gsMap 1.62__py3-none-any.whl → 1.64__py3-none-any.whl

gsMap/{regression_read.py → utils/regression_read.py}

@@ -60,7 +60,7 @@ def read_csv(fh, **kwargs):
     '''
     Read the csv data
     '''
-    return pd.read_csv(fh, delim_whitespace=True, na_values='.', **kwargs)
+    return pd.read_csv(fh, sep='\s+', na_values='.', **kwargs)
 
 
 # Fun for reading loading LD scores 

gsMap/visualize.py

@@ -1,12 +1,13 @@
-import argparse
 from pathlib import Path
 from typing import Literal
 
-import scanpy as sc
 import numpy as np
 import pandas as pd
 import plotly.express as px
-from gsMap.config import VisualizeConfig, add_Visualization_args
+import scanpy as sc
+from scipy.spatial import KDTree
+
+from gsMap.config import VisualizeConfig
 
 
 def load_ldsc(ldsc_input_file):
@@ -18,11 +19,19 @@ def load_ldsc(ldsc_input_file):
 
 
 # %%
-def load_st_coord(adata, ldsc, annotation):
+def load_st_coord(adata, feature_series: pd.Series, annotation):
     spot_name = adata.obs_names.to_list()
-    space_coord = pd.DataFrame(adata.obsm['spatial'], columns=['sx', 'sy'], index=spot_name)
-    space_coord = space_coord[space_coord.index.isin(ldsc.spot)]
-    space_coord_concat = pd.concat([space_coord.loc[ldsc.spot], ldsc.logp], axis=1)
+    assert 'spatial' in adata.obsm.keys(), 'spatial coordinates are not found in adata.obsm'
+
+    # to DataFrame
+    space_coord = adata.obsm['spatial']
+    if isinstance(space_coord, np.ndarray):
+        space_coord = pd.DataFrame(space_coord, columns=['sx', 'sy'], index=spot_name)
+    else:
+        space_coord = pd.DataFrame(space_coord.values, columns=['sx', 'sy'], index=spot_name)
+
+    space_coord = space_coord[space_coord.index.isin(feature_series.index)]
+    space_coord_concat = pd.concat([space_coord.loc[feature_series.index], feature_series], axis=1)
     space_coord_concat.head()
     if annotation is not None:
         annotation = pd.Series(adata.obs[annotation].values, index=adata.obs_names, name='annotation')
@@ -30,10 +39,25 @@ def load_st_coord(adata, ldsc, annotation):
     return space_coord_concat
 
 
-# %%
+def estimate_point_size_for_plot(coordinates, DEFAULT_PIXEL_WIDTH = 1000):
+    tree = KDTree(coordinates)
+    distances, _ = tree.query(coordinates, k=2)
+    avg_min_distance = np.mean(distances[:, 1])
+    # get the width and height of the plot
+    width = np.max(coordinates[:, 0]) - np.min(coordinates[:, 0])
+    height = np.max(coordinates[:, 1]) - np.min(coordinates[:, 1])
+
+    scale_factor = DEFAULT_PIXEL_WIDTH / max(width, height)
+    pixel_width = width * scale_factor
+    pixel_height = height * scale_factor
+
+    point_size = np.ceil(avg_min_distance * scale_factor)
+    return (pixel_width, pixel_height), point_size
+
+
 def draw_scatter(space_coord_concat, title=None, fig_style: Literal['dark', 'light'] = 'light',
-                 point_size: int = None, width=800, height=600, annotation=None):
-    # change theme to plotly_white
+                 point_size: int = None, width=800, height=600, annotation=None, color_by='logp'):
+    # Set theme based on fig_style
     if fig_style == 'dark':
         px.defaults.template = "plotly_dark"
     else:
@@ -50,24 +74,25 @@ def draw_scatter(space_coord_concat, title=None, fig_style: Literal['dark', 'lig
         (1 / 8, '#4575b4'),  # Dark Blue
         (0, '#313695')  # Deep Blue
     ]
-    # custom_color_scale = px.colors.diverging.balance
     custom_color_scale.reverse()
+
+    # Create the scatter plot
     fig = px.scatter(
         space_coord_concat,
         x='sx',
         y='sy',
-        color='logp',  # Color the points by the 'logp' column
+        color=color_by,
         symbol='annotation' if annotation is not None else None,
         title=title,
         color_continuous_scale=custom_color_scale,
-        range_color=[0, max(space_coord_concat.logp)],
+        range_color=[0, max(space_coord_concat[color_by])],
     )
 
+    # Update marker size if specified
     if point_size is not None:
-        fig.update_traces(marker=dict(size=point_size))
-
-    fig.update_layout(legend_title_text='Annotation')
+        fig.update_traces(marker=dict(size=point_size, symbol='circle'))
 
+    # Update layout for figure size
     fig.update_layout(
         autosize=False,
         width=width,
@@ -78,26 +103,74 @@ def draw_scatter(space_coord_concat, title=None, fig_style: Literal['dark', 'lig
     fig.update_layout(
         legend=dict(
             yanchor="top",
-            y=0.99,
+            y=0.95,
             xanchor="left",
-            x=-0.39,
+            x=1.0,
             font=dict(
                 size=10,
             )
         )
     )
-    # change color bar title
-    fig.update_layout(coloraxis_colorbar_title='-log10(p)')
+
+    # Update colorbar to be at the bottom and horizontal
+    fig.update_layout(
+        coloraxis_colorbar=dict(
+            orientation='h',  # Make the colorbar horizontal
+            x=0.5,  # Center the colorbar horizontally
+            y=-0.0,  # Position below the plot
+            xanchor='center',  # Anchor the colorbar at the center
+            yanchor='top',  # Anchor the colorbar at the top to keep it just below the plot
+            len=0.75,  # Length of the colorbar relative to the plot width
+            title=dict(
+                text='-log10(p)' if color_by == 'logp' else color_by,  # Colorbar title
+                side='top'  # Place the title at the top of the colorbar
+            )
+        )
+    )
+    # Remove gridlines, axis labels, and ticks
+    fig.update_xaxes(
+        showgrid=False,   # Hide x-axis gridlines
+        zeroline=False,   # Hide x-axis zero line
+        showticklabels=False,  # Hide x-axis tick labels
+        title=None,       # Remove x-axis title
+        scaleanchor='y',  # Link the x-axis scale to the y-axis scale
+    )
+
+    fig.update_yaxes(
+        showgrid=False,   # Hide y-axis gridlines
+        zeroline=False,   # Hide y-axis zero line
+        showticklabels=False,  # Hide y-axis tick labels
+        title=None        # Remove y-axis title
+    )
+
+    # Adjust margins to ensure no clipping and equal axis ratio
+    fig.update_layout(
+        margin=dict(l=0, r=0, t=20, b=10),  # Adjust margins to prevent clipping
+        height=width  # Ensure the figure height matches the width for equal axis ratio
+    )
+
+    # Adjust the title location and font size
+    fig.update_layout(
+        title=dict(
+            y=0.98,
+            x=0.5,  # Center the title horizontally
+            xanchor='center',  # Anchor the title at the center
+            yanchor='top',  # Anchor the title at the top
+            font=dict(
+                size=20  # Increase the title font size
+            )
+        ))
 
     return fig
 
 
+
 def run_Visualize(config: VisualizeConfig):
-    print(f'------Loading LDSC results of {config.input_ldsc_dir}...')
-    ldsc = load_ldsc(ldsc_input_file=Path(config.input_ldsc_dir) / f'{config.sample_name}_{config.trait_name}.csv.gz')
+    print(f'------Loading LDSC results of {config.ldsc_save_dir}...')
+    ldsc = load_ldsc(ldsc_input_file=Path(config.ldsc_save_dir) / f'{config.sample_name}_{config.trait_name}.csv.gz')
 
     print(f'------Loading ST data of {config.sample_name}...')
-    adata = sc.read_h5ad(f'{config.input_hdf5_path}')
+    adata = sc.read_h5ad(f'{config.hdf5_with_latent_path}')
 
     space_coord_concat = load_st_coord(adata, ldsc, annotation=config.annotation)
     fig = draw_scatter(space_coord_concat,
@@ -109,46 +182,18 @@ def run_Visualize(config: VisualizeConfig):
                        annotation=config.annotation
                        )
 
