Mercurial > repos > iuc > openalex_explorer
changeset 0:7a27a48d57c0 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/openalex commit 7bac5b8acf6091006591be468a252e57793db4d8
| author | iuc |
|---|---|
| date | Sat, 31 May 2025 12:25:39 +0000 |
| parents | |
| children | |
| files | openalex.xml openalex_fetch.py test-data/expected_citing_papers.tsv test-data/expected_citing_papers_doi.tsv test-data/expected_citing_papers_title.tsv test-data/expected_citing_papers_wddownload.tsv test-data/expected_summary.txt test-data/expected_summary_doi.txt test-data/expected_summary_title.txt test-data/expected_summary_wddownload.txt |
| diffstat | 10 files changed, 392 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/openalex.xml Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,88 @@ +<tool id="openalex_explorer" name="OpenAlex explorer" version="0.1.0+galaxy0" profile="23.1"> + <description>Fetch citing papers from OpenAlex using DOI, openAlex ID, or title</description> + <requirements> + <requirement type="package" version="3.10">python</requirement> + <requirement type="package" version="2.31.0">requests</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ +python3 '$__tool_directory__/openalex_fetch.py' +$input_type '$identifier' +--max-citations '$max_citations' +$download_pdfs +]]></command> + <inputs> + <param name="input_type" type="select" label="Input type" help="Select whether the identifier is an OpenAlex ID, DOI, or Title"> + <option value="--doi" selected="true">DOI</option> + <option value="--id">OpenAlex ID</option> + <option value="--title">Title</option> + </param> + <param name="identifier" type="text" label="Identifier" help="Enter the OpenAlex ID, DOI, or Title depending on your selection above"/> + <param name="download_pdfs" type="boolean" truevalue="--download" falsevalue="" label="Download available OA PDFs?" value="false"/> + <param name="max_citations" type="select" label="Max citing papers to fetch" help="Limit the number of citing papers to fetch"> + <option value="10">10</option> + <option value="20">20</option> + <option value="50" selected="true">50</option> + <option value="100">100</option> + <option value="all">All</option> + </param> + </inputs> + <outputs> + <data name="summary_out" format="txt" label="Citation Summary" from_work_dir="summary.txt"/> + <data name="tsv_out" format="tabular" label="Citing Papers TSV" from_work_dir="citing_papers.tsv"/> + <collection name="pdf_outputs" label="Downloaded PDFs" type="list" format="pdf"> + <discover_datasets pattern="__designation_and_ext__" directory="downloads"/> + </collection> + </outputs> + <tests> + <test> + <param name="input_type" value="--id"/> + <param name="identifier" value="W4398182689"/> + <param name="max_citations" value="10"/> + <param name="download_pdfs" value="false"/> + <output name="summary_out" file="expected_summary.txt"/> + <output name="tsv_out" file="expected_citing_papers.tsv"/> + </test> + <test> + <param name="input_type" value="--doi"/> + <param name="identifier" value="10.1093/nar/gkae410"/> + <param name="max_citations" value="50"/> + <param name="download_pdfs" value="false"/> + <output name="summary_out" file="expected_summary_doi.txt"/> + <output name="tsv_out" file="expected_citing_papers_doi.tsv"/> + </test> + <test> + <param name="input_type" value="--title"/> + <param name="identifier" value="The Galaxy platform for accessible, reproducible, and collaborative data analyses: 2024 update"/> + <param name="max_citations" value="50"/> + <param name="download_pdfs" value="false"/> + <output name="summary_out" file="expected_summary_title.txt"/> + <output name="tsv_out" file="expected_citing_papers_title.tsv"/> + </test> + <test> + <param name="input_type" value="--id"/> + <param name="identifier" value="W2088676066"/> + <param name="max_citations" value="10"/> + <param name="download_pdfs" value="true"/> + <output name="summary_out" file="expected_summary_wddownload.txt"/> + <output name="tsv_out" file="expected_citing_papers_wddownload.tsv"/> + <output_collection name="pdf_outputs" type="list" count="1"> + <!