Haris Zafeiropoulos

@article{skliros_unveiling_2024,
title = {Unveiling Emerging Opportunistic Fish Pathogens in Aquaculture: A Comprehensive Seasonal Study of Microbial Composition in Mediterranean Fish Hatcheries},
author = {Dimitrios Skliros and Maria Kostakou and Constantina Kokkari and Maria Ioanna Tsertou and Christina Pavloudi and Haris Zafeiropoulos and Pantelis Katharios and Emmanouil Flemetakis},
url = {https://www.mdpi.com/2076-2607/12/11/2281
https://imbbc.hcmr.gr/wp-content/uploads/2024/11/2024-Skliros-microorganisms-45.pdf},
doi = {10.3390/microorganisms12112281},
issn = {2076-2607},
year = {2024},
date = {2024-11-12},
urldate = {2024-11-12},
journal = {Microorganisms},
volume = {12},
number = {11},
pages = {2281},
abstract = {The importance of microbial communities in fish hatcheries for fish health and welfare has been recognized, with several studies mapping these communities during healthy rearing conditions and disease outbreaks. In this study, we analyzed the bacteriome of the live feeds, such as microalgae, rotifers, and Artemia, used in fish hatcheries that produce Mediterranean species. Our goal was to provide baseline information about their structure, emphasizing in environmental putative fish pathogenic bacteria. We conducted 16S rRNA amplicon Novaseq sequencing for our analysis, and we inferred 46,745 taxonomically annotated ASVs. Results showed that incoming environmental water plays a significant role in the presence of important taxa that constitute presumptive pathogens. Bio-statistical analyses revealed a relatively stable bacteriome among seasonal samplings for every hatchery but a diverse bacteriome between sampling stations and a distinct core bacteriome for each hatchery. Analysis of putative opportunistic fish pathogenic genera revealed some co-occurrence correlation events and a high average relative abundance of Vibrio, Tenacibaculum, and Photobacterium genera in live feeds, reaching a grand mean average of up to 7.3% for the hatchery of the Hellenic Center of Marine Research (HCMR), 12% for Hatchery A, and 11.5% for Hatchery B. Mapping the bacteriome in live feeds is pivotal for understanding the marine environment and distinct aquaculture practices and can guide improvements in hatchery management, enhancing fish health and sustainability in the Mediterranean region.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{zafeiropoulos_metagoflow_2022,
title = {metaGOflow: a workflow for the analysis of marine Genomic Observatories shotgun metagenomics data},
author = {Haris Zafeiropoulos and Martin Beracochea and Stelios Ninidakis and Katrina Exter and Antonis Potirakis and Gianluca De Moro and Lorna Richardson and Erwan Corre and João Machado and Evangelos Pafilis and Georgios Kotoulas and Ioulia Santi and Robert D Finn and Cymon J Cox and Christina Pavloudi},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2023/10/2023-Zafeiropoulos-GiGa-57.pdf
https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giad078/7321054},
doi = {10.1093/gigascience/giad078},
issn = {2047-217X},
year = {2023},
date = {2023-10-19},
urldate = {2023-10-23},
journal = {GigaScience},
volume = {12},
pages = {giad078},
abstract = {Abstract

Background
Genomic Observatories (GOs) are sites of long-term scientific study that undertake regular assessments of the genomic biodiversity. The European Marine Omics Biodiversity Observation Network (EMO BON) is a network of GOs that conduct regular biological community samplings to generate environmental and metagenomic data of microbial communities from designated marine stations around Europe. The development of an effective workflow is essential for the analysis of the EMO BON metagenomic data in a timely and reproducible manner.


Findings
Based on the established MGnify resource, we developed metaGOflow. metaGOflow supports the fast inference of taxonomic profiles from GO-derived data based on ribosomal RNA genes and their functional annotation using the raw reads. Thanks to the Research Object Crate packaging, relevant metadata about the sample under study, and the details of the bioinformatics analysis it has been subjected to, are inherited to the data product while its modular implementation allows running the workflow partially. The analysis of 2 EMO BON samples and 1 Tara Oceans sample was performed as a use case.


