Charles Tapley Hoyt cthoyt

## README.md

      
              2 files
            
          
              0 forks
            
          
                0 comments
              
            
              0 stars
            
          
                cthoyt
                / README.md
            
            
              Last active
              March 9, 2026 21:04
            
              
                Bioregistry to Twitter Mapping
              
          
    Why

Twitter isn't a friendly place anymore (to put it mildly), so it doesn't
track with the Bioregistry project values to promote it as a platform.
This gist will serve as a final resting place for the mappings,
outside of the Bioregistry itself.

  
## bartoc_examples.json
{
  "14": [
    "ffdd3a7e-f82e-4600-98b1-20402e74b0a6"
  ],
  "15": [
    "1837"
  ],
  "16": [
    "627"
  ],

## sssom-wikidata-demo.py
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "sssom-pydantic[wikidata]>=0.1.18",
# ]
# ///

from urllib.request import urlretrieve
from sssom_pydantic.contrib.wikidata import read_and_open_quickstatements

## bioregistry-to-jsonld.py
from typing import Any

import curies

from bioregistry import get_iri
import requests
from bs4 import BeautifulSoup
import json


## README.md

      
              3 files
            
          
              0 forks
            
          
                2 comments
              
            
              0 stars
            
          
                cthoyt
                / README.md
            
            
              Last active
              September 30, 2025 15:38
            
              
                Hierarchical Synonym Type Demo
              
          
    Hierarchical Synonym Type Demo

This demonstration goes along with information-artifact-ontology/ontology-metadata#194
to show what happens when ROBOT tries to convert an ontology that has hierarchical synonym type properties.
Unfortunately, it doesn't appear to write the child property in OBO. This is probably because the parser
only looks for direct children of oboInOwl:SynonymTypeProperty

  
## sssom_to_wikidata.py
import bioregistry
import quickstatements_client
import sssom
from curies.dataframe import filter_df_by_curies, filter_df_by_prefixes
from quickstatements_client import Line, Qualifier, TextLine, TextQualifier
from sssom import MappingSetDataFrame


def open_quickstatements_tab(msdf: MappingSetDataFrame) -> None:
    """Create a QuickStatements tab from mappings."""

## bioregistry-text-mining-regexes.tsv

          
            Prefix
            Resource Name
            RegEx
            Example

            
              anzctr
              Australian New Zealand Clinical Trials Registry
              ACTRN\d+
              ACTRN12623000498695

            
              beetlebase
              Tribolium Genome Database -- Insertion
              TC\d+
              TC010103

            
              blastrule
              BlastRule
              NBR\d+
              NBR016799

            
              cellopub
              Cellosaurus Publication
              CLPUB\d+
              CLPUB00496

            
              chembl
              ChEMBL
              CHEMBL\d+
              CHEMBL4303805

            
              chembl.cell
              ChEMBL database of bioactive drug-like small [...]
              CHEMBL\d+
              CHEMBL3307800

            
              chembl.compound
              ChEMBL
              CHEMBL\d+
              CHEMBL465070

            
              chembl.target
              ChEMBL target
              CHEMBL\d+
              CHEMBL3467

            
              chempro.competitor
              ChemPro Competitor
              LDCM\d+
              LDCM0160

## clinicaltrials-summary.py
# /// script
# requires-python = ">=3.11"
# dependencies = [
#     "clinicaltrials-downloader>=0.0.2",
#     "pyobo[grounding]",
#     "tabulate",
#     "pystow",
#     "click",
# ]
#

## swear_the_oaths.py
# /// script
# requires-python = ">=3.11"
# dependencies = [
#     "beautifulsoup4",
#     "requests",
#     "yt-dlp",
# ]
# ///

"""Download chapters from Wind and Truth.

## bioregistry_negative_mappings.py
import json

import bioregistry

if __name__ == "__main__":
    r = json.load(open("mismatch.json"))
    with open("mismatches.sssom.tsv", "w") as file:
        print(
            "subject_id",
            "subject_label",
	{
	"14": [
	"ffdd3a7e-f82e-4600-98b1-20402e74b0a6"
	],
	"15": [
	"1837"
	],
	"16": [
	"627"
	],
	# /// script
	# requires-python = ">=3.10"
	# dependencies = [
	# "sssom-pydantic[wikidata]>=0.1.18",
	# ]
	# ///

	from urllib.request import urlretrieve
	from sssom_pydantic.contrib.wikidata import read_and_open_quickstatements
	from typing import Any

	import curies

	from bioregistry import get_iri
	import requests
	from bs4 import BeautifulSoup
	import json
	import bioregistry
	import quickstatements_client
	import sssom
	from curies.dataframe import filter_df_by_curies, filter_df_by_prefixes
	from quickstatements_client import Line, Qualifier, TextLine, TextQualifier
	from sssom import MappingSetDataFrame


	def open_quickstatements_tab(msdf: MappingSetDataFrame) -> None:
	"""Create a QuickStatements tab from mappings."""
Prefix	Resource Name	RegEx	Example
anzctr	Australian New Zealand Clinical Trials Registry	ACTRN\d+	ACTRN12623000498695
beetlebase	Tribolium Genome Database -- Insertion	TC\d+	TC010103
blastrule	BlastRule	NBR\d+	NBR016799
cellopub	Cellosaurus Publication	CLPUB\d+	CLPUB00496
chembl	ChEMBL	CHEMBL\d+	CHEMBL4303805
chembl.cell	ChEMBL database of bioactive drug-like small [...]	CHEMBL\d+	CHEMBL3307800
chembl.compound	ChEMBL	CHEMBL\d+	CHEMBL465070
chembl.target	ChEMBL target	CHEMBL\d+	CHEMBL3467
chempro.competitor	ChemPro Competitor	LDCM\d+	LDCM0160
	# /// script
	# requires-python = ">=3.11"
	# dependencies = [
	# "clinicaltrials-downloader>=0.0.2",
	# "pyobo[grounding]",
	# "tabulate",
	# "pystow",
	# "click",
	# ]
	#
	import json

	import bioregistry

	if __name__ == "__main__":
	r = json.load(open("mismatch.json"))
	with open("mismatches.sssom.tsv", "w") as file:
	print(
	"subject_id",
	"subject_label",