The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens

Improving the enzymatic activity and stability of N-carbamoyl hydrolase using deep learning approach

BACKGROUND

Optically active D-amino acids are widely used as intermediates in the synthesis of antibiotics, insecticides, and peptide hormones. Currently, the two-enzyme cascade reaction is the most efficient way to produce D-amino acids using enzymes DHdt and DCase, but DCase is susceptible to heat inactivation. Here, to enhance the enzymatic activity and thermal stability of DCase, a rational design software "Feitian" was developed based on kcat prediction using the deep learning approach.

RESULTS

According to empirical design and prediction of "Feitian" software, six single-point mutants with high kcat value were selected and successfully constructed by site-directed mutagenesis. Out of six, three mutants (Q4C, T212S, and A302C) showed higher enzymatic activity than the wild-type. Furthermore, the combined triple-point mutant DCase-M3 (Q4C/T212S/A302C) exhibited a 4.25-fold increase in activity (29.77 ± 4.52 U) and a 2.25-fold increase in thermal stability as compared to the wild-type, respectively. Through the whole-cell reaction, the high titer of D-HPG (2.57 ± 0.43 mM) was produced by the mutant Q4C/T212S/A302C, which was about 2.04-fold of the wild-type. Molecular dynamics simulation results showed that DCase-M3 significantly enhances the rigidity of the catalytic site and thus increases the activity of DCase-M3.

CONCLUSIONS

In this study, an efficient rational design software "Feitian" was successfully developed with a prediction accuracy of about 50% in enzymatic activity. A triple-point mutant DCase-M3 (Q4C/T212S/A302C) with enhanced enzymatic activity and thermostability was successfully obtained, which could be applied to the development of a fully enzymatic process for the industrial production of D-HPG.

Low-frequency ERK and Akt activity dynamics are predictive of stochastic cell division events

Understanding the dynamics of intracellular signaling pathways, such as ERK1/2 (ERK) and Akt1/2 (Akt), in the context of cell fate decisions is important for advancing our knowledge of cellular processes and diseases, particularly cancer. While previous studies have established associations between ERK and Akt activities and proliferative cell fate, the heterogeneity of single-cell responses adds complexity to this understanding. This study employed a data-driven approach to address this challenge, developing machine learning models trained on a dataset of growth factor-induced ERK and Akt activity time courses in single cells, to predict cell division events. The most predictive models were developed by applying discrete wavelet transforms (DWTs) to extract low-frequency features from the time courses, followed by using Ensemble Integration, a data integration and predictive modeling framework. The results demonstrated that these models effectively predicted cell division events in MCF10A cells (F-measure=0.524, AUC=0.726). ERK dynamics were found to be more predictive than Akt, but the combination of both measurements further enhanced predictive performance. The ERK model`s performance also generalized to predicting division events in RPE cells, indicating the potential applicability of these models and our data-driven methodology for predicting cell division across different biological contexts. Interpretation of these models suggested that ERK dynamics throughout the cell cycle, rather than immediately after growth factor stimulation, were associated with the likelihood of cell division. Overall, this work contributes insights into the predictive power of intra-cellular signaling dynamics for cell fate decisions, and highlights the potential of machine learning approaches in unraveling complex cellular behaviors.

SAFPred: synteny-aware gene function prediction for bacteria using protein embeddings

MOTIVATION

Today, we know the function of only a small fraction of the protein sequences predicted from genomic data. This problem is even more salient for bacteria, which represent some of the most phylogenetically and metabolically diverse taxa on Earth. This low rate of bacterial gene annotation is compounded by the fact that most function prediction algorithms have focused on eukaryotes, and conventional annotation approaches rely on the presence of similar sequences in existing databases. However, often there are no such sequences for novel bacterial proteins. Thus, we need improved gene function prediction methods tailored for bacteria. Recently, transformer-based language models-adopted from the natural language processing field-have been used to obtain new representations of proteins, to replace amino acid sequences. These representations, referred to as protein embeddings, have shown promise for improving annotation of eukaryotes, but there have been only limited applications on bacterial genomes.

RESULTS

To predict gene functions in bacteria, we developed SAFPred, a novel synteny-aware gene function prediction tool based on protein embeddings from state-of-the-art protein language models. SAFpred also leverages the unique operon structure of bacteria through conserved synteny. SAFPred outperformed both conventional sequence-based annotation methods and state-of-the-art methods on multiple bacterial species, including for distant homolog detection, where the sequence similarity to the proteins in the training set was as low as 40%. Using SAFPred to identify gene functions across diverse enterococci, of which some species are major clinical threats, we identified 11 previously unrecognized putative novel toxins, with potential significance to human and animal health.

AVAILABILITY AND IMPLEMENTATION

https://github.com/AbeelLab/safpred.

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.

Mutual annotation-based prediction of protein domain functions with Domain2GO

Identifying unknown functional properties of proteins is essential for understanding their roles in both health and disease states. The domain composition of a protein can reveal critical information in this context, as domains are structural and functional units that dictate how the protein should act at the molecular level. The expensive and time-consuming nature of wet-lab experimental approaches prompted researchers to develop computational strategies for predicting the functions of proteins. In this study, we proposed a new method called Domain2GO that infers associations between protein domains and function-defining gene ontology (GO) terms, thus redefining the problem as domain function prediction. Domain2GO uses documented protein-level GO annotations together with proteins' domain annotations. Co-annotation patterns of domains and GO terms in the same proteins are examined using statistical resampling to obtain reliable associations. As a use-case study, we evaluated the biological relevance of examples selected from the Domain2GO-generated domain-GO term mappings via literature review. Then, we applied Domain2GO to predict unknown protein functions by propagating domain-associated GO terms to proteins annotated with these domains. For function prediction performance evaluation and comparison against other methods, we employed Critical Assessment of Function Annotation 3 (CAFA3) challenge datasets. The results demonstrated the high potential of Domain2GO, particularly for predicting molecular function and biological process terms, along with advantages such as producing interpretable results and having an exceptionally low computational cost. The approach presented here can be extended to other ontologies and biological entities to investigate unknown relationships in complex and large-scale biological data. The source code, datasets, results, and user instructions for Domain2GO are available at https://github.com/HUBioDataLab/Domain2GO. Additionally, we offer a user-friendly online tool at https://huggingface.co/spaces/HUBioDataLab/Domain2GO, which simplifies the prediction of functions of previously unannotated proteins solely using amino acid sequences.

