Experimental Annotation Research Articles

Expert-guided protein language models enable accurate and blazingly fast fitness prediction.

Exhaustive experimental annotation of the effect of all known protein variants remains daunting and expensive, stressing the need for scalable effect predictions. We introduce VespaG, a blazingly fast missense amino acid variant effect predictor, leveraging protein language model (pLM) embeddings as input to a minimal deep learning model. To overcome the sparsity of experimental training data, we created a dataset of 39 million single amino acid variants from the human proteome applying the multiple sequence alignment-based effect predictor GEMME as a pseudo standard-of-truth. This setup increases interpretability compared to the baseline pLM and is easily retrainable with novel or updated pLMs. Assessed against the ProteinGym benchmark (217 multiplex assays of variant effect-MAVE-with 2.5 million variants), VespaG achieved a mean Spearman correlation of 0.48 ± 0.02, matching top-performing methods evaluated on the same data. VespaG has the advantage of being orders of magnitude faster, predicting all mutational landscapes of all proteins in proteomes such as Homo sapiens or Drosophila melanogaster in under 30 min on a consumer laptop (12-core CPU, 16 GB RAM). VespaG is available freely at https://github.com/jschlensok/vespag. The associated training data and predictions are available at https://doi.org/10.5281/zenodo.11085958.

Artificial Intelligence Learns Protein Prediction.

From AlphaGO over StableDiffusion to ChatGPT, the recent decade of exponential advances in artificial intelligence (AI) has been altering life. In parallel, advances in computational biology are beginning to decode the language of life: AlphaFold2 leaped forward in protein structure prediction, and protein language models (pLMs) replaced expertise and evolutionary information from multiple sequence alignments with information learned from reoccurring patterns in databases of billions of proteins without experimental annotations other than the amino acid sequences. None of those tools could have been developed 10 years ago; all will increase the wealth of experimental data and speed up the cycle from idea to proof. AI is affecting molecular and medical biology at giant steps, and the most important might be the leap toward more powerful protein design.

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.

ToGC: a pipeline to correct gene model for functional excavation of dark GPCRs in Phytophthora sojae1

The accuracy of genomic annotation is crucial for subsequent functional investigations; however, computational protocols used in high-throughput annotation of open reading frames (ORFs) can introduce inconsistencies. These inconsistencies, which lead to non-uniform extension or truncation of sequence ends, pose challenges for downstream analyses. Existing strategies to rectify these inconsistencies are time-consuming and labor-intensive, lacking specific approaches. To address this gap, we developed toGC, a tool that integrates genomic annotation with RNA-seq datasets to rectify annotation inconsistencies. Using toGC, we achieved an accuracy of nearly 100% accuracy in correcting inconsistencies in published P. sojae ORFs. We applied this innovative pipeline to the GPCR-bigrams gene family, which was predicted to have 42 members in the P. sojae genome but lacked experimental validation. By employing toGC, we identified 32 GPCR-bigram ORFs with inconsistencies between previous annotations and toGC-corrected sequences. Notably, among these were 5 genes (GPCR-TKL9, GPCR-TKL15, GPCR-PDE3, GPCR-AC3, and GPCR-AC4) showed substantial inconsistencies. Experimental gene annotation confirmed the effectiveness of toGC, as sequences obtained through cloning matched those annotated by toGC. Importantly, we discovered two novel GPCRs (GPCR-AC3 and GPCR-AC4), which were previously mispredicted as a single gene. CRISPR/Cas9-mediated knockout experiments revealed the involvement of GPCR-AC4 but not GPCR-AC3 in oospore production, further confirming their status as two separate genes. In addition to P. sojae, the reliability of the toGC pipeline in Phytophthora capsici and Pythium ultimum further emphasizes the robustness of this pipeline. Our findings highlight the utility of toGC for reliable gene model correction, facilitating investigations into biological functions and offering potential applications in diverse species analyses.

Recent advancements in disulfide bridge characterization: Insights from mass spectrometry.