-    # save the figure to html
 
     # Visualization
-    output_dir = Path(config.output_figure_dir)
+    output_dir = Path(config.output_dir)
     output_dir.mkdir(parents=True, exist_ok=True, mode=0o755)
     output_file_html = output_dir / f'{config.sample_name}_{config.trait_name}.html'
     output_file_pdf = output_dir / f'{config.sample_name}_{config.trait_name}.pdf'
+    output_file_csv = output_dir / f'{config.sample_name}_{config.trait_name}.csv'
 
     fig.write_html(str(output_file_html))
     fig.write_image(str(output_file_pdf))
+    space_coord_concat.to_csv(str(output_file_csv))
 
     print(
         f'------The visualization result is saved in a html file: {output_file_html} which can interactively viewed in a web browser and a pdf file: {output_file_pdf}.')
-
-
-if __name__ == '__main__':
-    TEST = True
-    if TEST:
-        test_dir = '/storage/yangjianLab/chenwenhao/projects/202312_gsMap/data/gsMap_test/Nature_Neuroscience_2021'
-        name = 'E16.5_E1S1'
-
-        config = VisualizeConfig(
-            input_hdf5_path=f'/storage/yangjianLab/songliyang/SpatialData/Data/Embryo/Mice/Cell_MOSTA/h5ad/E16.5_E1S1.MOSTA.h5ad',
-            input_ldsc_dir=
-            f'/storage/yangjianLab/songliyang/SpatialData/Data/Embryo/Mice/Cell_MOSTA/ldsc_enrichment_frac/E16.5_E1S1/',
-            output_figure_dir='/storage/yangjianLab/chenwenhao/projects/202312_gsMap/data/gsMap_test/Nature_Neuroscience_2021/snake_workdir/Cortex_151507/figure/',
-            sample_name=name,
-            trait_name='GIANT_EUR_Height_2022_Nature',
-            fig_title='GIANT_EUR_Height_2022_Nature',
-            fig_height=800,
-            fig_width=800,
-            fig_style='light',
-            point_size=2,
-            annotation='annotation',
-        )
-        run_Visualize(config)
-    else:
-        parser = argparse.ArgumentParser(description="Visualization the results")
-        add_Visualization_args(parser)
-        args = parser.parse_args()
-        config = VisualizeConfig(**vars(args))
-
-        run_Visualize(config)
+    print(f'------The visualization data is saved in a csv file: {output_file_csv}.')

{gsmap-1.62.dist-info → gsmap-1.64.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gsMap
-Version: 1.62
+Version: 1.64
 Summary: Genetics-informed pathogenic spatial mapping
 Author-email: liyang <songliyang@westlake.edu.cn>, wenhao <chenwenhao@westlake.edu.cn>
 Requires-Python: >=3.8
@@ -26,6 +26,12 @@ Requires-Dist: pyranges
 Requires-Dist: pyfiglet
 Requires-Dist: plotly
 Requires-Dist: kaleido
+Requires-Dist: jinja2
+Requires-Dist: scanpy
+Requires-Dist: zarr
+Requires-Dist: bitarray
+Requires-Dist: pyarrow
+Requires-Dist: scikit-misc
 Requires-Dist: sphinx ; extra == "doc"
 Requires-Dist: sphinx-argparse ; extra == "doc"
 Requires-Dist: sphinx-autobuild ; extra == "doc"
@@ -46,21 +52,22 @@ Requires-Dist: sphinxcontrib-serializinghtml ; extra == "doc"
 Requires-Dist: furo ; extra == "doc"
 Requires-Dist: myst-parser ; extra == "doc"
 Requires-Dist: nbsphinx ; extra == "doc"
-Project-URL: Documentation, https://...
+Project-URL: Documentation, https://yanglab.westlake.edu.cn/gsmap/document
 Project-URL: Home, https://github.com/LeonSong1995/gsMap
-Project-URL: Website, https://...
+Project-URL: Website, https://yanglab.westlake.edu.cn/gsmap/home
 Provides-Extra: doc
 
