Sequence-based Information Research Articles

DeepNeoAG: Neoantigen epitope prediction from melanoma antigens using a synergistic deep learning model combining protein language models and multi-window scanning convolutional neural networks

Neoantigens, derived from tumor-specific mutations, play a crucial role in eliciting anti-tumor immune responses and have emerged as promising targets for personalized cancer immunotherapy. Accurately identifying neoantigens from a vast pool of potential candidates is crucial for developing effective therapeutic strategies. This study presents a novel deep learning model that leverages the power of protein language models (PLMs) and multi-window scanning convolutional neural networks (CNNs) to predict neoantigens from normal tumor antigens with high accuracy. In this study, we present DeepNeoAG, a novel framework combines the global sequence-level information captured by a pre-trained PLM with the local sequence-based information features extracted by a multi-window scanning CNN, enabling a comprehensive representation of the protein's mutational landscape. We demonstrate the superior performance of DeepNeoAG compared to existing methods and highlight its potential to accelerate the development of personalized cancer immunotherapies.

PLMC: Language Model of Protein Sequences Enhances Protein Crystallization Prediction.

X-ray diffraction crystallography has been most widely used for protein three-dimensional (3D) structure determination for which whether proteins are crystallizable is a central prerequisite. Yet, there are a number of procedures during protein crystallization, including protein material production, purification, and crystal production, which take turns affecting the crystallization outcome. Due to the expensive and laborious nature of this multi-stage process, various computational tools have been developed to predict protein crystallization propensity, which is then used to guide the experimental determination. In this study, we presented a novel deep learning framework, PLMC, to improve multi-stage protein crystallization propensity prediction by leveraging a pre-trained protein language model. To effectively train PLMC, two groups of features of each protein were integrated into a more comprehensive representation, including protein language embeddings from the large-scale protein sequence database and a handcrafted feature set consisting of physicochemical, sequence-based and disordered-related information. These features were further separately embedded for refinement, and then concatenated for the final prediction. Notably, our extensive benchmarking tests demonstrate that PLMC greatly outperforms other state-of-the-art methods by achieving AUC scores of 0.773, 0.893, and 0.913, respectively, at the aforementioned individual stages, and 0.982 at the final crystallization stage. Furthermore, PLMC is shown to be superior for predicting the crystallization of both globular and membrane proteins, as demonstrated by an AUC score of 0.991 for the latter. These results suggest the significant potential of PLMC in assisting researchers with the experimental design of crystallizable protein variants.

Machine learning approaches for influenza A virus risk assessment identifies predictive correlates using ferret model in vivo data

In vivo assessments of influenza A virus (IAV) pathogenicity and transmissibility in ferrets represent a crucial component of many pandemic risk assessment rubrics, but few systematic efforts to identify which data from in vivo experimentation are most useful for predicting pathogenesis and transmission outcomes have been conducted. To this aim, we aggregated viral and molecular data from 125 contemporary IAV (H1, H2, H3, H5, H7, and H9 subtypes) evaluated in ferrets under a consistent protocol. Three overarching predictive classification outcomes (lethality, morbidity, transmissibility) were constructed using machine learning (ML) techniques, employing datasets emphasizing virological and clinical parameters from inoculated ferrets, limited to viral sequence-based information, or combining both data types. Among 11 different ML algorithms tested and assessed, gradient boosting machines and random forest algorithms yielded the highest performance, with models for lethality and transmission consistently better performing than models predicting morbidity. Comparisons of feature selection among models was performed, and highest performing models were validated with results from external risk assessment studies. Our findings show that ML algorithms can be used to summarize complex in vivo experimental work into succinct summaries that inform and enhance risk assessment criteria for pandemic preparedness that take in vivo data into account.

