Search

Abstract Embeddings from protein Language Models (pLMs) are replacing evolutionary information from multiple sequence alignments (MSAs) as the most successful input for protein prediction. Is this because embeddings capture evolutionary information? We tested various approaches to explicitly incorporate evolutionary information into embeddings on various protein prediction tasks. While older pLMs (SeqVec, ProtBert) significantly improved through MSAs, the more recent pLM ProtT5 did not benefit. For most tasks, pLM-based outperformed MSA-based methods, and the combination of both even decreased performance for some (intrinsic disorder). We highlight the effectiveness of pLM-based methods and find limited benefits from integrating MSAs.

Abstract Skin inflammation with the potential sequel of moist epitheliolysis and edema constitute the most frequent breast radiotherapy (RT) acute side effects. The aim of this study was to compare the predictive value of tissue-derived radiomics features to the total breast volume (TBV) for the moist cells epitheliolysis as a surrogate for skin inflammation, and edema. Radiomics features were extracted from computed tomography (CT) scans of 252 breast cancer patients from two volumes of interest: TBV and glandular tissue (GT). Machine learning classifiers were trained on radiomics and clinical features, which were evaluated for both side effects. The best radiomics model was a least absolute shrinkage and selection operator (LASSO) classifier, using TBV features, predicting moist cells epitheliolysis, achieving an area under the receiver operating characteristic (AUROC) of 0.74. This was comparable to TBV breast volume (AUROC of 0.75). Combined models of radiomics and clinical features did not improve performance. Exclusion of volume-correlated features slightly reduced the predictive performance (AUROC 0.71). We could demonstrate the general propensity of planning CT-based radiomics models to predict breast RT-dependent side effects. Mammary tissue was more predictive than glandular tissue. The radiomics features performance was influenced by their high correlation to TBV volume.

Abstract Prediction methods inputting embeddings from protein language models have reached or even surpassed state-of-the-art performance on many protein prediction tasks. In natural language processing fine-tuning large language models has become the de facto standard. In contrast, most protein language model-based protein predictions do not back-propagate to the language model. Here, we compare the fine-tuning of three state-of-the-art models (ESM2, ProtT5, Ankh) on eight different tasks. Two results stand out. Firstly, task-specific supervised fine-tuning almost always improves downstream predictions. Secondly, parameter-efficient fine-tuning can reach similar improvements consuming substantially fewer resources at up to 4.5-fold acceleration of training over fine-tuning full models. Our results suggest to always try fine-tuning, in particular for problems with small datasets, such as for fitness landscape predictions of a single protein. For ease of adaptability, we provide easy-to-use notebooks to fine-tune all models used during this work for per-protein (pooling) and per-residue prediction tasks.

Abstract The identification of protein binding residues helps to understand their biological processes as protein function is often defined through ligand binding, such as to other proteins, small molecules, ions, or nucleotides. Methods predicting binding residues often err for intrinsically disordered proteins or regions (IDPs/IDPRs), often also referred to as molecular recognition features (MoRFs). Here, we presented a novel machine learning (ML) model trained to specifically predict binding regions in IDPRs. The proposed model, IDBindT5, leveraged embeddings from the protein language model (pLM) ProtT5 to reach a balanced accuracy of 57.2 ± 3.6% (95% confidence interval). Assessed on the same data set, this did not differ at the 95% CI from the state-of-the-art (SOTA) methods ANCHOR2 and DeepDISOBind that rely on expert-crafted features and evolutionary information from multiple sequence alignments (MSAs). Assessed on other data, methods such as SPOT-MoRF reached higher MCCs. IDBindT5’s SOTA predictions are much faster than other methods, easily enabling full-proteome analyses. Our findings emphasize the potential of pLMs as a promising approach for exploring and predicting features of disordered proteins. The model and a comprehensive manual are publicly available at https://github.com/jahnl/binding_in_disorder .

Summary: Structural features of proteins capture underlying information about protein evolution and function, which enhances the analysis of proteomic and transcriptomic data. Here, we develop Structural Analysis of Gene and protein Expression Signatures (SAGES), a method that describes expression data using features calculated from sequence-based prediction methods and 3D structural models. We used SAGES, along with machine learning, to characterize tissues from healthy individuals and those with breast cancer. We analyzed gene expression data from 23 breast cancer patients and genetic mutation data from the Catalog of Somatic Mutations In Cancer database as well as 17 breast tumor protein expression profiles. We identified prominent expression of intrinsically disordered regions in breast cancer proteins as well as relationships between drug perturbation signatures and breast cancer disease signatures. Our results suggest that SAGES is generally applicable to describe diverse biological phenomena including disease states and drug effects.

Abstract Background The success of AlphaFold2 in reliable protein three-dimensional (3D) structure prediction, assists the move of structural biology toward studies of protein dynamics and mutational impact on structure and function. This transition needs tools that qualitatively assess alternative 3D conformations. Results We introduce MutAmore, a bioinformatics tool that renders individual images of protein 3D structures for, e.g., sequence mutations into a visually intuitive movie format. MutAmore streamlines a pipeline casting single amino-acid variations (SAVs) into a dynamic 3D mutation movie providing a qualitative perspective on the mutational landscape of a protein. By default, the tool first generates all possible variants of the sequence reachable through SAVs (L*19 for proteins with L residues). Next, it predicts the structural conformation for all L*19 variants using state-of-the-art models. Finally, it visualizes the mutation matrix and produces a color-coded 3D animation. Alternatively, users can input other types of variants, e.g., from experimental structures. Conclusion MutAmore samples alternative protein configurations to study the dynamical space accessible from SAVs in the post-AlphaFold2 era of structural biology. As the field shifts towards the exploration of alternative conformations of proteins, MutAmore aids in the understanding of the structural impact of mutations by providing a flexible pipeline for the generation of protein mutation movies using current and future structure prediction models.