Automated annotation of disease subtypes

BACKGROUND

Distinguishing diseases into distinct subtypes is crucial for study and effective treatment strategies. The Open Targets Platform (OT) integrates biomedical, genetic, and biochemical datasets to empower disease ontologies, classifications, and potential gene targets. Nevertheless, many disease annotations are incomplete, requiring laborious expert medical input. This challenge is especially pronounced for rare and orphan diseases, where resources are scarce.

METHODS

We present a machine learning approach to identifying diseases with potential subtypes, using the approximately 23,000 diseases documented in OT. We derive novel features for predicting diseases with subtypes using direct evidence. Machine learning models were applied to analyze feature importance and evaluate predictive performance for discovering both known and novel disease subtypes.

RESULTS

Our model achieves a high (89.4%) ROC AUC (Area Under the Receiver Operating Characteristic Curve) in identifying known disease subtypes. We integrated pre-trained deep-learning language models and showed their benefits. Moreover, we identify 515 disease candidates predicted to possess previously unannotated subtypes.

CONCLUSIONS

Our models can partition diseases into distinct subtypes. This methodology enables a robust, scalable approach for improving knowledge-based annotations and a comprehensive assessment of disease ontology tiers. Our candidates are attractive targets for further study and personalized medicine, potentially aiding in the unveiling of new therapeutic indications for sought-after targets.

Leveraging conformal prediction to annotate enzyme function space with limited false positives

Machine learning (ML) is increasingly being used to guide biological discovery in biomedicine such as prioritizing promising small molecules in drug discovery. In those applications, ML models are used to predict the properties of biological systems, and researchers use these predictions to prioritize candidates as new biological hypotheses for downstream experimental validations. However, when applied to unseen situations, these models can be overconfident and produce a large number of false positives. One solution to address this issue is to quantify the model's prediction uncertainty and provide a set of hypotheses with a controlled false discovery rate (FDR) pre-specified by researchers. We propose CPEC, an ML framework for FDR-controlled biological discovery. We demonstrate its effectiveness using enzyme function annotation as a case study, simulating the discovery process of identifying the functions of less-characterized enzymes. CPEC integrates a deep learning model with a statistical tool known as conformal prediction, providing accurate and FDR-controlled function predictions for a given protein enzyme. Conformal prediction provides rigorous statistical guarantees to the predictive model and ensures that the expected FDR will not exceed a user-specified level with high probability. Evaluation experiments show that CPEC achieves reliable FDR control, better or comparable prediction performance at a lower FDR than existing methods, and accurate predictions for enzymes under-represented in the training data. We expect CPEC to be a useful tool for biological discovery applications where a high yield rate in validation experiments is desired but the experimental budget is limited.

Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learning

MOTIVATION

Whole-exome and genome sequencing have become common tools in diagnosing patients with rare diseases. Despite their success, this approach leaves many patients undiagnosed. A common argument is that more disease variants still await discovery, or the novelty of disease phenotypes results from a combination of variants in multiple disease-related genes. Interpreting the phenotypic consequences of genomic variants relies on information about gene functions, gene expression, physiology, and other genomic features. Phenotype-based methods to identify variants involved in genetic diseases combine molecular features with prior knowledge about the phenotypic consequences of altering gene functions. While phenotype-based methods have been successfully applied to prioritizing variants, such methods are based on known gene-disease or gene-phenotype associations as training data and are applicable to genes that have phenotypes associated, thereby limiting their scope. In addition, phenotypes are not assigned uniformly by different clinicians, and phenotype-based methods need to account for this variability.

RESULTS

We developed an Embedding-based Phenotype Variant Predictor (EmbedPVP), a computational method to prioritize variants involved in genetic diseases by combining genomic information and clinical phenotypes. EmbedPVP leverages a large amount of background knowledge from human and model organisms about molecular mechanisms through which abnormal phenotypes may arise. Specifically, EmbedPVP incorporates phenotypes linked to genes, functions of gene products, and the anatomical site of gene expression, and systematically relates them to their phenotypic effects through neuro-symbolic, knowledge-enhanced machine learning. We demonstrate EmbedPVP's efficacy on a large set of synthetic genomes and genomes matched with clinical information.

AVAILABILITY AND IMPLEMENTATION

EmbedPVP and all evaluation experiments are freely available at https://github.com/bio-ontology-research-group/EmbedPVP.

Protein function prediction through multi-view multi-label latent tensor reconstruction

BACKGROUND

In last two decades, the use of high-throughput sequencing technologies has accelerated the pace of discovery of proteins. However, due to the time and resource limitations of rigorous experimental functional characterization, the functions of a vast majority of them remain unknown. As a result, computational methods offering accurate, fast and large-scale assignment of functions to new and previously unannotated proteins are sought after. Leveraging the underlying associations between the multiplicity of features that describe proteins could reveal functional insights into the diverse roles of proteins and improve performance on the automatic function prediction task.

RESULTS

We present GO-LTR, a multi-view multi-label prediction model that relies on a high-order tensor approximation of model weights combined with non-linear activation functions. The model is capable of learning high-order relationships between multiple input views representing the proteins and predicting high-dimensional multi-label output consisting of protein functional categories. We demonstrate the competitiveness of our method on various performance measures. Experiments show that GO-LTR learns polynomial combinations between different protein features, resulting in improved performance. Additional investigations establish GO-LTR's practical potential in assigning functions to proteins under diverse challenging scenarios: very low sequence similarity to previously observed sequences, rarely observed and highly specific terms in the gene ontology.

IMPLEMENTATION

The code and data used for training GO-LTR is available at https://github.com/aalto-ics-kepaco/GO-LTR-prediction .