-- Also working with the line below but I guess count check would be suffice --> + <!-- <element name="NAC-MYB-based transcriptional regulation of secondary cell wall biosynthesis in land plants" file="downloads/NAC-MYB-based transcriptional regulation of secondary cell wall biosynthesis in land plants.pdf"/> --> + </output_collection> + </test> + </tests> + <help><![CDATA[ + This tool fetches citing papers from OpenAlex for a paper specified by OpenAlex ID, DOI, or Title. + + You can optionally download available Open Access PDFs. + + **Outputs:** + + - summary.txt: summary of total, OA, and closed access citing papers + + - citing_papers.tsv: list of citing papers with details (title, DOI, OA) + ]]></help> + <citations> + <citation type="doi">10.48550/arXiv.2205.01833</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/openalex_fetch.py Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,168 @@ +import argparse +import os + +import requests + + +# doi +def get_openalex_id_from_doi(doi): + url = f'https://api.openalex.org/works/https://doi.org/{doi}' + response = requests.get(url) + response.raise_for_status() + return response.json()['id'].split('/')[-1] + + +# title +def get_openalex_id_from_title(title): + url = f'https://api.openalex.org/works?search={title}' + response = requests.get(url) + response.raise_for_status() + results = response.json().get('results', []) + if not results: + raise ValueError("No paper found with the given title.") + return results[0]['id'].split('/')[-1] + + +# fetch papers +def fetch_citing_papers(openalex_id, max_citations=None): + all_citing_papers = [] + per_page = 200 + page = 1 + + work_url = f'https://api.openalex.org/works/{openalex_id}' + response = requests.get(work_url) + response.raise_for_status() + work_data = response.json() + + cited_by_url = work_data.get('cited_by_api_url') + if not cited_by_url: + raise ValueError("This work has no citing papers.") + + while True: + paged_url = f"{cited_by_url}&per_page={per_page}&page={page}" + response = requests.get(paged_url) + response.raise_for_status() + data = response.json() + + results = data.get('results', []) + if not results: + break + + all_citing_papers.extend(results) + + if max_citations and len(all_citing_papers) >= max_citations: + all_citing_papers = all_citing_papers[:max_citations] + break + + if len(results) < per_page: + break + + page += 1 + + return all_citing_papers + + +def download_pdf(url, title, folder_name): + try: + if not os.path.exists(folder_name): + os.makedirs(folder_name) + response = requests.get(url) + if response.status_code == 200: + safe_title = "".join(x for x in title if x.isalnum() or x in " _-").rstrip() + file_path = os.path.join(folder_name, f"{safe_title}.pdf") + with open(file_path, 'wb') as f: + f.write(response.content) + print(f"[✓] Downloaded: {file_path}") + else: + print(f"[x] Failed to download: {url}") + except Exception as e: + print(f"[!] Error downloading {url}: {e}") + + +def main(): + parser = argparse.ArgumentParser(description="Fetch citing papers from OpenAlex") + group = parser.add_mutually_exclusive_group(required=True) + group.add_argument('--id', help='OpenAlex ID of the paper (e.g., W2088676066)') + group.add_argument('--doi', help='DOI of the paper') + group.add_argument('--title', help='Title of the paper') + + parser.add_argument('--download', action='store_true', help='Download available OA PDFs') + parser.add_argument('--max-citations', type=str, default="50", dest='max_citations', help="Max citing papers to fetch or 