 # gsMap (genetically informed spatial mapping of cells for complex traits)
-[![stars-badge](https://img.shields.io/github/stars/LeonSong1995/MeDuSA?logo=GitHub&color=yellow)](https://github.com/LeonSong1995/gsMap/stargazers)
+[![stars-badge](https://img.shields.io/github/stars/LeonSong1995/gsMap?logo=GitHub&color=yellow)](https://github.com/LeonSong1995/gsMap/stargazers)
+[![pypi-badge](https://img.shields.io/pypi/v/gsMap)](https://pypi.org/p/gsMap)
 [![license-badge](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
+![Model architecture](schematic.png)
 
-## Features
+## 1.Citation
+Liyang Song, Wenhao Chen, Junren Hou, Minmin Guo, Jian Yang (2024) Spatially resolved mapping of cells associated with human complex traits. (Under review)
 
-....
-
-## Installation
+## 2.Installation
 
 install use pip:
 
@@ -71,52 +78,20 @@ pip install gsMap
 install from source:
 
 ```bash
-git clone
+git clone https://github.com/LeonSong1995/gsMap.git
 cd gsMap
 pip install -e .
 ```
 
-## Usage
-
-To use gsMap, navigate to the command line and enter `gsMap` followed by the subcommand that corresponds to the desired operation. Each subcommand may require specific arguments to run.
-
-### Basic Command Structure
-
-```bash
-gsmap subcommand [arguments...]
-```
-
-- `subcommand`: The specific operation you wish to perform.
-- `arguments`: The arguments and options required for the subcommand.
-
-### Available Subcommands
-
-(Provide a list and brief description of each available subcommand. For example:)
-
-- `run_find_latent_representations`: Finds latent representations using a GNN-VAE model.
-- `run_latent_to_gene`: Maps latent representations to gene markers.
-- `run_generate_ldscore`: Generates LD scores for genomic spots.
-- `run_spatial_ldsc`: Conducts spatial LDSC analysis.
-- `run_cauchy_combination`: Performs Cauchy combination tests for annotations.
-- `run_all_mode`: Executes a comprehensive pipeline covering all steps.
-
-### Examples
-
-To run a specific functionality, you need to provide the appropriate subcommand and arguments. For example:
-### Running Requirement
-
-
-```bash
-gsmap run_find_latent_representations --input_hdf5_path <path> --output_hdf5_path <path> --sample_name <name>
-```
+## 3.Usage
 
-This command initiates the process of finding latent representations based on the given HDF5 input and output paths and sample name.
+Please checkout the documentations and tutorials at
+[gsMap.docs](https://yanglab.westlake.edu.cn/gsmap/document).
 
-## Contributing
 
-...
+## 4.Online visualization
 
-## License
+To visualize the traits-embryo or traits-brain association spatial maps, please refer to [gsmap.visualization](https://yanglab.westlake.edu.cn/gsmap/visualize).
 
