references/citation.bib
@ARTICLE{Sever2026,
ABSTRACT = {The traditional publication process delays dissemination of new research, often by months, sometimes by years. Preprint servers decouple dissemination of research papers from their evaluation and certification by journals, allowing researchers to share work immediately, receive feedback from a much larger audience, and provide evidence of productivity long before formal publication. Launched in 2013 as a non-profit community service, the bioRxiv server brought preprinting to the life sciences and recently posted its 310,000th manuscript. The server now receives around ten million views per month and hosts papers spanning all areas of biology. Initially dominated by evolutionary biology, genetics/genomics and computational biology, bioRxiv has been increasingly populated by papers in neuroscience, cell and developmental biology, and many other fields. bioRxiv and its sister server, medRxiv, also played a critical role during the pandemic, rapidly disseminating new discoveries in immunology, virology and epidemiology related to the SARS-CoV-2 virus and its effects. Changes in journal and funder policies that encourage preprint posting helped drive adoption, as did the development of bioRxiv technologies that allow authors to transfer papers easily between bioRxiv and journals. A recent user survey found that 30\% of authors post their preprints weeks to months before submitting to a journal whereas 55\% post around the time of journal submission. Authors are motivated by a desire to share work early; they value the feedback they receive and very rarely experience any negative consequences of preprint posting. Rapid dissemination via bioRxiv is also encouraging new initiatives that experiment with the peer review process and the development of novel approaches to literature filtering and assessment.Competing Interest StatementRS is Chief Science \& Strategy Officer at openRxiv and an advisor to Sciencecast. SH is an employee of openRxiv, Co-Founder of PREreview, and an ASAPbio Ambassador. TR, OFG, SFR, SG, EC, KJB, MM, JS and MPO are openRxiv employees. WM is Director of Product Development and Marketing at CSHL Press and employed by CSHL. TKT is Chief Executive Officer at openRxiv. JI is Chair of the openRxiv Science and Medical Advisory Board and an MIT Press advisory board member.},
AUTHOR = {Sever, Richard and Hindle, Samantha and Roeder, Ted and Fereres, Sol and Fernández Gayol, Olaya and Ghosh, Sanchari and Proietti Onori, Martina and Croushore, Emma and Black, Kevin-John and Sussman, Linda and Argentine, Janet and Manos, Wayne and Muñoz, Marisol and Sinanan, Josh and Teal, Tracy K. and Inglis, John R.},
PUBLISHER = {Cold Spring Harbor Laboratory},
URL = {https://www.biorxiv.org/content/early/2026/02/26/833400},
DATE = {2026},
DOI = {10.1101/833400},
EPRINT = {https://www.biorxiv.org/content/early/2026/02/26/833400.full.pdf},
JOURNALTITLE = {bioRxiv},
TITLE = {bioRxiv: the preprint server for biology},
}
scripts/search_by_dates.py
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Search bioRxiv/medRxiv by date range with local filtering."""
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "polite-http",
# ]
# ///
import argparse
import json
import sys
from polite_http import http_client
client = http_client.HttpClient(base_url="https://api.biorxiv.org/", qps=1.0)
# ---------------------------------------------------------------------------
# Constants
# ---------------------------------------------------------------------------
BIORXIV_PAGE_SIZE = 30
BIORXIV_CATEGORIES = [
"animal_behavior_and_cognition",
"biochemistry",
"bioengineering",
"bioinformatics",
"biophysics",
"cancer_biology",
"cell_biology",
"clinical_trials",
"developmental_biology",
"ecology",
"epidemiology",
"evolutionary_biology",
"genetics",
"genomics",
"immunology",
"microbiology",
"molecular_biology",
"neuroscience",
"paleontology",
"pathology",
"pharmacology_and_toxicology",
"physiology",
"plant_biology",
"scientific_communication_and_education",
"synthetic_biology",
"systems_biology",
"zoology",
]
MEDRXIV_CATEGORIES = [
"addiction_medicine",
"allergy_and_immunology",
"anesthesia",
"cardiovascular_medicine",
"dentistry_and_oral_medicine",
"dermatology",
"emergency_medicine",
"endocrinology",
"epidemiology",
"forensic_medicine",
"gastroenterology",
"genetic_and_genomic_medicine",
"health_informatics",
"health_economics_and_outcomes_research",
"health_policy",
"health_systems_and_quality_improvement",
"hematology",
"hiv_aids",
"infectious_diseases",
"intensive_care_and_critical_care_medicine",
"medical_education",
"medical_ethics",
"nephrology",
"neurology",
"nursing",
"nutrition",
"obstetrics_and_gynecology",
"occupational_and_environmental_health",
"oncology",
"ophthalmology",
"orthopedics",
"otolaryngology",
"pain_medicine",
"palliative_care",
"pathology",
"pediatrics",
"pharmacology_and_therapeutics",
"primary_care_research",
"psychiatry_and_clinical_psychology",
"public_and_global_health",
"radiology_and_imaging",
"rehabilitation_medicine_and_physical_therapy",
"respiratory_medicine",
"rheumatology",
"sexual_and_reproductive_health",
"sports_medicine",
"surgery",
"toxicology",
"transplantation",
"urology",
]
def search_biorxiv(args):
"""Searches bioRxiv/medRxiv for preprints in the given date range."""