Conclusions
metaGOflow is an efficient and robust workflow that scales to the needs of projects producing big metagenomic data such as EMO BON. It highlights how containerization technologies along with modern workflow languages and metadata package approaches can support the needs of researchers when dealing with ever-increasing volumes of biological data. Despite being initially oriented to address the needs of EMO BON, metaGOflow is a flexible and easy-to-use workflow that can be broadly used for one-sample-at-a-time analysis of shotgun metagenomics data.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{rios_garza_metabolic_2023,
title = {Metabolic models of human gut microbiota: Advances and challenges},
author = {Daniel Rios Garza and Didier Gonze and Haris Zafeiropoulos and Bin Liu and Karoline Faust},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2023/02/2023-Rios-Garza-Cell-Systems-reprint12.pdf
https://linkinghub.elsevier.com/retrieve/pii/S2405471222004379},
doi = {10.1016/j.cels.2022.11.002},
issn = {24054712},
year = {2023},
date = {2023-02-28},
urldate = {2023-02-28},
journal = {Cell Systems},
volume = {14},
number = {2},
pages = {109--121},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{pavloudi_deciphering_2022,
title = {Deciphering the community structure and the functional potential of a hypersaline marsh microbial mat community},
author = {Christina Pavloudi and Haris Zafeiropoulos},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2022/12/2022-Pavloudi-Zafeiropoulos-FEMS-preprint.pdf
https://academic.oup.com/femsec/article/doi/10.1093/femsec/fiac141/6843573},
doi = {10.1093/femsec/fiac141},
issn = {1574-6941},
year = {2022},
date = {2022-12-12},
urldate = {2022-12-13},
journal = {FEMS Microbiology Ecology},
volume = {98},
number = {12},
pages = {fiac141},
abstract = {Abstract
Microbial mats are vertically stratified communities of microorganisms characterized by pronounced physiochemical gradients allowing for high species diversity and a wide range of metabolic capabilities. High Throughput Sequencing has the potential to reveal the biodiversity and function of such ecosystems in the cycling of elements. The present study combines 16S rRNA amplicon sequencing and shotgun metagenomics on a hypersaline marsh in Tristomo bay (Karpathos, Greece). Samples were collected in July 2018 and November 2019 from microbial mats, deeper sediment, aggregates observed in the water overlying the sediment, as well as sediment samples with no apparent layering. Metagenomic samples’ coassembly and binning revealed 250 bacterial and 39 archaeal metagenome-assembled genomes, with completeness estimates higher than 70% and contamination less than 5%. All MAGs had KEGG Orthology terms related to osmoadaptation, with the ‘salt in’ strategy ones being prominent. Halobacteria and Bacteroidetes were the most abundant taxa in the mats. Photosynthesis was most likely performed by purple sulphur and nonsulphur bacteria. All samples had the capacity for sulphate reduction, dissimilatory arsenic reduction, and conversion of pyruvate to oxaloacetate. Overall, both sequencing methodologies resulted in similar taxonomic compositions and revealed that the formation of the microbial mat in this marsh exhibits seasonal variation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{zafeiropoulos_prego_2022,
title = {PREGO: A Literature and Data-Mining Resource to Associate Microorganisms, Biological Processes, and Environment Types},
author = {Haris Zafeiropoulos and Savvas Paragkamian and Stelios Ninidakis and Georgios A Pavlopoulos and Lars Juhl Jensen and Evangelos Pafilis},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2022/03/2022-Zafeiropoulos-Micro-12.pdf
https://www.mdpi.com/2076-2607/10/2/293},
doi = {10.3390/microorganisms10020293},
issn = {2076-2607},
year = {2022},
date = {2022-01-01},
urldate = {2022-03-11},
journal = {Microorganisms},
volume = {10},
number = {2},
pages = {293},
abstract = {To elucidate ecosystem functioning, it is fundamental to recognize what processes occur in which environments (where) and which microorganisms carry them out (who). Here, we present PREGO, a one-stop-shop knowledge base providing such associations. PREGO combines text mining and data integration techniques to mine such what-where-who associations from data and metadata scattered in the scientific literature and in public omics repositories. Microorganisms, biological processes, and environment types are identified and mapped to ontology terms from established community resources. Analyses of comentions in text and co-occurrences in metagenomics data/metadata are performed to extract associations and a level of confidence