DeepGraphGO: graph neural network for large-scale, multispecies protein function prediction

Machine Learning Empowering Microbial Cell Factory: A Comprehensive Review

The wide application of machine learning has provided more possibilities for biological manufacturing, and the combination of machine learning and synthetic biology technology has ignited even more brilliant sparks, which has created an unpredictable value for the upgrading of microbial cell factories. The review delves into the synergies between machine learning and synthetic biology to create research worth investigating in biotechnology. We explore relevant databases, toolboxes, and machine learning-derived models. Furthermore, we examine specific applications of this combined approach in chemical production, human health, and environmental remediation. By elucidating these successful integrations, this review aims to provide valuable guidance for future research at the intersection of biomanufacturing and artificial intelligence.

MSNGO: multi-species protein function annotation based on 3D protein structure and network propagation

MOTIVATION

In recent years, protein function prediction has broken through the bottleneck of sequence features, significantly improving prediction accuracy using high-precision protein structures predicted by AlphaFold2. While single-species protein function prediction methods have achieved remarkable success, multi-species approaches still face challenges such as difficulties in multi-source data integration and insufficient knowledge transfer between distantly-related species. How to integrate large-scale data and provide effective cross-species label propagation for species with sparse protein annotations remains a critical and unresolved challenge. To address this problem, we propose the MSNGO (Multi-species protein Structures and Network to predict GO terms) model, which integrates structural features and network propagation methods. Our validation shows that using structural features can significantly improve the accuracy of multi-species protein function prediction.

RESULTS

We employ graph representation learning techniques to extract amino acid representations from protein structure contact maps and train a structural model using a graph convolution pooling module to derive protein-level structural features. After incorporating the sequence features from ESM-2, we apply a network propagation algorithm to aggregate information and update node representations within a heterogeneous network. The results demonstrate that MSNGO outperforms previous multi-species protein function prediction methods that rely on sequence features and protein-protein networks.

AVAILABILITY AND IMPLEMENTATION

https://github.com/blingbell/MSNGO.

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/.

GTPLM-GO: Enhancing Protein Function Prediction Through Dual-Branch Graph Transformer and Protein Language Model Fusing Sequence and Local-Global PPI Information

Currently, protein-protein interaction (PPI) networks have become an essential data source for protein function prediction. However, methods utilizing graph neural networks (GNNs) face significant challenges in modeling PPI networks. A primary issue is over-smoothing, which occurs when multiple GNN layers are stacked to capture global information. This architectural limitation inherently impairs the integration of local and global information within PPI networks, thereby limiting the accuracy of protein function prediction. To effectively utilize information within PPI networks, we propose GTPLM-GO, a protein function prediction method based on a dual-branch Graph Transformer and protein language model. The dual-branch Graph Transformer achieves the collaborative modeling of local and global information in PPI networks through two branches: a graph neural network and a linear attention-based Transformer encoder. GTPLM-GO integrates local-global PPI information with the functional semantic encoding constructed by the protein language model, overcoming the issue of inadequate information extraction in existing methods. Experimental results demonstrate that GTPLM-GO outperforms advanced network-based and sequence-based methods on PPI network datasets of varying scales.

Enzyme functional classification using artificial intelligence

Enzymes are essential for cellular metabolism, and elucidating their functions is critical for advancing biochemical research. However, experimental methods are often time consuming and resource intensive. To address this, significant efforts have been directed toward applying artificial intelligence (AI) to enzyme function prediction, enabling high-throughput and scalable approaches. In this review, we discuss advances in AI-driven enzyme functional annotation, transitioning from traditional machine learning (ML) methods to state-of-the-art deep learning approaches. We highlight how deep learning enables models to automatically extract features from raw data without manual intervention, leading to enhanced performance. Finally, we discuss the discovery of novel enzyme functions and generation of de novo enzymes through the integration of generative AIs and bio big data as future research directions.

HiSIF-DTA: A Hierarchical Semantic Information Fusion Framework for Drug-Target Affinity Prediction

Accurately identifying drug-target affinity (DTA) plays a significant role in promoting drug discovery and has attracted increasing attention in recent years. Exploring appropriate protein representation methods and increasing the abundance of protein information is critical in enhancing the accuracy of DTA prediction. Recently, numerous deep learning-based models have been proposed to utilize the sequential or structural features of target proteins. However, these models capture only the low-order semantics that exist in a single protein, while the high-order semantics abundant in biological networks are largely ignored. In this article, we propose HiSIF-DTA-a hierarchical semantic information fusion framework for DTA prediction. In this framework, a hierarchical protein graph is constructed that includes not only contact maps as low-order structural semantics but also protein-protein interaction (PPI) networks as high-order functional semantics. Particularly, two distinct hierarchical fusion strategies (i.e., Top-down and Bottom-Up) are designed to integrate the different protein semantics, therefore contributing to a richer protein representation. Comprehensive experimental results demonstrate that HiSIF-DTA outperforms current state -of-the-art methods for prediction on the benchmark datasets of the DTA task. Further validation on binary tasks and visualization analysis demonstrates the generalization and interpretation abilities of the proposed method.

SEGT-GO: a graph transformer method based on PPI serialization and explanatory artificial intelligence for protein function prediction

BACKGROUND

A massive amount of protein sequences have been obtained, but their functions remain challenging to discern. In recent research on protein function prediction, Protein-Protein Interaction (PPI) Networks have played a crucial role. Uncovering potential function relationships between distant proteins within PPI networks is essential for improving the accuracy of protein function prediction. Most current studies attempt to capture these distant relationships by stacking graph network layers, but performance gains diminish as the number of layers increases.

RESULTS

To further explore the potential functional relationships between multi-hop proteins in PPI networks, this paper proposes SEGT-GO, a Graph Transformer method based on PPI multi-hop neighborhood Serialization and Explainable artificial intelligence for large-scale multispecies protein function prediction. The multi-hop neighborhood serialization maps multi-hop information in the PPI Network into serialized feature embeddings, enabling the Graph Transformer to learn deeper functional features within the PPI Network. Based on game theory, the SHAP eXplainable Artificial Intelligence (XAI) framework optimizes model input and filters out feature noise, enhancing model performance.