# Strict Category Validation
if args.category:
if args.server == "biorxiv" and args.category not in BIORXIV_CATEGORIES:
sys.exit(
f"Error: Invalid category '{args.category}' for bioRxiv.\n"
f"Valid categories are: {', '.join(BIORXIV_CATEGORIES)}"
)
elif args.server == "medrxiv" and args.category not in MEDRXIV_CATEGORIES:
sys.exit(
f"Error: Invalid category '{args.category}' for medRxiv.\n"
f"Valid categories are: {', '.join(MEDRXIV_CATEGORIES)}"
)
base_url = (
f"https://api.biorxiv.org/details/{args.server}"
f"/{args.start_date}/{args.end_date}"
)
cursor = 0
all_results = []
total_fetched = 0
total_after_category = 0
page_num = 0
print(
f"Fetching metadata for {args.server} from {args.start_date}"
f" to {args.end_date}...",
file=sys.stderr,
)
if args.category:
print(f" Category filter: {args.category}", file=sys.stderr)
if args.keywords:
print(
f" Keyword filter ({args.match_logic}): {', '.join(args.keywords)}",
file=sys.stderr,
)
if args.author:
print(f" Author filter: {args.author}", file=sys.stderr)
while True:
url = f"{base_url}/{cursor}"
page_num += 1
data = client.fetch_json(url)
collection = data.get("collection", [])
if not collection:
break
total_fetched += len(collection)
# Print pagination progress to stderr
print(
f" [Page {page_num}] Fetched {total_fetched} papers...",
file=sys.stderr,
)
for paper in collection:
# Local Category Filtering
# The API may ignore the category query parameter, so we always
# enforce category filtering locally as a reliable fallback.
if args.category:
paper_category = paper.get("category", "").lower().replace(" ", "_")
if paper_category != args.category.lower():
continue
total_after_category += 1
# Local Author Filtering
if args.author:
author_list = paper.get("authors", "").lower().split(";")
if not any(args.author.lower() in a for a in author_list):
continue
# Local Keyword Filtering (checks title and abstract)
if args.keywords:
title = paper.get("title", "").lower()
abstract = paper.get("abstract", "").lower()
text_to_search = f"{title} {abstract}"
kw_lower = [k.lower() for k in args.keywords]
if args.match_logic == "AND":
if not all(kw in text_to_search for kw in kw_lower):
continue
else: # OR logic
if not any(kw in text_to_search for kw in kw_lower):
continue
# Strip abstract if not requested
if not args.include_abstracts and "abstract" in paper:
del paper["abstract"]
all_results.append(paper)
# The bioRxiv API returns results in pages of up to `BIORXIV_PAGE_SIZE`
# items. We advance `cursor` by the page size and stop once we get a short
# page. NOTE: We intentionally do NOT use `total_count` for
# termination because the API sometimes reports `BIORXIV_PAGE_SIZE` (the
# page size) rather than the true total, which causes premature stopping.
cursor += len(collection)
if len(collection) < BIORXIV_PAGE_SIZE:
# A short page is the only reliable signal that we've fetched everything.
break
# Print summary to stderr so the agent can assess results
print("\n--- Search Summary ---", file=sys.stderr)
print(
f" Total papers in date range: {total_fetched}"
+ (f" (across {page_num} page(s))" if page_num > 1 else ""),
file=sys.stderr,
)
if args.category:
print(
f" After category filter ('{args.category}'): {total_after_category}",
file=sys.stderr,
)
print(
f" Final results after all filters: {len(all_results)}",
file=sys.stderr,
)
if not all_results:
print(
" Tip: No results found. Try widening the date range, removing keyword"
" filters, or changing the category. If searching for a specific paper,"
" consider using search_by_doi.py with the paper's DOI instead.",
file=sys.stderr,
)
print(json.dumps(all_results, indent=2))
def main():
"""Parses arguments and searches bioRxiv/medRxiv."""
parser = argparse.ArgumentParser(
description="Search bioRxiv/medRxiv by date range with local filtering."