Abstract Background Venoms, which have evolved numerous times in animals, are ideal models of convergent trait evolution. However, detailed genomic studies of toxin-encoding genes exist for only a few animal groups. The hyper-diverse hymenopteran insects are the most speciose venomous clade, but investigation of the origin of their venom genes has been largely neglected. Results Utilizing a combination of genomic and proteo-transcriptomic data, we investigated the origin of 11 toxin genes in 29 published and 3 new hymenopteran genomes and compiled an up-to-date list of prevalent bee venom proteins. Observed patterns indicate that bee venom genes predominantly originate through single gene co-option with gene duplication contributing to subsequent diversification. Conclusions Most Hymenoptera venom genes are shared by all members of the clade and only melittin and the new venom protein family anthophilin1 appear unique to the bee lineage. Most venom proteins thus predate the mega-radiation of hymenopterans and the evolution of the aculeate stinger.

Abstract Patients suffering from painful spinal bone metastases (PSBMs) often undergo palliative radiation therapy (RT), with an efficacy of approximately two thirds of patients. In this exploratory investigation, we assessed the effectiveness of machine learning (ML) models trained on radiomics, semantic and clinical features to estimate complete pain response. Gross tumour volumes (GTV) and clinical target volumes (CTV) of 261 PSBMs were segmented on planning computed tomography (CT) scans. Radiomics, semantic and clinical features were collected for all patients. Random forest (RFC) and support vector machine (SVM) classifiers were compared using repeated nested cross-validation. The best radiomics classifier was trained on CTV with an area under the receiver-operator curve (AUROC) of 0.62 ± 0.01 (RFC; 95% confidence interval). The semantic model achieved a comparable AUROC of 0.63 ± 0.01 (RFC), significantly below the clinical model (SVM, AUROC: 0.80 ± 0.01); and slightly lower than the spinal instability neoplastic score (SINS; LR, AUROC: 0.65 ± 0.01). A combined model did not improve performance (AUROC: 0,74 ± 0,01). We could demonstrate that radiomics and semantic analyses of planning CTs allowed for limited prediction of therapy response to palliative RT. ML predictions based on established clinical parameters achieved the best results.

Abstract Three-finger toxins (3FTXs) are a functionally diverse family of toxins, apparently unique to venoms of caenophidian snakes. Although the ancestral function of 3FTXs is antagonism of nicotinic acetylcholine receptors, redundancy conferred by the accumulation of duplicate genes has facilitated extensive neofunctionalization, such that derived members of the family interact with a range of targets. 3FTXs are members of the LY6/UPAR family, but their non-toxin ancestor remains unknown. Combining traditional phylogenetic approaches, manual synteny analysis, and machine learning techniques (including AlphaFold2 and ProtT5), we have reconstructed a detailed evolutionary history of 3FTXs. We identify their immediate ancestor as a non-secretory LY6, unique to squamate reptiles, and propose that changes in molecular ecology resulting from loss of a membrane-anchoring domain and changes in gene expression, paved the way for the evolution of one of the most important families of snake toxins.

A new protein domain classification protocol incorporating deep learning strategies for detecting sequence and structure similarities between domain is used to systematically study and analyse the predicted AlphaFold2 structural models for proteins of 21 organisms.

Abstract Background Despite the immense importance of transmembrane proteins (TMP) for molecular biology and medicine, experimental 3D structures for TMPs remain about 4–5 times underrepresented compared to non-TMPs. Today’s top methods such as AlphaFold2 accurately predict 3D structures for many TMPs, but annotating transmembrane regions remains a limiting step for proteome-wide predictions. Results Here, we present TMbed, a novel method inputting embeddings from protein Language Models (pLMs, here ProtT5), to predict for each residue one of four classes: transmembrane helix (TMH), transmembrane strand (TMB), signal peptide, or other. TMbed completes predictions for entire proteomes within hours on a single consumer-grade desktop machine at performance levels similar or better than methods, which are using evolutionary information from multiple sequence alignments (MSAs) of protein families. On the per-protein level, TMbed correctly identified 94 ± 8% of the beta barrel TMPs (53 of 57) and 98 ± 1% of the alpha helical TMPs (557 of 571) in a non-redundant data set, at false positive rates well below 1% (erred on 30 of 5654 non-membrane proteins). On the per-segment level, TMbed correctly placed, on average, 9 of 10 transmembrane segments within five residues of the experimental observation. Our method can handle sequences of up to 4200 residues on standard graphics cards used in desktop PCs (e.g., NVIDIA GeForce RTX 3060). Conclusions Based on embeddings from pLMs and two novel filters (Gaussian and Viterbi), TMbed predicts alpha helical and beta barrel TMPs at least as accurately as any other method but at lower false positive rates. Given the few false positives and its outstanding speed, TMbed might be ideal to sieve through millions of 3D structures soon to be predicted, e.g., by AlphaFold2.

Abstract 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.

