Calculate object measures based on JSON file

flamingo_tools/measurements.py

@@ -2,7 +2,7 @@
 import os
 from concurrent import futures
 from functools import partial
-from typing import Optional
+from typing import List, Optional
 
 import numpy as np
 import pandas as pd
@@ -12,6 +12,7 @@
 
 from .file_utils import read_image_data
 from .segmentation.postprocessing import compute_table_on_the_fly
+import flamingo_tools.s3_utils as s3_utils
 
 
 def _measure_volume_and_surface(mask, resolution):
@@ -175,6 +176,8 @@ def compute_object_measures(
     resolution: float = 0.38,
     force: bool = False,
     feature_set: str = "default",
+    s3_flag: bool = False,
+    component_list: List[int] = [],
 ) -> None:
     """Compute simple intensity and morphology measures for each segmented cell in a segmentation.
 
@@ -201,9 +204,17 @@ def compute_object_measures(
     # First, we load the pre-computed segmentation table from MoBIE.
     if segmentation_table_path is None:
         table = None
+    elif s3_flag:
+        seg_table, fs = s3_utils.get_s3_path(segmentation_table_path)
+        with fs.open(seg_table, 'r') as f:
+            table = pd.read_csv(f, sep="\t")
     else:
         table = pd.read_csv(segmentation_table_path, sep="\t")
 
+    # filter table with largest component
+    if len(component_list) != 0 and "component_labels" in table.columns:
+        table = table[table['component_labels'].isin(component_list)]
+
     # Then, open the volumes.
     image = read_image_data(image_path, image_key)
     segmentation = read_image_data(segmentation_path, segmentation_key)

reproducibility/block_extraction/repro_block_extraction.py

@@ -7,7 +7,7 @@
 
 
 def repro_block_extraction(
-    ddict: dict,
+    json_file: str,
     output_dir: str,
     s3_credentials: Optional[str] = None,
     s3_bucket_name: Optional[str] = None,
@@ -17,7 +17,7 @@ def repro_block_extraction(
     tif_flag = True
     input_key = "s0"
 
-    with open(ddict, 'r') as myfile:
+    with open(json_file, 'r') as myfile:
         data = myfile.read()
     param_dicts = json.loads(data)
 

reproducibility/object_measures/2025-06-IHC-Apha_object_measures.json

@@ -0,0 +1,24 @@
+[
+	{
+		"cochlea": "M_AMD_OTOF1_L",
+		"image_channel": [
+			"Apha"
+		],
+		"segmentation_channel": "IHC_v2",
+		"component_list": [
+			1,
+			20
+		]
+	},
+	{
+		"cochlea": "M_AMD_OTOF2_L",
+		"image_channel": [
+			"Apha"
+		],
+		"segmentation_channel": "IHC_v2",
+		"component_list": [
+			1,
+			2
+		]
+	}
+]

reproducibility/object_measures/2025-06-SGN-PV-GFP_object_measures.json

@@ -0,0 +1,46 @@
+[
+	{
+		"cochlea": "M_LR_000144_L",
+		"image_channel": [
+			"PV_resized",
+			"GFP_resized"
+		],
+		"segmentation_channel": "SGN_resized_v2",
+		"component_list": [
+			1
+		]
+	},
+	{
+		"cochlea": "M_LR_000145_L",
+		"image_channel": [
+			"PV_resized",
+			"GFP_resized"
+		],
+		"segmentation_channel": "SGN_resized_v2",
+		"component_list": [
+			1
+		]
+	},
+	{
+		"cochlea": "M_LR_000151_R",
+		"image_channel": [
+			"PV_resized",
+			"GFP_resized"
+		],
+		"segmentation_channel": "SGN_resized_v2",
+		"component_list": [
+			1
+		]
+	},
+	{
+		"cochlea": "M_LR_000155_L",
+		"image_channel": [
+			"PV_resized",
+			"GFP_resized"
+		],
+		"segmentation_channel": "SGN_resized_v2",
+		"component_list": [
+			1
+		]
+	}
+]

reproducibility/object_measures/repro_object_measures.py

@@ -0,0 +1,84 @@
+import argparse
+import json
+import os
+from typing import Optional
+
+import flamingo_tools.s3_utils as s3_utils
+from flamingo_tools.measurements import compute_object_measures
+
+
+def repro_object_measures(
+    json_file: str,
+    output_dir: str,
+    s3_credentials: Optional[str] = None,
+    s3_bucket_name: Optional[str] = None,
+    s3_service_endpoint: Optional[str] = None,
+):
+    s3_flag = True
+    input_key = "s0"
+
+    with open(json_file, 'r') as myfile:
+        data = myfile.read()
+    param_dicts = json.loads(data)
+
+    for dic in param_dicts:
+        cochlea = dic["cochlea"]
+        image_channels = dic["image_channel"] if isinstance(dic["image_channel"], list) else [dic["image_channel"]]
+        seg_channel = dic["segmentation_channel"]
+        component_list = dic["component_list"]
+        print(f"Processing cochlea {cochlea}")
+
+        for img_channel in image_channels:
+
+            print(f"Processing image channel {img_channel}")
+            cochlea_str = "-".join(cochlea.split("_"))
+            img_str = "-".join(img_channel.split("_"))
+            seg_str = "-".join(seg_channel.split("_"))
+            output_table_path = os.path.join(output_dir, f"{cochlea_str}_{img_str}_{seg_str}_object-measures.tsv")
+
+            img_s3 = f"{cochlea}/images/ome-zarr/{img_channel}.ome.zarr"
+            seg_s3 = f"{cochlea}/images/ome-zarr/{seg_channel}.ome.zarr"
+            seg_table_s3 = f"{cochlea}/tables/{seg_channel}/default.tsv"
+
+            img_path, fs = s3_utils.get_s3_path(img_s3, bucket_name=s3_bucket_name,
+                                                service_endpoint=s3_service_endpoint, credential_file=s3_credentials)
+            seg_path, fs = s3_utils.get_s3_path(seg_s3, bucket_name=s3_bucket_name,
+                                                service_endpoint=s3_service_endpoint, credential_file=s3_credentials)
+
+            compute_object_measures(
+                image_path=img_path,
+                segmentation_path=seg_path,
+                segmentation_table_path=seg_table_s3,
+                output_table_path=output_table_path,
+                image_key=input_key,
+                segmentation_key=input_key,
+                s3_flag=s3_flag,
+                component_list=component_list)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Script to extract region of interest (ROI) block around center coordinate.")
+
+    parser.add_argument('-i', '--input', type=str, required=True, help="Input JSON dictionary.")
+    parser.add_argument('-o', "--output", type=str, required=True, help="Output directory.")
+
+    parser.add_argument("--s3_credentials", type=str, default=None,
+                        help="Input file containing S3 credentials. "
+                        "Optional if AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY were exported.")
+    parser.add_argument("--s3_bucket_name", type=str, default=None,
+                        help="S3 bucket name. Optional if BUCKET_NAME was exported.")
+    parser.add_argument("--s3_service_endpoint", type=str, default=None,
+                        help="S3 service endpoint. Optional if SERVICE_ENDPOINT was exported.")
+
+    args = parser.parse_args()
+
+    repro_object_measures(
+        args.input, args.output,
+        args.s3_credentials, args.s3_bucket_name, args.s3_service_endpoint,
+    )
+
+
+if __name__ == "__main__":
+
+    main()