'all'") + parser.add_argument('--output-dir', default='.', help='Directory to save output files') + args = parser.parse_args() + + output_dir = args.output_dir + summary_path = os.path.join(output_dir, "summary.txt") + tsv_path = os.path.join(output_dir, "citing_papers.tsv") + download_dir = os.path.join(output_dir, "downloads") + + if args.max_citations.lower() == "all": + max_citations = None + else: + max_citations = int(args.max_citations) + + try: + if args.title: + openalex_id = get_openalex_id_from_title(args.title) + elif args.doi: + openalex_id = get_openalex_id_from_doi(args.doi) + else: + openalex_id = args.id + + citing_papers = fetch_citing_papers(openalex_id, max_citations=max_citations) + + is_oa = 0 + is_not_oa = 0 + + for paper in citing_papers: + if not paper['locations']: + continue + location = paper['locations'][0] + is_open = location.get('is_oa', False) + landing_url = location.get('landing_page_url', 'No URL') + + if is_open: + is_oa += 1 + print("[OA]", landing_url) + if args.download: + pdf_url = location.get('pdf_url') + if pdf_url: + download_pdf(pdf_url, paper['title'], download_dir) + else: + print(f"[!] No direct PDF URL for: {paper['title']}") + + else: + is_not_oa += 1 + print("[Closed]", landing_url) + + print("\nSummary:") + print("Total citing papers:", len(citing_papers)) + print("Open Access papers:", is_oa) + print("Closed Access papers:", is_not_oa) + + # save summary + with open(summary_path, "w") as f: + f.write(f"Total citing papers: {len(citing_papers)}\n") + f.write(f"Open Access papers: {is_oa}\n") + f.write(f"Closed Access papers: {is_not_oa}\n") + + # save citing papers to a TSV file + with open(tsv_path, "w", encoding="utf-8") as f: + f.write("Title\tDOI\tIs_OA\n") + for paper in citing_papers: + raw_title = paper.get("title") or "N/A" + title = raw_title.replace("\t", " ") + doi = paper.get("doi", "N/A") + location = paper['locations'][0] if paper['locations'] else {} + is_oa = location.get("is_oa", False) + # landing_url = location.get("landing_page_url", "N/A") + # pdf_url = location.get("pdf_url", "N/A") + + f.write(f"{title}\t{doi}\t{is_oa}\n") + + except Exception as e: + print(f"[!] Error: {e}") + + +if __name__ == '__main__': + main()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_citing_papers.tsv Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,11 @@ +Title DOI Is_OA +Transforming Clinical Research: The Power of High-Throughput Omics Integration https://doi.org/10.3390/proteomes12030025 True +Database resources of the National Center for Biotechnology Information in 2025 https://doi.org/10.1093/nar/gkae979 True +The efflux pump ABCC1/MRP1 constitutively restricts PROTAC sensitivity in cancer cells https://doi.org/10.1016/j.chembiol.2024.11.009 True +The cell colony development is connected with the accumulation of embryogenesis-related proteins and dynamic distribution of cell wall components in in vitro cultures of Fagopyrum tataricum and Fagopyrum esculentum https://doi.org/10.1186/s12870-025-06119-3 True +16S rRNA sequencing reveals synergistic effects of silkworm feces and earthworms on soil microbial diversity and resilience under elevated temperatures https://doi.org/10.1016/j.apsoil.2025.105952 False +Evolution of sexual systems and regressive evolution in <i>Riccia</i> https://doi.org/10.1111/nph.20454 True +Applying the FAIR Principles to computational workflows https://doi.org/10.1038/s41597-025-04451-9 True +A case for global standardisation of genomics and wastewater-based epidemiology https://doi.org/10.1016/j.lanmic.2025.101092 True +Bioactive Polyphenolic Compounds from Propolis of Tetragonula carbonaria in the Gibberagee Region, New South Wales, Australia https://doi.org/10.3390/foods14060965 True +Comparative genomics reveals genetic diversity and differential metabolic potentials of the species of Arachnia and suggests reclassification of Arachnia propionica E10012 (=NBRC_14587) as novel species https://doi.org/10.1007/s00203-025-04302-6 False