Since 1992, all state-of-the-art methods for fast and sensitive identification of evolutionary, structural, and functional relations between proteins (also referred to as “homology detection”) use sequences and sequence-profiles (PSSMs). Protein Language Models (pLMs) generalize sequences, possibly capturing the same constraints as PSSMs, e.g., through embeddings. Here, we explored how to use such embeddings for nearest neighbor searches to identify relations between protein pairs with diverged sequences (remote homology detection for levels of

Ancestral sequence reconstruction is a technique that is gaining widespread use in molecular evolution studies and protein engineering. Accurate reconstruction requires the ability to handle appropriately large numbers of sequences, as well as insertion and deletion (indel) events, but available approaches exhibit limitations. To address these limitations, we developed Graphical Representation of Ancestral Sequence Predictions (GRASP), which efficiently implements maximum likelihood methods to enable the inference of ancestors of families with more than 10,000 members. GRASP implements partial order graphs (POGs) to represent and infer insertion and deletion events across ancestors, enabling the identification of building blocks for protein engineering. To validate the capacity to engineer novel proteins from realistic data, we predicted ancestor sequences across three distinct enzyme families: glucose-methanol-choline (GMC) oxidoreductases, cytochromes P450, and dihydroxy/sugar acid dehydratases (DHAD). All tested ancestors demonstrated enzymatic activity. Our study demonstrates the ability of GRASP (1) to support large data sets over 10,000 sequences and (2) to employ insertions and deletions to identify building blocks for engineering biologically active ancestors, by exploring variation over evolutionary time.

Predictions for millions of protein three-dimensional structures are only a few clicks away since the release of AlphaFold2 results for UniProt. However, many proteins have so-called intrinsically disordered regions (IDRs) that do not adopt unique structures in isolation. These IDRs are associated with several diseases, including Alzheimer’s Disease. We showed that three recent disorder measures of AlphaFold2 predictions (pLDDT, “experimentally resolved” prediction and “relative solvent accessibility”) correlated to some extent with IDRs. However, expert methods predict IDRs more reliably by combining complex machine learning models with expert-crafted input features and evolutionary information from multiple sequence alignments (MSAs). MSAs are not always available, especially for IDRs, and are computationally expensive to generate, limiting the scalability of the associated tools. Here, we present the novel method SETH that predicts residue disorder from embeddings generated by the protein Language Model ProtT5, which explicitly only uses single sequences as input. Thereby, our method, relying on a relatively shallow convolutional neural network, outperformed much more complex solutions while being much faster, allowing to create predictions for the human proteome in about 1 hour on a consumer-grade PC with one NVIDIA GeForce RTX 3060. Trained on a continuous disorder scale (CheZOD scores), our method captured subtle variations in disorder, thereby providing important information beyond the binary classification of most methods. High performance paired with speed revealed that SETH’s nuanced disorder predictions for entire proteomes capture aspects of the evolution of organisms. Additionally, SETH could also be used to filter out regions or proteins with probable low-quality AlphaFold2 3D structures to prioritize running the compute-intensive predictions for large data sets. SETH is freely publicly available at: https://github.com/Rostlab/SETH.

Abstract We modeled 3D structures of all SARS‐CoV‐2 proteins, generating 2,060 models that span 69% of the viral proteome and provide details not available elsewhere. We found that ˜6% of the proteome mimicked human proteins, while ˜7% was implicated in hijacking mechanisms that reverse post‐translational modifications, block host translation, and disable host defenses; a further ˜29% self‐assembled into heteromeric states that provided insight into how the viral replication and translation complex forms. To make these 3D models more accessible, we devised a structural coverage map, a novel visualization method to show what is—and is not—known about the 3D structure of the viral proteome. We integrated the coverage map into an accompanying online resource ( https://aquaria.ws/covid ) that can be used to find and explore models corresponding to the 79 structural states identified in this work. The resulting Aquaria‐COVID resource helps scientists use emerging structural data to understand the mechanisms underlying coronavirus infection and draws attention to the 31% of the viral proteome that remains structurally unknown or dark.

Abstract Knowing protein function is crucial to advance molecular and medical biology, yet experimental function annotations through the Gene Ontology (GO) exist for fewer than 0.5% of all known proteins. Computational methods bridge this sequence-annotation gap typically through homology-based annotation transfer by identifying sequence-similar proteins with known function or through prediction methods using evolutionary information. Here, we propose predicting GO terms through annotation transfer based on proximity of proteins in the SeqVec embedding rather than in sequence space. These embeddings originate from deep learned language models (LMs) for protein sequences (SeqVec) transferring the knowledge gained from predicting the next amino acid in 33 million protein sequences. Replicating the conditions of CAFA3, our method reaches an Fmax of 37 ± 2%, 50 ± 3%, and 57 ± 2% for BPO, MFO, and CCO, respectively. Numerically, this appears close to the top ten CAFA3 methods. When restricting the annotation transfer to proteins with

Abstract Background Any two unrelated people differ by about 20,000 missense mutations (also referred to as SAVs: Single Amino acid Variants or missense SNV). Many SAVs have been predicted to strongly affect molecular protein function. Common SAVs (> 5% of population) were predicted to have, on average, more effect on molecular protein function than rare SAVs (