DP-site: A dual deep learning-based method for protein-peptide interaction site prediction

BackgroundProtein-peptide interaction prediction is an important topic for several applications including various biological processes, understanding drug discovery, protein function abnormal cellular behaviors, and treating diseases. Over the years, studies have shown that experimental methods have improved the identification of this bio-molecular interaction. However, predicting protein-peptide interactions using these methods is laborious, time-consuming, dependent on third-party tools, and costly. MethodTo address these previous drawbacks, this study introduces a computational framework called DP-Site. The proposed framework concentrates on using a compound of a dual pipeline along with a combination predictor. A deep convolutional neural network for feature extraction and classification is embedded in pipeline 1. In addition, pipeline 2 includes a deep long-short-term memory-based and a random forest classifier for feature extraction and classification. In this investigation, the evolutionary, structure-based, sequence-based, and physicochemical information of proteins is utilized for identifying protein-peptide interaction at the residue level. ResultsThe proposed method is evaluated on both the ten-fold cross-validation and independent test sets. The robust and consistent results between cross-validation and independent test sets confirm the ability of the proposed method to predict peptide binding residues in proteins. Moreover, experimental findings demonstrate that DP-Site has significantly outperformed other state-of-the-art sequence-based and structure-based methods. The proposed method achieves a remarkable balance between a specificity of 0.799 and a sensitivity of 0.770, along with the best f-measure of 0.661 and the highest precision of 0.580 using an independent test set. ConclusionsThe outcome of various experiments confirms the proficiency of the proposed method and outperforms state-of-the-art sequence-based and structure-based methods in terms of the mentioned criteria. DP-Site can be accessed at https://github.com/shafiee 95/shima.shafiee.DP-Site.

DeepSS2GO: protein function prediction from secondary structure.

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

Abstract 3534: GeneLLM: Unveiling gene functions through literature-driven transformer embeddings

Abstract INTRODUCTION: Our understanding of gene properties has advanced through representation learning such as Alpha fold. Representation learning involves encoding the relationships between genes by embedding them into a numerical space. These embeddings, which capture complex genetic interactions and characteristics, can then be leveraged by machine learning models to predict various gene properties. Current embeddings derive from transcriptome or sequence data. Over the past 150 years, numerous experimental assays have uncovered gene functions and interactions- comprehensive knowledge documented in the literature but not always evident in transcriptome or sequence data. It has been posited that leveraging this knowledge to create gene embeddings; however, could result in machine learning models biased towards well-studied genes. METHODS AND RESULTS: We tested this hypothesis by developing a novel knowledge-embedding framework, GeneLLM. During training, GeneLLM learns to comprehend summaries of every gene- a compressed form of published knowledge- using Large Language Models (LLMs), fine-tuned for downstream tasks mapping cellular properties and biochemical processes. Despite the expected bias towards well-known genes, GeneLLM surprisingly showed high predictive power for an array of gene properties. Compared to baseline models, GeneLLM boosted an increase in performance of 20.3% correlation in gene conservation across species, 8.6% and 57.2% prediction accuracy in subcellular localization and gene ontology respectively. GeneLLM also showed competitive results on solubility prediction with 0.91 accuracy and a correlation of 0.71 for tissue-specific expression levels for 1001 cell lines. We also showed that the bias toward well-known genes could be mitigated by combining GeneLLM representation with transcriptome or sequence-based embedding. The combined embeddings exhibited superior performance to their individual components which suggests that GeneLLM extracts views complementary to existing embedding methods. CONCLUSION: The GeneLLM framework demonstrates the ability of LLMs to extract information from the rich knowledge available about the nexus of genes and their cellular traits. It also illustrates how bias in knowledge representation is complementary to other transcriptome and sequence-based information. This ability of GeneLLM to advance our understanding of genes, their roles in cellular processes, and their impact on oncogenesis, as well as in response and resistance mechanisms, highlights its potential in cancer research. Citation Format: Ala Jararweh, Kushal Virupakshappa, Oladimeji S. Macaulay, Aaron Segura, Olufunmilola M. Oyebamiji, Yue Hu, Avinash D. Sahu. GeneLLM: Unveiling gene functions through literature-driven transformer embeddings [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3534.

Developmental validation of the STRSeqTyper122 kit for massively parallel sequencing of forensic STRs.

Massively parallel sequencing allows for integrated genotyping of different types of forensic markers, which reduces DNA consumption, simplifies experimental processes, and provides additional sequence-based genetic information. The STRseqTyper122 kit genotypes 63 autosomal STRs, 16 X-STRs, 42 Y-STRs, and the Amelogenin locus. Amplicon sizes of 117 loci were below 300bp. In this study, MiSeq FGx sequencing metrics for STRseqTyper122 were presented. The genotyping accuracy of this kit was examined by comparing to certified genotypes of NIST standard reference materials and results from five capillary electrophoresis-based kits. The sensitivity of STRseqTyper122 reached 125pg, and > 80% of the loci were correctly called with 62.5pg and 31.25pg input genomic DNA. Repeatability, species specificity, and tolerance for DNA degradation and PCR inhibitors of this kit were also evaluated. STRseqTyper122 demonstrated reliable performance with routine case-work samples and provided a powerful tool for forensic applications.

Evolution of protein domain repertoires of CALHM6.

Calcium (Ca2+) homeostasis is essential in conducting various cellular processes including nerve transmission, muscular movement, and immune response. Changes in Ca2+concentration in the cytoplasm are significant in bringing about various immune responses such as pathogen clearance and apoptosis. Various key players are involved in calcium homeostasis such as calcium binders, pumps, and channels. Sequence-based evolutionary information has recently been exploited to predict the biophysical behaviors of proteins, giving critical clues about their functionality. Ion channels are reportedly the first channels developed during evolution. Calcium homeostasis modulator protein 6 (CALHM6) is one such channel. Comprised of a single domain called Ca_hom_mod, CALHM6 is a stable protein interacting with various other proteins in calcium regulation. No previous attempt has been made to trace the exact evolutionary events in the domain of CALHM6, leaving plenty of room for exploring its evolution across a wide range of organisms. The current study aims to answer the questions by employing a computational-based strategy that used profile Hidden Markov Models (HMMs) to scan for the CALHM6 domain, integrated the data with a time-calibrated phylogenetic tree using BEAST and Mesquite, and visualized through iTOL. Around 4,000 domains were identified, and 14,000 domain gain, loss, and duplication events were observed at the end which also included various protein domains other than CALHM6. The data were analyzed concerning CALHM6 evolution as well as the domain gain, loss, and duplication of its interacting partners: Calpain, Vinculin, protein S100-A7, Thioredoxin, Peroxiredoxin, and Calmodulin-like protein 5. Duplication events of CALHM6 near higher eukaryotes showed its increasing complexity in structure and function. This in-silico phylogenetic approach applied to trace the evolution of CALHM6 was an effective approach to get a better understanding of the protein CALHM6.

PepCNN deep learning tool for predicting peptide binding residues in proteins using sequence, structural, and language model features

Protein–peptide interactions play a crucial role in various cellular processes and are implicated in abnormal cellular behaviors leading to diseases such as cancer. Therefore, understanding these interactions is vital for both functional genomics and drug discovery efforts. Despite a significant increase in the availability of protein–peptide complexes, experimental methods for studying these interactions remain laborious, time-consuming, and expensive. Computational methods offer a complementary approach but often fall short in terms of prediction accuracy. To address these challenges, we introduce PepCNN, a deep learning-based prediction model that incorporates structural and sequence-based information from primary protein sequences. By utilizing a combination of half-sphere exposure, position specific scoring matrices from multiple-sequence alignment tool, and embedding from a pre-trained protein language model, PepCNN outperforms state-of-the-art methods in terms of specificity, precision, and AUC. The PepCNN software and datasets are publicly available at https://github.com/abelavit/PepCNN.git.

PFP-GO: Integrating protein sequence, domain and protein-protein interaction information for protein function prediction using ranked GO terms.

Protein function prediction is gradually emerging as an essential field in biological and computational studies. Though the latter has clinched a significant footprint, it has been observed that the application of computational information gathered from multiple sources has more significant influence than the one derived from a single source. Considering this fact, a methodology, PFP-GO, is proposed where heterogeneous sources like Protein Sequence, Protein Domain, and Protein-Protein Interaction Network have been processed separately for ranking each individual functional GO term. Based on this ranking, GO terms are propagated to the target proteins. While Protein sequence enriches the sequence-based information, Protein Domain and Protein-Protein Interaction Networks embed structural/functional and topological based information, respectively, during the phase of GO ranking. Performance analysis of PFP-GO is also based on Precision, Recall, and F-Score. The same was found to perform reasonably better when compared to the other existing state-of-art. PFP-GO has achieved an overall Precision, Recall, and F-Score of 0.67, 0.58, and 0.62, respectively. Furthermore, we check some of the top-ranked GO terms predicted by PFP-GO through multilayer network propagation that affect the 3D structure of the genome. The complete source code of PFP-GO is freely available at https://sites.google.com/view/pfp-go/.

Application of a Deep Learning Network for Joint Prediction of Associated Fluid Production in Unconventional Hydrocarbon Development

Machine learning (ML) approaches have risen in popularity for use in many oil and gas (O&G) applications. Time series-based predictive forecasting of hydrocarbon production using deep learning ML strategies that can generalize temporal or sequence-based information within data is fast gaining traction. The recent emphasis on hydrocarbon production provides opportunities to explore the use of deep learning ML to other facets of O&G development where dynamic, temporal dependencies exist and that also hold implications to production forecasting. This study proposes a combination of supervised and unsupervised ML approaches as part of a framework for the joint prediction of produced water and natural gas volumes associated with oil production from unconventional reservoirs in a time series fashion. The study focuses on the pay zones within the Spraberry and Wolfcamp Formations of the Midland Basin in the U.S. The joint prediction model is based on a deep neural network architecture leveraging long short-term memory (LSTM) layers. Our model has the capability to both reproduce and forecast produced water and natural gas volumes for wells at monthly resolution and has demonstrated 91 percent joint prediction accuracy to held out testing data with little disparity noted in prediction performance between the training and test datasets. Additionally, model predictions replicate water and gas production profiles to wells in the test dataset, even for circumstances that include irregularities in production trends. We apply the model in tandem with an Arps decline model to generate cumulative first and five-year estimates for oil, gas, and water production outlooks at the well and basin-levels. Production outlook totals are influenced by well completion, decline curve, and spatial and reservoir attributes. These types of model-derived outlooks can aid operators in formulating management or remedial solutions for the volumes of fluids expected from unconventional O&G development.

Biological Membrane-Penetrating Peptides: Computational Prediction and Applications.

Peptides comprise a versatile class of biomolecules that present a unique chemical space with diverse physicochemical and structural properties. Some classes of peptides are able to naturally cross the biological membranes, such as cell membrane and blood-brain barrier (BBB). Cell-penetrating peptides (CPPs) and blood-brain barrier-penetrating peptides (B3PPs) have been explored by the biotechnological and pharmaceutical industries to develop new therapeutic molecules and carrier systems. The computational prediction of peptides’ penetration into biological membranes has been emerged as an interesting strategy due to their high throughput and low-cost screening of large chemical libraries. Structure- and sequence-based information of peptides, as well as atomistic biophysical models, have been explored in computer-assisted discovery strategies to classify and identify new structures with pharmacokinetic properties related to the translocation through biomembranes. Computational strategies to predict the permeability into biomembranes include cheminformatic filters, molecular dynamics simulations, artificial intelligence algorithms, and statistical models, and the choice of the most adequate method depends on the purposes of the computational investigation. Here, we exhibit and discuss some principles and applications of these computational methods widely used to predict the permeability of peptides into biomembranes, exhibiting some of their pharmaceutical and biotechnological applications.

A multi-label learning framework for predicting antibiotic resistance genes via dual-view modeling.

