structflo-ner 0.2.3__tar.gz → 0.3.0__tar.gz

{structflo_ner-0.2.3 → structflo_ner-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: structflo-ner
-Version: 0.2.3
+Version: 0.3.0
 Summary: Drug discovery NER wrapper around LangExtract — zero-config entity extraction for chemistry and biology.
 License: Apache-2.0
 Requires-Python: >=3.10
@@ -43,7 +43,7 @@ Description-Content-Type: text/markdown
 
 ---
 
-**structflo.ner** is a lightweight NER library specialized for pharmaceutical and biological sciences. It uses [LangExtract](https://github.com/langextract/langextract) and fuzzy based tools to deliver **zero-configuration** entity extraction.
+**structflo.ner** is a lightweight NER library specialized for pharmaceutical and biological sciences. It uses [LangExtract](https://github.com/google/langextract) and fuzzy based tools to deliver **zero-configuration** entity extraction.
 
 It ships with two extraction engines:
 
@@ -111,7 +111,7 @@ Any model served by [Ollama](https://ollama.com/) works  gemma, llama, mistral,
 
 
 Render results as color-coded, interactive HTML directly in Jupyter notebooks:
-![Results](images/local-gen-viz.png)
+![Results](images/ner_visualization.gif)
 
 
 To get a PANDAS dataframe.

{structflo_ner-0.2.3 → structflo_ner-0.3.0}/README.md

@@ -30,7 +30,7 @@
 
 ---
 
-**structflo.ner** is a lightweight NER library specialized for pharmaceutical and biological sciences. It uses [LangExtract](https://github.com/langextract/langextract) and fuzzy based tools to deliver **zero-configuration** entity extraction.
+**structflo.ner** is a lightweight NER library specialized for pharmaceutical and biological sciences. It uses [LangExtract](https://github.com/google/langextract) and fuzzy based tools to deliver **zero-configuration** entity extraction.
 
 It ships with two extraction engines:
 
@@ -98,7 +98,7 @@ Any model served by [Ollama](https://ollama.com/) works  gemma, llama, mistral,
 
 
 Render results as color-coded, interactive HTML directly in Jupyter notebooks:
-![Results](images/local-gen-viz.png)
+![Results](images/ner_visualization.gif)
 
 
 To get a PANDAS dataframe.

{structflo_ner-0.2.3 → structflo_ner-0.3.0}/structflo/ner/__init__.py

@@ -63,7 +63,7 @@ from structflo.ner.profiles import (
     EntityProfile,
 )
 
-__version__ = "0.2.3"
+__version__ = "0.3.0"
 
 __all__ = [
     # Main classes

{structflo_ner-0.2.3 → structflo_ner-0.3.0}/structflo/ner/_examples.py

@@ -166,7 +166,12 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="IC50 of 2.3 nM",
-            attributes={"value": "2.3", "unit": "nM", "assay_type": "IC50"},
+            attributes={
+                "value": "2.3",
+                "unit": "nM",
+                "assay_type": "IC50",
+                "compound_name": "Compound 7",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -176,7 +181,12 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="EC50 of 45 nM",
-            attributes={"value": "45", "unit": "nM", "assay_type": "EC50"},
+            attributes={
+                "value": "45",
+                "unit": "nM",
+                "assay_type": "EC50",
+                "compound_name": "Compound 7",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -190,7 +200,12 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="Ki = 0.8 nM",
-            attributes={"value": "0.8", "unit": "nM", "assay_type": "Ki"},
+            attributes={
+                "value": "0.8",
+                "unit": "nM",
+                "assay_type": "Ki",
+                "compound_name": "Compound 7",
+            },
         ),
     ],
 )
@@ -317,7 +332,12 @@ _FULL_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="IC50 of 0.033 µM",
-            attributes={"value": "0.033", "unit": "µM", "assay_type": "IC50"},
+            attributes={
+                "value": "0.033",
+                "unit": "µM",
+                "assay_type": "IC50",
+                "compound_name": "Gefitinib",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -332,7 +352,12 @@ _FULL_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="IC50 of 0.4 µM",
-            attributes={"value": "0.4", "unit": "µM", "assay_type": "IC50"},
+            attributes={
+                "value": "0.4",
+                "unit": "µM",
+                "assay_type": "IC50",
+                "compound_name": "Gefitinib",
+            },
         ),
         lx.data.Extraction(
             extraction_class="mechanism_of_action",
@@ -418,7 +443,13 @@ _TB_EXAMPLE_1 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC of 0.03 ug/mL",
-            attributes={"value": "0.03", "unit": "ug/mL", "assay_type": "MIC", "strain": "H37Rv"},
+            attributes={
+                "value": "0.03",
+                "unit": "ug/mL",
+                "assay_type": "MIC",
+                "strain": "H37Rv",
+                "compound_name": "Bedaquiline",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -491,12 +522,24 @@ _TB_EXAMPLE_2 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC of 1 ng/mL",
-            attributes={"value": "1", "unit": "ng/mL", "assay_type": "MIC", "strain": "H37Rv"},
+            attributes={
+                "value": "1",
+                "unit": "ng/mL",
+                "assay_type": "MIC",
+                "strain": "H37Rv",
+                "compound_name": "BTZ043",
+            },
         ),
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC of 4 ng/mL",
-            attributes={"value": "4", "unit": "ng/mL", "assay_type": "MIC", "strain": "Erdman"},
+            attributes={
+                "value": "4",
+                "unit": "ng/mL",
+                "assay_type": "MIC",
+                "strain": "Erdman",
+                "compound_name": "BTZ043",
+            },
         ),
         lx.data.Extraction(
             extraction_class="compound_name",
@@ -510,7 +553,12 @@ _TB_EXAMPLE_2 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC of 0.6 ng/mL",
-            attributes={"value": "0.6", "unit": "ng/mL", "assay_type": "MIC"},
+            attributes={
+                "value": "0.6",
+                "unit": "ng/mL",
+                "assay_type": "MIC",
+                "compound_name": "PBTZ169",
+            },
         ),
         lx.data.Extraction(
             extraction_class="mechanism_of_action",
@@ -566,7 +614,12 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="IC50 of 85 nM",
-            attributes={"value": "85", "unit": "nM", "assay_type": "IC50"},
+            attributes={
+                "value": "85",
+                "unit": "nM",
+                "assay_type": "IC50",
+                "compound_name": "Compound 14a",
+            },
         ),
         lx.data.Extraction(
             extraction_class="screening_method",
@@ -584,7 +637,13 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC90 of 0.5 uM",
-            attributes={"value": "0.5", "unit": "uM", "assay_type": "MIC90", "strain": "H37Rv"},
+            attributes={
+                "value": "0.5",
+                "unit": "uM",
+                "assay_type": "MIC90",
+                "strain": "H37Rv",
+                "compound_name": "Compound 14a",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -594,7 +653,12 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="EC50 of 1.2 uM",
-            attributes={"value": "1.2", "unit": "uM", "assay_type": "EC50"},
+            attributes={
+                "value": "1.2",
+                "unit": "uM",
+                "assay_type": "EC50",
+                "compound_name": "Compound 14a",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -604,7 +668,12 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="MIC of 3.1 uM",
-            attributes={"value": "3.1", "unit": "uM", "assay_type": "MIC"},
+            attributes={
+                "value": "3.1",
+                "unit": "uM",
+                "assay_type": "MIC",
+                "compound_name": "Compound 14a",
+            },
         ),
         lx.data.Extraction(
             extraction_class="assay",
@@ -614,7 +683,12 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
         lx.data.Extraction(
             extraction_class="bioactivity",
             extraction_text="CC50 >50 uM",
-            attributes={"value": ">50", "unit": "uM", "assay_type": "CC50"},
+            attributes={
+                "value": ">50",
+                "unit": "uM",
+                "assay_type": "CC50",
+                "compound_name": "Compound 14a",
+            },
         ),
     ],
 )