is assigned to each of them thanks to a scoring scheme. The PREGO knowledge base contains associations for 364,508 microbial taxa, 1090 environmental types, 15,091 biological processes, and 7971 molecular functions with a total of almost 58 million associations. These associations are available through a web portal, an Application Programming Interface (API), and bulk download. By exploring environments and/or processes associated with each other or with microbes, PREGO aims to assist researchers in design and interpretation of experiments and their results. To demonstrate PREGO’s capabilities, a thorough presentation of its web interface is given along with a meta-analysis of experimental results from a lagoon-sediment study of sulfur-cycle related microbes.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{paragkamian_automating_2022,
title = {Automating the Curation Process of Historical Literature on Marine Biodiversity Using Text Mining: The DECO Workflow},
author = {Savvas Paragkamian and Georgia Sarafidou and Dimitra Mavraki and Christina Pavloudi and Joana Beja and Menashè Eliezer and Marina Lipizer and Laura Boicenco and Leen Vandepitte and Ruben Perez-Perez and Haris Zafeiropoulos and Christos Arvanitidis and Evangelos Pafilis and Vasilis Gerovasileiou},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2022/07/2022-Paragkaminan-fmars-53.pdf
},
doi = {10.3389/fmars.2022.940844},
issn = {2296-7745},
year = {2022},
date = {2022-01-01},
urldate = {2022-07-29},
journal = {Frontiers in Marine Science},
volume = {9},
pages = {940844},
abstract = {Historical biodiversity documents comprise an important link to the long-term data life cycle and provide useful insights on several aspects of biodiversity research and management. However, because of their historical context, they present specific challenges, primarily time- and effort-consuming in data curation. The data rescue process requires a multidisciplinary effort involving four tasks: (a) Document digitisation (b) Transcription, which involves text recognition and correction, and (c) Information Extraction, which is performed using text mining tools and involves the entity identification, their normalisation and their co-mentions in text. Finally, the extracted data go through (d) Publication to a data repository in a standardised format. Each of these tasks requires a dedicated multistep methodology with standards and procedures. During the past 8 years, Information Extraction (IE) tools have undergone remarkable advances, which created a landscape of various tools with distinct capabilities specific to biodiversity data. These tools recognise entities in text such as taxon names, localities, phenotypic traits and thus automate, accelerate and facilitate the curation process. Furthermore, they assist the normalisation and mapping of entities to specific identifiers. This work focuses on the IE step (c) from the marine historical biodiversity data perspective. It orchestrates IE tools and provides the curators with a unified view of the methodology; as a result the documentation of the strengths, limitations and dependencies of several tools was drafted. Additionally, the classification of tools into Graphical User Interface (web and standalone) applications and Command Line Interface ones enables the data curators to select the most suitable tool for their needs, according to their specific features. In addition, the high volume of already digitised marine documents that await curation is amassed and a demonstration of the methodology, with a new scalable, extendable and containerised tool, “DECO” (bioDivErsity data Curation programming wOrkflow) is presented. DECO’s usage will provide a solid basis for future curation initiatives and an augmented degree of reliability towards high value data products that allow for the connection between the past and the present, in marine biodiversity research.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{polymenakou_santorini_2021,
title = {The Santorini Volcanic Complex as a Valuable Source of Enzymes for Bioenergy},
author = {Paraskevi N Polymenakou and Paraskevi Nomikou and Haris Zafeiropoulos and Manolis Mandalakis and Thekla I Anastasiou and Stephanos Kilias and Nikos C Kyrpides and Georgios Kotoulas and Antoniοs Magoulas},
url = {https://www.mdpi.com/1996-1073/14/5/1414
https://imbbc.hcmr.gr/wp-content/uploads/2021/03/2021-Polymenakou-ENERGIES-24.pdf},
doi = {10.3390/en14051414},
issn = {1996-1073},
year = {2021},
date = {2021-01-01},
urldate = {2021-03-17},
journal = {Energies},
volume = {14},
number = {5},
pages = {1414},
abstract = {Marine microbial communities are an untapped reservoir of genetic and metabolic diversity and a valuable source for the discovery of new natural products of biotechnological interest. The newly discovered hydrothermal vent field of Santorini volcanic complex located in the Aegean Sea is gaining increasing interest for potential biotechnological exploitation. The conditions in these environments, i.e., high temperatures, low pH values and high concentration of heavy metals, often resemble harsh industrial settings. Thus, these environments may serve as pools of enzymes of enhanced catalytic properties that may provide benefits to biotechnology. Here, we screened 11 metagenomic libraries previously constructed from microbial mat samples covering the seafloor and the polymetallic chimneys of Kolumbo volcano as well as mat samples from Santorini caldera, to mine, in silico, genes associated with bioenergy applications. We particularly focused on genes encoding biomass hydrolysis enzymes such as cellulases, hemicellulases and lignin-degrading enzymes. A total of 10,417 genes were found for three specific groups of enzymes—i.e., the endoglucanases, the three different beta-glucosidases BGL, bglX and bglB, and the alpha-galactosidases melA, and rafA. Overall, we concluded that the Santorini–Kolumbo volcanic ecosystems constitute a significant resource of novel genes with potential applications in bioenergy that deserve further investigation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{zafeiropoulos_0s_2021,
title = {0s and 1s in marine molecular research: a regional HPC perspective},
author = {Haris Zafeiropoulos and Anastasia Gioti and Stelios Ninidakis and Antonis Potirakis and Savvas Paragkamian and Nelina Angelova and Aglaia Antoniou and Theodoros Danis and Eliza Kaitetzidou and Panagiotis Kasapidis and Jon Bent Kristoffersen and Vasileios Papadogiannis and Christina Pavloudi and Quoc Viet Ha and Jacques Lagnel and Nikos Pattakos and Giorgos Perantinos and Dimitris Sidirokastritis and Panagiotis Vavilis and Georgios Kotoulas and Tereza Manousaki and Elena Sarropoulou and Costas S Tsigenopoulos and Christos Arvanitidis and Antonios Magoulas and Evangelos Pafilis},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2021/08/2021-Zafeiropoulos-GiGa-63.pdf
https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giab053/6353916},
doi = {10.1093/gigascience/giab053},
issn = {2047-217X},
year = {2021},
date = {2021-01-01},
urldate = {2021-08-23},
journal = {GigaScience},
volume = {10},
number = {8},
pages = {giab053},
abstract = {Abstract
High-performance computing (HPC) systems have become indispensable for modern marine research, providing support to an increasing number and diversity of users. Pairing with the impetus offered by high-throughput methods to key areas such as non-model organism studies, their operation continuously evolves to meet the corresponding computational challenges. Here, we present a Tier 2 (regional) HPC facility, operating for over a decade at the Institute of Marine Biology, Biotechnology, and Aquaculture of the Hellenic Centre for Marine Research in Greece. Strategic choices made in design and upgrades aimed to strike a balance between depth (the need for a few high-memory nodes) and breadth (a number of slimmer nodes), as dictated by the idiosyncrasy of the supported research. Qualitative computational requirement analysis of the latter revealed the diversity of marine fields, methods, and approaches adopted to translate data into knowledge. In addition, hardware and software architectures, usage statistics, policy, and user management aspects of the facility are presented. Drawing upon the last decade’s experience from the different levels of operation of the Institute of Marine Biology, Biotechnology, and Aquaculture HPC facility, a number of lessons are presented; these have contributed to the facility’s future directions in light of emerging distribution technologies (e.g., containers) and Research Infrastructure evolution. In combination with detailed knowledge of the facility usage and its upcoming upgrade, future collaborations in marine research and beyond are envisioned.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{zafeiropoulos_dark_2021,
title = {The Dark mAtteR iNvestigator (DARN) tool: getting to know the known unknowns in COI amplicon data},
author = {Haris Zafeiropoulos and Laura Gargan and Sanni Hintikka and Christina Pavloudi and Jens Carlsson},
url = {https://imbbc.hcmr.gr/wp-content/uploads/2021/12/2021-Zafeiropoulos-ΜΒΜΓ-81.pdf
https://mbmg.pensoft.net/article/69657/},
doi = {10.3897/mbmg.5.69657},
issn = {2534-9708},
year = {2021},
date = {2021-01-01},
urldate = {2021-12-01},
journal = {Metabarcoding and Metagenomics},
volume = {5},
pages = {e69657},
abstract = {The mitochondrial cytochrome C oxidase subunit I gene (COI) is commonly used in environmental DNA (eDNA) metabarcoding studies, especially for assessing metazoan diversity. Yet, a great number of COI operational taxonomic units (OTUs) or/and amplicon sequence variants (ASVs) retrieved from such studies do not get a taxonomic assignment with a reference sequence. To assess and investigate such sequences, we have developed the Dark mAtteR iNvestigator (DARN) software tool. For this purpose, a reference COI-oriented phylogenetic tree was built from 1,593 consensus sequences covering all the three domains of life. With respect to eukaryotes, consensus sequences at the family level were constructed from 183,330 sequences retrieved from the Midori reference 2 database, which represented 70% of the initial number of reference sequences. Similarly, sequences from 431 bacterial and 15 archaeal taxa at the family level (29% and 1% of the initial number of reference sequences respectively) were retrieved from the BOLD and the PFam databases. DARN makes use of this phylogenetic tree to investigate COI pre-processed sequences of amplicon samples to provide both a tabular and a graphical overview of their phylogenetic assignments. To evaluate DARN, both environmental and bulk metabarcoding samples from different aquatic environments using various primer sets were analysed. We demonstrate that a large proportion of non-target prokaryotic organisms, such as bacteria and archaea, are also amplified in eDNA samples and we suggest prokaryotic COI sequences to be included in the reference databases used for the taxonomy assignment to allow for further analyses of dark matter. DARN source code is available on GitHub at https://github.com/hariszaf/darn and as a Docker image at https://hub.docker.com/r/hariszaf/darn.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{zafeiropoulos_pema_2020,
title = {PEMA: a flexible Pipeline for Environmental DNA Metabarcoding Analysis of the 16S/18S ribosomal RNA, ITS, and COI marker genes},
author = {Haris Zafeiropoulos and Ha Quoc Viet and Katerina Vasileiadou and Antonis Potirakis and Christos Arvanitidis and Pantelis Topalis and Christina Pavloudi and Evangelos Pafilis},
url = {https://doi.org/10.1093/gigascience/giaa022},
doi = {10.1093/gigascience/giaa022},
issn = {2047-217X},
year = {2020},
date = {2020-01-01},
journal = {GigaScience},
volume = {9},
number = {3},
abstract = {Environmental DNA and metabarcoding allow the identification of a mixture of species and launch a new era in bio- and eco-assessment. Many steps are required to obtain taxonomically assigned matrices from raw data. For most of these, a plethora of tools are available; each tool's execution parameters need to be tailored to reflect each experiment's idiosyncrasy. Adding to this complexity, the computation capacity of high-performance computing systems is frequently required for such analyses. To address the difficulties, bioinformatic pipelines need to combine state-of-the art technologies and algorithms with an easy to get-set-use framework, allowing researchers to tune each study. Software containerization technologies ease the sharing and running of software packages across operating systems; thus, they strongly facilitate pipeline development and usage. Likewise programming languages specialized for big data pipelines incorporate features like roll-back checkpoints and on-demand partial pipeline execution.PEMA is a containerized assembly of key metabarcoding analysis tools that requires low effort in setting up, running, and customizing to researchers’ needs. Based on third-party tools, PEMA performs read pre-processing, (molecular) operational taxonomic unit clustering, amplicon sequence variant inference, and taxonomy assignment for 16S and 18S ribosomal RNA, as well as ITS and COI marker gene data. Owing to its simplified parameterization and checkpoint support, PEMA allows users to explore alternative algorithms for specific steps of the pipeline without the need of a complete re-execution. PEMA was evaluated against both mock communities and previously published datasets and achieved results of comparable quality.A high-performance computing–based approach was used to develop PEMA; however, it can be used in personal computers as well. PEMA's time-efficient performance and good results will allow it to be used for accurate environmental DNA metabarcoding analysis, thus enhancing the applicability of next-generation biodiversity assessment studies.},
note = {_eprint: https://academic.oup.com/gigascience/article-pdf/9/3/giaa022/32894405/giaa022.pdf},
keywords = {},
pubstate = {published},
tppubtype = {article}
}