Disulfide bridges (DSB) play an important role in stabilizing three-dimensional structures of biopharmaceuticals, single purified proteins, and various cyclic peptide drugs that contain disulfide in their structures. Incorrect cross-linking known as DSB scrambling results in misfolded structures that can be inactive, immunogenic, and susceptible to aggregation. Very few articles have been published on the experimental annotation of DSBs in proteins and cyclic peptide drugs. Accurate characterization of the disulfide bond is essential for understanding protein confirmation. Characterizing DSBs using mass spectrometry (MS) involves the chemical and enzymatic digestion of samples to obtain smaller peptide fragments, in both reduced and nonreduced forms. Subsequently, these samples are analyzed using MS to locate the DSB, either through interpretation or by employing various software tools. The main challenge in DSB analysis methods using sample preparation is to obtain a sample solution in which nonnative DSBs are not formed due to high pH, temperature, and presence of free sulfhydryl groups. Formation of nonnative DSBs can lead to erroneous annotation of disulfide bond. Sample preparation techniques, fragmentation methods for DSB analysis, and contemporary approaches for DSB mapping using this fragmentation were discussed. This review presents the latest advancement in MS-based characterization; also a critical perspective is presented for further annotation of DSBs using MS, primarily for single purified proteins or peptides that are densely connected and rich in cysteine. Despite significant breakthroughs resulting from advancements in MS, the analysis of disulfide bonds is not straightforward; it necessitates expertise in sample preparation and interpretation.

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein-DNA binding site prediction.

Efficient and accurate recognition of protein-DNA interactions is vital for understanding the molecular mechanisms of related biological processes and further guiding drug discovery. Although the current experimental protocols are the most precise way to determine protein-DNA binding sites, they tend to be labor-intensive and time-consuming. There is an immediate need to design efficient computational approaches for predicting DNA-binding sites. Here, we proposed ULDNA, a new deep-learning model, to deduce DNA-binding sites from protein sequences. This model leverages an LSTM-attention architecture, embedded with three unsupervised language models that are pre-trained on large-scale sequences from multiple database sources. To prove its effectiveness, ULDNA was tested on 229 protein chains with experimental annotation of DNA-binding sites. Results from computational experiments revealed that ULDNA significantly improves the accuracy of DNA-binding site prediction in comparison with 17 state-of-the-art methods. In-depth data analyses showed that the major strength of ULDNA stems from employing three transformer language models. Specifically, these language models capture complementary feature embeddings with evolution diversity, in which the complex DNA-binding patterns are buried. Meanwhile, the specially crafted LSTM-attention network effectively decodes evolution diversity-based embeddings as DNA-binding results at the residue level. Our findings demonstrated a new pipeline for predicting DNA-binding sites on a large scale with high accuracy from protein sequence alone.

Active Learning Approach for Guiding Site-of-Metabolism Measurement and Annotation.

The ability to determine and predict metabolically labile atom positions in a molecule (also called "sites of metabolism" or "SoMs") is of high interest to the design and optimization of bioactive compounds, such as drugs, agrochemicals, and cosmetics. In recent years, several in silico models for SoM prediction have become available, many of which include a machine-learning component. The bottleneck in advancing these approaches is the coverage of distinct atom environments and rare and complex biotransformation events with high-quality experimental data. Pharmaceutical companies typically have measured metabolism data available for several hundred to several thousand compounds. However, even for metabolism experts, interpreting these data and assigning SoMs are challenging and time-consuming. Therefore, a significant proportion of the potential of the existing metabolism data, particularly in machine learning, remains dormant. Here, we report on the development and validation of an active learning approach that identifies the most informative atoms across molecular data sets for SoM annotation. The active learning approach, built on a highly efficient reimplementation of SoM predictor FAME 3, enables experts to prioritize their SoM experimental measurements and annotation efforts on the most rewarding atom environments. We show that this active learning approach yields competitive SoM predictors while requiring the annotation of only 20% of the atom positions required by FAME 3. The source code of the approach presented in this work is publicly available.

FunPredCATH: An ensemble method for predicting protein function using CATH

MotivationThe 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. MethodologyWe 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. MethodsIn 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. EvaluationWe 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. ContributionsFunPredCATH 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.

DescribePROT in 2023: more, higher-quality and experimental annotations and improved data download options.

The DescribePROT database of amino acid-level descriptors of protein structures and functions was substantially expanded since its release in 2020. This expansion includes substantial increase in the size, scope, and quality of the underlying data, the addition of experimental structural information, the inclusion of new data download options, and an upgraded graphical interface. DescribePROT currently covers 19 structural and functional descriptors for proteins in 273 reference proteomes generated by 11 accurate and complementary predictive tools. Users can search our resource in multiple ways, interact with the data using the graphical interface, and download data at various scales including individual proteins, entire proteomes, and whole database. The annotations in DescribePROT are useful for a broad spectrum of studies that include investigations of protein structure and function, development and validation of predictive tools, and to support efforts in understanding molecular underpinnings of diseases and development of therapeutics. DescribePROT can be freely accessed at http://biomine.cs.vcu.edu/servers/DESCRIBEPROT/.

Generative models for protein sequence modeling: recent advances and future directions.

The widespread adoption of high-throughput omics technologies has exponentially increased the amount of protein sequence data involved in many salient disease pathways and their respective therapeutics and diagnostics. Despite the availability of large-scale sequence data, the lack of experimental fitness annotations underpins the need for self-supervised and unsupervised machine learning (ML) methods. These techniques leverage the meaningful features encoded in abundant unlabeled sequences to accomplish complex protein engineering tasks. Proficiency in the rapidly evolving fields of protein engineering and generative AI is required to realize the full potential of ML models as a tool for protein fitness landscape navigation. Here, we support this work by (i) providing an overview of the architecture and mathematical details of the most successful ML models applicable to sequence data (e.g. variational autoencoders, autoregressive models, generative adversarial neural networks, and diffusion models), (ii) guiding how to effectively implement these models on protein sequence data to predict fitness or generate high-fitness sequences and (iii) highlighting several successful studies that implement these techniques in protein engineering (from paratope regions and subcellular localization prediction to high-fitness sequences and protein design rules generation). By providing a comprehensive survey of model details, novel architecture developments, comparisons of model applications, and current challenges, this study intends to provide structured guidance and robust framework for delivering a prospective outlook in the ML-driven protein engineering field.

Rapid and Automated Ab Initio Metabolite Collisional Cross Section Prediction from SMILES Input.

We implemented an ab initio CCS prediction workflow which incrementally refines generated structures using molecular mechanics, a deep learning potential, conformational clustering, and quantum mechanics (QM). Automating intermediate steps for a high performance computing (HPC) environment allows users to input the SMILES structure of small organic molecules and obtain a Boltzmann averaged collisional cross section (CCS) value as output. The CCS of a molecular species is a metric measured by ion mobility spectrometry (IMS) which can improve annotation of untargeted metabolomics experiments. We report only a minor drop in accuracy when we expedite the CCS calculation by replacing the QM geometry refinement step with a single-point energy calculation. Even though the workflow involves stochastic steps (i.e., conformation generation and clustering), the final CCS value was highly reproducible for multiple iterations on L-carnosine. Finally, we illustrate that the gas phase ensembles modeled for the workflow are intermediate files which can be used for the prediction of other properties such as aqueous phase nuclear magnetic resonance chemical shift prediction. The software is available at the following link: https://github.com/DasSusanta/snakemake_ccs.

Computational Prediction of Protein Intrinsically Disordered Region Related Interactions and Functions.

Intrinsically Disordered Proteins (IDPs) and Regions (IDRs) exist widely. Although without well-defined structures, they participate in many important biological processes. In addition, they are also widely related to human diseases and have become potential targets in drug discovery. However, there is a big gap between the experimental annotations related to IDPs/IDRs and their actual number. In recent decades, the computational methods related to IDPs/IDRs have been developed vigorously, including predicting IDPs/IDRs, the binding modes of IDPs/IDRs, the binding sites of IDPs/IDRs, and the molecular functions of IDPs/IDRs according to different tasks. In view of the correlation between these predictors, we have reviewed these prediction methods uniformly for the first time, summarized their computational methods and predictive performance, and discussed some problems and perspectives.

The ProteomeXchange consortium at 10 years: 2023 update.

