gsMap 1.73.0__tar.gz → 1.73.2__tar.gz

gsmap-1.73.2/.github/workflows/test_linux.yml

@@ -0,0 +1,100 @@
+name: test
+
+on:
+  push:
+    branches: [main, "[0-9]+.[0-9]+.x"]
+  pull_request:
+  schedule:
+    - cron: "0 0 * * *"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    defaults:
+      run:
+        shell: bash -e {0} # -e to fail on error
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python: ["3.10", "3.13"]
+
+    name: Python ${{ matrix.python }} integration
+
+    env:
+      PYTHON: ${{ matrix.python }}
+      TEST_DATA_URL: https://yanglab.westlake.edu.cn/data/gsMap/gsMap_test_data.tar.gz
+      TEST_DATA_DIR: ${{ github.workspace }}/test_data
+      WORK_DIR: ${{ github.workspace }}/gsmap_workdir
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install dependencies
+        run: |
+          uv pip install --system -e ".[tests]"
+
+      - name: Create workdir
+        run: |
+          mkdir -p $WORK_DIR
+          echo "Created workdir: $WORK_DIR"
+
+      - name: Cache test data
+        uses: actions/cache@v3
+        id: cache-test-data
+        with:
+          path: ${{ env.TEST_DATA_DIR }}
+          key: test-data-v1
+
+      - name: Download and extract test data
+        if: steps.cache-test-data.outputs.cache-hit != 'true'
+        run: |
+          echo "Downloading test data from $TEST_DATA_URL"
+          curl -L $TEST_DATA_URL -o gsMap_test_data.tar.gz
+          tar -xzf gsMap_test_data.tar.gz -C ${{ github.workspace }}
+          rm gsMap_test_data.tar.gz
+          echo "Test data extracted to ${{ github.workspace }}"
+          ls -la $TEST_DATA_DIR
+
+      - name: Run pytest
+        env:
+          MPLBACKEND: agg
+          DISPLAY: :0
+          COLUMNS: 120
+        run: |
+          python -m pytest --cov=src \
+              --junitxml=junit.xml -o junit_family=legacy \
+              --cov-report=term-missing \
+              --cov-report=xml \
+              --cov-config=.coveragerc \
+              -v -s --color=yes \
+              --run-real-data \
+              --work-dir=$WORK_DIR \
+              --test-data=$TEST_DATA_DIR
+
+      - uses: codecov/codecov-action@v4
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: ./coverage.xml
+          fail_ci_if_error: false
+
+      - name: Upload test results to Codecov
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

{gsmap-1.73.0 → gsmap-1.73.2}/.pre-commit-config.yaml

@@ -18,7 +18,7 @@ repos:
         types: [yaml]
 
   - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.21
+    rev: 0.7.22
     hooks:
       - id: mdformat
         additional_dependencies:
@@ -29,7 +29,7 @@ repos:
           )$
 
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.43.0
+    rev: v0.44.0
     hooks:
       - id: markdownlint-fix
         exclude: |
@@ -38,7 +38,7 @@ repos:
           )$
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.2
+    rev: v0.11.5
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{gsmap-1.73.0 → gsmap-1.73.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gsMap
-Version: 1.73.0
+Version: 1.73.2
 Summary: Genetics-informed pathogenic spatial mapping
 Author-email: liyang <songliyang@westlake.edu.cn>, wenhao <chenwenhao@westlake.edu.cn>
 Requires-Python: >=3.10
@@ -97,6 +97,14 @@ conda activate gsMap
 pip install gsMap
 ```
 
+Install using conda:
+
+```bash
+conda create -n gsMap python>=3.10
+conda activate gsMap
+conda install bioconda::gsmap
+```
+
 Install from source:
 