{structflo_ner-0.2.3 → structflo_ner-0.3.0}/structflo/ner/_prompts.py

@@ -18,9 +18,12 @@ BIOLOGY_PROMPT = (
 
 BIOACTIVITY_PROMPT = (
     "Extract bioactivity measurements and assay data from the text. "
-    "Include: potency values (IC50, EC50, Ki, Kd, GI50, CC50), selectivity ratios, "
+    "Include: potency values (IC50, MIC, EC50, Ki, Kd, GI50, CC50), selectivity ratios, "
     "percent inhibition values, and Hill coefficients. "
-    "For each value, capture the numeric value, unit (nM, µM, mM), and measurement type. "
+    "For each value, capture the numeric value, unit (nM, µM, mM, µg/mL, ng/mL), and measurement type. "
+    "Also capture the compound — its name, code name, or identifier (e.g. 'Compound 7', 'BTZ043', "
+    "'CHEMBL1234', 'SACC-3000') — that the measurement applies to, as a 'compound_name' attribute, "
+    "if it can be identified from the surrounding context. "
     "Also extract assay descriptions: cell lines used (e.g. 'HeLa', 'A549'), assay formats "
     "(e.g. 'cell viability', 'binding assay', 'enzymatic assay'), and organisms."
 )
@@ -40,8 +43,9 @@ FULL_PROMPT = (
     "- Chemical entities: compound names (generic, IUPAC, code names, brand names), "
     "SMILES strings (only if explicitly written), CAS numbers, molecular formulas.\n"
     "- Biological targets: protein names, gene names, receptor names, enzyme names, pathways.\n"
-    "- Bioactivity data: IC50, EC50, Ki, Kd, and other potency/selectivity measurements "
-    "with their numeric values and units.\n"
+    "- Bioactivity data: IC50, MIC, EC50, Ki, Kd, and other potency/selectivity measurements "
+    "with their numeric values, units, and the compound name or identifier they apply to "
+    "(captured as a 'compound_name' attribute).\n"
     "- Assay information: cell lines, assay formats, experimental organisms.\n"
     "- Diseases and indications: cancer types, disease names, therapeutic areas.\n"
     "- Mechanisms of action: binding modes, inhibition types, selectivity descriptions.\n"
@@ -52,6 +56,9 @@ FULL_PROMPT = (
 
 TB_PROMPT = (
     "Extract drug discovery entities from this tuberculosis research text.\n\n"
+    "For each bioactivity measurement (IC50, MIC, MIC90, EC50, CC50, etc.), capture the "
+    "compound name, code, or identifier it belongs to as a 'compound_name' attribute "
+    "(e.g. 'BTZ043 showed a MIC of 1 ng/mL' → compound_name: 'BTZ043').\n\n"
     "DISAMBIGUATION RULES:\n"
     "- Mycobacterial proteins (e.g. ClpC1, DprE1, InhA, AtpE, MmpL3, QcrB) "
     "are biological targets, NOT compounds.\n"