The increasing prevalence of antibiotic resistance has become a global health crisis. For the purpose of safety regulation, it is of high importance to identify antibiotic resistance genes (ARGs) in bacteria. Although culture-based methods can identify ARGs relatively more accurately, the identifying process is time-consuming and specialized knowledge is required. With the rapid development of whole genome sequencing technology, researchers attempt to identify ARGs by computing sequence similarity from public databases. However, these computational methods might fail to detect ARGs due to the low sequence identity to known ARGs. Moreover, existing methods cannot effectively address the issue of multidrug resistance prediction for ARGs, which is a great challenge to clinical treatments. To address the challenges, we propose an end-to-end multi-label learning framework for predicting ARGs. More specifically, the task of ARGs prediction is modeled as a problem of multi-label learning, and a deep neural network-based end-to-end framework is proposed, in which a specific loss function is introduced to employ the advantage of multi-label learning for ARGs prediction. In addition, a dual-view modeling mechanism is employed to make full use of the semantic associations among two views of ARGs, i.e. sequence-based information and structure-based information. Extensive experiments are conducted on publicly available data, and experimental results demonstrate the effectiveness of the proposed framework on the task of ARGs prediction.

Evaluating the relevance of sequence conservation in the prediction of pathogenic missense variants.

Evolutionary information is the primary tool for detecting functional conservation in nucleic acid and protein. This information has been extensively used to predict structure, interactions and functions in macromolecules. Pathogenicity prediction models rely on multiple sequence alignment information at different levels. However, most accurate genome-wide variant deleteriousness ranking algorithms consider different features to assess the impact of variants. Here, we analyze three different ways of extracting evolutionary information from sequence alignments in the context of pathogenicity predictions at DNA and protein levels. We showed that protein sequence-based information is slightly more informative in the annotation of Clinvar missense variants than those obtained at the DNA level. Furthermore, to achieve the performance of state-of-the-art methods, such as CADD and REVEL, the conservation of reference and variant, encoded as frequencies of reference/alternate alleles or wild-type/mutant residues, should be included. Our results on a large set of missense variants show that a basic method based on three input features derived from the protein sequence profile performs similarly to the CADD algorithm which uses hundreds of genomic features. As expected, our method results in ~ 3% lower area under the receiver-operating characteristic curve (AUC). When compared with an ensemble-based algorithm (REVEL). Nevertheless, the combination of predictions of multiple methods can help to identify more reliable predictions. These observations indicate that for missense variants, evolutionary information, when properly encoded, plays the primary role in ranking pathogenicity.

Molecular mechanisms of transgenerational epigenetic inheritance.

Increasing evidence indicates that non-DNA sequence-based epigenetic information can be inherited across several generations in organisms ranging from yeast to plants to humans. This raises the possibility of heritable 'epimutations' contributing to heritable phenotypic variation and thus to evolution. Recent work has shed light on both the signals that underpin these epimutations, including DNA methylation, histone modifications and non-coding RNAs, and the mechanisms by which they are transmitted across generations at the molecular level. These mechanisms can vary greatly among species and have a more limited effect in mammals than in plants and other animal species. Nevertheless, common principles are emerging, with transmission occurring either via direct replicative mechanisms or indirect reconstruction of the signal in subsequent generations. As these processes become clearer we continue to improve our understanding of the distinctive features and relative contribution of DNA sequence and epigenetic variation to heritable differences in phenotype.

UPFPSR: a ubiquitylation predictor for plant through combining sequence information and random forest.

As one of the most significant protein post-translational modifications (PTMs) in eukaryotes, ubiquitylation plays an essential role in regulating diverse cellular functions, such as apoptosis, cell division, DNA repair and replication, intracellular transport and immune reactions. Traditional experimental methods have the defect of being time-consuming, costly and labor-intensive. Therefore, it is highly desired to develop automated computational methods that can recognize potential ubiquitylation sites rapidly and accurately. In this study, we propose a novel predictor, named UPFPSR, for predicting lysine ubiquitylation sites in plant. UPFPSR is developed using multiple physicochemical properties of amino acids and sequence-based statistical information. In order to find a suitable classification algorithm, four traditional algorithms and two deep learning networks are compared, and the random forest with superior performance is selected ultimately. An extensive benchmarking shows that UPFPSR outperforms the most advanced ubiquitylation prediction tool on each measurement indicator, with the accuracy of 77.3%, precision of 75%, recall of 81.7%, F1-score of 0.7824, and AUC of 0.84 on the independent test dataset. The results indicate that UPFPSR can provide new guidance for further experimental study on ubiquitylation. The data sets and source code used in this study are freely available at https://github.com/ysw-sunshine/UPFPSR.