 ....
 

gsmap-1.64.dist-info/RECORD

@@ -0,0 +1,30 @@
+gsMap/__init__.py,sha256=hH_7cxKCiXvoE-nLdYVifzx31Y227kJExpLs9O9ecRo,78
+gsMap/__main__.py,sha256=jR-HT42Zzfj2f-7kFJy0bkWjNxcV1MyfQHXFpef2nSE,62
+gsMap/cauchy_combination_test.py,sha256=zBPR7DOaNkr7rRoua4tAjRZL7ArjCyMRSQlPSUdHNSE,5694
+gsMap/config.py,sha256=hMUvlwlKZXeRdTJZfMINz_8DadVhEIT6X6fyJf11M9E,41134
+gsMap/diagnosis.py,sha256=pp3ONVaWCOoNCog1_6eud38yicBFxL-XhH7D8iTBgF4,13220
+gsMap/find_latent_representation.py,sha256=BVv4dyTolrlciHG3I-vwNDh2ruPpTf9jiT1hMKZnpto,6044
+gsMap/format_sumstats.py,sha256=9OBxuunoOLml3LKZvvRsPEEjQvT1Cuqb0w6lqsRIYPw,13714
+gsMap/generate_ldscore.py,sha256=2JfQoMWeQ0-B-zRHakmwq8ovkeewlnWHUCnih6od6ZE,29089
+gsMap/latent_to_gene.py,sha256=6TlOWDhzzrj18o9gJk2b-WMOkeXqscK8CJJKxCtilHg,9640
+gsMap/main.py,sha256=skyBtESdjvuXd9HNq5c83OPxQTNgLVErkYhwuJm8tE4,1285
+gsMap/report.py,sha256=H0uYAru2L5-d41_LFHPPdoJbtiTzP4f8kX-mirUNAfc,6963
+gsMap/run_all_mode.py,sha256=sPEct9fRw7aAQuU7BNChxk-I8YQcXuq--mtBn-2wTTY,8388
+gsMap/spatial_ldsc_multiple_sumstats.py,sha256=09j2zG98JUjQvSHPaRIDQVMZZLYDd1JBFaZTkW7tdvY,18470
+gsMap/visualize.py,sha256=FLIRHHj1KntLMFDjAhg1jZnJUdvrncR74pCW2Kj5pus,7453
+gsMap/GNN_VAE/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gsMap/GNN_VAE/adjacency_matrix.py,sha256=pmSfK9TTwdrsWTmHvCqVrbRE0PAiq1lvgmxzrdQgpiU,3500
+gsMap/GNN_VAE/model.py,sha256=Fixl8-2zN3T5MmMtpMIvxsBYydM3QVR4uC3Hhsg0DzI,3349
+gsMap/GNN_VAE/train.py,sha256=KnvZYHImRzTwJl1H0dkZZqWASdZ5VgYTCifQVW8TavM,3389
+gsMap/templates/report_template.html,sha256=pdxHFl_W0W351NUzuJTf_Ay_BfKlEbD_fztNabAGmmg,8214
+gsMap/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gsMap/utils/generate_r2_matrix.py,sha256=A1BrUnlTrYjRwEKxK0I1FbZ5SCQzcviWVM-JzFHHRkw,29352
+gsMap/utils/jackknife.py,sha256=nEDPVQJOPQ_uqfUCGX_v5cQwokgCqUmJTT_8rVFuIQo,18244
+gsMap/utils/make_annotations.py,sha256=lCbtahT27WFOwLgZrEUE5QcNRuMXmAFYUfsFR-cT-m0,22197
+gsMap/utils/manhattan_plot.py,sha256=k3n-NNgMsov9-8UQrirVqG560FUfJ4d6wNG8C0OeCjY,26235
+gsMap/utils/regression_read.py,sha256=n_hZZzQXHU-CSLvSofXmQM5Jw4Zpufv3U2HoUW344ko,8768
+gsmap-1.64.dist-info/entry_points.txt,sha256=s_P2Za22O077tc1FPLKMinbdRVXaN_HTcDBgWMYpqA4,41
+gsmap-1.64.dist-info/LICENSE,sha256=Ni2F-lLSv_H1xaVT3CoSrkiKzMvlgwh-dq8PE1esGyI,1094
+gsmap-1.64.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+gsmap-1.64.dist-info/METADATA,sha256=ITHEobajRdMgQkc-ZpI708Xb5cB95_NxX-uDWVMPa60,3376
+gsmap-1.64.dist-info/RECORD,,