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_citing_papers_doi.tsv Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,51 @@ +Title DOI Is_OA +Transforming Clinical Research: The Power of High-Throughput Omics Integration https://doi.org/10.3390/proteomes12030025 True +Database resources of the National Center for Biotechnology Information in 2025 https://doi.org/10.1093/nar/gkae979 True +The efflux pump ABCC1/MRP1 constitutively restricts PROTAC sensitivity in cancer cells https://doi.org/10.1016/j.chembiol.2024.11.009 True +The cell colony development is connected with the accumulation of embryogenesis-related proteins and dynamic distribution of cell wall components in in vitro cultures of Fagopyrum tataricum and Fagopyrum esculentum https://doi.org/10.1186/s12870-025-06119-3 True +16S rRNA sequencing reveals synergistic effects of silkworm feces and earthworms on soil microbial diversity and resilience under elevated temperatures https://doi.org/10.1016/j.apsoil.2025.105952 False +Evolution of sexual systems and regressive evolution in <i>Riccia</i> https://doi.org/10.1111/nph.20454 True +Applying the FAIR Principles to computational workflows https://doi.org/10.1038/s41597-025-04451-9 True +A case for global standardisation of genomics and wastewater-based epidemiology https://doi.org/10.1016/j.lanmic.2025.101092 True +Bioactive Polyphenolic Compounds from Propolis of Tetragonula carbonaria in the Gibberagee Region, New South Wales, Australia https://doi.org/10.3390/foods14060965 True +Comparative genomics reveals genetic diversity and differential metabolic potentials of the species of Arachnia and suggests reclassification of Arachnia propionica E10012 (=NBRC_14587) as novel species https://doi.org/10.1007/s00203-025-04302-6 False +A novel <i>Erwiniaceae</i> gut symbiont modulates gene expression of the intracellular bacterium <i>Cardinium</i> in the stored product mite <i>Tyrophagus putrescentiae</i> https://doi.org/10.1128/msphere.00879-24 True +Playbook workflow builder: Interactive construction of bioinformatics workflows https://doi.org/10.1371/journal.pcbi.1012901 True +Quiescent cell re-entry is limited by macroautophagy-induced lysosomal damage https://doi.org/10.1016/j.cell.2025.03.009 False +Targets of the transcription factor Six1 identify previously unreported candidate deafness genes https://doi.org/10.1242/dev.204533 True +iNAP 2.0: Harnessing metabolic complementarity in microbial network analysis https://doi.org/10.1002/imt2.235 True +A Novel Bacitracin-like Peptide from Mangrove-Isolated Bacillus paralicheniformis NNS4-3 against MRSA and Its Genomic Insights https://doi.org/10.3390/antibiotics13080716 True +Learning and teaching biological data science in the Bioconductor community https://doi.org/10.1371/journal.pcbi.1012925 True +Investigating proteogenomic divergence in patient-derived xenograft models of ovarian cancer https://doi.org/10.1038/s41598-024-84874-3 True +Three mitochondrial genomes of Kibakoganea Nagai, 1984 (Coleoptera: Scarabaeidae: Rutelinae) and phylogenetic relationship of Rutelini https://doi.org/10.1016/j.aspen.2024.102369 False +Galaxy @Sciensano: a comprehensive bioinformatics portal for genomics-based microbial typing, characterization, and outbreak detection https://doi.org/10.1186/s12864-024-11182-5 True +Comparative Analysis of Seventeen Mitochondrial Genomes of Mileewinae Leafhoppers, Including the Unique Species <i>Mileewa digitata</i> (Hemiptera: Cicadellidae: Mileewinae) From Xizang, China, and New Insights Into Phylogenetic Relationships Within Mileewini https://doi.org/10.1002/ece3.70830 True +Reproducible research policies and software/data management in scientific