Computational Prediction of N- and O-Linked Glycosylation Sites for Human and Mouse Proteins.

Protein glycosylation is one of the most complex posttranslational modifications (PTM) that play a fundamental role in protein function. Identification and annotation of these sites using experimental approaches are challenging and time consuming. Hence, there is a demand to build fast and efficient computational methods to address this problem. Here, we present the SPRINT-Gly framework containing the largest dataset and a prediction model of glycosylation sites for a given protein sequence. In this framework, we construct a large dataset containing N- and O-linked glycosylation sites of human and mouse proteins, collected from different sources. We then introduce the SPRINT-Gly method to predict putative N- and O-linked sites. SPRINT-Gly is a machine learning-based approach consisting of a number of trained predictive models for glycosylation sites in both human and mouse proteins, separately. The method is built by incorporating sequence-based, predicted structural, and physicochemical information of the neighboring residues of each N- and O-linked glycosylation site and by training deep learning neural network and support vector machine as classifiers. SPRINT-Gly outperformed other existing methods by achieving 18% and 50% higher Matthew's correlation coefficient for N- and O-linked glycosylation site prediction, respectively. SPRINT-Gly is publicly available as an online and stand-alone predictor at https://sparks-lab.org/server/sprint-gly/ .

Sequence-based assessment of expediency of tri-, tetra-, and penta-nucleotides repeat autosomal STR markers in the central Indian population using Next Generation Sequencing (NGS)

Present-day forensic DNA analysis is witnessing a paradigm shift from size-based allele determination by capillary electrophoresis (CE) to sequence-based allele determination by Next Generation Sequencing (NGS). An attempt has been made to evaluate the sequence-based allelic data at two tri (D12ATA63, D22S1045), two tetra (D18S51, D1S1656), and two penta- (Penta D, Penta E) nucleotides repeat STR markers in the central Indian population. 183.33 times allele gain has been observed in D1S1656 after evaluating individual allelic sequences in comparison to the size-based alleles. Despite not witnessing any sequence-based allele gain, highest power of discrimination (0.978), Polymorphic Information Content (0.9), Power of Exclusion (0.807), typical paternity index (5.31), Expected heterozygosity (0.906), and lowest matching probability (0.022) was observed at Penta E marker suggesting its more usefulness among the considered markers for forensic and paternity applications. A giant leap in sequence-based allelic information showed a significant increase in forensic and paternity parameters (p = 0.646) in D1S1656. Substitution of TAGA with either TAGG or TAGC was found to be responsible for the generation of sequence variant alleles in D1S1656. Besides, the observation of rs4847015 SNP in 11.5% of sequences further increases the evidentiary value of D1S1656 in comparison to other STR markers analyzed in this study.

Epigenetic Marks and Variation of Sequence-Based Information Along Genomic Regions Are Predictive of Recombination Hot/Cold Spots in Saccharomyces cerevisiae.

Characterization and identification of recombination hotspots provide important insights into the mechanism of recombination and genome evolution. In contrast with existing sequence-based models for predicting recombination hotspots which were defined in a ORF-based manner, here, we first defined recombination hot/cold spots based on public high-resolution Spo11-oligo-seq data, then characterized them in terms of DNA sequence and epigenetic marks, and finally presented classifiers to identify hotspots. We found that, in addition to some previously discovered DNA-based features like GC-skew, recombination hotspots in yeast can also be characterized by some remarkable features associated with DNA physical properties and shape. More importantly, by using DNA-based features and several epigenetic marks, we built several classifiers to discriminate hotspots from coldspots, and found that SVM classifier performs the best with an accuracy of ∼92%, which is also the highest among the models in comparison. Feature importance analysis combined with prediction results show that epigenetic marks and variation of sequence-based features along the hotspots contribute dominantly to hotspot identification. By using incremental feature selection method, an optimal feature subset that consists of much less features was obtained without sacrificing prediction accuracy.