)
parser.add_argument(
"--server",
choices=["biorxiv", "medrxiv"],
default="biorxiv",
help="The preprint server to query.",
)
parser.add_argument(
"--start_date",
required=True,
help="Start date (YYYY-MM-DD)",
)
parser.add_argument(
"--end_date",
required=True,
help="End date (YYYY-MM-DD)",
)
parser.add_argument("--category", help="Strict server-side category filter")
parser.add_argument("--author", help="Local author filter (case-insensitive)")
parser.add_argument(
"--keywords",
nargs="+",
help="Local keyword filters applied to title and abstract",
)
parser.add_argument(
"--match_logic",
choices=["AND", "OR"],
default="AND",
help="Keyword matching logic",
)
parser.add_argument(
"--include_abstracts",
action="store_true",
help="Include full abstracts in the JSON output",
)
args = parser.parse_args()
search_biorxiv(args)
if __name__ == "__main__":
main()
scripts/search_by_doi.py
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Fetch specific bioRxiv/medRxiv metadata by DOI."""
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "polite-http",
# ]
# ///
import argparse
import json
import sys
from polite_http import http_client
_CLIENT = http_client.HttpClient(base_url="https://api.biorxiv.org/", qps=1.0)
def search_by_doi(args):
"""Retrieves metadata for a single paper identified by its DOI."""
# Clean up DOI string if a URL was accidentally passed
doi = args.doi.replace("https://doi.org/", "").replace("http://doi.org/", "")
url = f"https://api.biorxiv.org/details/{args.server}/{doi}"
data = _CLIENT.fetch_json(url)
collection = data.get("collection", [])
if not collection:
sys.exit(f"Error: No paper found for DOI '{doi}' on {args.server}.")
paper = collection[0]
if not args.include_abstracts:
paper.pop("abstract", None)
print(json.dumps(paper, indent=2))
def main():
"""Parses arguments and fetches metadata by DOI."""
parser = argparse.ArgumentParser(
description="Fetch specific bioRxiv/medRxiv metadata by DOI."
)
parser.add_argument(
"--server",
choices=["biorxiv", "medrxiv"],
default="biorxiv",
help="The preprint server to query.",
)
parser.add_argument("--doi", required=True, help="The DOI of the paper")
parser.add_argument(
"--include_abstracts",
action="store_true",
help="Include full abstracts in the JSON output",
)
args = parser.parse_args()
search_by_doi(args)
if __name__ == "__main__":
main()
SKILL.md
---
name: literature-search-biorxiv
description: >
Browse and filter life sciences, biology, and medical preprints
from bioRxiv and medRxiv. Supports fetching paper metadata by DOI,
and browsing by date range with category and keyword filters. Keyword
filtering is local, so date ranges MUST be narrow (1-4 weeks) with a
category to prevent timeouts.
---
# bioRxiv and medRxiv Literature Search
## Prerequisites
1. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
`uv` is installed and on PATH.
2. **User Notification**: If .licenses/literature_search_biorxiv_LICENSE.txt
does not already exist in the workspace root directory then (1) prominently
notify the user to check the terms at https://api.biorxiv.org/ and
https://www.biorxiv.org/content/about-biorxiv and to always check the
license of the papers retrieved by the skill for any restrictions, then (2)
create the file recording the notification text and timestamp.
## Search Strategy Guide (Read First)
**This skill browses a date-based preprint archive. It is NOT a keyword search
engine.** Choose your approach based on what you already know:
- **A DOI** (e.g., from a citation): Use `search_by_doi.py`. Fast and
reliable.
- **Approximate date + category**: Use `search_by_dates.py` with a 1–4 week
range and `--category`.
- **Only a topic or keywords, no date**: **Do NOT use this skill for
discovery.** Use a keyword-capable literature skill first to find relevant
DOIs, then return here to fetch metadata.
> **CRITICAL ANTI-PATTERN — Do NOT do this:** Do NOT attempt to search broad
> date ranges (months or years) with `--keywords` hoping to find a specific
> paper. The bioRxiv API does not support server-side keyword search. The script
> must download ALL metadata for the entire date range and filter locally in
> Python. Broad ranges will result in thousands of API calls, timeouts, and your
> request being blocked for API abuse. This is the #1 reason this skill fails.
## Core Rules
- **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the
database rather than accessing the database directly. The scripts
automatically enforce the required rate limit gracefully.
- **Local Filtering (CRITICAL WARNING)**: Unlike arXiv, the bioRxiv API **does
not support server-side keyword or author searches**. Keyword and author
filtering is performed *locally* by the scripts after downloading all
metadata for a specified date range. You **MUST** use narrow date ranges
(e.g., 1-4 weeks) AND the `--category` filter when searching with
`--keywords` or `--author`.
- **Abstracts Excluded By Default**: To save context space in the resulting
JSON, abstracts are stripped from the output by default. If you are
searching by `--keywords` and want to read the abstracts of the resulting
papers to understand their context, you **MUST** pass the
`--include_abstracts` flag.
- **Output Redirection**: Search commands output JSON arrays to standard
output. Always redirect output to a file (e.g., `> results.json`) and parse
the file separately.