Exploring salt tolerance mechanisms using machine learning for transcriptomic insights: case study in Spartina alterniflora

Salt stress poses a significant threat to global cereal crop production, emphasizing the need for a comprehensive understanding of salt tolerance mechanisms. Accurate functional annotations of differentially expressed genes are crucial for gaining insights into the salt tolerance mechanism. The challenge of predicting gene functions in under-studied species, especially when excluding infrequent GO terms, persists. Therefore, we proposed the use of NetGO 3.0, a machine learning-based annotation method that does not rely on homology information between species, to predict the functions of differentially expressed genes under salt stress. Spartina alterniflora, a halophyte with salt glands, exhibits remarkable salt tolerance, making it an excellent candidate for in-depth transcriptomic analysis. However, current research on the S. alterniflora transcriptome under salt stress is limited. In this study we used S. alterniflora as an example to investigate its transcriptional responses to various salt concentrations, with a focus on understanding its salt tolerance mechanisms. Transcriptomic analysis revealed substantial changes impacting key pathways, such as gene transcription, ion transport, and ROS metabolism. Notably, we identified a member of the SWEET gene family in S. alterniflora, SA_12G129900.m1, showing convergent selection with the rice ortholog SWEET15. Additionally, our genome-wide analyses explored alternative splicing responses to salt stress, providing insights into the parallel functions of alternative splicing and transcriptional regulation in enhancing salt tolerance in S. alterniflora. Surprisingly, there was minimal overlap between differentially expressed and differentially spliced genes following salt exposure. This innovative approach, combining transcriptomic analysis with machine learning-based annotation, avoids the reliance on homology information and facilitates the discovery of unknown gene functions, and is applicable across all sequenced species.

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.

Multi-Omics integration can be used to rescue metabolic information for some of the dark region of the Pseudomonas putida proteome

In every omics experiment, genes or their products are identified for which even state of the art tools are unable to assign a function. In the biotechnology chassis organism Pseudomonas putida, these proteins of unknown function make up 14% of the proteome. This missing information can bias analyses since these proteins can carry out functions which impact the engineering of organisms. As a consequence of predicting protein function across all organisms, function prediction tools generally fail to use all of the types of data available for any specific organism, including protein and transcript expression information. Additionally, the release of Alphafold predictions for all Uniprot proteins provides a novel opportunity for leveraging structural information. We constructed a bespoke machine learning model to predict the function of recalcitrant proteins of unknown function in Pseudomonas putida based on these sources of data, which annotated 1079 terms to 213 proteins. Among the predicted functions supplied by the model, we found evidence for a significant overrepresentation of nitrogen metabolism and macromolecule processing proteins. These findings were corroborated by manual analyses of selected proteins which identified, among others, a functionally unannotated operon that likely encodes a branch of the shikimate pathway.

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.

Protein homeostasis imprinting across evolution

Protein homeostasis (a.k.a. proteostasis) is associated with the primary functions of life, and therefore with evolution. However, it is unclear how cellular proteostasis machines have evolved to adjust protein biogenesis needs to environmental constraints. Herein, we describe a novel computational approach, based on semantic network analysis, to evaluate proteostasis plasticity during evolution. We show that the molecular components of the proteostasis network (PN) are reliable metrics to deconvolute the life forms into Archaea, Bacteria and Eukarya and to assess the evolution rates among species. Semantic graphs were used as new criteria to evaluate PN complexity in 93 Eukarya, 250 Bacteria and 62 Archaea, thus representing a novel strategy for taxonomic classification, which provided information about species divergence. Kingdom-specific PN components were identified, suggesting that PN complexity may correlate with evolution. We found that the gains that occurred throughout PN evolution revealed a dichotomy within both the PN conserved modules and within kingdom-specific modules. Additionally, many of these components contribute to the evolutionary imprinting of other conserved mechanisms. Finally, the current study suggests a new way to exploit the genomic annotation of biomedical ontologies, deriving new knowledge from the semantic comparison of different biological systems.

AnnoPRO: a strategy for protein function annotation based on multi-scale protein representation and a hybrid deep learning of dual-path encoding

Protein function annotation has been one of the longstanding issues in biological sciences, and various computational methods have been developed. However, the existing methods suffer from a serious long-tail problem, with a large number of GO families containing few annotated proteins. Herein, an innovative strategy named AnnoPRO was therefore constructed by enabling sequence-based multi-scale protein representation, dual-path protein encoding using pre-training, and function annotation by long short-term memory-based decoding. A variety of case studies based on different benchmarks were conducted, which confirmed the superior performance of AnnoPRO among available methods. Source code and models have been made freely available at: https://github.com/idrblab/AnnoPRO and https://zenodo.org/records/10012272.

FunPredCATH: An ensemble method for predicting protein function using CATH

MOTIVATION

The growth of unannotated proteins in UniProt increases at a very high rate every year due to more efficient sequencing methods. However, the experimental annotation of proteins is a lengthy and expensive process. Using computational techniques to narrow the search can speed up the process by providing highly specific Gene Ontology (GO) terms.

METHODOLOGY

We propose an ensemble approach that combines three generic base predictors that predict Gene Ontology (BP, CC and MF) terms from sequences across different species. We train our models on UniProtGOA annotation data and use the CATH domain resources to identify the protein families. We then calculate a score based on the prevalence of individual GO terms in the functional families that is then used as an indicator of confidence when assigning the GO term to an uncharacterised protein.

METHODS

In the ensemble, we use a statistics-based method that scores the occurrence of GO terms in a CATH FunFam against a background set of proteins annotated by the same GO term. We also developed a set-based method that uses Set Intersection and Set Union to score the occurrence of GO terms within the same CATH FunFam. Finally, we also use FunFams-Plus, a predictor method developed by the Orengo Group at UCL to predict GO terms for uncharacterised proteins in the CAFA3 challenge.

EVALUATION

We evaluated the methods against the CAFA3 benchmark and DomFun. We used the Precision, Recall and Fmax metrics and the benchmark datasets that are used in CAFA3 to evaluate our models and compare them to the CAFA3 results. Our results show that FunPredCATH compares well with top CAFA methods in the different ontologies and benchmarks.

CONTRIBUTIONS

FunPredCATH compares well with other prediction methods on CAFA3, and the ensemble approach outperforms the base methods. We show that non-IEA models obtain higher Fmax scores than the IEA counterparts, while the models including IEA annotations have higher coverage at the expense of a lower Fmax score.

CryptoCEN: A Co-Expression Network for Cryptococcus neoformans reveals novel proteins involved in DNA damage repair

Elucidating gene function is a major goal in biology, especially among non-model organisms. However, doing so is complicated by the fact that molecular conservation does not always mirror functional conservation, and that complex relationships among genes are responsible for encoding pathways and higher-order biological processes. Co-expression, a promising approach for predicting gene function, relies on the general principal that genes with similar expression patterns across multiple conditions will likely be involved in the same biological process. For Cryptococcus neoformans, a prevalent human fungal pathogen greatly diverged from model yeasts, approximately 60% of the predicted genes in the genome lack functional annotations. Here, we leveraged a large amount of publicly available transcriptomic data to generate a C. neoformans Co-Expression Network (CryptoCEN), successfully recapitulating known protein networks, predicting gene function, and enabling insights into the principles influencing co-expression. With 100% predictive accuracy, we used CryptoCEN to identify 13 new DNA damage response genes, underscoring the utility of guilt-by-association for determining gene function. Overall, co-expression is a powerful tool for uncovering gene function, and decreases the experimental tests needed to identify functions for currently under-annotated genes.

Numerical stability of DeepGOPlus inference

Convolutional neural networks (CNNs) are currently among the most widely-used deep neural network (DNN) architectures available and achieve state-of-the-art performance for many problems. Originally applied to computer vision tasks, CNNs work well with any data with a spatial relationship, besides images, and have been applied to different fields. However, recent works have highlighted numerical stability challenges in DNNs, which also relates to their known sensitivity to noise injection. These challenges can jeopardise their performance and reliability. This paper investigates DeepGOPlus, a CNN that predicts protein function. DeepGOPlus has achieved state-of-the-art performance and can successfully take advantage and annotate the abounding protein sequences emerging in proteomics. We determine the numerical stability of the model's inference stage by quantifying the numerical uncertainty resulting from perturbations of the underlying floating-point data. In addition, we explore the opportunity to use reduced-precision floating point formats for DeepGOPlus inference, to reduce memory consumption and latency. This is achieved by instrumenting DeepGOPlus' execution using Monte Carlo Arithmetic, a technique that experimentally quantifies floating point operation errors and VPREC, a tool that emulates results with customizable floating point precision formats. Focus is placed on the inference stage as it is the primary deliverable of the DeepGOPlus model, widely applicable across different environments. All in all, our results show that although the DeepGOPlus CNN is very stable numerically, it can only be selectively implemented with lower-precision floating-point formats. We conclude that predictions obtained from the pre-trained DeepGOPlus model are very reliable numerically, and use existing floating-point formats efficiently.

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.

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.

Host-guest systems for the SAMPL9 blinded prediction challenge: phenothiazine as a privileged scaffold for binding to cyclodextrins

Model systems are widely used in biology and chemistry to gain insight into more complex systems. In the field of computational chemistry, researchers use host-guest systems, relatively simple exemplars of noncovalent binding, to train and test the computational methods used in drug discovery. Indeed, host-guest systems have been developed to support the community-wide blinded SAMPL prediction challenges for over a decade. While seeking new host-guest systems for the recent SAMPL9 binding prediction challenge, which is the focus of the present PCCP Themed Collection, we identified phenothiazine as a privileged scaffold for guests of β cyclodextrin (βCD) and its derivatives. Building on this observation, we used calorimetry and NMR spectroscopy to characterize the noncovalent association of native βCD and three methylated derivatives of βCD with five phenothiazine drugs. The strongest association observed, that of thioridazine and one of the methyl derivatives, exceeds the well-known high affinity of rimantidine with βCD. Intriguingly, however, methylation of βCD at the 3 position abolished detectible binding for all of the drugs studied. The dataset has a clear pattern of entropy-enthalpy compensation. The NMR data show that all of the drugs position at least one aromatic proton at the secondary face of the CD, and most also show evidence of deep penetration of the binding site. The results of this study were used in the SAMPL9 blinded binding affinity-prediction challenge, which are detailed in accompanying papers of the present Themed Collection. These data also open the phenothiazines and, potentially, chemically similar drugs, such as the tricyclic antidepressants, as relatively potent binders of βCD, setting the stage for future SAMPL challenge datasets and for possible applications as drug reversal agents.

DisProt in 2024: improving function annotation of intrinsically disordered proteins

DisProt (URL: https://disprot.org) is the gold standard database for intrinsically disordered proteins and regions, providing valuable information about their functions. The latest version of DisProt brings significant advancements, including a broader representation of functions and an enhanced curation process. These improvements aim to increase both the quality of annotations and their coverage at the sequence level. Higher coverage has been achieved by adopting additional evidence codes. Quality of annotations has been improved by systematically applying Minimum Information About Disorder Experiments (MIADE) principles and reporting all the details of the experimental setup that could potentially influence the structural state of a protein. The DisProt database now includes new thematic datasets and has expanded the adoption of Gene Ontology terms, resulting in an extensive functional repertoire which is automatically propagated to UniProtKB. Finally, we show that DisProt's curated annotations strongly correlate with disorder predictions inferred from AlphaFold2 pLDDT (predicted Local Distance Difference Test) confidence scores. This comparison highlights the utility of DisProt in explaining apparent uncertainty of certain well-defined predicted structures, which often correspond to folding-upon-binding fragments. Overall, DisProt serves as a comprehensive resource, combining experimental evidence of disorder information to enhance our understanding of intrinsically disordered proteins and their functional implications.