(e)DNA-based assessments within one of the World's largest river survey programs: summarized insights from the 4th Joint Danube Survey

With the 4th Joint Danube Survey in 2019 (JDS4), for the first time, DNA- and environmental DNA-based approaches were integrated into the program of the JDS, focussing on the three biological quality elements of fish, macrozoobenthos and phytobenthos, and additionally on the sediment community (Liska et al. 2021, Weigand and Astrin 2021). The rationals for including (e)DNA-based tools into the survey's program were that i) many hard-to-identify organism groups can be assessed down to their species level, ii) taxonomic information can be unlocked even in cases where morphotaxonomic knowledge and expertise are limited, iii) all developmental stages, cryptic species and indeterminable sexes can be potentially identified, iv) taxalists relying on sequence-based information are reproducible and comparable in space and time (aspects, which are particularly important for a longitudinal survey involving many countries), and, v) this additional line of taxonomic evidence will help to draw a more precise and comprehensive picture of the Danubian biota. The target groups were assessed using group-specific (e)DNA-based metabarcoding approaches (for fish: Pont et al. 2021; macrozoobenthos: Beermann et al. 2021; phytobenthos: Zimmermann et al. 2021; sediment community: Cordier et al. 2021). The coverage of barcode libraries for Danubian biota were checked prior to conducting the metabarcoding approaches. Coverage values based on JDS3 outcomes were >90% for fish (12S, but depending on reference database), 84% for macrozoobenthos (COI) and 69% and 88% for all, respectively, only abundant phytobenthos species (18S + rbcL), so that (e)DNA-based approaches were expected to be implemented effectively from this perspective (Weigand and Astrin 2021). Although still a certain degree of methodological variation exists, the outcomes clearly demonstrate the huge potential of (e)DNA-based approaches for complementary biodiversity and ecological status class assessments: eDNA water analysis of fish revealed most of the taxa also detected by the traditional fish survey, but was particularly effective in detecting hard-to-capture benthic taxa (including endangered sturgeon species) and fish traces originating from waste water treatment plants (Pont et al. 2021). Many of the traditionally assigned macrozoobenthos species were detected by DNA metabarcoding as well, but sequence data allowed to add a plethora of new chironomid and oligochaete species to the taxalist. Molecular ecological status class assessments based on presence-absence values of macrozoobenthos species were largely congruent to traditional abundance or presence-absence-based outcomes (Beermann et al. 2021, Weigand 2021). Although traditional light microscopy, which is based on identifying phytobenthos species by their frostules, revealed a higher number of diatom species, the molecular assessment detected much more taxa (i.e. MOTUs), which await species-level taxonomic annotation in the future (Zimmermann et al. 2021). Metabarcoding of the sediment community was particularly effective to assess meiofaunal species and allowed the molecular inference of fine sediment quality based on local community structures of vulnerable nematode species (Cordier et al. 2021). Finally, all (e)DNA-based taxalists were compiled to inform invasive alien species detection in the Danube River Basin. However, despite their promising performance and large coherence with traditional outcomes during JDS4, the full potential of (e)DNA-based approaches in the context of larger environmental surveys might be further released by developing and curating catchment-specific DNA barcode reference libraries, focussing on a small(er) set of standardized (e)DNA-based approaches, integrating genetic diversity (and spatiotemporal changes thereof) in ecological status class assessments, installing a dense, large-scale environmental DNA-based screening, based on which traditional surveys can be performed at conspicuous sites, and, educating and training national authorities in state-of-the-art molecular tools. developing and curating catchment-specific DNA barcode reference libraries, focussing on a small(er) set of standardized (e)DNA-based approaches, integrating genetic diversity (and spatiotemporal changes thereof) in ecological status class assessments, installing a dense, large-scale environmental DNA-based screening, based on which traditional surveys can be performed at conspicuous sites, and, educating and training national authorities in state-of-the-art molecular tools. Already today, (e)DNA-based methods can be seen as an effective and complementary tool to provide consolidated results for biodiversity and ecological status class assessments in a highly integrative and international setup, as pursued during JDS4.