Abstract Background Deep mutational scanning (DMS) studies exploit the mutational landscape of sequence variation by systematically and comprehensively assaying the effect of single amino acid variants (SAVs; also referred to as missense mutations, or non-synonymous Single Nucleotide Variants – missense SNVs or nsSNVs) for particular proteins. We assembled SAV annotations from 22 different DMS experiments and normalized the effect scores to evaluate variant effect prediction methods. Three trained on traditional variant effect data (PolyPhen-2, SIFT, SNAP2), a regression method optimized on DMS data (Envision), and a naïve prediction using conservation information from homologs. Results On a set of 32,981 SAVs, all methods captured some aspects of the experimental effect scores, albeit not the same. Traditional methods such as SNAP2 correlated slightly more with measurements and better classified binary states (effect or neutral). Envision appeared to better estimate the precise degree of effect. Most surprising was that the simple naïve conservation approach using PSI-BLAST in many cases outperformed other methods. All methods captured beneficial effects (gain-of-function) significantly worse than deleterious (loss-of-function). For the few proteins with multiple independent experimental measurements, experiments differed substantially, but agreed more with each other than with predictions. Conclusions DMS provides a new powerful experimental means of understanding the dynamics of the protein sequence space. As always, promising new beginnings have to overcome challenges. While our results demonstrated that DMS will be crucial to improve variant effect prediction methods, data diversity hindered simplification and generalization.

Abstract Background Predicting protein function and structure from sequence is one important challenge for computational biology. For 26 years, most state-of-the-art approaches combined machine learning and evolutionary information. However, for some applications retrieving related proteins is becoming too time-consuming. Additionally, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome. Both these problems are addressed by the new methodology introduced here. Results We introduced a novel way to represent protein sequences as continuous vectors (embeddings) by using the language model ELMo taken from natural language processing. By modeling protein sequences, ELMo effectively captured the biophysical properties of the language of life from unlabeled big data (UniRef50). We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple neural networks for two different tasks. At the per-residue level, secondary structure (Q3 = 79% ± 1, Q8 = 68% ± 1) and regions with intrinsic disorder (MCC = 0.59 ± 0.03) were predicted significantly better than through one-hot encoding or through Word2vec-like approaches. At the per-protein level, subcellular localization was predicted in ten classes (Q10 = 68% ± 1) and membrane-bound were distinguished from water-soluble proteins (Q2 = 87% ± 1). Although SeqVec embeddings generated the best predictions from single sequences, no solution improved over the best existing method using evolutionary information. Nevertheless, our approach improved over some popular methods using evolutionary information and for some proteins even did beat the best. Thus, they prove to condense the underlying principles of protein sequences. Overall, the important novelty is speed: where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created embeddings on average in 0.03 s. As this speed-up is independent of the size of growing sequence databases, SeqVec provides a highly scalable approach for the analysis of big data in proteomics, i.e. microbiome or metaproteome analysis. Conclusion Transfer-learning succeeded to extract information from unlabeled sequence databases relevant for various protein prediction tasks. SeqVec modeled the language of life, namely the principles underlying protein sequences better than any features suggested by textbooks and prediction methods. The exception is evolutionary information, however, that information is not available on the level of a single sequence.

Abstract Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. Results Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. Conclusion We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

Abstract Background The CATH database provides a hierarchical classification of protein domain structures including a sub-classification of superfamilies into functional families (FunFams). We analyzed the similarity of binding site annotations in these FunFams and incorporated FunFams into the prediction of protein binding residues. Results FunFam members agreed, on average, in 36.9 ± 0.6% of their binding residue annotations. This constituted a 6.7-fold increase over randomly grouped proteins and a 1.2-fold increase (1.1-fold on the same dataset) over proteins with the same enzymatic function (identical Enzyme Commission, EC, number). Mapping de novo binding residue prediction methods (BindPredict-CCS, BindPredict-CC) onto FunFam resulted in consensus predictions for those residues that were aligned and predicted alike (binding/non-binding) within a FunFam. This simple consensus increased the F1-score (for binding) 1.5-fold over the original prediction method. Variation of the threshold for how many proteins in the consensus prediction had to agree provided a convenient control of accuracy/precision and coverage/recall, e.g. reaching a precision as high as 60.8 ± 0.4% for a stringent threshold. Conclusions The FunFams outperformed even the carefully curated EC numbers in terms of agreement of binding site residues. Additionally, we assume that our proof-of-principle through the prediction of protein binding residues will be relevant for many other solutions profiting from FunFams to infer functional information at the residue level.

Abstract Background Sub-nuclear structures or locations are associated with various nuclear processes. Proteins localized in these substructures are important to understand the interior nuclear mechanisms. Despite advances in high-throughput methods, experimental protein annotations remain limited. Predictions of cellular compartments have become very accurate, largely at the expense of leaving out substructures inside the nucleus making a fine-grained analysis impossible. Results Here, we present a new method (LocNuclei) that predicts nuclear substructures from sequence alone. LocNuclei used a string-based Profile Kernel with Support Vector Machines (SVMs). It distinguishes sub-nuclear localization in 13 distinct substructures and distinguishes between nuclear proteins confined to the nucleus and those that are also native to other compartments (traveler proteins). High performance was achieved by implicitly leveraging a large biological knowledge-base in creating predictions by homology-based inference through BLAST. Using this approach, the performance reached AUC = 0.70–0.74 and Q13 = 59–65%. Travelling proteins (nucleus and other) were identified at Q2 = 70–74%. A Gene Ontology (GO) analysis of the enrichment of biological processes revealed that the predicted sub-nuclear compartments matched the expected functionality. Analysis of protein-protein interactions (PPI) show that formation of compartments and functionality of proteins in these compartments highly rely on interactions between proteins. This suggested that the LocNuclei predictions carry important information about function. The source code and data sets are available through GitHub: https://github.com/Rostlab/LocNuclei. Conclusions LocNuclei predicts subnuclear compartments and traveler proteins accurately. These predictions carry important information about functionality and PPIs.

