oncodash · njmmatthieu · Dec 8, 2025 · Dec 10, 2025 · Dec 10, 2025 · Dec 10, 2025
diff --git a/.gitignore b/.gitignore
@@ -1,10 +1,18 @@
-.venv
 .vscode
 biocypher-*
 *__pycache__*
 neo4j.pass
 backup
-data
 *.DS_Store
 notebooks
-tmp.sh
+tmp.sh
+
+import.report
+
+data
+
+.venv
+poetry.lock
+uv.lock
+*.egg-info
+build
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,33 @@
+repos:
+-   repo: local
+    hooks:
+    -   id: patient_id
+        name: Check for patient ids starting with "D", "H" or "M".
+        always_run: true
+        args: [--multiline]
+        entry: '[DHM][0-9]{3}'
+        language: pygrep
+    # -   id: M-code-patient_id
+    #     name: Check for patient ids starting with an "M".
+    #     always_run: true
+    #     args: [--multiline]
+    #     entry: 'M[0-9]{3}'
+    #     language: pygrep
+    # -   id: D-code-patient_id
+    #     name: Check for patient ids starting with an "D".
+    #     always_run: true
+    #     args: [--multiline]
+    #     entry: 'D[0-9]{3}'
+    #     language: pygrep
+    -   id: OC-code-patient_id
+        name: Check for patient ids starting with "OC".
+        always_run: true
+        args: [--multiline]
+        entry: 'OC[0-9]{3}'
+        language: pygrep
+    -   id: EOC-patient_code
+        name: Check for EOC patient codes.
+        always_run: true
+        args: [--multiline]
+        entry: 'EOC[0-9]{3}'
+        language: pygrep
diff --git a/README.md b/README.md
@@ -29,6 +29,16 @@ shell` inside the project directory.
 
 If you have a problem with the poetry install command, it may be that the 'poetry lock' command has not been ran after changing dependencies modification in '$ONCODASHKB_HOME/pyproject.toml'. Try running 'poetry lock' to fix the issue.
 
+### Requirements for preventing publishing patient ids
+
+Please, install [pre-commit](https://pre-commit.com/) hooks before committing or pushing anything new:
+
+```
+pre-commit install
+pre-commit install --hook-type pre-push
+pre-commit install --hook-type commit-msg
+```
+
 ### Database
 
 Theoretically, any graph database supported by Biocypher may be used.

diff --git a/config/biocypher_config.yaml b/config/biocypher_config.yaml
@@ -8,15 +8,15 @@ biocypher:
         url: https://github.com/biolink/biolink-model/raw/v3.2.1/biolink-model.owl.ttl
         root_node: entity
 
-    tail_ontologies:
-        so_variant:
-            url: http://purl.obolibrary.org/obo/so.owl
-            head_join_node: sequence variant
-            tail_join_node: sequence_variant
-        so_feature:
-            url: http://purl.obolibrary.org/obo/so.owl
-            head_join_node: attribute
-            tail_join_node: sequence_feature
+    # tail_ontologies:
+    #     so_variant:
+    #         url: http://purl.obolibrary.org/obo/so.owl
+    #         head_join_node: sequence variant
+    #         tail_join_node: sequence_variant
+    #     so_feature:
+    #         url: http://purl.obolibrary.org/obo/so.owl
+    #         head_join_node: attribute
+    #         tail_join_node: sequence_feature
 #        go_biological_process:
 #            url: http://purl.obolibrary.org/obo/go.owl
 #            head_join_node: biological process

diff --git a/config/schema_config.yaml b/config/schema_config.yaml
@@ -11,14 +11,15 @@ alteration:
     properties:
         citation_PM_ids: str
         consequence: str
+        homogenous: str
         level_of_evidence: str
         mutation_effect_description: str
+        name: str
         oncogenic: str
         reference_genome: str
         tumor_type: str
         tumor_type_summary: str
         variant_summary: str
-        name: str
 
 disease:
     represented_as: node
@@ -33,7 +34,7 @@ drug:
         name: str
 
 gene status:
-    is_a: outcome
+    is_a: phenomenon
     represented_as: node
     label_in_input: gene_status
     properties:
@@ -43,6 +44,7 @@ gene:
     represented_as: node
     label_in_input: gene
     properties:
+        gene_summary: str
         name: str
 
 # protein:
@@ -112,7 +114,7 @@ sample carries alteration:
 # A gene is linked to its gene status (gain or loss of function),
 # which are represented as nodes, so as to allow a causal path
 # to go through alteration -> gene status -> transcript activity.
-# Hence, outcomes have at least two instances:
+# Hence, phenomenons have at least two instances:
 # - Gene:GoF, and
 # - Gene:LoF.
 