Mass spectrometry (MS) is by far the most used experimental approach in high-throughput proteomics. The ProteomeXchange (PX) consortium of proteomics resources (http://www.proteomexchange.org) was originally set up to standardize data submission and dissemination of public MS proteomics data. It is now 10 years since the initial data workflow was implemented. In this manuscript, we describe the main developments in PX since the previous update manuscript inNucleicAcids Researchwas published in 2020. The six members of the Consortium are PRIDE, PeptideAtlas (including PASSEL), MassIVE, jPOST, iProX and Panorama Public. We report the current data submission statistics, showcasing that the number of datasets submitted to PX resources has continued to increase every year. As of June 2022, more than 34 233 datasets had been submitted to PX resources, and from those, 20 062 (58.6%) just in the last three years. We also report the development of the Universal Spectrum Identifiers and the improvements in capturing the experimental metadata annotations. In parallel, we highlight that data re-use activities of public datasets continue to increase, enabling connections between PX resources and other popular bioinformatics resources, novel research and also new data resources. Finally, we summarise the current state-of-the-art in data management practices for sensitive human (clinical) proteomics data.

DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms.

MotivationProtein functions are often described using the Gene Ontology (GO) which is an ontology consisting of over 50 000 classes and a large set of formal axioms. Predicting the functions of proteins is one of the key challenges in computational biology and a variety of machine learning methods have been developed for this purpose. However, these methods usually require a significant amount of training data and cannot make predictions for GO classes that have only few or no experimental annotations.ResultsWe developed DeepGOZero, a machine learning model which improves predictions for functions with no or only a small number of annotations. To achieve this goal, we rely on a model-theoretic approach for learning ontology embeddings and combine it with neural networks for protein function prediction. DeepGOZero can exploit formal axioms in the GO to make zero-shot predictions, i.e., predict protein functions even if not a single protein in the training phase was associated with that function. Furthermore, the zero-shot prediction method employed by DeepGOZero is generic and can be applied whenever associations with ontology classes need to be predicted.Availability and implementation http://github.com/bio-ontology-research-group/deepgozero.Supplementary information Supplementary data are available at Bioinformatics online.

Mebipred: identifying metal-binding potential in protein sequence.

Motivationmetal-binding proteins have a central role in maintaining life processes. Nearly one-third of known protein structures contain metal ions that are used for a variety of needs, such as catalysis, DNA/RNA binding, protein structure stability, etc. Identifying metal-binding proteins is thus crucial for understanding the mechanisms of cellular activity. However, experimental annotation of protein metal-binding potential is severely lacking, while computational techniques are often imprecise and of limited applicability.Resultswe developed a novel machine learning-based method, mebipred, for identifying metal-binding proteins from sequence-derived features. This method is over 80% accurate in recognizing proteins that bind metal ion-containing ligands; the specific identity of 11 ubiquitously present metal ions can also be annotated. mebipred is reference-free, i.e. no sequence alignments are involved, and is thus faster than alignment-based methods; it is also more accurate than other sequence-based prediction methods. Additionally, mebipred can identify protein metal-binding capabilities from short sequence stretches, e.g. translated sequencing reads, and, thus, may be useful for the annotation of metal requirements of metagenomic samples. We performed an analysis of available microbiome data and found that ocean, hot spring sediments and soil microbiomes use a more diverse set of metals than human host-related ones. For human microbiomes, physiological conditions explain the observed metal preferences. Similarly, subtle changes in ocean sample ion concentration affect the abundance of relevant metal-binding proteins. These results highlight mebipred’s utility in analyzing microbiome metal requirements.Availability and implementation mebipred is available as a web server at services.bromberglab.org/mebipred and as a standalone package at https://pypi.org/project/mymetal/.Supplementary information Supplementary data are available at Bioinformatics online.

Referenced Kendrick Mass Defect Annotation and Class-Based Filtering of Imaging MS Lipidomics Experiments.

Because of their diverse functionalities in cells, lipids are of primary importance when characterizing molecular profiles of physiological and disease states. Imaging mass spectrometry (IMS) provides the spatial distributions of lipid populations in tissues. Referenced Kendrick mass defect (RKMD) analysis is an effective mass spectrometry (MS) data analysis tool for classification and annotation of lipids. Herein, we extend the capabilities of RKMD analysis and demonstrate an integrated method for lipid annotation and chemical structure-based filtering for IMS datasets. Annotation of lipid features with lipid molecular class, radyl carbon chain length, and degree of unsaturation allows image reconstruction and visualization based on each structural characteristic. We show a proof-of-concept application of the method to a computationally generated IMS dataset and validate that the RKMD method is highly specific for lipid components in the presence of confounding background ions. Moreover, we demonstrate an application of the RKMD-based annotation and filtering to matrix-assisted laser desorption/ionization (MALDI) IMS lipidomic data from human kidney tissue analysis.