computing journals: a survey, discussion, and perspectives https://doi.org/10.3389/fcomp.2024.1491823 True +Investigation of Exome-Wide Tumor Heterogeneity on Colorectal Tissue-Based Single Cells https://doi.org/10.3390/ijms26020737 True +The central clock drives metabolic rhythms in muscle stem cells https://doi.org/10.1101/2025.01.15.633124 True +Bone Marrow Stromal Cells Generate a Pro-Healing Inflammasome When Cultured on Titanium–Aluminum–Vanadium Surfaces with Microscale/Nanoscale Structural Features https://doi.org/10.3390/biomimetics10010066 True +Holzapfeliella saturejae sp. nov. isolated from flowers of winter savoury Satureja montana L. https://doi.org/10.1099/ijsem.0.006654 False +Validating a clinically based MS-MLPA threshold through comparison with Sanger sequencing in glioblastoma patients https://doi.org/10.1186/s13148-025-01822-2 True +Fine-tuning mechanical constraints uncouple patterning and gene expression in murine pseudo-embryos https://doi.org/10.1101/2025.01.28.635012 True +Integrative analysis of patient-derived tumoroids and ex vivo organoid modeling of ARID1A loss in bladder cancer reveals therapeutic molecular targets https://doi.org/10.1016/j.canlet.2025.217506 True +Predicting coarse-grained representations of biogeochemical cycles from metabarcoding data https://doi.org/10.1101/2025.01.30.635649 True +Transcriptome atlases of rat brain regions and their adaptation to diabetes resolution following gastrectomy in the Goto-Kakizaki rat https://doi.org/10.1186/s13041-025-01176-z True +Comparative Chloroplast Genomics and Phylogeny of Crinum brachynema (Amaryllidaceae): A Narrow Endemic Geophyte of the Western Ghats of India https://doi.org/10.1007/s11105-025-01536-y False +Guidance framework to apply best practices in ecological data analysis: lessons learned from building Galaxy-Ecology https://doi.org/10.1093/gigascience/giae122 True +Association of escitalopram-induced shifts in gut microbiota and sphingolipid metabolism with depression-like behavior in wistar-kyoto rats https://doi.org/10.1038/s41398-025-03277-8 True +RBM43 controls PGC1α translation and a PGC1α-STING signaling axis https://doi.org/10.1016/j.cmet.2025.01.013 False +Two transmembrane transcriptional regulators coordinate to activate chitin-induced natural transformation in Vibrio cholerae https://doi.org/10.1371/journal.pgen.1011606 True +Biodiversity of strains belonging to the freshwater genus Aquirufa in a riparian forest restoration area in Salzburg, Austria, with a focus on the description of Aquirufa salirivi sp. nov. and Aquirufa novilacunae sp. nov https://doi.org/10.1007/s10123-025-00642-x True +Aquirufa esocilacus sp. nov., Aquirufa originis sp. nov., Aquirufa avitistagni, and Aquirufa echingensis sp. nov. discovered in small freshwater habitats in Austria during a citizen science project https://doi.org/10.1007/s00203-025-04275-6 True +Metatranscriptomes of activated sludge microbiomes from saline wastewater treatment plant https://doi.org/10.1038/s41597-025-04682-w True +High-Throughput Sequencing Enables Rapid Analyses of Nematode Mitochondrial Genomes from an Environmental Sample https://doi.org/10.3390/pathogens14030234 True +Hydrogen Radical Chemistry at High-Symmetry {2Fe2S} Centers Probed Using a Muonium Surrogate https://doi.org/10.1021/acs.inorgchem.4c05126 True +Isolation and characterization of fMGyn-Pae01, a phiKZ-like jumbo phage infecting Pseudomonas aeruginosa https://doi.org/10.1186/s12985-025-02679-w True +A single amino acid variant in the variable region I of AAV capsid confers liver detargeting https://doi.org/10.1101/2025.03.04.641478 True +Transposon insertion causes ctnnb2 transcript instability that results in the maternal effect zebrafish ichabod (ich) mutation https://doi.org/10.1101/2025.02.28.640854 True +Comprehensive identification of