CONCLUSIONS

Compared to the advanced network method DeepGraphGO, SEGT-GO achieves more competitive results in standard large-scale datasets and superior results on small ones, validating its ability to extract functional information from deep proteins. Furthermore, SEGT-GO achieves superior results in cross-species learning and prediction of the functions of unseen proteins, further proving the method's strong generalization.

DPFunc: accurately predicting protein function via deep learning with domain-guided structure information

Computational methods for predicting protein function are of great significance in understanding biological mechanisms and treating complex diseases. However, existing computational approaches of protein function prediction lack interpretability, making it difficult to understand the relations between protein structures and functions. In this study, we propose a deep learning-based solution, named DPFunc, for accurate protein function prediction with domain-guided structure information. DPFunc can detect significant regions in protein structures and accurately predict corresponding functions under the guidance of domain information. It outperforms current state-of-the-art methods and achieves a significant improvement over existing structure-based methods. Detailed analyses demonstrate that the guidance of domain information contributes to DPFunc for protein function prediction, enabling our method to detect key residues or regions in protein structures, which are closely related to their functions. In summary, DPFunc serves as an effective tool for large-scale protein function prediction, which pushes the border of protein understanding in biological systems.

Deep learning methods for protein function prediction

Predicting protein function from protein sequence, structure, interaction, and other relevant information is important for generating hypotheses for biological experiments and studying biological systems, and therefore has been a major challenge in protein bioinformatics. Numerous computational methods had been developed to advance protein function prediction gradually in the last two decades. Particularly, in the recent years, leveraging the revolutionary advances in artificial intelligence (AI), more and more deep learning methods have been developed to improve protein function prediction at a faster pace. Here, we provide an in-depth review of the recent developments of deep learning methods for protein function prediction. We summarize the significant advances in the field, identify several remaining major challenges to be tackled, and suggest some potential directions to explore. The data sources and evaluation metrics widely used in protein function prediction are also discussed to assist the machine learning, AI, and bioinformatics communities to develop more cutting-edge methods to advance protein function prediction.

Annotating protein functions via fusing multiple biological modalities

Understanding the function of proteins is of great significance for revealing disease pathogenesis and discovering new targets. Benefiting from the explosive growth of the protein universal, deep learning has been applied to accelerate the protein annotation cycle from different biological modalities. However, most existing deep learning-based methods not only fail to effectively fuse different biological modalities, resulting in low-quality protein representations, but also suffer from the convergence of suboptimal solution caused by sparse label representations. Aiming at the above issue, we propose a multiprocedural approach for fusing heterogeneous biological modalities and annotating protein functions, i.e., MIF2GO (Multimodal Information Fusion to infer Gene Ontology terms), which sequentially fuses up to six biological modalities ranging from different biological levels in three steps, thus leading to powerful protein representations. Evaluation results on seven benchmark datasets show that the proposed method not only considerably outperforms state-of-the-art performance, but also demonstrates great robustness and generalizability across species. Besides, we also present biological insights into the associations between those modalities and protein functions. This research provides a robust framework for integrating multimodal biological data, offering a scalable solution for protein function annotation, ultimately facilitating advancements in precision medicine and the discovery of novel therapeutic strategies.

FAPM: functional annotation of proteins using multimodal models beyond structural modeling

MOTIVATION

Assigning accurate property labels to proteins, like functional terms and catalytic activity, is challenging, especially for proteins without homologs and "tail labels" with few known examples. Previous methods mainly focused on protein sequence features, overlooking the semantic meaning of protein labels.

RESULTS

We introduce functional annotation of proteins using multimodal models (FAPM), a contrastive multimodal model that links natural language with protein sequence language. This model combines a pretrained protein sequence model with a pretrained large language model to generate labels, such as Gene Ontology (GO) functional terms and catalytic activity predictions, in natural language. Our results show that FAPM excels in understanding protein properties, outperforming models based solely on protein sequences or structures. It achieves state-of-the-art performance on public benchmarks and in-house experimentally annotated phage proteins, which often have few known homologs. Additionally, FAPM's flexibility allows it to incorporate extra text prompts, like taxonomy information, enhancing both its predictive performance and explainability. This novel approach offers a promising alternative to current methods that rely on multiple sequence alignment for protein annotation.

AVAILABILITY AND IMPLEMENTATION

The online demo is at: https://huggingface.co/spaces/wenkai/FAPM_demo.

The macroevolutionary dynamics of pharyngognathy in fishes fail to support the key innovation hypothesis

Key innovations, traits that provide species access to novel niches, are thought to be a major generator of biodiversity. One commonly cited example of key innovation is pharyngognathy, a set of modifications to the pharyngeal jaws found in some highly species-rich fish clades such as cichlids and wrasses. Here, using comparative phylogenomics and phylogenetic comparative methods, we investigate the genomic basis of pharyngognathy and the impact of this innovation on diversification. Whole genomes resolve the relationships of fish clades with this innovation and their close relatives, but high levels of topological discordance suggest the innovation may have evolved fewer times than previously thought. Closer examination of the topology of noncoding elements accelerated in clades with the pharyngognathy innovation reveals hidden patterns of shared ancestry across putatively independent transitions to pharyngognathy. When our updated phylogenomic relationships are used alongside large-scale phylogenetic and ecological datasets, we find no evidence pharyngognathy consistently modifies the macroevolutionary landscape of trophic ecology nor does it increase diversification. Our results highlight the necessity of incorporating genomic information in studies of key innovation.