Evaluation of crowdsourced mortality prediction models as a framework for assessing artificial intelligence in medicine

OBJECTIVE

Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question.

MATERIALS AND METHODS

Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system.

RESULTS

The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort.

DISCUSSION

Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data.

CONCLUSION

This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction

Predicting the effects of mutations in proteins is critical to many applications, from understanding genetic disease to designing novel proteins that can address our most pressing challenges in climate, agriculture and healthcare. Despite a surge in machine learning-based protein models to tackle these questions, an assessment of their respective benefits is challenging due to the use of distinct, often contrived, experimental datasets, and the variable performance of models across different protein families. Addressing these challenges requires scale. To that end we introduce ProteinGym, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design. It encompasses both a broad collection of over 250 standardized deep mutational scanning assays, spanning millions of mutated sequences, as well as curated clinical datasets providing high-quality expert annotations about mutation effects. We devise a robust evaluation framework that combines metrics for both fitness prediction and design, factors in known limitations of the underlying experimental methods, and covers both zero-shot and supervised settings. We report the performance of a diverse set of over 70 high-performing models from various subfields (eg., alignment-based, inverse folding) into a unified benchmark suite. We open source the corresponding codebase, datasets, MSAs, structures, model predictions and develop a user-friendly website that facilitates data access and analysis.

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.

A Comparative Analysis of the Protein Cargo of Extracellular Vesicles from Helminth Parasites

Helminth parasites cause debilitating-sometimes fatal-diseases in humans and animals. Despite their impact on global health, mechanisms underlying host-parasite interactions are still poorly understood. One such mechanism involves the exchange of extracellular vesicles (EVs), which are membrane-enclosed subcellular nanoparticles. To date, EV secretion has been studied in helminth parasites, including EV protein content. However, information is highly heterogeneous, since it was generated in multiple species, using varied protocols for EV isolation and data analysis. Here, we compared the protein cargo of helminth EVs to identify common markers for each taxon. For this, we integrated published proteomic data and performed a comparative analysis through an orthology approach. Overall, only three proteins were common in the EVs of the seven analyzed species. Additionally, varied repertoires of proteins with moonlighting activity, vaccine antigens, canonical and non-canonical proteins related to EV biogenesis, taxon-specific proteins of unknown function and RNA-binding proteins were observed in platyhelminth and nematode EVs. Despite the lack of consensus on EV isolation protocols and protein annotation, several proteins were shown to be consistently detected in EV preparations from organisms at different taxa levels, providing a starting point for a selective biochemical characterization.

Enzyme function and evolution through the lens of bioinformatics

Enzymes have been shaped by evolution over billions of years to catalyse the chemical reactions that support life on earth. Dispersed in the literature, or organised in online databases, knowledge about enzymes can be structured in distinct dimensions, either related to their quality as biological macromolecules, such as their sequence and structure, or related to their chemical functions, such as the catalytic site, kinetics, mechanism, and overall reaction. The evolution of enzymes can only be understood when each of these dimensions is considered. In addition, many of the properties of enzymes only make sense in the light of evolution. We start this review by outlining the main paradigms of enzyme evolution, including gene duplication and divergence, convergent evolution, and evolution by recombination of domains. In the second part, we overview the current collective knowledge about enzymes, as organised by different types of data and collected in several databases. We also highlight some increasingly powerful computational tools that can be used to close gaps in understanding, in particular for types of data that require laborious experimental protocols. We believe that recent advances in protein structure prediction will be a powerful catalyst for the prediction of binding, mechanism, and ultimately, chemical reactions. A comprehensive mapping of enzyme function and evolution may be attainable in the near future.

Learning sequence, structure, and function representations of proteins with language models

The sequence-structure-function relationships that ultimately generate the diversity of extant observed proteins is complex, as proteins bridge the gap between multiple informational and physical scales involved in nearly all cellular processes. One limitation of existing protein annotation databases such as UniProt is that less than 1% of proteins have experimentally verified functions, and computational methods are needed to fill in the missing information. Here, we demonstrate that a multi-aspect framework based on protein language models can learn sequence-structure-function representations of amino acid sequences, and can provide the foundation for sensitive sequence-structure-function aware protein sequence search and annotation. Based on this model, we introduce a multi-aspect information retrieval system for proteins, Protein-Vec, covering sequence, structure, and function aspects, that enables computational protein annotation and function prediction at tree-of-life scales.

SAP: Synteny-aware gene function prediction for bacteria using protein embeddings

Motivation

Today, we know the function of only a small fraction of the protein sequences predicted from genomic data. This problem is even more salient for bacteria, which represent some of the most phylogenetically and metabolically diverse taxa on Earth. This low rate of bacterial gene annotation is compounded by the fact that most function prediction algorithms have focused on eukaryotes, and conventional annotation approaches rely on the presence of similar sequences in existing databases. However, often there are no such sequences for novel bacterial proteins. Thus, we need improved gene function prediction methods tailored for prokaryotes. Recently, transformer-based language models - adopted from the natural language processing field - have been used to obtain new representations of proteins, to replace amino acid sequences. These representations, referred to as protein embeddings, have shown promise for improving annotation of eukaryotes, but there have been only limited applications on bacterial genomes.

Results

To predict gene functions in bacteria, we developed SAP, a novel synteny-aware gene function prediction tool based on protein embeddings from state-of-the-art protein language models. SAP also leverages the unique operon structure of bacteria through conserved synteny. SAP outperformed both conventional sequence-based annotation methods and state-of-the-art methods on multiple bacterial species, including for distant homolog detection, where the sequence similarity to the proteins in the training set was as low as 40%. Using SAP to identify gene functions across diverse enterococci, of which some species are major clinical threats, we identified 11 previously unrecognized putative novel toxins, with potential significance to human and animal health.

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.

Predicting enzymatic function of protein sequences with attention

MOTIVATION

There is a growing number of available protein sequences, but only a limited amount has been manually annotated. For example, only 0.25% of all entries of UniProtKB are reviewed by human annotators. Further developing automatic tools to infer protein function from sequence alone can alleviate part of this gap. In this article, we investigate the potential of Transformer deep neural networks on a specific case of functional sequence annotation: the prediction of enzymatic classes.