Abstract Background The subcellular localization of a protein is an important aspect of its function. However, the experimental annotation of locations is not even complete for well-studied model organisms. Text mining might aid database curators to add experimental annotations from the scientific literature. Existing extraction methods have difficulties to distinguish relationships between proteins and cellular locations co-mentioned in the same sentence. Results LocText was created as a new method to extract protein locations from abstracts and full texts. LocText learned patterns from syntax parse trees and was trained and evaluated on a newly improved LocTextCorpus. Combined with an automatic named-entity recognizer, LocText achieved high precision (P = 86%±4). After completing development, we mined the latest research publications for three organisms: human (Homo sapiens), budding yeast (Saccharomyces cerevisiae), and thale cress (Arabidopsis thaliana). Examining 60 novel, text-mined annotations, we found that 65% (human), 85% (yeast), and 80% (cress) were correct. Of all validated annotations, 40% were completely novel, i.e. did neither appear in the annotations nor the text descriptions of Swiss-Prot. Conclusions LocText provides a cost-effective, semi-automated workflow to assist database curators in identifying novel protein localization annotations. The annotations suggested through text-mining would be verified by experts to guarantee high-quality standards of manually-curated databases such as Swiss-Prot.

Abstract Any two unrelated individuals differ by about 10,000 single amino acid variants (SAVs). Do these impact molecular function? Experimental answers cannot answer comprehensively, while state-of-the-art prediction methods can. We predicted the functional impacts of SAVs within human and for variants between human and other species. Several surprising results stood out. Firstly, four methods (CADD, PolyPhen-2, SIFT, and SNAP2) agreed within 10 percentage points on the percentage of rare SAVs predicted with effect. However, they differed substantially for the common SAVs: SNAP2 predicted, on average, more effect for common than for rare SAVs. Given the large ExAC data sets sampling 60,706 individuals, the differences were extremely significant (p-value

Polyisoprenyl-glycosyltransferases (PI-GTs) catalyse the addition of sugar to lipid carriers, which is the first step in the production of sugar donors for glycosylation. Here Ardiccioni et al.present the structure of a bacterial PI-GT and propose a mechanistic basis for sugar transfer.

Sulfur, most abundantly found in the environment as sulfate (SO42-), is an essential element in metabolites required by all living cells, including amino acids, co-factors and vitamins. However, current understanding of the cellular delivery of SO42- at the molecular level is limited. CysZ has been described as a SO42- permease, but its sequence family is without known structural precedent. Based on crystallographic structure information, SO42- binding and flux experiments, we provide insight into the molecular mechanism of CysZ-mediated translocation of SO42- across membranes. CysZ structures from three different bacterial species display a hitherto unknown fold and have subunits organized with inverted transmembrane topology. CysZ from Pseudomonas denitrificans assembles as a trimer of antiparallel dimers and the CysZ structures from two other species recapitulate dimers from this assembly. Mutational studies highlight the functional relevance of conserved CysZ residues.

Many tools visualize protein-protein interaction (PPI) networks. The tool introduced here, CellMap, adds one crucial novelty by visualizing PPI networks in the context of subcellular localization, i.e. the location in the cell or cellular component in which a PPI happens. Users can upload images of cells and define areas of interest against which PPIs for selected proteins are displayed (by default on a cartoon of a cell). Annotations of localization are provided by the user or through our in-house database. The visualizer and server are written in JavaScript, making CellMap easy to customize and to extend by researchers and developers.

MOTIVATION:Protein-protein interactions (PPIs) play a key role in many cellular processes. Most annotations of PPIs mix experimental and computational data. The mix optimizes coverage, but obfuscates the annotation origin. Some resources excel at focusing on reliable experimental data. Here, we focused on new pairs of interacting proteins for several model organisms based solely on sequence-based prediction methods. RESULTS:We extracted reliable experimental data about which proteins interact (binary) for eight diverse model organisms from public databases, namely from Escherichia coli, Schizosaccharomyces pombe, Plasmodium falciparum, Drosophila melanogaster, Caenorhabditis elegans, Mus musculus, Rattus norvegicus, Arabidopsis thaliana, and for the previously used Homo sapiens and Saccharomyces cerevisiae. Those data were the base to develop a PPI prediction method for each model organism. The method used evolutionary information through a profile-kernel Support Vector Machine (SVM). With the resulting eight models, we predicted all possible protein pairs in each organism and made the top predictions available through a web application. Almost all of the PPIs made available were predicted between proteins that have not been observed in any interaction, in particular for less well-studied organisms. Thus, our work complements existing resources and is particularly helpful for designing experiments because of its uniqueness. Experimental annotations and computational predictions are strongly influenced by the fact that some proteins have many partners and others few. To optimize machine learning, recent methods explicitly ignored such a network-structure and rely either on domain knowledge or sequence-only methods. Our approach is independent of domain-knowledge and leverages evolutionary information. The database interface representing our results is accessible from https://rostlab.org/services/ppipair/. The data can also be downloaded from https://figshare.com/collections/ProfPPI-DB/4141784.