An experimental analysis of graph representation learning for Gene Ontology based protein function prediction

Understanding protein function is crucial for deciphering biological systems and facilitating various biomedical applications. Computational methods for predicting Gene Ontology functions of proteins emerged in the 2000s to bridge the gap between the number of annotated proteins and the rapidly growing number of newly discovered amino acid sequences. Recently, there has been a surge in studies applying graph representation learning techniques to biological networks to enhance protein function prediction tools. In this review, we provide fundamental concepts in graph embedding algorithms. This study described graph representation learning methods for protein function prediction based on four principal data categories, namely PPI network, protein structure, Gene Ontology graph, and integrated graph. The commonly used approaches for each category were summarized and diagrammed, with the specific results of each method explained in detail. Finally, existing limitations and potential solutions were discussed, and directions for future research within the protein research community were suggested.

RecGOBD: accurate recognition of gene ontology related brain development protein functions through multi-feature fusion and attention mechanisms

Motivation

Protein function prediction is crucial in bioinformatics, driven by the growth of protein sequence data from high-throughput technologies. Traditional methods are costly and slow, underscoring the need for computational solutions. While deep learning offers powerful tools, many models lack optimization for brain development datasets, critical for neurodevelopmental disorder research. To address this, we developed RecGOBD (Recognition of Gene Ontology-related Brain Development protein function), a model tailored to predict protein functions essential to brain development.

Result

RecGOBD targets 10 key gene ontology (GO) terms for brain development, embedding protein sequences associated with these terms. Leveraging advanced pre-trained models, it captures both sequence and structure data, aligning them with GO terms through attention mechanisms. The category attention layer enhances prediction accuracy. RecGOBD surpassed five benchmark models in AUROC, AUPR, and Fmax metrics and was further used to predict autism-related protein functions and assess mutation impacts on GO terms. These findings highlight RecGOBD's potential in advancing protein function prediction for neurodevelopmental disorders.

Availability and implementation

All Python codes associated with this study are available at https://github.com/ZL-Xia/RECGOBD.git.

Deep learning model for protein multi-label subcellular localization and function prediction based on multi-task collaborative training

The functional study of proteins is a critical task in modern biology, playing a pivotal role in understanding the mechanisms of pathogenesis, developing new drugs, and discovering novel drug targets. However, existing computational models for subcellular localization face significant challenges, such as reliance on known Gene Ontology (GO) annotation databases or overlooking the relationship between GO annotations and subcellular localization. To address these issues, we propose DeepMTC, an end-to-end deep learning-based multi-task collaborative training model. DeepMTC integrates the interrelationship between subcellular localization and the functional annotation of proteins, leveraging multi-task collaborative training to eliminate dependence on known GO databases. This strategy gives DeepMTC a distinct advantage in predicting newly discovered proteins without prior functional annotations. First, DeepMTC leverages pre-trained language model with high accuracy to obtain the 3D structure and sequence features of proteins. Additionally, it employs a graph transformer module to encode protein sequence features, addressing the problem of long-range dependencies in graph neural networks. Finally, DeepMTC uses a functional cross-attention mechanism to efficiently combine upstream learned functional features to perform the subcellular localization task. The experimental results demonstrate that DeepMTC outperforms state-of-the-art models in both protein function prediction and subcellular localization. Moreover, interpretability experiments revealed that DeepMTC can accurately identify the key residues and functional domains of proteins, confirming its superior performance. The code and dataset of DeepMTC are freely available at https://github.com/ghli16/DeepMTC.

GORetriever: reranking protein-description-based GO candidates by literature-driven deep information retrieval for protein function annotation

SUMMARY

The vast majority of proteins still lack experimentally validated functional annotations, which highlights the importance of developing high-performance automated protein function prediction/annotation (AFP) methods. While existing approaches focus on protein sequences, networks, and structural data, textual information related to proteins has been overlooked. However, roughly 82% of SwissProt proteins already possess literature information that experts have annotated. To efficiently and effectively use literature information, we present GORetriever, a two-stage deep information retrieval-based method for AFP. Given a target protein, in the first stage, candidate Gene Ontology (GO) terms are retrieved by using annotated proteins with similar descriptions. In the second stage, the GO terms are reranked based on semantic matching between the GO definitions and textual information (literature and protein description) of the target protein. Extensive experiments over benchmark datasets demonstrate the remarkable effectiveness of GORetriever in enhancing the AFP performance. Note that GORetriever is the key component of GOCurator, which has achieved first place in the latest critical assessment of protein function annotation (CAFA5: over 1600 teams participated), held in 2023-2024.

AVAILABILITY AND IMPLEMENTATION

GORetriever is publicly available at https://github.com/ZhuLab-Fudan/GORetriever.

Ten quick tips for ensuring machine learning model validity

Artificial Intelligence (AI) and Machine Learning (ML) models are increasingly deployed on biomedical and health data to shed insights on biological mechanism, predict disease outcomes, and support clinical decision-making. However, ensuring model validity is challenging. The 10 quick tips described here discuss useful practices on how to check AI/ML models from 2 perspectives-the user and the developer.

A novel prediction approach driven by graph representation learning for heavy metal concentrations

The potential risk of heavy metals (HMs) to public health is an issue of great concern. Early prediction is an effective means to reduce the accumulation of HMs. The current prediction methods rarely take internal correlations between environmental factors into consideration, which negatively affects the accuracy of the prediction model and the interpretability of intrinsic mechanisms. Graph representation learning (GraRL) can simultaneously learn the attribute relationships between environmental factors and graph structural information. Herein, we developed the GraRL-HM method to predict the HM concentrations in soil-rice systems. The method consists of two modules, which are PeTPG and GCN-HM. In PeTPG, a graphic structure was generated using graph representation and communitization technology to explore the correlations and transmission paths of different environmental factors. Subsequently, the GCN-HM model based on the graph convolutional neural network (GCN) was used to predict the HM concentrations. The GraRL-HM method was validated by 2295 sets of data covering 21 environmental factors. The results indicated that the PeTPG model simplified correlation paths between factor nodes from 396 to 184, reducing by 53.5 % graph scale by eliminating the invalid paths. The concise and efficient graph structure enhanced the learning efficiency and representation accuracy of downstream prediction models. The GCN-HM model was superior to the four benchmark models in predicting the HM concentration in the crop, improving R2 by 36.1 %. This study develops a novel approach to improve the prediction accuracy of pollutant accumulation and provides valuable insights into intelligent regulation and planting guidance for heavy metal pollution control.

ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning

Designing de novo proteins beyond those found in nature holds significant promise for advancements in both scientific and engineering applications. Current methodologies for protein design often rely on AI-based models, such as surrogate models that address end-to-end problems by linking protein structure to material properties or vice versa. However, these models frequently focus on specific material objectives or structural properties, limiting their flexibility when incorporating out-of-domain knowledge into the design process or comprehensive data analysis is required. In this study, we introduce ProtAgents, a platform for de novo protein design based on Large Language Models (LLMs), where multiple AI agents with distinct capabilities collaboratively address complex tasks within a dynamic environment. The versatility in agent development allows for expertise in diverse domains, including knowledge retrieval, protein structure analysis, physics-based simulations, and results analysis. The dynamic collaboration between agents, empowered by LLMs, provides a versatile approach to tackling protein design and analysis problems, as demonstrated through diverse examples in this study. The problems of interest encompass designing new proteins, analyzing protein structures and obtaining new first-principles data - natural vibrational frequencies - via physics simulations. The concerted effort of the system allows for powerful automated and synergistic design of de novo proteins with targeted mechanical properties. The flexibility in designing the agents, on one hand, and their capacity in autonomous collaboration through the dynamic LLM-based multi-agent environment on the other hand, unleashes great potentials of LLMs in addressing multi-objective materials problems and opens up new avenues for autonomous materials discovery and design.

GPSFun: geometry-aware protein sequence function predictions with language models

Knowledge of protein function is essential for elucidating disease mechanisms and discovering new drug targets. However, there is a widening gap between the exponential growth of protein sequences and their limited function annotations. In our prior studies, we have developed a series of methods including GraphPPIS, GraphSite, LMetalSite and SPROF-GO for protein function annotations at residue or protein level. To further enhance their applicability and performance, we now present GPSFun, a versatile web server for Geometry-aware Protein Sequence Function annotations, which equips our previous tools with language models and geometric deep learning. Specifically, GPSFun employs large language models to efficiently predict 3D conformations of the input protein sequences and extract informative sequence embeddings. Subsequently, geometric graph neural networks are utilized to capture the sequence and structure patterns in the protein graphs, facilitating various downstream predictions including protein-ligand binding sites, gene ontologies, subcellular locations and protein solubility. Notably, GPSFun achieves superior performance to state-of-the-art methods across diverse tasks without requiring multiple sequence alignments or experimental protein structures. GPSFun is freely available to all users at https://bio-web1.nscc-gz.cn/app/GPSFun with user-friendly interfaces and rich visualizations.

DualNetGO: a dual network model for protein function prediction via effective feature selection

MOTIVATION

Protein-protein interaction (PPI) networks are crucial for automatically annotating protein functions. As multiple PPI networks exist for the same set of proteins that capture properties from different aspects, it is a challenging task to effectively utilize these heterogeneous networks. Recently, several deep learning models have combined PPI networks from all evidence, or concatenated all graph embeddings for protein function prediction. However, the lack of a judicious selection procedure prevents the effective harness of information from different PPI networks, as these networks vary in densities, structures, and noise levels. Consequently, combining protein features indiscriminately could increase the noise level, leading to decreased model performance.

RESULTS

We develop DualNetGO, a dual-network model comprised of a Classifier and a Selector, to predict protein functions by effectively selecting features from different sources including graph embeddings of PPI networks, protein domain, and subcellular location information. Evaluation of DualNetGO on human and mouse datasets in comparison with other network-based models shows at least 4.5%, 6.2%, and 14.2% improvement on Fmax in BP, MF, and CC gene ontology categories, respectively, for human, and 3.3%, 10.6%, and 7.7% improvement on Fmax for mouse. We demonstrate the generalization capability of our model by training and testing on the CAFA3 data, and show its versatility by incorporating Esm2 embeddings. We further show that our model is insensitive to the choice of graph embedding method and is time- and memory-saving. These results demonstrate that combining a subset of features including PPI networks and protein attributes selected by our model is more effective in utilizing PPI network information than only using one kind of or concatenating graph embeddings from all kinds of PPI networks.

AVAILABILITY AND IMPLEMENTATION

The source code of DualNetGO and some of the experiment data are available at: https://github.com/georgedashen/DualNetGO.

Best practices for machine learning in antibody discovery and development

In the past 40 years, therapeutic antibody discovery and development have advanced considerably, with machine learning (ML) offering a promising way to speed up the process by reducing costs and the number of experiments required. Recent progress in ML-guided antibody design and development (D&D) has been hindered by the diversity of data sets and evaluation methods, which makes it difficult to conduct comparisons and assess utility. Establishing standards and guidelines will be crucial for the wider adoption of ML and the advancement of the field. This perspective critically reviews current practices, highlights common pitfalls and proposes method development and evaluation guidelines for various ML-based techniques in therapeutic antibody D&D. Addressing challenges across the ML process, best practices are recommended for each stage to enhance reproducibility and progress.

POLAT: Protein function prediction based on soft mask graph network and residue-Label ATtention

MOTIVATION

Elucidating protein function is a central problem in biochemistry, genetics, and molecular biology. Developing computational methods for protein function prediction is critical due to the significant gap between sequence and functional data. Recent advances in protein structure prediction, which strongly correlates with function, make it feasible to use structure to predict function. However, current structure-based methods overlook the fact that individual residues may contribute differently to the protein's function and do not take into account the correlation between protein residues and their functions. The challenge of effectively utilizing the relationship between protein residues and function-level information to predict protein function remains unsolved.