RESULTS

We show that our EnzBert transformer models, trained to predict Enzyme Commission (EC) numbers by specialization of a protein language model, outperforms state-of-the-art tools for monofunctional enzyme class prediction based on sequences only. Accuracy is improved from 84% to 95% on the prediction of EC numbers at level two on the EC40 benchmark. To evaluate the prediction quality at level four, the most detailed level of EC numbers, we built two new time-based benchmarks for comparison with state-of-the-art methods ECPred and DeepEC: the macro-F1 score is respectively improved from 41% to 54% and from 20% to 26%. Finally, we also show that using a simple combination of attention maps is on par with, or better than, other classical interpretability methods on the EC prediction task. More specifically, important residues identified by attention maps tend to correspond to known catalytic sites. Quantitatively, we report a max F-Gain score of 96.05%, while classical interpretability methods reach 91.44% at best.

AVAILABILITY AND IMPLEMENTATION

Source code and datasets are respectively available at https://gitlab.inria.fr/nbuton/tfpc and https://doi.org/10.5281/zenodo.7253910.

Broad functional profiling of fission yeast proteins using phenomics and machine learning

Many proteins remain poorly characterized even in well-studied organisms, presenting a bottleneck for research. We applied phenomics and machine-learning approaches with Schizosaccharomyces pombe for broad cues on protein functions. We assayed colony-growth phenotypes to measure the fitness of deletion mutants for 3509 non-essential genes in 131 conditions with different nutrients, drugs, and stresses. These analyses exposed phenotypes for 3492 mutants, including 124 mutants of 'priority unstudied' proteins conserved in humans, providing varied functional clues. For example, over 900 proteins were newly implicated in the resistance to oxidative stress. Phenotype-correlation networks suggested roles for poorly characterized proteins through 'guilt by association' with known proteins. For complementary functional insights, we predicted Gene Ontology (GO) terms using machine learning methods exploiting protein-network and protein-homology data (NET-FF). We obtained 56,594 high-scoring GO predictions, of which 22,060 also featured high information content. Our phenotype-correlation data and NET-FF predictions showed a strong concordance with existing PomBase GO annotations and protein networks, with integrated analyses revealing 1675 novel GO predictions for 783 genes, including 47 predictions for 23 priority unstudied proteins. Experimental validation identified new proteins involved in cellular aging, showing that these predictions and phenomics data provide a rich resource to uncover new protein functions.

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.

HiFun: homology independent protein function prediction by a novel protein-language self-attention model

Protein function prediction based on amino acid sequence alone is an extremely challenging but important task, especially in metagenomics/metatranscriptomics field, in which novel proteins have been uncovered exponentially from new microorganisms. Many of them are extremely low homology to known proteins and cannot be annotated with homology-based or information integrative methods. To overcome this problem, we proposed a Homology Independent protein Function annotation method (HiFun) based on a unified deep-learning model by reassembling the sequence as protein language. The robustness of HiFun was evaluated using the benchmark datasets and metrics in the CAFA3 challenge. To navigate the utility of HiFun, we annotated 2 212 663 unknown proteins and discovered novel motifs in the UHGP-50 catalog. We proved that HiFun can extract latent function related structure features which empowers it ability to achieve function annotation for non-homology proteins. HiFun can substantially improve newly proteins annotation and expand our understanding of microorganisms' adaptation in various ecological niches. Moreover, we provided a free and accessible webservice at http://www.unimd.org/HiFun, requiring only protein sequences as input, offering researchers an efficient and practical platform for predicting protein functions.

Projecting genetic associations through gene expression patterns highlights disease etiology and drug mechanisms

Genes act in concert with each other in specific contexts to perform their functions. Determining how these genes influence complex traits requires a mechanistic understanding of expression regulation across different conditions. It has been shown that this insight is critical for developing new therapies. Transcriptome-wide association studies have helped uncover the role of individual genes in disease-relevant mechanisms. However, modern models of the architecture of complex traits predict that gene-gene interactions play a crucial role in disease origin and progression. Here we introduce PhenoPLIER, a computational approach that maps gene-trait associations and pharmacological perturbation data into a common latent representation for a joint analysis. This representation is based on modules of genes with similar expression patterns across the same conditions. We observe that diseases are significantly associated with gene modules expressed in relevant cell types, and our approach is accurate in predicting known drug-disease pairs and inferring mechanisms of action. Furthermore, using a CRISPR screen to analyze lipid regulation, we find that functionally important players lack associations but are prioritized in trait-associated modules by PhenoPLIER. By incorporating groups of co-expressed genes, PhenoPLIER can contextualize genetic associations and reveal potential targets missed by single-gene strategies.

FunTaxIS-lite: a simple and light solution to investigate protein functions in all living organisms

MOTIVATION

Defining the full domain of protein functions belonging to an organism is a complex challenge that is due to the huge heterogeneity of the taxonomy, where single or small groups of species can bear unique functional characteristics. FunTaxIS-lite provides a solution to this challenge by determining taxon-based constraints on Gene Ontology (GO) terms, which specify the functions that an organism can or cannot perform. The tool employs a set of rules to generate and spread the constraints across both the taxon hierarchy and the GO graph.

RESULTS

The taxon-based constraints produced by FunTaxIS-lite extend those provided by the Gene Ontology Consortium by an average of 300%. The implementation of these rules significantly reduces errors in function predictions made by automatic algorithms and can assist in correcting inconsistent protein annotations in databases.

AVAILABILITY AND IMPLEMENTATION

FunTaxIS-lite is available on https://www.medcomp.medicina.unipd.it/funtaxis-lite and from https://github.com/MedCompUnipd/FunTaxIS-lite.