Following publication of the original article [1], the author reported that an incorrect figure has been published as Figure 2. The correct Figure 2 is shown below.

In the past, short protein-coding genes were often disregarded by genome annotation pipelines. Transcriptome sequencing (RNAseq) signals outside of annotated genes have usually been interpreted to indicate either ncRNA or pervasive transcription. Therefore, in addition to the transcriptome, the translatome (RIBOseq) of the enteric pathogen Escherichia coli O157:H7 strain Sakai was determined at two optimal growth conditions and a severe stress condition combining low temperature and high osmotic pressure. All intergenic open reading frames potentially encoding a protein of ≥ 30 amino acids were investigated with regard to coverage by transcription and translation signals and their translatability expressed by the ribosomal coverage value. This led to discovery of 465 unique, putative novel genes not yet annotated in this E. coli strain, which are evenly distributed over both DNA strands of the genome. For 255 of the novel genes, annotated homologs in other bacteria were found, and a machine-learning algorithm, trained on small protein-coding E. coli genes, predicted that 89% of these translated open reading frames represent bona fide genes. The remaining 210 putative novel genes without annotated homologs were compared to the 255 novel genes with homologs and to 250 short annotated genes of this E. coli strain. All three groups turned out to be similar with respect to their translatability distribution, fractions of differentially regulated genes, secondary structure composition, and the distribution of evolutionary constraint, suggesting that both novel groups represent legitimate genes. However, the machine-learning algorithm only recognized a small fraction of the 210 genes without annotated homologs. It is possible that these genes represent a novel group of genes, which have unusual features dissimilar to the genes of the machine-learning algorithm training set.

Developments in experimental and computational biology are advancing our understanding of how protein sequence variation impacts molecular protein function. However, the leap from the micro level of molecular function to the macro level of the whole organism, e.g. disease, remains barred. Here, we present new results emphasizing earlier work that suggested some links from molecular function to disease. We focused on non-synonymous single nucleotide variants, also referred to as single amino acid variants (SAVs). Building upon OMIA (Online Mendelian Inheritance in Animals), we introduced a curated set of 117 disease-causing SAVs in animals. Methods optimized to capture effects upon molecular function often correctly predict human (OMIM) and animal (OMIA) Mendelian disease-causing variants. We also predicted effects of human disease-causing variants in the mouse model, i.e. we put OMIM SAVs into mouse orthologs. Overall, fewer variants were predicted with effect in the model organism than in the original organism. Our results, along with other recent studies, demonstrate that predictions of molecular effects capture some important aspects of disease. Thus, in silico methods focusing on the micro level of molecular function can help to understand the macro system level of disease.

Recent experiments established that a culture of Saccharomyces cerevisiae (baker’s yeast) survives sudden high temperatures by specifically duplicating the entire chromosome III and two chromosomal fragments (from IV and XII). Heat shock proteins (HSPs) are not significantly over-abundant in the duplication. In contrast, we suggest a simple algorithm to “postdict” the experimental results: Find a small enough chromosome with minimal protein disorder and duplicate this region. This algorithm largely explains all observed duplications. In particular, all regions duplicated in the experiment reduced the overall content of protein disorder. The differential analysis of the functional makeup of the duplication remained inconclusive. Gene Ontology (GO) enrichment suggested over-representation in processes related to reproduction and nutrient uptake. Analyzing the protein-protein interaction network (PPI) revealed that few network-central proteins were duplicated. The predictive hypothesis hinges upon the concept of reducing proteins with long regions of disorder in order to become less sensitive to heat shock attack.

BioJS is an open source software project that develops visualization tools for different types of biological data. Here we report on the factors that influenced the growth of the BioJS user and developer community, and outline our strategy for building on this growth. The lessons we have learned on BioJS may also be relevant to other open source software projects.

Many prokaryotic organisms have adapted to incredibly extreme habitats. The genomes of such extremophiles differ from their non-extremophile relatives. For example, some proteins in thermophiles sustain high temperatures by being more compact than homologs in non-extremophiles. Conversely, some proteins have increased volumes to compensate for freezing effects in psychrophiles that survive in the cold. Here, we revealed that some differences in organisms surviving in extreme habitats correlate with a simple single feature, namely the fraction of proteins predicted to have long disordered regions. We predicted disorder with different methods for 46 completely sequenced organisms from diverse habitats and found a correlation between protein disorder and the extremity of the environment. More specifically, the overall percentage of proteins with long disordered regions tended to be more similar between organisms of similar habitats than between organisms of similar taxonomy. For example, predictions tended to detect substantially more proteins with long disordered regions in prokaryotic halophiles (survive high salt) than in their taxonomic neighbors. Another peculiar environment is that of high radiation survived, e.g. by Deinococcus radiodurans. The relatively high fraction of disorder predicted in this extremophile might provide a shield against mutations. Although our analysis fails to establish causation, the observed correlation between such a simplistic, coarse-grained, microscopic molecular feature (disorder content) and a macroscopic variable (habitat) remains stunning.