gsmap-1.62.dist-info/RECORD

@@ -1,24 +0,0 @@
-gsMap/__init__.py,sha256=RJYX4ncfccRzcIr2GQI4s5QYvjfLD-KKlzWeHaZMtzk,78
-gsMap/__main__.py,sha256=jR-HT42Zzfj2f-7kFJy0bkWjNxcV1MyfQHXFpef2nSE,62
-gsMap/cauchy_combination_test.py,sha256=WI71HmSJ38Q2VEohnVrWHL02MnY0clqX9Fb5VrXCCz4,6758
-gsMap/config.py,sha256=2-gQR-nJRI9XfxegGCuUYMPDf43nuo7gWXR8JhtKWjs,39578
-gsMap/find_latent_representation.py,sha256=liRXtQKixYwGA6ZQmfXXVeHAypobACYO1wYT-wyr3AU,8337
-gsMap/format_sumstats.py,sha256=wC8eSFCbD8qpq5JOaxhYP5iL3JZ6NmG-JPThyQ52tDM,13838
-gsMap/generate_ldscore.py,sha256=s2nhq9MvQa6wfRRsCe93lv54zyimvNn1aW0-dG-PsXo,25494
-gsMap/generate_r2_matrix.py,sha256=BGe4WrCm19nQwzYz5vmNIC7tfIM2_QUMPd8JdfFDock,29761
-gsMap/jackknife.py,sha256=nEDPVQJOPQ_uqfUCGX_v5cQwokgCqUmJTT_8rVFuIQo,18244
-gsMap/latent_to_gene.py,sha256=lvEokL3po0kTnMk7mQvBwN0gkfO26myudRRQX1pX0BQ,11269
-gsMap/main.py,sha256=ttGY1uSmHaC6R1fPfuvonr3Nj5lZt_U3UFw15VQKDIM,1511
-gsMap/make_annotations.py,sha256=QhI3aTO9eOUuqvDXLe23eUGjld7bt_1H6vtvWX5TR5Y,23984
-gsMap/regression_read.py,sha256=ATfUapl4zypkUwo8xivzD7aGlZNSMavR-xVavSsmVkI,8780
-gsMap/spatial_ldsc_multiple_sumstats.py,sha256=Ixt8HpWZyJ7L1OA539mkvykdIDoZG9VT9ivwRmCOSwA,14440
-gsMap/visualize.py,sha256=FMuSInYfNZQMLHgh-jjER4j-U78SQVNCZJOTnL-xhgM,5645
-gsMap/GNN_VAE/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gsMap/GNN_VAE/adjacency_matrix.py,sha256=0-qw5qHGrGugkjgVyWLYjC0Qa_iKvR1TnFxAgCaxJFw,3500
-gsMap/GNN_VAE/model.py,sha256=3uWTM_zjgCjBGnuutiua0ZV2W7WiIG5RA9Y9gRHmYA8,3349
-gsMap/GNN_VAE/train.py,sha256=cAj81gJ9AwV-f5gqS1PjNtfkcZ1s_TtRcDIPIb4AtoM,3389
-gsmap-1.62.dist-info/entry_points.txt,sha256=s_P2Za22O077tc1FPLKMinbdRVXaN_HTcDBgWMYpqA4,41
-gsmap-1.62.dist-info/LICENSE,sha256=Ni2F-lLSv_H1xaVT3CoSrkiKzMvlgwh-dq8PE1esGyI,1094
-gsmap-1.62.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-gsmap-1.62.dist-info/METADATA,sha256=E9L2xZn1IRR2cmoC_gMjWoTF2fIx6qY9VDlSLg6_MrQ,3924
-gsmap-1.62.dist-info/RECORD,,