Bioinformatic Techniques for Vaccine Development: Epitope Prediction and Structural Vaccinology.

Structural vaccinology involves characterizing the interactions between an antigen and antibodies or host immune receptors. Central to this is the task of epitope prediction, which involves describing the binding affinity and interactions of a given peptide typically to the major histocompatibility complex in the case of T-cells or to the antibodies in the case of B-cells. Several computational models exist for this purpose which we will review here. Generally, epitope predictions for MHC-I and MHC-II are substantially different tasks as well as epitope prediction for continuous versus discontinuous B-cell epitopes. Overall, these models suffer from overprediction of epitopes although general themes support both the use of neural networks as well as the incorporation of more abundant and more varied experimental annotation into model training as valuable in improving predictive performance.

Protein embeddings and deep learning predict binding residues for various ligand classes

One important aspect of protein function is the binding of proteins to ligands, including small molecules, metal ions, and macromolecules such as DNA or RNA. Despite decades of experimental progress many binding sites remain obscure. Here, we proposed bindEmbed21, a method predicting whether a protein residue binds to metal ions, nucleic acids, or small molecules. The Artificial Intelligence (AI)-based method exclusively uses embeddings from the Transformer-based protein Language Model (pLM) ProtT5 as input. Using only single sequences without creating multiple sequence alignments (MSAs), bindEmbed21DL outperformed MSA-based predictions. Combination with homology-based inference increased performance to F1 = 48 ± 3% (95% CI) and MCC = 0.46 ± 0.04 when merging all three ligand classes into one. All results were confirmed by three independent data sets. Focusing on very reliably predicted residues could complement experimental evidence: For the 25% most strongly predicted binding residues, at least 73% were correctly predicted even when ignoring the problem of missing experimental annotations. The new method bindEmbed21 is fast, simple, and broadly applicable—neither using structure nor MSAs. Thereby, it found binding residues in over 42% of all human proteins not otherwise implied in binding and predicted about 6% of all residues as binding to metal ions, nucleic acids, or small molecules.

Identification of active deubiquitinases in the chicken tissues.

The existing protein annotation in chicken is mostly limited to computational predictions based on orthology to other proteins, which often leads to a significant underestimation of the function of these proteins. Genome-scale experimental annotation can provide insight into the actual enzymatic activities of chicken proteins. Amongst post-translational modifications, ubiquitination is of interest as anomalies in ubiquitination are implicated in such diseases as inflammatory disorders, infectious diseases, or malignancies. Ubiquitination is controlled by deubiquitinases (DUBs), which remove ubiquitin from protein substrates. However, the DUBs have not been systematically annotated and quantified in chicken tissues. Here we used a chemoproteomics approach, which is based on active-site probes specific to DUBs, and identified 26 active DUBs in the chicken spleen, cecum, and liver.

DELEAT: gene essentiality prediction and deletion design for bacterial genome reduction

BackgroundThe study of gene essentiality is fundamental to understand the basic principles of life, as well as for applications in many fields. In recent decades, dozens of sets of essential genes have been determined using different experimental and bioinformatics approaches, and this information has been useful for genome reduction of model organisms. Multiple in silico strategies have been developed to predict gene essentiality, but no optimal algorithm or set of gene features has been found yet, especially for non-model organisms with incomplete functional annotation.ResultsWe have developed DELEAT v0.1 (DELetion design by Essentiality Analysis Tool), an easy-to-use bioinformatic tool which integrates an in silico gene essentiality classifier in a pipeline allowing automatic design of large-scale deletions in any bacterial genome. The essentiality classifier consists of a novel logistic regression model based on only six gene features which are not dependent on experimental data or functional annotation. As a proof of concept, we have applied this pipeline to the determination of dispensable regions in the genome of Bartonella quintana str. Toulouse. In this already reduced genome, 35 possible deletions have been delimited, spanning 29% of the genome.ConclusionsBuilt on in silico gene essentiality predictions, we have developed an analysis pipeline which assists researchers throughout multiple stages of bacterial genome reduction projects, and created a novel classifier which is simple, fast, and universally applicable to any bacterial organism with a GenBank annotation file.