Prot2GO: Predicting GO Annotations From Protein Sequences and Interactions

Protein is the main material basis of living organisms and plays crucial role in life activities. Understanding the function of protein is of great significance for new drug discovery, disease treatment and vaccine development. In recent years, with the widespread application of deep learning in bioinformatics, researchers have proposed many deep learning models to predict protein functions. However, the existing deep learning methods usually only consider protein sequences, and thus cannot effectively integrate multi-source data to annotate protein functions. In this article, we propose the Prot2GO model, which can integrate protein sequence and PPI network data to predict protein functions. We utilize an improved biased random walk algorithm to extract the features of PPI network. For sequence data, we use a convolutional neural network to obtain the local features of the sequence and a recurrent neural network to capture the long-range associations between amino acid residues in protein sequence. Moreover, Prot2GO adopts the attention mechanism to identify protein motifs and structural domains. Experiments show that Prot2GO model achieves the state-of-the-art performance on multiple metrics.

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.

CryptoCEN: A Co-Expression Network for Cryptococcus neoformans reveals novel proteins involved in DNA damage repair

Elucidating gene function is a major goal in biology, especially among non-model organisms. However, doing so is complicated by the fact that molecular conservation does not always mirror functional conservation, and that complex relationships among genes are responsible for encoding pathways and higher-order biological processes. Co-expression, a promising approach for predicting gene function, relies on the general principal that genes with similar expression patterns across multiple conditions will likely be involved in the same biological process. For Cryptococcus neoformans, a prevalent human fungal pathogen greatly diverged from model yeasts, approximately 60% of the predicted genes in the genome lack functional annotations. Here, we leveraged a large amount of publicly available transcriptomic data to generate a C. neoformans Co-Expression Network (CryptoCEN), successfully recapitulating known protein networks, predicting gene function, and enabling insights into the principles influencing co-expression. With 100% predictive accuracy, we used CryptoCEN to identify 13 new DNA damage response genes, underscoring the utility of guilt-by-association for determining gene function. Overall, co-expression is a powerful tool for uncovering gene function, and decreases the experimental tests needed to identify functions for currently under-annotated genes.

Phylogenetic inference of the emergence of sequence modules and protein-protein interactions in the ADAMTS-TSL family

Numerous computational methods based on sequences or structures have been developed for the characterization of protein function, but they are still unsatisfactory to deal with the multiple functions of multi-domain protein families. Here we propose an original approach based on 1) the detection of conserved sequence modules using partial local multiple alignment, 2) the phylogenetic inference of species/genes/modules/functions evolutionary histories, and 3) the identification of co-appearances of modules and functions. Applying our framework to the multidomain ADAMTS-TSL family including ADAMTS (A Disintegrin-like and Metalloproteinase with ThromboSpondin motif) and ADAMTS-like proteins over nine species including human, we identify 45 sequence module signatures that are associated with the occurrence of 278 Protein-Protein Interactions in ancestral genes. Some of these signatures are supported by published experimental data and the others provide new insights (e.g. ADAMTS-5). The module signatures of ADAMTS ancestors notably highlight the dual variability of the propeptide and ancillary regions suggesting the importance of these two regions in the specialization of ADAMTS during evolution. Our analyses further indicate convergent interactions of ADAMTS with COMP and CCN2 proteins. Overall, our study provides 186 sequence module signatures that discriminate distinct subgroups of ADAMTS and ADAMTSL and that may result from selective pressures on novel functions and phenotypes.

Current successes and remaining challenges in protein function prediction

In recent years, improvements in protein function prediction methods have led to increased success in annotating protein sequences. However, the functions of over 30% of protein-coding genes remain unknown for many sequenced genomes. Protein functions vary widely, from catalyzing chemical reactions to binding DNA or RNA or forming structures in the cell, and some types of functions are challenging to predict due to the physical features associated with those functions. Other complications in understanding protein functions arise due to the fact that many proteins have more than one function or very small differences in sequence or structure that correspond to different functions. We will discuss some of the recent developments in predicting protein functions and some of the remaining challenges.

Co-Expression Networks in Sunflower: Harnessing the Power of Multi-Study Transcriptomic Public Data to Identify and Categorize Candidate Genes for Fungal Resistance

Fungal plant diseases are a major threat to food security worldwide. Current efforts to identify and list loci involved in different biological processes are more complicated than originally thought, even when complete genome assemblies are available. Despite numerous experimental and computational efforts to characterize gene functions in plants, about ~40% of protein-coding genes in the model plant Arabidopsis thaliana L. are still not categorized in the Gene Ontology (GO) Biological Process (BP) annotation. In non-model organisms, such as sunflower (Helianthus annuus L.), the number of BP term annotations is far fewer, ~22%. In the current study, we performed gene co-expression network analysis using eight terabytes of public transcriptome datasets and expression-based functional prediction to categorize and identify loci involved in the response to fungal pathogens. We were able to construct a reference gene network of healthy green tissue (GreenGCN) and a gene network of healthy and stressed root tissues (RootGCN). Both networks achieved robust, high-quality scores on the metrics of guilt-by-association and selective constraints versus gene connectivity. We were able to identify eight modules enriched in defense functions, of which two out of the three modules in the RootGCN were also conserved in the GreenGCN, suggesting similar defense-related expression patterns. We identified 16 WRKY genes involved in defense related functions and 65 previously uncharacterized loci now linked to defense response. In addition, we identified and classified 122 loci previously identified within QTLs or near candidate loci reported in GWAS studies of disease resistance in sunflower linked to defense response. All in all, we have implemented a valuable strategy to better describe genes within specific biological processes.