hub mRNAs and lncRNAs in colorectal cancer using galaxy: an in silico transcriptome analysis https://doi.org/10.1007/s12672-025-02026-z True +Phylogenomic Analysis Reveals Evolutionary Relationships of Tropical Drosophilidae: From <i>Drosophila</i> to <i>Scaptodrosophila</i> https://doi.org/10.1002/ece3.71100 True +Genome sequencing and identification of candidate variants for a red/black color polymorphism in tilapia (Oreochromis spp.) https://doi.org/10.1016/j.aquaculture.2025.742411 True +Higher Order Volatile Fatty Acid Metabolism and Atypical Polyhydroxyalkanoate Production in Fermentation-Enhanced Biological Phosphorus Removal https://doi.org/10.1016/j.watres.2025.123503 True +Phosphorelay changes and plasticity underlie the life history evolution of Bacillus subtilis sporulation and germination in serial batch culture https://doi.org/10.1099/mic.0.001540 False +Comammox Nitrospira dominates the nitrifying bacterial community in the external canister biofilter in the tank fish farm https://doi.org/10.1016/j.jwpe.2025.107494 False
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_citing_papers_title.tsv Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,51 @@ +Title DOI Is_OA +Transforming Clinical Research: The Power of High-Throughput Omics Integration https://doi.org/10.3390/proteomes12030025 True +Database resources of the National Center for Biotechnology Information in 2025 https://doi.org/10.1093/nar/gkae979 True +The efflux pump ABCC1/MRP1 constitutively restricts PROTAC sensitivity in cancer cells https://doi.org/10.1016/j.chembiol.2024.11.009 True +The cell colony development is connected with the accumulation of embryogenesis-related proteins and dynamic distribution of cell wall components in in vitro cultures of Fagopyrum tataricum and Fagopyrum esculentum https://doi.org/10.1186/s12870-025-06119-3 True +16S rRNA sequencing reveals synergistic effects of silkworm feces and earthworms on soil microbial diversity and resilience under elevated temperatures https://doi.org/10.1016/j.apsoil.2025.105952 False +Evolution of sexual systems and regressive evolution in <i>Riccia</i> https://doi.org/10.1111/nph.20454 True +Applying the FAIR Principles to computational workflows https://doi.org/10.1038/s41597-025-04451-9 True +A case for global standardisation of genomics and wastewater-based epidemiology https://doi.org/10.1016/j.lanmic.2025.101092 True +Bioactive Polyphenolic Compounds from Propolis of Tetragonula carbonaria in the Gibberagee Region, New South Wales, Australia https://doi.org/10.3390/foods14060965 True +Comparative genomics reveals genetic diversity and differential metabolic potentials of the species of Arachnia and suggests reclassification of Arachnia propionica E10012 (=NBRC_14587) as novel species https://doi.org/10.1007/s00203-025-04302-6 False +A novel <i>Erwiniaceae</i> gut symbiont modulates gene expression of the intracellular bacterium <i>Cardinium</i> in the stored product mite <i>Tyrophagus putrescentiae</i> https://doi.org/10.1128/msphere.00879-24 True +Playbook workflow builder: Interactive construction of bioinformatics workflows https://doi.org/10.1371/journal.pcbi.1012901 True +Quiescent cell re-entry is limited by macroautophagy-induced lysosomal damage https://doi.org/10.1016/j.cell.2025.03.009 False +Targets of the transcription factor Six1 identify previously unreported candidate deafness genes https://doi.org/10.1242/dev.204533 True +iNAP 2.0: Harnessing metabolic complementarity in microbial network analysis https://doi.org/10.1002/imt2.235 True +A Novel Bacitracin-like Peptide from Mangrove-Isolated Bacillus paralicheniformis NNS4-3 against MRSA and Its Genomic Insights https://doi.org/10.3390/antibiotics13080716 True +Learning and teaching biological data science in the Bioconductor community