Speed is of the essence in combating Ebola; thus, computational approaches should form a significant component of Ebola research. As for the development of any modern drug, computational biology is uniquely positioned to contribute through comparative analysis of the genome sequences of Ebola strains as well as 3-D protein modeling. Other computational approaches to Ebola may include large-scale docking studies of Ebola proteins with human proteins and with small-molecule libraries, computational modeling of the spread of the virus, computational mining of the Ebola literature, and creation of a curated Ebola database. Taken together, such computational efforts could significantly accelerate traditional scientific approaches. In recognition of the need for important and immediate solutions from the field of computational biology against Ebola, the International Society for Computational Biology (ISCB) announces a prize for an important computational advance in fighting the Ebola virus. ISCB will confer the ISCB Fight against Ebola Award, along with a prize of US$2,000, at its July 2016 annual meeting (ISCB Intelligent Systems for Molecular Biology [ISMB] 2016, Orlando, Florida).

Summary: The HeatMapViewer is a BioJS component that lays-out and renders two-dimensional (2D) plots or heat maps that are ideally suited to visualize matrix formatted data in biology such as for the display of microarray experiments or the outcome of mutational studies and the study of SNP-like sequence variants. It can be easily integrated into documents and provides a powerful, interactive way to visualize heat maps in web applications. The software uses a scalable graphics technology that adapts the visualization component to any required resolution, a useful feature for a presentation with many different data-points. The component can be applied to present various biological data types. Here, we present two such cases – showing gene expression data and visualizing mutability landscape analysis. Availability: https://github.com/biojs/biojs; http://dx.doi.org/10.5281/zenodo.7706.

One of the most accurate multi-class protein classification systems continues to be the profile-based SVM kernel introduced by the Leslie group. Unfortunately, its CPU requirements render it too slow for practical applications of large-scale classification tasks. Here, we introduce several software improvements that enable significant acceleration. Using various non-redundant data sets, we demonstrate that our new implementation reaches a maximal speed-up as high as 14-fold for calculating the same kernel matrix. Some predictions are over 200 times faster and render the kernel as possibly the top contender in a low ratio of speed/performance. Additionally, we explain how to parallelize various computations and provide an integrative program that reduces creating a production-quality classifier to a single program call. The new implementation is available as a Debian package under a free academic license and does not depend on commercial software. For non-Debian based distributions, the source package ships with a traditional Makefile-based installer. Download and installation instructions can be found at https://rostlab.org/owiki/index.php/Fast_Profile_Kernel. Bugs and other issues may be reported at https://rostlab.org/bugzilla3/enter_bug.cgi?product=fastprofkernel.

Nature Communications 6: Article number: 7866 (2015); Published: 22 July 2015; Updated: 10 February 2016. The original version of this Article contained an error in the spelling of the author Edda Kloppmann, which was incorrectly given as Edda Kloppman. This has now been corrected in both the PDF and HTML versions of the Article.

The intricate molecular details of protein-protein interactions (PPIs) are crucial for function. Therefore, measuring the same interacting protein pair again, we expect the same result. This work measured the similarity in the molecular details of interaction for the same and for homologous protein pairs between different experiments. All scores analyzed suggested that different experiments often find exceptions in the interfaces of similar PPIs: up to 22% of all comparisons revealed some differences even for sequence-identical pairs of proteins. The corresponding number for pairs of close homologs reached 68%. Conversely, the interfaces differed entirely for 12-29% of all comparisons. All these estimates were calculated after redundancy reduction. The magnitude of interface differences ranged from subtle to the extreme, as illustrated by a few examples. An extreme case was a change of the interacting domains between two observations of the same biological interaction. One reason for different interfaces was the number of copies of an interaction in the same complex: the probability of observing alternative binding modes increases with the number of copies. Even after removing the special cases with alternative hetero-interfaces to the same homomer, a substantial variability remained. Our results strongly support the surprising notion that there are many alternative solutions to make the intricate molecular details of PPIs crucial for function.

The soluble monomeric domain of lipoprotein YxeF from the Gram positive bacterium B. subtilis was selected by the Northeast Structural Genomics Consortium (NESG) as a target of a biomedical theme project focusing on the structure determination of the soluble domains of bacterial lipoproteins. The solution NMR structure of YxeF reveals a calycin fold and distant homology with the lipocalin Blc from the Gram-negative bacterium E.coli. In particular, the characteristic β-barrel, which is open to the solvent at one end, is extremely well conserved in YxeF with respect to Blc. The identification of YxeF as the first lipocalin homologue occurring in a Gram-positive bacterium suggests that lipocalins emerged before the evolutionary divergence of Gram positive and Gram negative bacteria. Since YxeF is devoid of the α-helix that packs in all lipocalins with known structure against the β-barrel to form a second hydrophobic core, we propose to introduce a new lipocalin sub-family named 'slim lipocalins', with YxeF and the other members of Pfam family PF11631 to which YxeF belongs constituting the first representatives. The results presented here exemplify the impact of structural genomics to enhance our understanding of biology and to generate new biological hypotheses.

