structflo-ner 0.7.0__tar.gz → 0.7.1__tar.gz

{structflo_ner-0.7.0 → structflo_ner-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: structflo-ner
-Version: 0.7.0
+Version: 0.7.1
 Summary: Drug discovery NER wrapper around LangExtract — zero-config entity extraction for chemistry and biology.
 License: Apache-2.0
 Requires-Python: >=3.10

{structflo_ner-0.7.0 → structflo_ner-0.7.1}/structflo/ner/__init__.py

@@ -63,7 +63,7 @@ from structflo.ner.profiles import (
     EntityProfile,
 )
 
-__version__ = "0.7.0"
+__version__ = "0.7.1"
 
 __all__ = [
     # Main classes

{structflo_ner-0.7.0 → structflo_ner-0.7.1}/structflo/ner/_examples.py

@@ -984,7 +984,8 @@ _TB_EXAMPLE_6 = lx.data.ExampleData(
 
 # Strain panel: organism column headers are the strain, a protein column the
 # target, a cytotoxicity column the assay; a column dosed with a second drug
-# names the combination partner. The disease stays a disease entity.
+# names the combination partner, which is also a compound. The disease stays a
+# disease entity.
 _TB_EXAMPLE_7 = lx.data.ExampleData(
     text=(
         "Table 3. Antibacterial activity against hospital-acquired pneumonia isolates\n\n"
@@ -1005,6 +1006,10 @@ _TB_EXAMPLE_7 = lx.data.ExampleData(
             extraction_text="CHEMBL5311027",
             attributes={"synonyms": "9c"},
         ),
+        lx.data.Extraction(
+            extraction_class="compound_name",
+            extraction_text="polymyxin B",
+        ),
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="0.25",

{structflo_ner-0.7.0 → structflo_ner-0.7.1}/structflo/ner/_prompts.py

@@ -32,13 +32,16 @@ _TB_SLOT_ATTRIBUTES = (
     "stated.\n"
     "- target: the protein the value was measured against: an enzyme, receptor, channel or "
     "other molecular target, as written ('InhA', 'DprE1', 'hERG', 'KasA', 'PDE4B', "
-    "'BACE1'). null for whole-cell, organism and cytotoxicity values unless one is named.\n"
+    "'BACE1'), also when it heads a table column. null for whole-cell, organism and "
+    "cytotoxicity values unless one is named.\n"
     "- strain: the organism the value was measured against, as written: species, strain, "
     "isolate or virus (H37Rv, M. tuberculosis, E. coli ATCC 25922, A. baumannii ATCC 19606, "
-    "Pf3D7, Dd2, S. mansoni, HIV-1, norovirus). An organism always goes here, never in assay or target, even "
-    "when it heads a table column or is all that names the assay. null when not stated.\n"
+    "Pf3D7, Dd2, S. mansoni, HIV-1, norovirus). An organism always goes here, never in assay "
+    "or target, even when it heads a table column or is all that names the assay. null when "
+    "not stated.\n"
     "- combination: a second compound dosed together with the one measured (a combination "
-    "or potentiation partner), as written ('avibactam', 'polymyxin B 0.5 µg/mL'). Not a "
+    "or potentiation partner), as written ('avibactam', 'polymyxin B 0.5 µg/mL'), also when "
+    "a table column is headed by the partner's name alone. Not a "
     "reference compound the value is relative to ('% of isoproterenol') or an agonist, substrate "
     "or tracer the assay uses. null for a single agent.\n"
 )
@@ -46,8 +49,10 @@ _BIOACTIVITY_TABLES = (
     "In a data table, extract every cell value as its own bioactivity. An ID or registry "
     "column, when present, supplies the compound_name and the row label is only its synonym; "
     "otherwise the row label is the compound_name. A column header fills the attribute for "
-    "what it names (an assay or cell line, a protein target, an organism or strain), and the "
-    "endpoint and unit often come from the caption or a footnote ('CC50 in µM')."
+    "what it names (an assay or cell line, a protein target, an organism or strain, a partner "
+    "drug dosed alongside); a header you cannot place goes in assay, so no table value is left "
+    "without its column. The endpoint and unit often come from the caption or a footnote "
+    "('CC50 in µM')."
 )
 
 CHEMISTRY_PROMPT = (
@@ -129,6 +134,8 @@ TB_PROMPT = (
     "- A disease or infection is a disease entity wherever it is named, in prose, a heading "
     "or a table cell (tuberculosis, HIV infection, malaria, schistosomiasis, glioblastoma in 'U87 (glioblastoma)'), "
     "even when its organism also fills a bioactivity's strain.\n"
+    "- A combination partner is also a compound_name entity, extracted once like any other "
+    "compound.\n"
     "- Use target for proteins in a drug-targeting context, gene_name for loci, "
     "protein_name for non-drug-target proteins.\n\n"
     "Extract only what is explicitly stated; do not infer or generate values."