Biology subjects

Rost, B.

Publications and source records attributed to Rost, B..

At least 55 records · Page 3Linked to original sources

bioRxiv2022

CATHe: Detection of remote homologues for CATH superfamilies using embeddings from protein language models

1.CATH is a protein domain classification resource that combines an automated workflow of structure and sequence comparison alongside expert manual curation to construct a hierarchical classification of evolutionary and structural relationships. The aim of this study was to develop algorithms for detecting remote homologues that might be missed by state-of-the-art HMM-based approaches. The proposed algorithm for this task (CATHe) combines a neural network with sequence representations obtained from protein language models. The employed dataset consisted of remote homologues that had less than 20% sequence identity. The CATHe models trained on 1773 largest, and 50 largest CATH superfamilies had an accuracy of 85.6+-0.4, and 98.15+-0.30 respectively. To examine whether CATHe was able to detect more remote homologues than HMM-based approaches, we employed a dataset consisting of protein regions that had annotations in Pfam, but not in CATH. For this experiment, we used highly reliable CATHe predictions (expected error rate <0.5%), which provided CATH annotations for 4.62 million Pfam domains. For a subset of these domains from homo sapiens, we structurally validated 90.86% of the predictions by comparing their corresponding AlphaFold structures with experimental structures from the CATHe predicted superfamilies.

bioinformatics↗

bioRxiv2022

Bee core venom genes predominantly originated before aculeate stingers evolved

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. Utilising a combination of genomic and proteo-transcriptomic data, we investigated the origin of 11 toxin genes in 29 published and three 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. 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.

evolutionary biology↗

bioRxiv2021

Contrastive learning on protein embeddings enlightens midnight zone at lightning speed

Experimental structures are leveraged through multiple sequence alignments, or more generally through homology-based inference (HBI), facilitating the transfer of information from a protein with known annotation to a query without any annotation. A recent alternative expands the concept of HBI from sequence-distance lookup to embedding-based annotation transfer (EAT). These embeddings are derived from protein Language Models (pLMs). Here, we introduce using single protein representations from pLMs for contrastive learning. This learning procedure creates a new set of embeddings that optimizes constraints captured by hierarchical classifications of protein 3D structures defined by the CATH resource. The approach, dubbed ProtTucker, has an improved ability to recognize distant homologous relationships than more traditional techniques such as threading or fold recognition. Thus, these embeddings have allowed sequence comparison to step into the "midnight zone" of protein similarity, i.e., the region in which distantly related sequences have a seemingly random pairwise sequence similarity. The novelty of this work is in the particular combination of tools and sampling techniques that ascertained good performance comparable or better to existing state-of-the-art sequence comparison methods. Additionally, since this method does not need to generate alignments it is also orders of magnitudes faster. The code is available at https://github.com/Rostlab/EAT.

bioinformatics↗

bioRxiv2021

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.

bioinformatics↗

bioRxiv2021

Protein language model embeddings for fast, accurate, alignment-free protein structure prediction

All state-of-the-art (SOTA) protein structure predictions rely on evolutionary information captured in multiple sequence alignments (MSAs), primarily on evolutionary couplings (co-evolution). Such information is not available for all proteins and is computationally expensive to generate. Prediction models based on Artificial Intelligence (AI) using only single sequences as input are easier and cheaper but perform so poorly that speed becomes irrelevant. Here, we described the first competitive AI solution exclusively inputting embeddings extracted from pre-trained protein Language Models (pLMs), namely from the transformer pLM ProtT5, from single sequences into a relatively shallow (few free parameters) convolutional neural network (CNN) trained on inter-residue distances, i.e. protein structure in 2D. The major advance originated from processing the attention heads learned by ProtT5. Although these models required at no point any MSA, they matched the performance of methods relying on co-evolution. Although not reaching the very top, our lean approach came close at substantially lower costs thereby speeding up development and each future prediction. By generating protein-specific rather than family-averaged predictions, these new solutions could distinguish between structural features differentiating members of the same family of proteins with similar structure predicted alike by all other top methods.

bioinformatics↗

bioRxiv2021

Light Attention Predicts Protein Location from the Language of Life

SummaryAlthough knowing where a protein functions in a cell is important to characterize biological processes, this information remains unavailable for most known proteins. Machine learning narrows the gap through predictions from expert-designed input features leveraging information from multiple sequence alignments (MSAs) that is resource expensive to generate. Here, we showcased using embeddings from protein language models (pLMs) for competitive localization prediction without MSAs. Our lightweight deep neural network architecture used a softmax weighted aggregation mechanism with linear complexity in sequence length referred to as light attention (LA). The method significantly outperformed the state-of-the-art (SOTA) for ten localization classes by about eight percentage points (Q10). So far, this might be the highest improvement of just embeddings over MSAs. Our new test set highlighted the limits of standard static data sets: while inviting new models, they might not suffice to claim improvements over the SOTA. AvailabilityOnline predictions are available at http://embed.protein.properties. Predictions for the human proteome are available at https://zenodo.org/record/5047020. Code is provided at https://github.com/HannesStark/protein-localization.

