Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bagel #103

Merged
merged 7 commits into from
Aug 7, 2024
Merged

Bagel #103

Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions dags/roger/config/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,21 @@ class AnnotationConfig(DictLike):
"sapbert": {
"classification_url": "https://med-nemo.apps.renci.org/annotate/",
"annotator_url": "https://babel-sapbert.apps.renci.org/annotate/",
"score_threshold": 0.8,
"bagel": {
"enabled": False,
"url": "https://bagel.apps.renci.org/group_synonyms_openai",
"prompt": "bagel/ask_classes",
"llm_args": {
"llm_model_name": "gpt-4o-2024-05-13",
"organization": "",
"access_key": "",
"llm_model_args": {
"top_p": 0,
"temperature": 0.1
}
}
}
},
}
)
Expand Down
22 changes: 17 additions & 5 deletions dags/roger/config/config.yaml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
redisgraph:
username: ""
password: "12345"
password: "weak"
host: localhost
graph: test
port: 6379
Expand Down Expand Up @@ -42,13 +42,25 @@ bulk_loader:

annotation:
clear_http_cache: false
annotator_type: monarch
annotator_type: sapbert
annotator_args:
monarch:
url: "https://api.monarchinitiative.org/api/nlp/annotate/entities?min_length=4&longest_only=false&include_abbreviation=false&include_acronym=false&include_numbers=false&content="
sapbert:
classification_url: "https://med-nemo.apps.renci.org/annotate/"
annotator_url: "https://babel-sapbert.apps.renci.org/annotate/"
annotator_url: "https://sap-qdrant.apps.renci.org/annotate/"
score_threshold: 0.5
bagel:
enabled: false
url: "http://localhost:9099/group_synonyms_openai"
prompt: "bagel/ask_classes"
llm_args:
llm_model_name: "gpt-4o-2024-05-13"
organization:
access_key:
llm_model_args:
top_p: 0
temperature: 0.1
normalizer: "https://nodenormalization-dev.apps.renci.org/get_normalized_nodes?conflate=false&description=true&curie="
synonym_service: "https://name-resolution-sri.renci.org/reverse_lookup"
ontology_metadata: "https://api.monarchinitiative.org/api/bioentity/"
Expand Down Expand Up @@ -93,9 +105,9 @@ indexing:
action: "files"

elasticsearch:
host: elasticsearch
host: localhost
username: elastic
password: ""
password: "12345"
nboost_host: ""
scheme: "http"
ca_path: ""
Expand Down
50 changes: 50 additions & 0 deletions dags/roger/pipelines/bdc_pipelines.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
"Dug pipeline for dbGaP data set"

from roger.pipelines import DugPipeline

class BIOLINCCdbGaPPipeline(DugPipeline):
"Pipeline for the dbGaP data set"
pipeline_name = 'biolincc'
parser_name = 'biolincc'


class covid19dbGaPPipeline(DugPipeline):
"Pipeline for the dbGaP data set"
pipeline_name = 'covid19-dbgap'
parser_name = 'covid19'

class dirDbGaPPipeline(DugPipeline):
pipeline_name = "dir-dbgap"
parser_name = "dir"

class LungMapDbGaPPipeline(DugPipeline):
pipeline_name = "lungmap-dbgap"
parser_name = "lungmap"

class nsrrDbGaPPipeline(DugPipeline):
pipeline_name = "nsrr-dbgap"
parser_name = "nsrr"

class ParentDbGaPPipeline(DugPipeline):
pipeline_name = "parent-dbgap"
parser_name = "parent"

class PCGCDbGaPPipeline(DugPipeline):
pipeline_name = "pcgc-dbgap"
parser_name = "pcgc"

class RecoverDbGaPPipeline(DugPipeline):
pipeline_name = "recover-dbgap"
parser_name = "recover"

class TopmedDBGaPPipeline(DugPipeline):
pipeline_name = "topmed-gen3-dbgap"
parser_name = "topmeddbgap"

class CureSCPipeline(DugPipeline):
pipeline_name = "curesc-dbgap"
parser_name = "curesc"

class SmallDataDbGap(DugPipeline):
pipeline_name = "small-data-dbgap"
parser_name = "topmeddbgap"
2 changes: 1 addition & 1 deletion requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ jsonpickle
redisgraph-bulk-loader==0.12.3
pytest
PyYAML
git+https://github.com/helxplatform/dug@2.13.1
git+https://github.com/helxplatform/dug@develop
orjson
kg-utils==0.0.6
bmt==1.1.0
Expand Down
Loading