@@ -155,15 +157,6 @@ patient has chronic illness:
 
 ### AFFECTS
 
-alteration affects gene:
-    is_a: affects
-    represented_as: edge
-    label_in_input: alteration_affects_gene
-    source: alteration
-    taregt: gene
-    properties:
-        name: str
-
 gene status affects gene:
     is_a: affects
     represented_as: edge

diff --git a/hooks/install_hooks.sh b/hooks/install_hooks.sh
diff --git a/hooks/leaking-data b/hooks/leaking-data
diff --git a/hooks/pre-commit b/hooks/pre-commit
diff --git a/hooks/pre-push b/hooks/pre-push
diff --git a/make_macos.sh b/make_macos.sh
@@ -1,12 +1,5 @@
 #!/usr/bin/bash
 
-# When using Neo4j installed on system (like Ubuntu's packaged version),
-# the current directory must be writable by user "neo4j",
-# and all parent directories must be executable by "other".
-# Every interaction with the database must be done by user "neo4j",
-# and the import will try to write reports in the current directory.
-# NEO_USER="sudo -u neo4j"
-
 # Exit on error.
 set -e
 set -o pipefail
@@ -22,9 +15,6 @@ if [[ "$2" == "debug" ]] ; then
     weave_args="-v DEBUG"
 fi
 
-# export JAVA_HOME="/usr/lib/jvm/java-21-openjdk-amd64"
-
-
 echo "Activate virtual environment..." >&2
 source $(poetry env info --path)/bin/activate
 
@@ -43,16 +33,12 @@ fi
 echo "Weave data..." >&2
 
 cmd="python3 ${py_args} $(pwd)/weave.py --verbose INFO \
-    --clinical                   $data_dir/DECIDER/$data_version/clinical_export.csv \
-    --single_nucleotide_variants $data_dir/DECIDER/$data_version/snv_external.csv  \
-    --copy_number_alterations    $data_dir/DECIDER/$data_version/cna_external.csv \
-    --gene_ontology_genes        $data_dir/DECIDER/$data_version/OncoKB_gene_symbols.conf \
-    --oncokb                     $data_dir/DECIDER/$data_version/treatments.csv \
-    --gene_ontology              $data_dir/GO/goa_human.gaf.gz \
-    --gene_ontology_owl          $data_dir/GO/go.owl \
-    --gene_ontology_reverse
+    --clinical                              $data_dir/DECIDER/$data_version/clinical_export.csv \
+    --short-mutations-local                 $data_dir/DECIDER/$data_version/snv_local.csv \
+    --short-mutations-external              $data_dir/DECIDER/$data_version/snv_external.csv  \
+    --copy-number-amplifications-local      $data_dir/DECIDER/$data_version/cna_local.csv \
+    --copy-number-amplifications-external   $data_dir/DECIDER/$data_version/cna_external.csv  \
     ${weave_args}" # \
-    #--small_molecules           $data_dir/omnipath_networks/omnipath_webservice_interactions__small_molecule_interactions_filtered.tsv.gz"
 
 echo "Weaving command:" >&2
 echo "$cmd" >&2
@@ -63,15 +49,14 @@ $cmd > tmp.sh
 if [[ "$2" != "debug" ]] ; then
     echo "Run import script..." >&2
     chmod a+x  $(cat tmp.sh)
-    $(cat tmp.sh) | tee /dev/tty | ${NEO_USER} sh
+    sh $(cat tmp.sh)
 
     echo "Restart Neo4j..." >&2
     $server start
     sleep 5
 
     echo "Send a test query..." >&2
-    sudo -u neo4j cypher-shell --username neo4j --database oncodash --password $(cat neo4j.pass) "MATCH (p:Patient) RETURN p LIMIT 20;"
+    cypher-shell --username neo4j --database oncodash --password $(cat neo4j.pass) "MATCH (p:Patient) RETURN p LIMIT 20;"
 fi
 
-echo "Done" >&2
-
+echo "Done" >&2
diff --git a/oncodashkb/adapters/clinical.yaml b/oncodashkb/adapters/clinical.yaml
@@ -1,11 +1,10 @@
 row:
     map:
-        columns:
-            - cohort_code
+        column: cohort_code
         to_subject: patient
 transformers:
     - map:
-        columns: survival
+        column: survival
         to_property: survival
         for_object: patient
     - map: