spacr 0.3.1__py3-none-any.whl → 0.3.2__py3-none-any.whl

{spacr-0.3.1.dist-info → spacr-0.3.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-spacr/__init__.py,sha256=bKVlCCJatRBMqjfxSXds2D_Swjf30T6agvAQ0Usz80o,1176
+spacr/__init__.py,sha256=3TNo4PgxHZTHOhyPc8AORvG3tzdPFEc30KAtsOou174,1618
 spacr/__main__.py,sha256=bkAJJD2kjIqOP-u1kLvct9jQQCeUXzlEjdgitwi1Lm8,75
 spacr/app_annotate.py,sha256=nEIL7Fle9CDKGo3sucG_03DgjUQt5W1M1IHBIpVBr08,2171
 spacr/app_classify.py,sha256=urTP_wlZ58hSyM5a19slYlBxN0PdC-9-ga0hvq8CGWc,165
@@ -7,27 +7,28 @@ spacr/app_mask.py,sha256=l-dBY8ftzCMdDe6-pXc2Nh_u-idNL9G7UOARiLJBtds,153
 spacr/app_measure.py,sha256=_K7APYIeOKpV6e_LcqabBjvEi7mfq9Fch8175x1x0k8,162
 spacr/app_sequencing.py,sha256=DjG26jy4cpddnV8WOOAIiExtOe9MleVMY4MFa5uTo5w,157
 spacr/app_umap.py,sha256=ZWAmf_OsIKbYvolYuWPMYhdlVe-n2CADoJulAizMiEo,153
-spacr/chris.py,sha256=YlBjSgeZaY8HPy6jkrT_ISAnCMAKVfvCxF0I9eAZLFM,2418
-spacr/core.py,sha256=uyZdJ93ysd8oXgRX9b-6iTCldJ0CM1dq5VxF-xbZyN8,150703
-spacr/deep_spacr.py,sha256=a2YewgkQvLV-95NYJAutnojvJmX4S8z_wv6Tb-XIgUI,34484
-spacr/graph_learning.py,sha256=1tR-ZxvXE3dBz1Saw7BeVFcrsUFu9OlUZeZVifih9eo,13070
-spacr/gui.py,sha256=zUkIyAuOwwoMDoExxtI-QHRfOhE1R2rulXJDNxwSLGc,7947
-spacr/gui_core.py,sha256=ZUIqvK7x6NzgrmuTRbvwCTTSpU3yWUaId6MZjXv16us,40128
-spacr/gui_elements.py,sha256=OA514FUVRKAcdu9CFVOt7UEzn1vztakQ-rDyKqV0b9A,129771
-spacr/gui_utils.py,sha256=DCI--DNoYDWY1q0Aohd0XwFqjdPM3K5kCgRKiJGTnfc,30697
-spacr/io.py,sha256=VjH_1zXmf0yEdtABnsoabCEIpU0S3wB-7Hog7_ntCdE,117267
-spacr/logger.py,sha256=7Zqr3TuuOQLWT32gYr2q1qvv7x0a2JhLANmZcnBXAW8,670
-spacr/measure.py,sha256=ooMOP2OE0BHUNqIkg0ltwV2FiO6hZDIcRC6A0YmGcws,54875
-spacr/mediar.py,sha256=5HaCyZYiOff74PCvHwKj-jSRua0QRoIv1mvElPfVKtY,14830
-spacr/plot.py,sha256=yFC5m54lB8xVnC7vQp50-FvRn6lCjCt2mgi2GeiRwSs,73979
-spacr/sequencing.py,sha256=92KmjFa8Ptwmpf-GtyH3-uX6djFOYR5lJjMBHeciqhs,66921
-spacr/settings.py,sha256=PfIPLyMyBAfOodtdgNT8QzbysNDxTnsONXdI-fKtIDQ,68038
-spacr/sim.py,sha256=FveaVgBi3eypO2oVB5Dx-v0CC1Ny7UPfXkJiiRRodAk,71212
-spacr/sim_app.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-spacr/timelapse.py,sha256=KMYCgHzf9LTZe-lWl5mvH2EjbKRE6OhpwdY13wEumGc,39504
-spacr/utils.py,sha256=JGjL_Tg5ec1qmaf9BV3gqlREUpxjK8hutgPEGj5mAEs,189141
+spacr/cellpose.py,sha256=zv4BzhaP2O-mtQ-pUfYvpOyxgn1ke_bDWgdHD5UWm9I,13942
+spacr/core.py,sha256=KNsjpQR_L5mAABrJ4U_JMNsUMav81ILvnjL0Jf2ohU8,43858
+spacr/deep_spacr.py,sha256=HT7x_xHoM8s-AX6aSEHv4mf4wMld9PNDTgzsX-0FqO4,39416
+spacr/gui.py,sha256=ndmWP4F0QO5j6DM6MNzoGtzv_7Yj4LTW2SLi9URBZIQ,8055
+spacr/gui_core.py,sha256=OJQxzpehIyDzjSjIsvxSHat4NIjkqjX0VZAUQTnzEzg,40921
+spacr/gui_elements.py,sha256=3ru8FPZtXCZSj7167GJj18-Zo6TVebhAzkit-mmqmTI,135342
+spacr/gui_utils.py,sha256=76utRICvY0k_6X8CA1P_TmYBJARp4b87OkI9t39tldA,45822
+spacr/io.py,sha256=_P0Rb1ftBlheb9Yd0Bm8py_MeV2bh0ZxDlVRYOZAfBY,144579
+spacr/logger.py,sha256=lJhTqt-_wfAunCPl93xE65Wr9Y1oIHJWaZMjunHUeIw,1538
+spacr/measure.py,sha256=8MRjQdB-2n8JVLjEpF3cxvfT-Udug27uJ2ErJJ5t1ic,56000
+spacr/mediar.py,sha256=FwLvbLQW5LQzPgvJZG8Lw7GniA2vbZx6Jv6vIKu7I5c,14743
+spacr/ml.py,sha256=uf43GIxxgSasq9OiWQYnQO0fV3d5yTPEHkV78jHb-i4,42540
+spacr/openai.py,sha256=5vBZ3Jl2llYcW3oaTEXgdyCB2aJujMUIO5K038z7w_A,1246
+spacr/plot.py,sha256=kPVUlMaRSH2zZIm64o8FmhHILMCRRmzs-uFVPQEIupw,85281
+spacr/sequencing.py,sha256=t18mgpK6rhWuB1LtFOsPxqgpFXxuUmrD06ecsaVQ0Gw,19655
+spacr/settings.py,sha256=IaRnHXRVrkOOfA0ymavXOJTjPE56_BdOPrbEHq7oONQ,73508
+spacr/sim.py,sha256=1xKhXimNU3ukzIw-3l9cF3Znc_brW8h20yv8fSTzvss,71173
+spacr/submodules.py,sha256=ojBFEnOZ_YTGcOvSFEAPP6J7-w08QIAFJLEPYjUCkMM,18337
+spacr/timelapse.py,sha256=FSYpUtAVy6xc3lwprRYgyDTT9ysUhfRQ4zrP9_h2mvg,39465
+spacr/toxo.py,sha256=nkV8w1wvaEsDFoSIOVvU5UcIIaTngHfgKNhhZYzBDyY,9893
+spacr/utils.py,sha256=nW4s7wy4spk3T3yYTQGLvonDz5KX6t_d0NKiHcqMPN0,193044
 spacr/version.py,sha256=axH5tnGwtgSnJHb5IDhiu4Zjk5GhLyAEDRe-rnaoFOA,409
-spacr/resources/MEDIAR/.git,sha256=nHbNNUgehWnXyS2LbJZitX4kbpd1urzYgE0WZYvdMfc,53
 spacr/resources/MEDIAR/.gitignore,sha256=Ff1q9Nme14JUd-4Q3jZ65aeQ5X4uttptssVDgBVHYo8,152
 spacr/resources/MEDIAR/LICENSE,sha256=yEj_TRDLUfDpHDNM0StALXIt6mLqSgaV2hcCwa6_TcY,1065
 spacr/resources/MEDIAR/README.md,sha256=TlL2XhmmNhYTtaBlMCnlJRW-K7qOVeqH1ABLabZAe2k,11877
@@ -79,7 +80,8 @@ spacr/resources/MEDIAR/train_tools/data_utils/custom/__init__.py,sha256=SalCNvPy
 spacr/resources/MEDIAR/train_tools/data_utils/custom/modalities.pkl,sha256=C1D7NkUZ5er7Kdeyhhwjo0IGUvCsVfKPBzcwfaORd8Q,3762
 spacr/resources/MEDIAR/train_tools/models/MEDIARFormer.py,sha256=UN8BYjraTNNdZUAGjl3yF566ERHAHQvj3GAQ6OETUOI,3615
 spacr/resources/MEDIAR/train_tools/models/__init__.py,sha256=CkY6rZxr-c9XxXNpQbYUYvHXDpf9E6rUmY1bQ47aEP8,28
-spacr/resources/MEDIAR_weights/.DS_Store,sha256=1lFlJ5EFymdzGAUAaI30vcaaLHt3F1LwpG7xILf9jsM,6148
+spacr/resources/data/lopit.csv,sha256=ERI5f9W8RdJGiSx_khoaylD374f8kmvLia1xjhD_mII,4421709
+spacr/resources/data/toxoplasma_metadata.csv,sha256=9TXx0VlClDHAxQmaLhoklE8NuETduXaGHZjhR_6lZfs,2969409
 spacr/resources/font/open_sans/OFL.txt,sha256=bGMoWBRrE2RcdzDiuYiB8A9OVFlJ0sA2imWwce2DAdo,4484
 "spacr/resources/font/open_sans/OpenSans-Italic-VariableFont_wdth,wght.ttf",sha256=QSoWv9h46CRX_fdlqFM3O2d3-PF3R1srnb4zUezcLm0,580280
 "spacr/resources/font/open_sans/OpenSans-VariableFont_wdth,wght.ttf",sha256=E3RLvAefD0kuT7OxShXSQrjZYA-qzUI9WM35N_6nzms,529700
@@ -120,13 +122,14 @@ spacr/resources/font/open_sans/static/OpenSans_SemiCondensed-MediumItalic.ttf,sh
 spacr/resources/font/open_sans/static/OpenSans_SemiCondensed-Regular.ttf,sha256=skg4DCl15zL9ZD4MAL9fOt4WjonKYBUOMj46ItSAe5Q,130848
 spacr/resources/font/open_sans/static/OpenSans_SemiCondensed-SemiBold.ttf,sha256=uCiR97jg6sUHtGKVPNtJEg1zZG5Y9ArQ-raqBGjaeGg,130856
 spacr/resources/font/open_sans/static/OpenSans_SemiCondensed-SemiBoldItalic.ttf,sha256=a5-0oOIrtJltQRa64uFKCdtcjzPvEJ71f_cYavG2i3E,137132
-spacr/resources/icons/.DS_Store,sha256=1lFlJ5EFymdzGAUAaI30vcaaLHt3F1LwpG7xILf9jsM,6148
 spacr/resources/icons/abort.png,sha256=avtIRT7aCJsdZ1WnY_rZStm6cCji5bYPLnlptdcTNcM,6583
 spacr/resources/icons/annotate.png,sha256=GFgh7DiUMwPG_-xE6W1qU8V_qzSwBi1xKenfoaQxeFA,15495
 spacr/resources/icons/cellpose_all.png,sha256=HVWOIOBF8p3-On-2UahwMyQXp7awsoC5yWExU1ahDag,20271
 spacr/resources/icons/cellpose_masks.png,sha256=HVWOIOBF8p3-On-2UahwMyQXp7awsoC5yWExU1ahDag,20271
 spacr/resources/icons/classify.png,sha256=-iv4sqAwUVJO3CG6fHKHf3_BB0s-I2i4prg-iR7dSBM,35897
+spacr/resources/icons/convert.png,sha256=vLyTkQeUZ9q-pirhtZeXDq3-DzfjoPMjLlgKl5Wv6R0,7069
 spacr/resources/icons/default.png,sha256=KoNhaSHukO4wDyivyYEgSbb5mGj-sAxmhKikLLtNpWs,20341
+spacr/resources/icons/dna_matrix.mp4,sha256=NegOQkn4q4kHhFgqcIX2dd58wVytBtnkmbgg0ZegL8U,23462876
 spacr/resources/icons/download.png,sha256=1nUoWRaTc4vIsK6gompdeqk0cIv2GdH-gCNHaEBX6Mc,20467
 spacr/resources/icons/logo.pdf,sha256=VB4cS41V3VV_QxD7l6CwdQKQiYLErugLBxWoCoxjQU0,377925
 spacr/resources/icons/logo_spacr.png,sha256=qG3e3bdrAefhl1281rfo0R2XP0qA-c-oaBCXjxMGXkw,42587
@@ -142,18 +145,14 @@ spacr/resources/icons/regression.png,sha256=WIrKY4fSojBOCDkHno4Qb-KH7jcHh6G67dOK
 spacr/resources/icons/run.png,sha256=ICzyAvsRBCXNAbdn5N3PxCxxVyqxkfC4zOI5Zc8vbxQ,8974
 spacr/resources/icons/sequencing.png,sha256=P9E_Y76ZysWMKst3_hAw-_4F510XPW1l1TsDElVzt4o,17775
 spacr/resources/icons/settings.png,sha256=y5Ow5BxJDDsrqom0VNbOMDGGUs6odxbSMDy6y4r_F0w,22269
-spacr/resources/icons/spacr_logo_rotation.gif,sha256=bgIx1Hx41Ob90SY-q3PBa3CSxtVRnF9XX-ApUSr0wvY,1502560
 spacr/resources/icons/train_cellpose.png,sha256=_PZ_R_B6azuUACmscScAkugmgLZvCPKQFGIAsszqNLk,3858
 spacr/resources/icons/umap.png,sha256=dOLF3DeLYy9k0nkUybiZMe1wzHQwLJFRmgccppw-8bI,27457
 spacr/resources/images/plate1_E01_T0001F001L01A01Z01C02.tif,sha256=Tl0ZUfZ_AYAbu0up_nO0tPRtF1BxXhWQ3T3pURBCCRo,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A02Z01C01.tif,sha256=m8N-V71rA1TT4dFlENNg8s0Q0YEXXs8slIn7yObmZJQ,7958528
 spacr/resources/images/plate1_E01_T0001F001L01A03Z01C03.tif,sha256=Pbhk7xn-KUP6RSIhJsxQcrHFImBm3GEpLkzx7WOc-5M,7958528
-spacr/resources/models/cp/toxo_plaque_cyto_e25000_X1120_Y1120.CP_model,sha256=z8BbHWZPRnE9D_BHO0fBREE85c1vkltDs-incs2ytXQ,26566572
-spacr/resources/models/cp/toxo_plaque_cyto_e25000_X1120_Y1120.CP_model_settings.csv,sha256=fBAGuL_B8ERVdVizO3BHozTDSbZUh1yFzsYK3wkQN68,420
-spacr/resources/models/cp/toxo_pv_lumen.CP_model,sha256=2y_CindYhmTvVwBH39SNILF3rI3x9SsRn6qrMxHy3l0,26562451
-spacr-0.3.1.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
-spacr-0.3.1.dist-info/METADATA,sha256=Fi3B8Vxgz4IzfYodV9zMgRdFLXTtVtel4OCdE06o5cI,5646
-spacr-0.3.1.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-spacr-0.3.1.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
-spacr-0.3.1.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
-spacr-0.3.1.dist-info/RECORD,,
+spacr-0.3.2.dist-info/LICENSE,sha256=SR-2MeGc6SCM1UORJYyarSWY_A-JaOMFDj7ReSs9tRM,1083
+spacr-0.3.2.dist-info/METADATA,sha256=T4leZtOLZyUy19ueD2g_TmAQdTRCbkS29QJXcVf6ciw,5837
+spacr-0.3.2.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+spacr-0.3.2.dist-info/entry_points.txt,sha256=BMC0ql9aNNpv8lUZ8sgDLQMsqaVnX5L535gEhKUP5ho,296
+spacr-0.3.2.dist-info/top_level.txt,sha256=GJPU8FgwRXGzKeut6JopsSRY2R8T3i9lDgya42tLInY,6
+spacr-0.3.2.dist-info/RECORD,,

spacr/chris.py

@@ -1,50 +0,0 @@
-import pandas as pd 
-import numpy as np
-from .core import _permutation_importance, _shap_analysis
-
-def join_measurments_and_annotation(src, tables = ['cell', 'nucleus', 'pathogen','cytoplasm']):
-    
-    from .io import _read_and_merge_data, _read_db
-    
-    db_loc = [src+'/measurements/measurements.db']
-    loc = src+'/measurements/measurements.db'
-    df, _ = _read_and_merge_data(db_loc, 
-                                 tables, 
-                                 verbose=True, 
-                                 include_multinucleated=True, 
-                                 include_multiinfected=True, 
-                                 include_noninfected=True)
-    
-    paths_df = _read_db(loc, tables=['png_list'])
-
-    merged_df = pd.merge(df, paths_df[0], on='prcfo', how='left')
-
-    return merged_df
-
-def plate_heatmap(src, model_type='xgboost', variable='predictions', grouping='mean', min_max='allq', cmap='viridis', channel_of_interest=3, min_count=25, n_estimators=100, col_to_compare='col', pos='c1', neg='c2', exclude=None, n_repeats=10, clean=True, nr_to_plot=20, verbose=False, n_jobs=-1):
-    from .io import _read_and_merge_data
-    from .plot import _plot_plates
-
-    db_loc = [src+'/measurements/measurements.db']
-    tables = ['cell', 'nucleus', 'pathogen','cytoplasm']
-    include_multinucleated, include_multiinfected, include_noninfected = True, 2.0, True
-    
-    df = join_measurments_and_annotation(src, tables=['cell', 'nucleus', 'pathogen', 'cytoplasm'])
-        
-    if not channel_of_interest is None:
-        df['recruitment'] = df[f'pathogen_channel_{channel_of_interest}_mean_intensity']/df[f'cytoplasm_channel_{channel_of_interest}_mean_intensity']
-        feature_string = f'channel_{channel_of_interest}'
-    else:
-        feature_string = None
-    
-    output = _permutation_importance(df, feature_string, col_to_compare, pos, neg, exclude, n_repeats, clean, nr_to_plot, n_estimators=n_estimators, random_state=42, model_type=model_type, n_jobs=n_jobs)
-    
-    _shap_analysis(output[3], output[4], output[5])
-
-    features = output[0].select_dtypes(include=[np.number]).columns.tolist()
-
-    if not variable in features:
-        raise ValueError(f"Variable {variable} not found in the dataframe. Please choose one of the following: {features}")
-    
-    plate_heatmap = _plot_plates(output[0], variable, grouping, min_max, cmap, min_count)
-    return [output, plate_heatmap]

spacr/graph_learning.py

@@ -1,340 +0,0 @@
-import os
-os.environ['DGLBACKEND'] = 'pytorch'
-import torch, dgl
-import pandas as pd
-import torch.nn as nn
-from torchvision import datasets, transforms
-from sklearn.preprocessing import StandardScaler
-from PIL import Image
-import dgl.nn.pytorch as dglnn
-from sklearn.datasets import make_classification
-from .utils import SelectChannels
-from IPython.display import display
-
-# approach outline
-#
-#    1. Data Preparation:
-#        Test Mode: Load MNIST data and generate synthetic gRNA data.
-#        Real Data: Load image paths and sequencing data as fractions.
-#
-#    2. Graph Construction:
-#        Each well is represented as a graph.
-#        Each graph has cell nodes (with image features) and gRNA nodes (with gRNA fraction features).
-#        Each cell node is connected to each gRNA node within the same well.
-#
-#    3. Model Training:
-#        Use an encoder-decoder architecture with the Graph Transformer model.
-#        The encoder processes the cell and gRNA nodes.
-#        The decoder outputs the phenotype score for each cell node.
-#        The model is trained on all wells (including positive and negative controls).
-#        The model learns to score the gRNA in column 1 (negative control) as 0 and the gRNA in column 2 (positive control) as 1 based on the cell features.
-#
-#    4. Model Application:
-#        Apply the trained model to all wells to get classification probabilities.
-#
-#    5. Evaluation:
-#        Evaluate the model's performance using the control wells.
-#
-#    6. Association Analysis:
-#        Analyze the association between gRNAs and the classification scores.
-#
-# The model learns the associations between cell features and phenotype scores based on the controls and then generalizes this learning to the screening wells.