Patterns of transcription factor binding and epigenome at promoters allow interpretable predictability of multiple functions of non-coding and coding genes

Understanding the biological roles of all genes only through experimental methods is challenging. A computational approach with reliable interpretability is needed to infer the function of genes, particularly for non-coding RNAs. We have analyzed genomic features that are present across both coding and non-coding genes like transcription factor (TF) and cofactor ChIP-seq (823), histone modifications ChIP-seq (n = 621), cap analysis gene expression (CAGE) tags (n = 255), and DNase hypersensitivity profiles (n = 255) to predict ontology-based functions of genes. Our approach for gene function prediction was reliable (>90% balanced accuracy) for 486 gene-sets. PubMed abstract mining and CRISPR screens supported the inferred association of genes with biological functions, for which our method had high accuracy. Further analysis revealed that TF-binding patterns at promoters have high predictive strength for multiple functions. TF-binding patterns at the promoter add an unexplored dimension of explainable regulatory aspects of genes and their functions. Therefore, we performed a comprehensive analysis for the functional-specificity of TF-binding patterns at promoters and used them for clustering functions to reveal many latent groups of gene-sets involved in common major cellular processes. We also showed how our approach could be used to infer the functions of non-coding genes using the CRISPR screens of coding genes, which were validated using a long non-coding RNA CRISPR screen. Thus our results demonstrated the generality of our approach by using gene-sets from CRISPR screens. Overall, our approach opens an avenue for predicting the involvement of non-coding genes in various functions.

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.

BioSeq-Diabolo: Biological sequence similarity analysis using Diabolo

As the key for biological sequence structure and function prediction, disease diagnosis and treatment, biological sequence similarity analysis has attracted more and more attentions. However, the exiting computational methods failed to accurately analyse the biological sequence similarities because of the various data types (DNA, RNA, protein, disease, etc) and their low sequence similarities (remote homology). Therefore, new concepts and techniques are desired to solve this challenging problem. Biological sequences (DNA, RNA and protein sequences) can be considered as the sentences of "the book of life", and their similarities can be considered as the biological language semantics (BLS). In this study, we are seeking the semantics analysis techniques derived from the natural language processing (NLP) to comprehensively and accurately analyse the biological sequence similarities. 27 semantics analysis methods derived from NLP were introduced to analyse biological sequence similarities, bringing new concepts and techniques to biological sequence similarity analysis. Experimental results show that these semantics analysis methods are able to facilitate the development of protein remote homology detection, circRNA-disease associations identification and protein function annotation, achieving better performance than the other state-of-the-art predictors in the related fields. Based on these semantics analysis methods, a platform called BioSeq-Diabolo has been constructed, which is named after a popular traditional sport in China. The users only need to input the embeddings of the biological sequence data. BioSeq-Diabolo will intelligently identify the task, and then accurately analyse the biological sequence similarities based on biological language semantics. BioSeq-Diabolo will integrate different biological sequence similarities in a supervised manner by using Learning to Rank (LTR), and the performance of the constructed methods will be evaluated and analysed so as to recommend the best methods for the users. The web server and stand-alone package of BioSeq-Diabolo can be accessed at http://bliulab.net/BioSeq-Diabolo/server/.

TEMPROT: protein function annotation using transformers embeddings and homology search

BACKGROUND

Although the development of sequencing technologies has provided a large number of protein sequences, the analysis of functions that each one plays is still difficult due to the efforts of laboratorial methods, making necessary the usage of computational methods to decrease this gap. As the main source of information available about proteins is their sequences, approaches that can use this information, such as classification based on the patterns of the amino acids and the inference based on sequence similarity using alignment tools, are able to predict a large collection of proteins. The methods available in the literature that use this type of feature can achieve good results, however, they present restrictions of protein length as input to their models. In this work, we present a new method, called TEMPROT, based on the fine-tuning and extraction of embeddings from an available architecture pre-trained on protein sequences. We also describe TEMPROT+, an ensemble between TEMPROT and BLASTp, a local alignment tool that analyzes sequence similarity, which improves the results of our former approach.

RESULTS

The evaluation of our proposed classifiers with the literature approaches has been conducted on our dataset, which was derived from CAFA3 challenge database. Both TEMPROT and TEMPROT+ achieved competitive results on [Formula: see text], [Formula: see text], AuPRC and IAuPRC metrics on Biological Process (BP), Cellular Component (CC) and Molecular Function (MF) ontologies compared to state-of-the-art models, with the main results equal to 0.581, 0.692 and 0.662 of [Formula: see text] on BP, CC and MF, respectively.

CONCLUSIONS

The comparison with the literature showed that our model presented competitive results compared the state-of-the-art approaches considering the amino acid sequence pattern recognition and homology analysis. Our model also presented improvements related to the input size that the model can use to train compared to the literature methods.

Bioinformatics characterization of BcsA-like orphan proteins suggest they form a novel family of pseudomonad cyclic-β-glucan synthases

Bacteria produce a variety of polysaccharides with functional roles in cell surface coating, surface and host interactions, and biofilms. We have identified an 'Orphan' bacterial cellulose synthase catalytic subunit (BcsA)-like protein found in four model pseudomonads, P. aeruginosa PA01, P. fluorescens SBW25, P. putida KT2440 and P. syringae pv. tomato DC3000. Pairwise alignments indicated that the Orphan and BcsA proteins shared less than 41% sequence identity suggesting they may not have the same structural folds or function. We identified 112 Orphans among soil and plant-associated pseudomonads as well as in phytopathogenic and human opportunistic pathogenic strains. The wide distribution of these highly conserved proteins suggest they form a novel family of synthases producing a different polysaccharide. In silico analysis, including sequence comparisons, secondary structure and topology predictions, and protein structural modelling, revealed a two-domain transmembrane ovoid-like structure for the Orphan protein with a periplasmic glycosyl hydrolase family GH17 domain linked via a transmembrane region to a cytoplasmic glycosyltransferase family GT2 domain. We suggest the GT2 domain synthesises β-(1,3)-glucan that is transferred to the GH17 domain where it is cleaved and cyclised to produce cyclic-β-(1,3)-glucan (CβG). Our structural models are consistent with enzymatic characterisation and recent molecular simulations of the PaPA01 and PpKT2440 GH17 domains. It also provides a functional explanation linking PaPAK and PaPA14 Orphan (also known as NdvB) transposon mutants with CβG production and biofilm-associated antibiotic resistance. Importantly, cyclic glucans are also involved in osmoregulation, plant infection and induced systemic suppression, and our findings suggest this novel family of CβG synthases may provide similar range of adaptive responses for pseudomonads.