https://doi.org/10.1371/journal.pcbi.1012925 True +Investigating proteogenomic divergence in patient-derived xenograft models of ovarian cancer https://doi.org/10.1038/s41598-024-84874-3 True +Three mitochondrial genomes of Kibakoganea Nagai, 1984 (Coleoptera: Scarabaeidae: Rutelinae) and phylogenetic relationship of Rutelini https://doi.org/10.1016/j.aspen.2024.102369 False +Galaxy @Sciensano: a comprehensive bioinformatics portal for genomics-based microbial typing, characterization, and outbreak detection https://doi.org/10.1186/s12864-024-11182-5 True +Comparative Analysis of Seventeen Mitochondrial Genomes of Mileewinae Leafhoppers, Including the Unique Species <i>Mileewa digitata</i> (Hemiptera: Cicadellidae: Mileewinae) From Xizang, China, and New Insights Into Phylogenetic Relationships Within Mileewini https://doi.org/10.1002/ece3.70830 True +Reproducible research policies and software/data management in scientific computing journals: a survey, discussion, and perspectives https://doi.org/10.3389/fcomp.2024.1491823 True +Investigation of Exome-Wide Tumor Heterogeneity on Colorectal Tissue-Based Single Cells https://doi.org/10.3390/ijms26020737 True +The central clock drives metabolic rhythms in muscle stem cells https://doi.org/10.1101/2025.01.15.633124 True +Bone Marrow Stromal Cells Generate a Pro-Healing Inflammasome When Cultured on Titanium–Aluminum–Vanadium Surfaces with Microscale/Nanoscale Structural Features https://doi.org/10.3390/biomimetics10010066 True +Holzapfeliella saturejae sp. nov. isolated from flowers of winter savoury Satureja montana L. https://doi.org/10.1099/ijsem.0.006654 False +Validating a clinically based MS-MLPA threshold through comparison with Sanger sequencing in glioblastoma patients https://doi.org/10.1186/s13148-025-01822-2 True +Fine-tuning mechanical constraints uncouple patterning and gene expression in murine pseudo-embryos https://doi.org/10.1101/2025.01.28.635012 True +Integrative analysis of patient-derived tumoroids and ex vivo organoid modeling of ARID1A loss in bladder cancer reveals therapeutic molecular targets https://doi.org/10.1016/j.canlet.2025.217506 True +Predicting coarse-grained representations of biogeochemical cycles from metabarcoding data https://doi.org/10.1101/2025.01.30.635649 True +Transcriptome atlases of rat brain regions and their adaptation to diabetes resolution following gastrectomy in the Goto-Kakizaki rat https://doi.org/10.1186/s13041-025-01176-z True +Comparative Chloroplast Genomics and Phylogeny of Crinum brachynema (Amaryllidaceae): A Narrow Endemic Geophyte of the Western Ghats of India https://doi.org/10.1007/s11105-025-01536-y False +Guidance framework to apply best practices in ecological data analysis: lessons learned from building Galaxy-Ecology https://doi.org/10.1093/gigascience/giae122 True +Association of escitalopram-induced shifts in gut microbiota and sphingolipid metabolism with depression-like behavior in wistar-kyoto rats https://doi.org/10.1038/s41398-025-03277-8 True +RBM43 controls PGC1α translation and a PGC1α-STING signaling axis https://doi.org/10.1016/j.cmet.2025.01.013 False +Two transmembrane transcriptional regulators coordinate to activate chitin-induced natural transformation in Vibrio cholerae https://doi.org/10.1371/journal.pgen.1011606 True +Biodiversity of strains belonging to the freshwater genus Aquirufa in a riparian forest restoration area in Salzburg, Austria, with a focus on the description of Aquirufa salirivi sp. nov. and Aquirufa novilacunae sp. nov https://doi.org/10.1007/s10123-025-00642-x True +Aquirufa esocilacus sp. nov., Aquirufa originis sp. nov., Aquirufa avitistagni, and Aquirufa echingensis sp. nov. discovered in small freshwater habitats in Austria during a citizen science project https://doi.org/10.1007/s00203-025-04275-6 True +Metatranscriptomes of activated