-
-# Load MNIST data for testing
-def load_mnist_data():
-    transform = transforms.Compose([
-        transforms.Resize((28, 28)),
-        transforms.ToTensor(),
-        transforms.Normalize((0.1307,), (0.3081,))
-    ])
-    mnist_train = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
-    mnist_test = datasets.MNIST(root='./data', train=False, download=True, transform=transform)
-    return mnist_train, mnist_test
-
-# Generate synthetic gRNA data
-def generate_synthetic_grna_data(n_samples, n_features):
-    X, y = make_classification(n_samples=n_samples, n_features=n_features, n_informative=5, n_redundant=0, n_classes=2, random_state=42)
-    synthetic_data = pd.DataFrame(X, columns=[f'feature_{i}' for i in range(n_features)])
-    synthetic_data['label'] = y
-    return synthetic_data
-
-# Preprocess image
-def preprocess_image(image_path, image_size=224, channels=[1,2,3], normalize=True):
-
-    if normalize:
-        preprocess = transforms.Compose([
-            transforms.ToTensor(),
-            transforms.CenterCrop(size=(image_size, image_size)),
-            SelectChannels(channels),
-            transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
-    else:
-        preprocess = transforms.Compose([
-            transforms.ToTensor(),
-            transforms.CenterCrop(size=(image_size, image_size)),
-            SelectChannels(channels)])
-    
-    image = Image.open(image_path).convert('RGB')
-    return preprocess(image)
-
-def extract_metadata_from_path(path):
-    """
-    Extract metadata from the image path.
-    The path format is expected to be plate_well_field_objectnumber.png
-
-    Parameters:
-    path (str): The path to the image file.
-
-    Returns:
-    dict: A dictionary with the extracted metadata.
-    """
-    filename = os.path.basename(path)
-    name, ext = os.path.splitext(filename)
-
-    # Ensure the file has the correct extension
-    if ext.lower() != '.png':
-        raise ValueError("Expected a .png file")
-
-    # Split the name by underscores
-    parts = name.split('_')
-    if len(parts) != 4:
-        raise ValueError("Expected filename format: plate_well_field_objectnumber.png")
-
-    plate, well, field, object_number = parts
-
-    return {'plate': plate, 'well': well,'field': field, 'object_number': object_number}
-
-# Load images
-def load_images(image_paths, image_size=224, channels=[1,2,3], normalize=True):
-    images = []
-    metadata_list = []
-    for path in image_paths:
-        image = preprocess_image(path, image_size, channels, normalize)
-        images.append(image)
-        metadata = extract_metadata_from_path(path)  # Extract metadata from image path or database
-        metadata_list.append(metadata)
-    return torch.stack(images), metadata_list
-
-# Normalize sequencing data
-def normalize_sequencing_data(sequencing_data):
-    scaler = StandardScaler()
-    sequencing_data.iloc[:, 2:] = scaler.fit_transform(sequencing_data.iloc[:, 2:])
-    return sequencing_data
-
-# Construct graph for each well
-def construct_well_graph(images, image_metadata, grna_data):
-    cell_nodes = len(images)
-    grna_nodes = grna_data.shape[0]
-    
-    graph = dgl.DGLGraph()
-    graph.add_nodes(cell_nodes + grna_nodes)
-
-    cell_features = torch.stack(images)
-    grna_features = torch.tensor(grna_data).float()
-
-    features = torch.cat([cell_features, grna_features], dim=0)
-    graph.ndata['features'] = features
-
-    for i in range(cell_nodes):
-        for j in range(cell_nodes, cell_nodes + grna_nodes):
-            graph.add_edge(i, j)
-            graph.add_edge(j, i)
-    
-    return graph
-
-def create_graphs_for_wells(images, metadata_list, sequencing_data):
-    graphs = []
-    labels = []
-
-    for well in sequencing_data['well'].unique():
-        well_images = [img for img, meta in zip(images, metadata_list) if meta['well'] == well]
-        well_metadata = [meta for meta in metadata_list if meta['well'] == well]
-        well_grna_data = sequencing_data[sequencing_data['well'] == well].iloc[:, 2:].values
