and RMSE = 18 mV. Therefore, the model can capture nontrivial voltage gating properties in regions where few mutations are known. The success of predictive modeling of BK voltage gating demonstrates the potential of combining physics and statistical learning for overcoming data scarcity in nontrivial protein function prediction.