Disordered proteins are highly abundant in regulatory processes such as transcription and cell-signaling. Different methods have been developed to predict protein disorder often focusing on different types of disordered regions. Here, we present MD, a novel META-Disorder prediction method that molds various sources of information predominantly obtained from orthogonal prediction methods, to significantly improve in performance over its constituents. In sustained cross-validation, MD not only outperforms its origins, but it also compares favorably to other state-of-the-art prediction methods in a variety of tests that we applied.http://www.rostlab.org/services/md/

Natively unstructured or disordered protein regions may increase the functional complexity of an organism; they are particularly abundant in eukaryotes and often evade structure determination. Many computational methods predict unstructured regions by training on outliers in otherwise well-ordered structures. Here, we introduce an approach that uses a neural network in a very different and novel way. We hypothesize that very long contiguous segments with nonregular secondary structure (NORS regions) differ significantly from regular, well-structured loops, and that a method detecting such features could predict natively unstructured regions. Training our new method, NORSnet, on predicted information rather than on experimental data yielded three major advantages: it removed the overlap between testing and training, it systematically covered entire proteomes, and it explicitly focused on one particular aspect of unstructured regions with a simple structural interpretation, namely that they are loops. Our hypothesis was correct: well-structured and unstructured loops differ so substantially that NORSnet succeeded in their distinction. Benchmarks on previously used and new experimental data of unstructured regions revealed that NORSnet performed very well. Although it was not the best single prediction method, NORSnet was sufficiently accurate to flag unstructured regions in proteins that were previously not annotated. In one application, NORSnet revealed previously undetected unstructured regions in putative targets for structural genomics and may thereby contribute to increasing structural coverage of large eukaryotic families. NORSnet found unstructured regions more often in domain boundaries than expected at random. In another application, we estimated that 50%-70% of all worm proteins observed to have more than seven protein-protein interaction partners have unstructured regions. The comparative analysis between NORSnet and DISOPRED2 suggested that long unstructured loops are a major part of unstructured regions in molecular networks.

Protein-protein interactions, a key to almost any biological process, are mediated by molecular mechanisms that are not entirely clear. The study of these mechanisms often focuses on all residues at protein-protein interfaces. However, only a small subset of all interface residues is actually essential for recognition or binding. Commonly referred to as "hotspots," these essential residues are defined as residues that impede protein-protein interactions if mutated. While no in silico tool identifies hotspots in unbound chains, numerous prediction methods were designed to identify all the residues in a protein that are likely to be a part of protein-protein interfaces. These methods typically identify successfully only a small fraction of all interface residues. Here, we analyzed the hypothesis that the two subsets correspond (i.e., that in silico methods may predict few residues because they preferentially predict hotspots). We demonstrate that this is indeed the case and that we can therefore predict directly from the sequence of a single protein which residues are interaction hotspots (without knowledge of the interaction partner). Our results suggested that most protein complexes are stabilized by similar basic principles. The ability to accurately and efficiently identify hotspots from sequence enables the annotation and analysis of protein-protein interaction hotspots in entire organisms and thus may benefit function prediction and drug development. The server for prediction is available at http://www.rostlab.org/services/isis.

Experimental high-throughput studies of protein-protein interactions are beginning to provide enough data for comprehensive computational studies. Today, about ten large data sets, each with thousands of interacting pairs, coarsely sample the interactions in fly, human, worm, and yeast. Another about 55,000 pairs of interacting proteins have been identified by more careful, detailed biochemical experiments. Most interactions are experimentally observed in prokaryotes and simple eukaryotes; very few interactions are observed in higher eukaryotes such as mammals. It is commonly assumed that pathways in mammals can be inferred through homology to model organisms, e.g. the experimental observation that two yeast proteins interact is transferred to infer that the two corresponding proteins in human also interact. Two pairs for which the interaction is conserved are often described as interologs. The goal of this investigation was a large-scale comprehensive analysis of such inferences, i.e. of the evolutionary conservation of interologs. Here, we introduced a novel score for measuring the overlap between protein-protein interaction data sets. This measure appeared to reflect the overall quality of the data and was the basis for our two surprising results from our large-scale analysis. Firstly, homology-based inferences of physical protein-protein interactions appeared far less successful than expected. In fact, such inferences were accurate only for extremely high levels of sequence similarity. Secondly, and most surprisingly, the identification of interacting partners through sequence similarity was significantly more reliable for protein pairs within the same organism than for pairs between species. Our analysis underlined that the discrepancies between different datasets are large, even when using the same type of experiment on the same organism. This reality considerably constrains the power of homology-based transfer of interactions. In particular, the experimental probing of interactions in distant model organisms has to be undertaken with some caution. More comprehensive images of protein-protein networks will require the combination of many high-throughput methods, including in silico inferences and predictions. http://www.rostlab.org/results/2006/ppi_homology/

RIKEN's FANTOM project has revealed many previously unknown coding sequences, as well as an unexpected degree of variation in transcripts resulting from alternative promoter usage and splicing. Ever more transcripts that do not code for proteins have been identified by transcriptome studies, in general. Increasing evidence points to the important cellular roles of such non-coding RNAs (ncRNAs). The distinction of protein-coding RNA transcripts from ncRNA transcripts is therefore an important problem in understanding the transcriptome and carrying out its annotation. Very few in silico methods have specifically addressed this problem. Here, we introduce CONC (for "coding or non-coding"), a novel method based on support vector machines that classifies transcripts according to features they would have if they were coding for proteins. These features include peptide length, amino acid composition, predicted secondary structure content, predicted percentage of exposed residues, compositional entropy, number of homologs from database searches, and alignment entropy. Nucleotide frequencies are also incorporated into the method. Confirmed coding cDNAs for eukaryotic proteins from the Swiss-Prot database constituted the set of true positives, ncRNAs from RNAdb and NONCODE the true negatives. Ten-fold cross-validation suggested that CONC distinguished coding RNAs from ncRNAs at about 97% specificity and 98% sensitivity. Applied to 102,801 mouse cDNAs from the FANTOM3 dataset, our method reliably identified over 14,000 ncRNAs and estimated the total number of ncRNAs to be about 28,000.