-
-        graph = construct_well_graph(well_images, well_metadata, well_grna_data)
-        graphs.append(graph)
-
-        if well_metadata[0]['column'] == 1:  # Negative control
-            labels.append(0)
-        elif well_metadata[0]['column'] == 2:  # Positive control
-            labels.append(1)
-        else:
-            labels.append(-1)  # Screen wells, will be used for evaluation
-
-    return graphs, labels
-
-# Define Encoder-Decoder Transformer Model
-class Encoder(nn.Module):
-    def __init__(self, in_feats, hidden_feats):
-        super(Encoder, self).__init__()
-        self.conv1 = dglnn.GraphConv(in_feats, hidden_feats)
-        self.conv2 = dglnn.GraphConv(hidden_feats, hidden_feats)
-
-    def forward(self, g, features):
-        x = self.conv1(g, features)
-        x = torch.relu(x)
-        x = self.conv2(g, x)
-        x = torch.relu(x)
-        return x
-
-class Decoder(nn.Module):
-    def __init__(self, hidden_feats, out_feats):
-        super(Decoder, self).__init__()
-        self.linear = nn.Linear(hidden_feats, out_feats)
-
-    def forward(self, x):
-        return self.linear(x)
-
-class GraphTransformer(nn.Module):
-    def __init__(self, in_feats, hidden_feats, out_feats):
-        super(GraphTransformer, self).__init__()
-        self.encoder = Encoder(in_feats, hidden_feats)
-        self.decoder = Decoder(hidden_feats, out_feats)
-
-    def forward(self, g, features):
-        x = self.encoder(g, features)
-        with g.local_scope():
-            g.ndata['h'] = x
-            hg = dgl.mean_nodes(g, 'h')
-        return self.decoder(hg)
-
-def train(graphs, labels, model, loss_fn, optimizer, epochs=100):
-    for epoch in range(epochs):
-        model.train()
-        total_loss = 0
-        correct = 0
-        total = 0
-        
-        for graph, label in zip(graphs, labels):
-            if label == -1:
-                continue  # Skip screen wells for training
-            
-            features = graph.ndata['features']
-            logits = model(graph, features)
-            loss = loss_fn(logits, torch.tensor([label]))
-
-            optimizer.zero_grad()
-            loss.backward()
-            optimizer.step()
-            
-            total_loss += loss.item()
-            _, predicted = torch.max(logits, 1)
-            correct += (predicted == label).sum().item()
-            total += 1
-        
-        accuracy = correct / total if total > 0 else 0
-        print(f'Epoch {epoch}, Loss: {total_loss / total:.4f}, Accuracy: {accuracy * 100:.2f}%')
-
-def apply_model(graphs, model):
-    model.eval()
-    results = []
-
-    with torch.no_grad():
-        for graph in graphs:
-            features = graph.ndata['features']
-            logits = model(graph, features)
-            probabilities = torch.softmax(logits, dim=1)
-            results.append(probabilities[:, 1].item())
-    
-    return results
-
-def analyze_associations(probabilities, sequencing_data):
-    # Analyze associations between gRNAs and classification scores
-    sequencing_data['positive_prob'] = probabilities
-    return sequencing_data.groupby('gRNA').positive_prob.mean().sort_values(ascending=False)
-
-def process_sequencing_df(seq):
-
-    if isinstance(seq, pd.DataFrame):
-        sequencing_df = seq
-    elif isinstance(seq, str):
-        sequencing_df = pd.read_csv(seq)
-
-    # Check if 'plate_row' column exists and split into 'plate' and 'row'
-    if 'plate_row' in sequencing_df.columns:
-        sequencing_df[['plate', 'row']] = sequencing_df['plate_row'].str.split('_', expand=True)
-
-    # Check if 'plate', 'row' and 'col' or 'plate', 'row' and 'column' exist
-    if {'plate', 'row', 'col'}.issubset(sequencing_df.columns) or {'plate', 'row', 'column'}.issubset(sequencing_df.columns):
-        if 'col' in sequencing_df.columns:
-            sequencing_df['prc'] = sequencing_df[['plate', 'row', 'col']].agg('_'.join, axis=1)
-        elif 'column' in sequencing_df.columns:
-            sequencing_df['prc'] = sequencing_df[['plate', 'row', 'column']].agg('_'.join, axis=1)