bioinformatics↗

bioRxiv2021

PredictProtein - Predicting Protein Structure and Function for 29 Years

Since 1992 PredictProtein (https://predictprotein.org) is a one-stop online resource for protein sequence analysis with its main site hosted at the Luxembourg Centre for Systems Biomedicine (LCSB) and queried monthly by over 3,000 users in 2020. PredictProtein was the first Internet server for protein predictions. It pioneered combining evolutionary information and machine learning. Given a protein sequence as input, the server outputs multiple sequence alignments, predictions of protein structure in 1D and 2D (secondary structure, solvent accessibility, transmembrane segments, disordered regions, protein flexibility, and disulfide bridges) and predictions of protein function (functional effects of sequence variation or point mutations, Gene Ontology (GO) terms, subcellular localization, and protein-, RNA-, and DNA binding). PredictProteins infrastructure has moved to the LCSB increasing throughput; the use of MMseqs2 sequence search reduced runtime five-fold; user interface elements improved usability, and new prediction methods were added. PredictProtein recently included predictions from deep learning embeddings (GO and secondary structure) and a method for the prediction of proteins and residues binding DNA, RNA, or other proteins. PredictProtein.org aspires to provide reliable predictions to computational and experimental biologists alike. All scripts and methods are freely available for offline execution in high-throughput settings. AvailabilityFreely accessible webserver PredictProtein.org; Source and docker images: github.com/rostlab

bioinformatics↗

bioRxiv2021

Clustering FunFams using sequence embeddings improves EC purity

MotivationClassifying proteins into functional families can improve our understanding of protein function and can allow transferring annotations within one family. For this, functional families need to be "pure", i.e., contain only proteins with identical function. Functional Families (FunFams) cluster proteins within CATH superfamilies into such groups of proteins sharing function. 11% of all FunFams (22,830 of 203,639) contain EC annotations and of those, 7% (1,526 of 22,830) have inconsistent functional annotations. ResultsWe propose an approach to further cluster FunFams into functionally more consistent sub-families by encoding their sequences through embeddings. These embeddings originate from language models transferring knowledge gained from predicting missing amino acids in a sequence (ProtBERT) and have been further optimized to distinguish between proteins belonging to the same or a different CATH superfamily (PB-Tucker). Using distances between embeddings and DBSCAN to cluster FunFams and identify outliers, doubled the number of pure clusters per FunFam compared to random clustering. Our approach was not limited to FunFams but also succeeded on families created using sequence similarity alone. Complementing EC annotations, we observed similar results for binding annotations. Thus, we expect an increased purity also for other aspects of function. Our results can help generating FunFams; the resulting clusters with improved functional consistency allow more reliable inference of annotations. We expect this approach to succeed equally for any other grouping of proteins by their phenotypes. AvailabilityCode and embeddings are available via GitHub: https://github.com/Rostlab/FunFamsClustering

bioinformatics↗

bioRxiv2020

Embeddings from deep learning transfer GO annotations beyond homology

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 <20% pairwise sequence identity to the query, performance drops (Fmax BPO 33{+/-}2%, MFO 43{+/-}3%, CCO 53{+/-}2%); this still outperforms naive sequence-based transfer. Preliminary results from CAFA4 appear to confirm these findings. Overall, this new concept is likely to change the annotation of proteins, in particular for proteins from smaller families or proteins with intrinsically disordered regions.

bioinformatics↗

bioRxiv2020

Systematic modeling of SARS-CoV-2 protein structures

In response to the COVID-19 pandemic, many life scientists are focused on SARS-CoV-2. To help them use available structural data, we systematically modeled all viral proteins using all related 3D structures, generating 872 models that provide detail not available elsewhere. To organise these models, we created a structural coverage map: a novel, one-stop visualization summarizing what is -- and is not -- known about the 3D structure of the viral proteome. The map highlights structural evidence for viral protein interactions, mimicry, and hijacking; it also helps researchers find 3D models of interest, which can then be mapped with UniProt, PredictProtein, or CATH features. The resulting Aquaria-COVID resource (https://aquaria.ws/covid) helps scientists understand molecular mechanisms underlying coronavirus infection. Based on insights gained using our resource, we propose mechanisms by which the virus may enter immune cells, sense the cell type, then switch focus from viral reproduction to disrupting host immune responses. SignificanceCurrently, much of the COVID-19 viral proteome has unknown molecular structure. To improve this, we generated [~]1,000 structural models, designed to capture multiple states for each viral protein. To organise these models, we created a structure coverage map: a novel, one-stop visualization summarizing what is -- and is not -- known about viral protein structure. We used these data to create an online resource, designed to help COVID-19 researchers gain insight into the key molecular processes that drive infection. Based on insights gained using our resource, we speculate that the virus may sense the type of cells it infects and, within certain cells, it may switch from reproduction to disruption of the immune system.

bioinformatics↗

bioRxiv2020

Serotonin suppresses slow oscillations by activating somatostatin interneurons via the 5-HT2A receptor

Serotonin (5-HT) is one of the major neuromodulators present in the mammalian brain and has been shown to play a role in multiple physiological processes. The mechanisms by which 5-HT modulates cortical network activity, however, are not yet fully understood. We investigated the effects of 5-HT on slow oscillations (SOs), a synchronized cortical network activity universally present across species. SOs are observed during anesthesia and are considered to be the default cortical activity pattern. We discovered that ({+/-})3,4-methylenedioxymethamphetamine (MDMA) and fenfluramine, two potent 5-HT releasers, inhibit SOs within the entorhinal cortex (EC) in anesthetized mice. Combining opto- and pharmacogenetic manipulations with in vitro electrophysiological recordings, we uncovered that somatostatin-expressing (Sst) interneurons activated by the 5-HT2A receptor (5-HT2AR) play an important role in the suppression of SOs. Since 5-HT2AR signaling is involved in the etiology of different psychiatric disorders and mediates the psychological effects of many psychoactive serotonergic drugs, we propose that the newly discovered link between Sst interneurons and 5-HT will contribute to our understanding of these complex topics.

neuroscience↗

bioRxiv2019

Identifying and engineering ancient variants of enzymes using Graphical Representation of Ancestral Sequence Predictions (GRASP)

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. Author summaryMassive sequencing projects expose the extent of natural, genetic diversity. Here, we describe a method with capacity to perform ancestor sequence reconstruction from data sets in excess of 10,000 sequences, poised to recover ancestral diversity, including the evolutionary events that determine present-time biological function and structure. We introduce a novel strategy for suggesting "indel variants" that are distinct from, but can be explored alongside, substitution variants for creating ancestral libraries. We demonstrate how indels can be used as building blocks to form "hybrid ancestors"; based on this strategy, we synthesise ancestor variants, with varying enzymatic activities, for wide-ranging applications in the biotechnology sector.

bioinformatics↗

bioRxiv2019

An exhaustive analysis of single amino acid variants in helical transmembrane proteins

Single nucleotide variants (SNVs) have been widely studied in the past due to being the main source of human genetic variation. Less is known about the effect of single amino acid variants (SAVs) due to the immense resources required for comprehensive experimental studies. In contrast, in silico methods predicting the effects of sequence variants upon molecular function and upon the organism are readily available and have contributed unexpected suggestions, e.g. that SAVs common to a human population (shared by >5% of the population) have, on average, more significant impact on the molecular function of proteins than do rare SAVs (shared by <1% of the population). Here, we investigated the impact of variants in a human population upon helical transmembrane proteins (TMPs). Three main results stood out. Firstly, common SAVs, on average, have stronger effects than rare SAVs for TMPs, and are enriched, in particular, in the membrane helices. Secondly, proteins with seven transmembrane helices (7TM, including GPCRs, i.e. G protein-coupled receptors) are depleted of SAVs in comparison to other proteins, possibly due to increased evolutionary constraints in these important proteins. Thirdly, rare SAVs with strong effect are significantly absent (over common SAVs) in signal peptide regions.

bioinformatics↗

bioRxiv2019

End-to-end multitask learning, from protein language to protein features without alignments

Correctly predicting features of protein structure and function from amino acid sequence alone remains a supreme challenge for computational biology. For almost three decades, state-of-the-art approaches combined machine learning and evolutionary information from multiple sequence alignments. Exponentially growing sequence databases make it infeasible to gather evolutionary information for entire microbiomes or meta-proteomics. On top, for many important proteins (e.g. dark proteome and intrinsically disordered proteins) evolutionary information remains limited. Here, we introduced a novel approach combining recent advances of Language Models (LMs) with multi-task learning to successfully predict aspects of protein structure (secondary structure) and function (cellular component or subcellular localization) without using any evolutionary information from alignments. Our approach fused self-supervised pre-training LMs on an unlabeled big dataset (UniRef50, corresponding to 9.6 billion words) with supervised training on labelled high-quality data in one single end-to-end network. We provided a proof-of-principle for the novel concept through the semi-successful per-residue prediction of protein secondary structure and through per-protein predictions of localization (Q10=69%) and the distinction between integral membrane and water-soluble proteins (Q2=89%). Although these results did not reach the levels obtained by the best available methods using evolutionary information from alignments, these less accurate multi-task predictions have the advantage of speed: they are 300-3000 times faster (where HHblits needs 30-300 seconds on average, our method needed 0.045 seconds). These new results push the boundaries of predictability towards grayer and darker areas of the protein space, allowing to make reliable predictions for proteins which were not accessible by previous methods. On top, our method remains scalable as it removes the necessity to search sequence databases for evolutionary related proteins.

bioinformatics↗

bioRxiv2019

Variant effect predictions capture some aspects of deep mutational scanning experiments

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) for particular proteins. Different experimental protocols proxy effect through a diversity of measures. We evaluated three early prediction methods trained on traditional variant effect data (PolyPhen-2, SIFT, SNAP2) along with a regression method optimized on DMS data (Envision). On a common subset of 32,981 SAVs, all methods capture some aspects of variant effects, albeit not the same. Early effect prediction methods correlated slightly more with measurements and better classified binary states (effect or neutral), while Envision predicted better the precise degree of effect. Most surprising was that a simple approach predicting residues conserved in families (found and aligned by PSI-BLAST) in many cases outperformed other methods. All methods predicted beneficial effects (gain-of-function) significantly worse than deleterious (loss-of-function). For the few proteins with several DMS measurements, experiments agreed more with each other than predictions with experiments. Our findings highlight challenges and opportunities of DMS for improving variant effect predictions.

bioinformatics↗

bioRxiv2019

Spectrum of protein localization in proteomes captures evolutionary relation between species

The native subcellular localization or cellular compartment of a protein is the one in which it acts most often; it is one aspect of protein function. Do ten eukaryotic model organisms differ in their location spectrum, i.e. the fraction of its proteome in each of its seven major compartments? As experimental annotations of locations remain biased and incomplete, we need prediction methods to answer this question. To gauge the bias of prediction methods, we merged all available experimental annotations for the human proteome. In doing so, we found important values in both Swiss-Prot and the Human Protein Atlas (HPA). After systematic bias corrections, the complete but faulty prediction methods appeared to be more appropriate to compare location spectra between species than the incomplete more accurate experimental data. This work compared the location spectra for ten eukaryotes: Homo sapiens, Gorilla gorilla, Pan troglodytes, Mus musculus, Rattus norvegicus, Drosophila melanogaster, Anopheles gambiae, Caenorhabitis elegans, Saccharomyces cerevisiae and Schizosaccharomyces pombe. Overall, the predicted location spectra were similar. However, the detailed differences were significant enough to plot trees and 2D (PCA) maps relating the ten organisms using a simple Euclidean distance in seven states, corresponding to the seven studied localization classes. The relations based on the simple predicted location spectra captured aspects of cross-species comparisons usually revealed only by much more detailed evolutionary comparisons.

bioinformatics↗

bioRxiv2019

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

The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. 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 (P. aureginosa only). We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. 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 expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. We finally report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bioontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

bioinformatics↗

bioRxiv2019

Modeling the Language of Life - Deep Learning Protein Sequences

BackgroundOne common task in Computational Biology is the prediction of aspects of protein function and structure from their amino acid sequence. For 26 years, most state-of-the-art approaches toward this end have been marrying machine learning and evolutionary information. The retrieval of related proteins from ever growing sequence databases is becoming so time-consuming that the analysis of entire proteomes becomes challenging. On top, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome.\n\nResultsWe introduce a novel way to represent protein sequences as continuous vectors (embeddings) by using the deep bi-directional model ELMo taken from natural language processing (NLP). The model has effectively captured the biophysical properties of protein sequences from unlabeled big data (UniRef50). After training, this knowledge is transferred to single protein sequences by predicting relevant sequence features. We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple convolutional neural networks on existing data sets for two completely different prediction tasks. At the per-residue level, we significantly improved secondary structure (for NetSurfP-2.0 data set: Q3=79%{+/-}1, Q8=68%{+/-}1) and disorder predictions (MCC=0.59{+/-}0.03) over methods not using evolutionary information. At the per-protein level, we predicted subcellular localization in ten classes (for DeepLoc data set: Q10=68%{+/-}1) and distinguished membrane-bound from water-soluble proteins (Q2= 87%{+/-}1). All results built upon the embeddings gained from the new tool SeqVec neither explicitly nor implicitly using evolutionary information. Nevertheless, it improved over some methods using such information. Where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created the vector representation on average in 0.03 seconds.\n\nConclusionWe have shown that transfer learning can be used to capture biochemical or biophysical properties of protein sequences from large unlabeled sequence databases. The effectiveness of the proposed approach was showcased for different prediction tasks using only single protein sequences. SeqVec embeddings enable predictions that outperform even some methods using evolutionary information. Thus, they prove to condense the underlying principles of protein sequences. This might be the first step towards competitive predictions based only on single protein sequences.\n\nAvailabilitySeqVec: https://github.com/mheinzinger/SeqVec Prediction server: https://embed.protein.properties

bioinformatics↗