dwinston

diff --git a/jsonschema/nmdc.schema.json b/jsonschema/nmdc.schema.json
index 3a18b59..1efa788 100644
--- a/jsonschema/nmdc.schema.json
+++ b/jsonschema/nmdc.schema.json
@@ -53,6 +53,28 @@
          "title": "Agent",
          "type": "object"
       },
+      "AnalysisTypeEnum": {
+         "description": "",

dwinston

diff --git a/src/schema/basic_slots.yaml b/src/schema/basic_slots.yaml
index 17c8bf3..1fa4bda 100644
--- a/src/schema/basic_slots.yaml
+++ b/src/schema/basic_slots.yaml
@@ -29,7 +29,7 @@ slots:
     description: >-
       A unique identifier for a thing.
       Must be either a CURIE shorthand for a URI or a complete URI
-    #required: false # for now we setting this to false until we develop an id template
+    #required: false # for now we are setting this to false until we develop an id template

dwinston

dwinston

dwinston

"""
Build a subsumption map scoped to ENVO terms in use by NMDC biosamples
"""
from collections import defaultdict
import json

from rdflib import Graph
from rdflib.namespace import Namespace
from tqdm import tqdm

dwinston

{"biosample_set": [{
    "id": "fake3",
    "env_broad_scale" : {
        "term" : {"id": "ENVO:01000253"}
    }, 
    "env_local_scale" : {
        "term" : {"id": "ENVO:01000621"}
    }, 
    "env_medium" : {
        "term" : {"id": "ENVO:01000017"}

dwinston

{"biosample_set": [{
    "id": "fake2",
    "env_broad_scale" : {
        "term" : {"id": "ENVO:01000253"}
    }, 
    "env_local_scale" : {
        "term" : {"id": "ENVO:01000621"}
    }, 
    "env_medium" : {
        "term" : {"id": "ENVO:01000017"}

dwinston

{ 
    "name" : "FT ICR-MS analysis results", 
    "description" : "FT ICR-MS-based metabolite assignment results table", 
    "filter" : "{\"url\": {\"$regex\": \"nom\\\\/results\"}, \"description\": {\"$regex\": \"FT ICR-MS\"}}", 
    "id" : "nmdc:sys045mx19"
}
{ 
    "name" : "GC-MS Metabolomics Results", 
    "description" : "GC-MS-based metabolite assignment results table", 
    "filter" : "{\"url\": {\"$regex\": \"metabolomics\\\\/results\"}}", 

dwinston

from dagster import (
    ModeDefinition, PresetDefinition, resource, StringSource,
    build_init_resource_context, RunRequest, sensor,
)

class ApiClient:
    def __init__(self, base_url: str, site_id: str, client_id: str, client_secret: str):
        self.base_url = base_url
        self.site_id = site_id
        self.client_id = client_id

dwinston

"""
A script developed to get all Zulip messages sent by non-bot users to public streams.

Need to pip install pymongo tqdm zulip, and run a local MongoDB server.
But you can also adapt the script to append to an in-memory Python list, and not need MongoDB or pymongo.
I found that the total volume of data in my case (see in-script comments) was 700MB uncompressed.

Developed at the Recurse Center (https://www.recurse.com/) in order to apply PageRank to Zulip entities.
Licensed as <https://opensource.org/licenses/MIT>(year=2021, copyright_holder="Donny Winston").
"""