RESULT

We proposed a protein function prediction method based on Soft Mask Graph Networks and Residue-Label Attention (POLAT), which could combine sequence features, predicted structure features, and function-level information to get an accurate prediction. We use soft mask graph networks to adaptively extract the residues relevant to functions. A residue-label attention mechanism is adopted to obtain the protein-level encoded features of a protein, which are then concatenated with a protein-level embedding and fed into a dense classifier to determine the probabilities of each function. POLAT achieves 0.670, 0.515, 0.578 Fmax and 0.677, 0.409, 0.507 AUPR on the PDB cdhit test set for the MFO, BPO, and CCO domains, respectively, outperforming the existing structure-based SOTA method GAT-GO (Fmax 0.633, 0.492, 0.547; AUPR 0.660, 0.381, 0.479). POLAT is also competitive in extensive experiments among sequence-based and multimodal methods and achieves the SOTA performance in three out of six metrics.

A comprehensive review and comparison of existing computational methods for protein function prediction

Protein function prediction is critical for understanding the cellular physiological and biochemical processes, and it opens up new possibilities for advancements in fields such as disease research and drug discovery. During the past decades, with the exponential growth of protein sequence data, many computational methods for predicting protein function have been proposed. Therefore, a systematic review and comparison of these methods are necessary. In this study, we divide these methods into four different categories, including sequence-based methods, 3D structure-based methods, PPI network-based methods and hybrid information-based methods. Furthermore, their advantages and disadvantages are discussed, and then their performance is comprehensively evaluated and compared. Finally, we discuss the challenges and opportunities present in this field.

Predicting Protein Functions Based on Heterogeneous Graph Attention Technique

In bioinformatics, protein function prediction stands as a fundamental area of research and plays a crucial role in addressing various biological challenges, such as the identification of potential targets for drug discovery and the elucidation of disease mechanisms. However, known functional annotation databases usually provide positive experimental annotations that proteins carry out a given function, and rarely record negative experimental annotations that proteins do not carry out a given function. Therefore, existing computational methods based on deep learning models focus on these positive annotations for prediction and ignore these scarce but informative negative annotations, leading to an underestimation of precision. To address this issue, we introduce a deep learning method that utilizes a heterogeneous graph attention technique. The method first constructs a heterogeneous graph that covers the protein-protein interaction network, ontology structure, and positive and negative annotation information. Then, it learns embedding representations of proteins and ontology terms by using the heterogeneous graph attention technique. Finally, it leverages these learned representations to reconstruct the positive protein-term associations and score unobserved functional annotations. It can enhance the predictive performance by incorporating these known limited negative annotations into the constructed heterogeneous graph. Experimental results on three species (i.e., Human, Mouse, and Arabidopsis) demonstrate that our method can achieve better performance in predicting new protein annotations than state-of-the-art methods.

PLMSearch: Protein language model powers accurate and fast sequence search for remote homology

Homologous protein search is one of the most commonly used methods for protein annotation and analysis. Compared to structure search, detecting distant evolutionary relationships from sequences alone remains challenging. Here we propose PLMSearch (Protein Language Model), a homologous protein search method with only sequences as input. PLMSearch uses deep representations from a pre-trained protein language model and trains the similarity prediction model with a large number of real structure similarity. This enables PLMSearch to capture the remote homology information concealed behind the sequences. Extensive experimental results show that PLMSearch can search millions of query-target protein pairs in seconds like MMseqs2 while increasing the sensitivity by more than threefold, and is comparable to state-of-the-art structure search methods. In particular, unlike traditional sequence search methods, PLMSearch can recall most remote homology pairs with dissimilar sequences but similar structures. PLMSearch is freely available at https://dmiip.sjtu.edu.cn/PLMSearch .

DeepSS2GO: protein function prediction from secondary structure

Predicting protein function is crucial for understanding biological life processes, preventing diseases and developing new drug targets. In recent years, methods based on sequence, structure and biological networks for protein function annotation have been extensively researched. Although obtaining a protein in three-dimensional structure through experimental or computational methods enhances the accuracy of function prediction, the sheer volume of proteins sequenced by high-throughput technologies presents a significant challenge. To address this issue, we introduce a deep neural network model DeepSS2GO (Secondary Structure to Gene Ontology). It is a predictor incorporating secondary structure features along with primary sequence and homology information. The algorithm expertly combines the speed of sequence-based information with the accuracy of structure-based features while streamlining the redundant data in primary sequences and bypassing the time-consuming challenges of tertiary structure analysis. The results show that the prediction performance surpasses state-of-the-art algorithms. It has the ability to predict key functions by effectively utilizing secondary structure information, rather than broadly predicting general Gene Ontology terms. Additionally, DeepSS2GO predicts five times faster than advanced algorithms, making it highly applicable to massive sequencing data. The source code and trained models are available at https://github.com/orca233/DeepSS2GO.

GO2Sum: generating human-readable functional summary of proteins from GO terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent a function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

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

MOTIVATION

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.

RESULTS

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.

AVAILABILITY AND IMPLEMENTATION

Source code can be accessed at https://github.com/markuswenzel/xai-proteins.

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.

Artificial intelligence for neurodegenerative experimental models

INTRODUCTION

Experimental models are essential tools in neurodegenerative disease research. However, the translation of insights and drugs discovered in model systems has proven immensely challenging, marred by high failure rates in human clinical trials.

METHODS

Here we review the application of artificial intelligence (AI) and machine learning (ML) in experimental medicine for dementia research.

RESULTS

Considering the specific challenges of reproducibility and translation between other species or model systems and human biology in preclinical dementia research, we highlight best practices and resources that can be leveraged to quantify and evaluate translatability. We then evaluate how AI and ML approaches could be applied to enhance both cross-model reproducibility and translation to human biology, while sustaining biological interpretability.

DISCUSSION

AI and ML approaches in experimental medicine remain in their infancy. However, they have great potential to strengthen preclinical research and translation if based upon adequate, robust, and reproducible experimental data.

HIGHLIGHTS

There are increasing applications of AI in experimental medicine. We identified issues in reproducibility, cross-species translation, and data curation in the field. Our review highlights data resources and AI approaches as solutions. Multi-omics analysis with AI offers exciting future possibilities in drug discovery.

Intelligent Protein Design and Molecular Characterization Techniques: A Comprehensive Review

In recent years, the widespread application of artificial intelligence algorithms in protein structure, function prediction, and de novo protein design has significantly accelerated the process of intelligent protein design and led to many noteworthy achievements. This advancement in protein intelligent design holds great potential to accelerate the development of new drugs, enhance the efficiency of biocatalysts, and even create entirely new biomaterials. Protein characterization is the key to the performance of intelligent protein design. However, there is no consensus on the most suitable characterization method for intelligent protein design tasks. This review describes the methods, characteristics, and representative applications of traditional descriptors, sequence-based and structure-based protein characterization. It discusses their advantages, disadvantages, and scope of application. It is hoped that this could help researchers to better understand the limitations and application scenarios of these methods, and provide valuable references for choosing appropriate protein characterization techniques for related research in the field, so as to better carry out protein research.

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

Domain-PFP allows protein function prediction using function-aware domain embedding representations

Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, substantially outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment.

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

MOTIVATION

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 article 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.

RESULTS

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.

AVAILABILITY AND IMPLEMENTATION

The data underlying this article are available at https://github.com/lyjps/Struct2GO.

CACO: A Core-Attachment Method With Cross-Species Functional Ortholog Information to Detect Human Protein Complexes

Protein complexes play an essential role in living cells. Detecting protein complexes is crucial to understand protein functions and treat complex diseases. Due to high time and resource consumption of experiment approaches, many computational approaches have been proposed to detect protein complexes. However, most of them are only based on protein-protein interaction (PPI) networks, which heavily suffer from the noise in PPI networks. Therefore, we propose a novel core-attachment method, named CACO, to detect human protein complexes, by integrating the functional information from other species via protein ortholog relations. First, CACO constructs a cross-species ortholog relation matrix and transfers GO terms from other species as a reference to evaluate the confidence of PPIs. Then, a PPI filter strategy is adopted to clean the PPI network and thus a weighted clean PPI network is constructed. Finally, a new effective core-attachment algorithm is proposed to detect protein complexes from the weighted PPI network. Compared to other thirteen state-of-the-art methods, CACO outperforms all of them in terms of F-measure and Composite Score, showing that integrating ortholog information and the proposed core-attachment algorithm are effective in detecting protein complexes.

Domain-PFP: Protein Function Prediction Using Function-Aware Domain Embedding Representations

Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, significantly outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment.

Large-scale predicting protein functions through heterogeneous feature fusion

As the volume of protein sequence and structure data grows rapidly, the functions of the overwhelming majority of proteins cannot be experimentally determined. Automated annotation of protein function at a large scale is becoming increasingly important. Existing computational prediction methods are typically based on expanding the relatively small number of experimentally determined functions to large collections of proteins with various clues, including sequence homology, protein-protein interaction, gene co-expression, etc. Although there has been some progress in protein function prediction in recent years, the development of accurate and reliable solutions still has a long way to go. Here we exploit AlphaFold predicted three-dimensional structural information, together with other non-structural clues, to develop a large-scale approach termed PredGO to annotate Gene Ontology (GO) functions for proteins. We use a pre-trained language model, geometric vector perceptrons and attention mechanisms to extract heterogeneous features of proteins and fuse these features for function prediction. The computational results demonstrate that the proposed method outperforms other state-of-the-art approaches for predicting GO functions of proteins in terms of both coverage and accuracy. The improvement of coverage is because the number of structures predicted by AlphaFold is greatly increased, and on the other hand, PredGO can extensively use non-structural information for functional prediction. Moreover, we show that over 205 000 ($\sim $100%) entries in UniProt for human are annotated by PredGO, over 186 000 ($\sim $90%) of which are based on predicted structure. The webserver and database are available at http://predgo.denglab.org/.

Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function

MOTIVATION

Millions of protein sequences have been generated by numerous genome and transcriptome sequencing projects. However, experimentally determining the function of the proteins is still a time consuming, low-throughput, and expensive process, leading to a large protein sequence-function gap. Therefore, it is important to develop computational methods to accurately predict protein function to fill the gap. Even though many methods have been developed to use protein sequences as input to predict function, much fewer methods leverage protein structures in protein function prediction because there was lack of accurate protein structures for most proteins until recently.

RESULTS

We developed TransFun-a method using a transformer-based protein language model and 3D-equivariant graph neural networks to distill information from both protein sequences and structures to predict protein function. It extracts feature embeddings from protein sequences using a pre-trained protein language model (ESM) via transfer learning and combines them with 3D structures of proteins predicted by AlphaFold2 through equivariant graph neural networks. Benchmarked on the CAFA3 test dataset and a new test dataset, TransFun outperforms several state-of-the-art methods, indicating that the language model and 3D-equivariant graph neural networks are effective methods to leverage protein sequences and structures to improve protein function prediction. Combining TransFun predictions and sequence similarity-based predictions can further increase prediction accuracy.

AVAILABILITY AND IMPLEMENTATION

The source code of TransFun is available at https://github.com/jianlin-cheng/TransFun.

MMSMAPlus: a multi-view multi-scale multi-attention embedding model for protein function prediction

Protein is the most important component in organisms and plays an indispensable role in life activities. In recent years, a large number of intelligent methods have been proposed to predict protein function. These methods obtain different types of protein information, including sequence, structure and interaction network. Among them, protein sequences have gained significant attention where methods are investigated to extract the information from different views of features. However, how to fully exploit the views for effective protein sequence analysis remains a challenge. In this regard, we propose a multi-view, multi-scale and multi-attention deep neural model (MMSMA) for protein function prediction. First, MMSMA extracts multi-view features from protein sequences, including one-hot encoding features, evolutionary information features, deep semantic features and overlapping property features based on physiochemistry. Second, a specific multi-scale multi-attention deep network model (MSMA) is built for each view to realize the deep feature learning and preliminary classification. In MSMA, both multi-scale local patterns and long-range dependence from protein sequences can be captured. Third, a multi-view adaptive decision mechanism is developed to make a comprehensive decision based on the classification results of all the views. To further improve the prediction performance, an extended version of MMSMA, MMSMAPlus, is proposed to integrate homology-based protein prediction under the framework of multi-view deep neural model. Experimental results show that the MMSMAPlus has promising performance and is significantly superior to the state-of-the-art methods. The source code can be found at https://github.com/wzy-2020/MMSMAPlus.

CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction

MOTIVATION

Protein function annotation is fundamental to understanding biological mechanisms. The abundant genome-scale protein-protein interaction (PPI) networks, together with other protein biological attributes, provide rich information for annotating protein functions. As PPI networks and biological attributes describe protein functions from different perspectives, it is highly challenging to cross-fuse them for protein function prediction. Recently, several methods combine the PPI networks and protein attributes via the graph neural networks (GNNs). However, GNNs may inherit or even magnify the bias caused by noisy edges in PPI networks. Besides, GNNs with stacking of many layers may cause the over-smoothing problem of node representations.

RESULTS

We develop a novel protein function prediction method, CFAGO, to integrate single-species PPI networks and protein biological attributes via a multi-head attention mechanism. CFAGO is first pre-trained with an encoder-decoder architecture to capture the universal protein representation of the two sources. It is then fine-tuned to learn more effective protein representations for protein function prediction. Benchmark experiments on human and mouse datasets show CFAGO outperforms state-of-the-art single-species network-based methods by at least 7.59%, 6.90%, 11.68% in terms of m-AUPR, M-AUPR, and Fmax, respectively, demonstrating cross-fusion by multi-head attention mechanism can greatly improve the protein function prediction. We further evaluate the quality of captured protein representations in terms of Davies Bouldin Score, whose results show that cross-fused protein representations by multi-head attention mechanism are at least 2.7% better than that of original and concatenated representations. We believe CFAGO is an effective tool for protein function prediction.

AVAILABILITY AND IMPLEMENTATION

The source code of CFAGO and experiments data are available at: http://bliulab.net/CFAGO/.

A systematic review of state-of-the-art strategies for machine learning-based protein function prediction

New drug discovery is inseparable from the discovery of drug targets, and the vast majority of the known targets are proteins. At the same time, proteins are essential structural and functional elements of living cells necessary for the maintenance of all forms of life. Therefore, protein functions have become the focus of many pharmacological and biological studies. Traditional experimental techniques are no longer adequate for rapidly growing annotation of protein sequences, and approaches to protein function prediction using computational methods have emerged and flourished. A significant trend has been to use machine learning to achieve this goal. In this review, approaches to protein function prediction based on the sequence, structure, protein-protein interaction (PPI) networks, and fusion of multi-information sources are discussed. The current status of research on protein function prediction using machine learning is considered, and existing challenges and prominent breakthroughs are discussed to provide ideas and methods for future studies.

Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function

Motivation

Millions of protein sequences have been generated by numerous genome and transcriptome sequencing projects. However, experimentally determining the function of the proteins is still a time consuming, low-throughput, and expensive process, leading to a large protein sequence-function gap. Therefore, it is important to develop computational methods to accurately predict protein function to fill the gap. Even though many methods have been developed to use protein sequences as input to predict function, much fewer methods leverage protein structures in protein function prediction because there was lack of accurate protein structures for most proteins until recently.

Results

We developed TransFun - a method using a transformer-based protein language model and 3D-equivariant graph neural networks to distill information from both protein sequences and structures to predict protein function. It extracts feature embeddings from protein sequences using a pre-trained protein language model (ESM) via transfer learning and combines them with 3D structures of proteins predicted by AlphaFold2 through equivariant graph neural networks. Benchmarked on the CAFA3 test dataset and a new test dataset, TransFun outperforms several state-of-the-art methods, indicating the language model and 3D-equivariant graph neural networks are effective methods to leverage protein sequences and structures to improve protein function prediction. Combining TransFun predictions and sequence similarity-based predictions can further increase prediction accuracy.

Availability

The source code of TransFun is available at https://github.com/jianlin-cheng/TransFun.

Contact

chengji@missouri.edu.

Elucidating the functional roles of prokaryotic proteins using big data and artificial intelligence

Annotating protein sequences according to their biological functions is one of the key steps in understanding microbial diversity, metabolic potentials, and evolutionary histories. However, even in the best-studied prokaryotic genomes, not all proteins can be characterized by classical in vivo, in vitro, and/or in silico methods-a challenge rapidly growing alongside the advent of next-generation sequencing technologies and their enormous extension of 'omics' data in public databases. These so-called hypothetical proteins (HPs) represent a huge knowledge gap and hidden potential for biotechnological applications. Opportunities for leveraging the available 'Big Data' have recently proliferated with the use of artificial intelligence (AI). Here, we review the aims and methods of protein annotation and explain the different principles behind machine and deep learning algorithms including recent research examples, in order to assist both biologists wishing to apply AI tools in developing comprehensive genome annotations and computer scientists who want to contribute to this leading edge of biological research.

Defining the extent of gene function using ROC curvature

MOTIVATION

Interactions between proteins help us understand how genes are functionally related and how they contribute to phenotypes. Experiments provide imperfect 'ground truth' information about a small subset of potential interactions in a specific biological context, which can then be extended to the whole genome across different contexts, such as conditions, tissues or species, through machine learning methods. However, evaluating the performance of these methods remains a critical challenge. Here, we propose to evaluate the generalizability of gene characterizations through the shape of performance curves.

RESULTS

We identify Functional Equivalence Classes (FECs), subsets of annotated and unannotated genes that jointly drive performance, by assessing the presence of straight lines in ROC curves built from gene-centric prediction tasks, such as function or interaction predictions. FECs are widespread across data types and methods, they can be used to evaluate the extent and context-specificity of functional annotations in a data-driven manner. For example, FECs suggest that B cell markers can be decomposed into shared primary markers (10-50 genes), and tissue-specific secondary markers (100-500 genes). In addition, FECs suggest the existence of functional modules that span a wide range of the genome, with marker sets spanning at most 5% of the genome and data-driven extensions of Gene Ontology sets spanning up to 40% of the genome. Simple to assess visually and statistically, the identification of FECs in performance curves paves the way for novel functional characterization and increased robustness in the definition of functional gene sets.

AVAILABILITY AND IMPLEMENTATION

Code for analyses and figures is available at https://github.com/yexilein/pyroc.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Hierarchical deep learning for predicting GO annotations by integrating protein knowledge

MOTIVATION

Experimental testing and manual curation are the most precise ways for assigning Gene Ontology (GO) terms describing protein functions. However, they are expensive, time-consuming and cannot cope with the exponential growth of data generated by high-throughput sequencing methods. Hence, researchers need reliable computational systems to help fill the gap with automatic function prediction. The results of the last Critical Assessment of Function Annotation challenge revealed that GO-terms prediction remains a very challenging task. Recent developments on deep learning are significantly breaking out the frontiers leading to new knowledge in protein research thanks to the integration of data from multiple sources. However, deep models hitherto developed for functional prediction are mainly focused on sequence data and have not achieved breakthrough performances yet.

RESULTS

We propose DeeProtGO, a novel deep-learning model for predicting GO annotations by integrating protein knowledge. DeeProtGO was trained for solving 18 different prediction problems, defined by the three GO sub-ontologies, the type of proteins, and the taxonomic kingdom. Our experiments reported higher prediction quality when more protein knowledge is integrated. We also benchmarked DeeProtGO against state-of-the-art methods on public datasets, and showed it can effectively improve the prediction of GO annotations.

AVAILABILITY AND IMPLEMENTATION

DeeProtGO and a case of use are available at https://github.com/gamerino/DeeProtGO.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

AcneGrader: An ensemble pruning of the deep learning base models to grade acne

BACKGROUND

Acne is one of the most common skin lesions in adolescents. Some severe or inflammatory acne leads to scars, which may have major impacts on patients' quality of life or even job prospects. Grading acne plays an important role in diagnosis, and the diagnosis is made by counting the number of acne. It is a labor-intensive job and it is easy for dermatologists to make mistakes, so it is very important to develop automatic diagnosis methods. Ensemble learning may improve the prediction results of the base models, but its time complexity is relatively high. The ensemble pruning strategy may solve this computational challenge by removing the redundant base models.

MATERIALS AND METHODS

This study proposed a novel ensemble pruning framework of deep learning models to accurately detect and grade acne using images. First, we train multi-base models and prune the redundancy models according to the performance and diversity of the models. Then, we construct the new features of the training data by the base models we select in the previous step. Next, we remove the redundancy models further by a feature selection algorithm. Finally, we integrate all the base models by classifiers. The ensemble pruning algorithm was proposed to prune the deep learning base models.

RESULTS

The experimental data showed that the ensemble pruned framework achieved a prediction accuracy of 85.82% on the acne dataset, better than the existing studies. To verify our method's effectiveness, we test our method in a skin cancer dataset and greatly outperform the state-of-the-art methods.

CONCLUSION

The method we proposed is used to grade acne. Our method's performance outperforms state-of-the-art methods on two datasets, and it can also remove redundancy models to reduce computational complexity.

MGEGFP: a multi-view graph embedding method for gene function prediction based on adaptive estimation with GCN

In recent years, a number of computational approaches have been proposed to effectively integrate multiple heterogeneous biological networks, and have shown impressive performance for inferring gene function. However, the previous methods do not fully represent the critical neighborhood relationship between genes during the feature learning process. Furthermore, it is difficult to accurately estimate the contributions of different views for multi-view integration. In this paper, we propose MGEGFP, a multi-view graph embedding method based on adaptive estimation with Graph Convolutional Network (GCN), to learn high-quality gene representations among multiple interaction networks for function prediction. First, we design a dual-channel GCN encoder to disentangle the view-specific information and the consensus pattern across diverse networks. By the aid of disentangled representations, we develop a multi-gate module to adaptively estimate the contributions of different views during each reconstruction process and make full use of the multiplexity advantages, where a diversity preservation constraint is designed to prevent the over-fitting problem. To validate the effectiveness of our model, we conduct experiments on networks from the STRING database for both yeast and human datasets, and compare the performance with seven state-of-the-art methods in five evaluation metrics. Moreover, the ablation study manifests the important contribution of the designed dual-channel encoder, multi-gate module and the diversity preservation constraint in MGEGFP. The experimental results confirm the superiority of our proposed method and suggest that MGEGFP can be a useful tool for gene function prediction.

A field study to estimate heavy metal concentrations in a soil-rice system: Application of graph neural networks

Accurate prediction of the concentration of heavy metals is of great significance for assessing the quality of agricultural products and reducing health risks. However, the complexity and interconnectivity of the farmland ecosystem restricts the improvement of the prediction accuracy of traditional methods. This research explored the application potential of graph neural network (GNN) technology, which can extract and learn information in large-scale networks in detail, in the field of heavy metal prediction for the first time. In this study, a heavy metal prediction model for rice, CoNet-GNN, was proposed with 17 environmental factors as input variables using the co-occurrence network and GNN. Experimental results using a dataset from a field study showed that the R² of CoNet-GNN for predicting Cd, Pb, Cr, As, and Hg had outstanding values of 0.872, 0.711, 0.683, 0.489, and 0.824, respectively. Sensitivity analysis further indicated that CoNet-GNN had good stability and robustness. Compared with random forest, gradient boosting, and multilayer perceptron, CoNet-GNN made a remarkable improvement to the prediction accuracy of all studied heavy metals. Therefore, CoNet-GNN can effectively simulate the rich relationships and laws between various factors in the soil-rice system and effectively characterize the influence diffusion path. Furthermore, it provides new ideas for heavy metal prediction based on network research methods and expands the technical scope of heavy metal evaluation.