- **List Sources** If this skill is used, ensure this is mentioned in the
output AND list the URLs of all papers that were used in producing the
output.
## Utility Scripts
All tools enforce a cross-process rate limits and retry with backoff on failure.
To ensure you respect terms-of-service, do NOT write custom `curl` queries.
**Pagination:** The bioRxiv API returns results in pages of up to 100 papers.
The `search_by_dates.py` script automatically fetches all pages and reports
pagination progress to stderr (e.g., `[Page 2] Fetched 200/543 papers...`). The
JSON output to stdout contains the **complete** filtered result set across all
pages — no manual pagination is needed.
### 1. Search by Dates (`search_by_dates.py`)
Search for preprints within an explicit date range, optionally filtering by
category, keywords, or author.
```bash
# Broad category search over a 2-week period
uv run scripts/search_by_dates.py --server biorxiv \
--start_date 2024-01-01 --end_date 2024-01-14 \
--category neuroscience > results.json
# Deep keyword filtering using OR logic and including abstracts
uv run scripts/search_by_dates.py --server medrxiv \
--start_date 2023-11-01 --end_date 2023-11-30 \
--category infectious_diseases \
--keywords "covid" "sars-cov-2" --match_logic OR \
--include_abstracts > covid_papers.json
# Finding papers by a specific author in a narrow window
uv run scripts/search_by_dates.py \
--start_date 2024-05-01 --end_date 2024-05-14 \
--author "Smith" > smith_papers.json
```
*Required Arguments:*
- `--start_date`: YYYY-MM-DD
- `--end_date`: YYYY-MM-DD
*Optional Arguments:*
- `--server`: `biorxiv` (default) or `medrxiv`
- `--category`: A valid subject category (see below). **Highly recommended** —
dramatically reduces the data the script must download and filter.
- `--keywords`: List of strings to search in the title/abstract.
- `--match_logic`: `AND` (default) or `OR` for keywords.
- `--author`: Author name (case-insensitive string match).
- `--include_abstracts`: Flag to include full abstracts in the JSON output.
### 2. Fetch Metadata by DOI (`search_by_doi.py`)
Retrieve the detailed JSON metadata for a single paper if you already know its
DOI. **This is the most reliable entry point.**
```bash
uv run scripts/search_by_doi.py --server biorxiv \
--doi "10.1101/2023.08.15.551388" \
--include_abstracts > paper_info.json
```
### Downloading Full-Text PDFs
> **This skill does NOT support PDF downloads.** To download the full-text PDF
> of a bioRxiv or medRxiv preprint, use the **`literature-search-europepmc`**
> skill. First, use the paper's DOI to look up its PMCID via EuropePMC, then use
> EuropePMC's PDF retrieval to download the document.
## Valid Subject Categories
You can pass these to the `--category` flag in `search_by_dates.py`. The script
will strictly validate them.
### bioRxiv Categories:
`animal_behavior_and_cognition`, `biochemistry`, `bioengineering`,
`bioinformatics`, `biophysics`, `cancer_biology`, `cell_biology`,
`clinical_trials`, `developmental_biology`, `ecology`, `epidemiology`,
`evolutionary_biology`, `genetics`, `genomics`, `immunology`, `microbiology`,
`molecular_biology`, `neuroscience`, `paleontology`, `pathology`,
`pharmacology_and_toxicology`, `physiology`, `plant_biology`,
`scientific_communication_and_education`, `synthetic_biology`,
`systems_biology`, `zoology`
### medRxiv Categories:
`addiction_medicine`, `allergy_and_immunology`, `anesthesia`,
`cardiovascular_medicine`, `dentistry_and_oral_medicine`, `dermatology`,
`emergency_medicine`, `endocrinology`, `epidemiology`, `forensic_medicine`,
`gastroenterology`, `genetic_and_genomic_medicine`, `health_informatics`,
`health_economics_and_outcomes_research`, `health_policy`,
`health_systems_and_quality_improvement`, `hematology`, `hiv_aids`,
`infectious_diseases`, `intensive_care_and_critical_care_medicine`,
`medical_education`, `medical_ethics`, `nephrology`, `neurology`, `nursing`,
`nutrition`, `obstetrics_and_gynecology`,
`occupational_and_environmental_health`, `oncology`, `ophthalmology`,
`orthopedics`, `otolaryngology`, `pain_medicine`, `palliative_care`,
`pathology`, `pediatrics`, `pharmacology_and_therapeutics`,
`primary_care_research`, `psychiatry_and_clinical_psychology`,
`public_and_global_health`, `radiology_and_imaging`,
`rehabilitation_medicine_and_physical_therapy`, `respiratory_medicine`,
`rheumatology`, `sexual_and_reproductive_health`, `sports_medicine`, `surgery`,
`toxicology`, `transplantation`, `urology`