-
-    # Check if 'count', 'total_reads', 'read_fraction', 'grna' exist and create new dataframe
-    if {'count', 'total_reads', 'read_fraction', 'grna'}.issubset(sequencing_df.columns):
-        new_df = sequencing_df[['grna', 'prc', 'count', 'total_reads', 'read_fraction']]
-        return new_df
-    
-    return sequencing_df
-
-def train_graph_transformer(src, lr=0.01, epochs=100, hidden_feats=128, n_classes=2, row_limit=None, image_size=224, channels=[1,2,3], normalize=True, test_mode=False):
-    if test_mode:
-        # Load MNIST data
-        mnist_train, mnist_test = load_mnist_data()
-        
-        # Generate synthetic gRNA data
-        synthetic_grna_data = generate_synthetic_grna_data(len(mnist_train), 10)  # 10 synthetic features
-        sequencing_data = synthetic_grna_data
-        
-        # Load MNIST images and metadata
-        images = [] 
-        metadata_list = []
-        for idx, (img, label) in enumerate(mnist_train):
-            images.append(img)
-            metadata_list.append({'index': idx, 'plate': 'plate1', 'well': idx, 'column': label})
-        images = torch.stack(images)
-
-        # Normalize synthetic sequencing data
-        sequencing_data = normalize_sequencing_data(sequencing_data)
-    else:
-        from .io import _read_and_join_tables
-        from .utils import get_db_paths, get_sequencing_paths, correct_paths
-
-        db_paths = get_db_paths(src)
-        seq_paths = get_sequencing_paths(src)
-
-        if isinstance(src, str):
-            src = [src]
-
-        sequencing_data = pd.DataFrame()
-        for seq in seq_paths:
-            sequencing_df = pd.read_csv(seq)
-            sequencing_df = process_sequencing_df(sequencing_df)
-            sequencing_data = pd.concat([sequencing_data, sequencing_df], axis=0)
-
-        all_df = pd.DataFrame()
-        image_paths = []
-        for i, db_path in enumerate(db_paths):
-            df = _read_and_join_tables(db_path, table_names=['png_list'])
-            df, image_paths_tmp = correct_paths(df, src[i])
-            all_df = pd.concat([all_df, df], axis=0)
-            image_paths.extend(image_paths_tmp)
-
-        if row_limit is not None:
-            all_df = all_df.sample(n=row_limit, random_state=42)
-
-        images, metadata_list = load_images(image_paths, image_size, channels, normalize)
-        sequencing_data = normalize_sequencing_data(sequencing_data)
-
-    # Step 1: Create graphs for each well
-    graphs, labels = create_graphs_for_wells(images, metadata_list, sequencing_data)
-
-    # Step 2: Train Graph Transformer Model
-    in_feats = graphs[0].ndata['features'].shape[1]
-    model = GraphTransformer(in_feats, hidden_feats, n_classes)
-    loss_fn = nn.CrossEntropyLoss()
-    optimizer = torch.optim.Adam(model.parameters(), lr=lr)
-
-    # Train the model
-    train(graphs, labels, model, loss_fn, optimizer, epochs)
-
-    # Step 3: Apply the model to all wells (including screen wells)
-    screen_graphs = [graph for graph, label in zip(graphs, labels) if label == -1]
-    probabilities = apply_model(screen_graphs, model)
-
-    # Step 4: Analyze associations between gRNAs and classification scores
-    associations = analyze_associations(probabilities, sequencing_data)
-    print("Top associated gRNAs with positive control phenotype:")
-    print(associations.head())
-
-    return model, associations

spacr/resources/MEDIAR/.git

@@ -1 +0,0 @@
-gitdir: ../../../.git/modules/spacr/resources/MEDIAR

spacr/resources/models/cp/toxo_plaque_cyto_e25000_X1120_Y1120.CP_model_settings.csv

@@ -1,23 +0,0 @@
-Key,Value
-img_src,/nas_mnt/carruthers/patrick/Plaque_assay_training/train
-model_name,toxo_plaque
-model_type,cyto
-Signal_to_noise,10
-background,200
-remove_background,False
-learning_rate,0.2
-weight_decay,1e-05
-batch_size,8
-n_epochs,25000
-from_scratch,False
-diameter,30
-resize,True
-width_height,"[1120, 1120]"
-verbose,True
-channels,"[0, 0]"
-normalize,True
-percentiles,
-circular,False
-invert,False
-grayscale,True
-test,False