sludge microbiomes from saline wastewater treatment plant https://doi.org/10.1038/s41597-025-04682-w True +High-Throughput Sequencing Enables Rapid Analyses of Nematode Mitochondrial Genomes from an Environmental Sample https://doi.org/10.3390/pathogens14030234 True +Hydrogen Radical Chemistry at High-Symmetry {2Fe2S} Centers Probed Using a Muonium Surrogate https://doi.org/10.1021/acs.inorgchem.4c05126 True +Isolation and characterization of fMGyn-Pae01, a phiKZ-like jumbo phage infecting Pseudomonas aeruginosa https://doi.org/10.1186/s12985-025-02679-w True +A single amino acid variant in the variable region I of AAV capsid confers liver detargeting https://doi.org/10.1101/2025.03.04.641478 True +Transposon insertion causes ctnnb2 transcript instability that results in the maternal effect zebrafish ichabod (ich) mutation https://doi.org/10.1101/2025.02.28.640854 True +Comprehensive identification of hub mRNAs and lncRNAs in colorectal cancer using galaxy: an in silico transcriptome analysis https://doi.org/10.1007/s12672-025-02026-z True +Phylogenomic Analysis Reveals Evolutionary Relationships of Tropical Drosophilidae: From <i>Drosophila</i> to <i>Scaptodrosophila</i> https://doi.org/10.1002/ece3.71100 True +Genome sequencing and identification of candidate variants for a red/black color polymorphism in tilapia (Oreochromis spp.) https://doi.org/10.1016/j.aquaculture.2025.742411 True +Higher Order Volatile Fatty Acid Metabolism and Atypical Polyhydroxyalkanoate Production in Fermentation-Enhanced Biological Phosphorus Removal https://doi.org/10.1016/j.watres.2025.123503 True +Phosphorelay changes and plasticity underlie the life history evolution of Bacillus subtilis sporulation and germination in serial batch culture https://doi.org/10.1099/mic.0.001540 False +Comammox Nitrospira dominates the nitrifying bacterial community in the external canister biofilter in the tank fish farm https://doi.org/10.1016/j.jwpe.2025.107494 False
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_citing_papers_wddownload.tsv Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,11 @@ +Title DOI Is_OA +Insights into Land Plant Evolution Garnered from the Marchantia polymorpha Genome https://doi.org/10.1016/j.cell.2017.09.030 True +NAC-MYB-based transcriptional regulation of secondary cell wall biosynthesis in land plants https://doi.org/10.3389/fpls.2015.00288 True +<i>Marchantia polymorpha</i>: Taxonomy, Phylogeny and Morphology of a Model System https://doi.org/10.1093/pcp/pcv192 True +Lignification: Flexibility, Biosynthesis and Regulation https://doi.org/10.1016/j.tplants.2016.04.006 False +Plant vascular development: from early specification to differentiation https://doi.org/10.1038/nrm.2015.6 False +The Moss <i>Physcomitrium</i> (<i>Physcomitrella</i>) <i>patens</i>: A Model Organism for Non-Seed Plants https://doi.org/10.1105/tpc.19.00828 True +Functions and Regulation of Programmed Cell Death in Plant Development https://doi.org/10.1146/annurev-cellbio-111315-124915 False +Only in dying, life: programmed cell death during plant development https://doi.org/10.1016/j.tplants.2014.10.003 False +A Transcriptome Atlas of Physcomitrella patens Provides Insights into the Evolution and Development of Land Plants https://doi.org/10.1016/j.molp.2015.12.002 True +Insights into the Diversification and Evolution of R2R3-MYB Transcription Factors in Plants https://doi.org/10.1104/pp.19.01082 True
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_summary.txt Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,3 @@ +Total citing papers: 10 +Open Access papers: 8 +Closed Access papers: 2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expected_summary_doi.txt Sat May 31 12:25:39 2025 +0000 @@ -0,0 +1,3 @@ +Total citing papers: 50 +Open Access papers: 41 +Closed Access papers: 9