 ```bash

{gsmap-1.73.0 → gsmap-1.73.2}/README.md

@@ -33,6 +33,14 @@ conda activate gsMap
 pip install gsMap
 ```
 
+Install using conda:
+
+```bash
+conda create -n gsMap python>=3.10
+conda activate gsMap
+conda install bioconda::gsmap
+```
+
 Install from source:
 
 ```bash

gsmap-1.73.2/docs/source/10x.md

@@ -0,0 +1,137 @@
+# Cases on 10x Visium Data
+
+Here we provide case applications based on 10x Visium data (which are not at single-cell resolution). For convenience, we used the `Quick Mode` here, but you can also follow the {doc}`Step by Step <step_by_step>` Guide to analyze 10x Visium data—the steps are the same.
+
+A frequently asked question is how to provide annotations for 10x Visium data. Note that gsMap can run without annotations. The most convenient approaches are to either leave the `annotation` parameter unset (in {doc}`Step by Step <step_by_step>`) or provide annotations from spatial clustering methods, such as [SpaGCN](https://github.com/jianhuupenn/SpaGCN).
+
+## Preparation
+
+Make sure you have {doc}`installed <install>` the `gsMap` package before proceeding.
+
+### 1. Download Dependencies
+
+The `gsMap` package in quick mode requires the following resources:
+
+- **Gene transfer format (GTF) file**, for gene coordinates on the genome.
+- **LD reference panel**, in quick mode, we provide a pre-built LD score snp-by-gene matrix based on 1000G_EUR_Phase3.
+- **SNP weight file**, to adjust correlations between SNP-trait association statistics.
+- **Homologous gene transformations file** (optional), to map genes between species.
+
+To download all the required files:
+
+```bash
+wget https://yanglab.westlake.edu.cn/data/gsMap/gsMap_resource.tar.gz
+tar -xvzf gsMap_resource.tar.gz
+```
+
+Directory structure:
+
+```bash
+tree -L 2
+
+gsMap_resource
+    ├── genome_annotation
+    │   ├── enhancer
+    │   └── gtf
+    ├── homologs
+    │   ├── macaque_human_homologs.txt
+    │   └── mouse_human_homologs.txt
+    ├── LD_Reference_Panel
+    │   └── 1000G_EUR_Phase3_plink
+    ├── LDSC_resource
+    │   ├── hapmap3_snps
+    │   └── weights_hm3_no_hla
+    └── quick_mode
+        ├── baseline
+        ├── SNP_gene_pair
+        └── snp_gene_weight_matrix.h5ad
+```
+
+### 2. Download Example Data
+
+You can download the example 10x Visium data as follows:
+
+```bash
+wget https://yanglab.westlake.edu.cn/data/gsMap/Visium_example_data.tar.gz
+tar -xvzf Visium_example_data.tar.gz
+```
+
+Directory structure:
+
+```bash
+tree -L 2
+
+Visium_example_data/
+├── GWAS
+│   ├── IQ_NG_2018.sumstats.gz
+│   └── Serum_creatinine.sumstats.gz
+└── ST
+    ├── V1_Adult_Mouse_Brain_Coronal_Section.h5ad
+    ├── V1_Mouse_Brain_Sagittal_Posterior_Section.h5ad
+    └── V1_Mouse_Kidney.h5ad
+```
+
+## Case1
+
+Data: Visium data of adult mouse coronal section
+Trait: IQ
+<span style="color:#31a354"> Required memory: 11G (2902 cells) </span>
+
+```bash
+gsmap quick_mode \
+    --workdir './example_quick_mode/Visium' \
+    --homolog_file 'gsMap_resource/homologs/mouse_human_homologs.txt' \
+    --sample_name 'V1_Adult_Mouse_Brain_Coronal_Section' \
+    --gsMap_resource_dir 'gsMap_resource' \
+    --hdf5_path 'Visium_example_data/ST/V1_Adult_Mouse_Brain_Coronal_Section.h5ad' \
+    --annotation 'domain' \
+    --data_layer 'count' \
+    --sumstats_file 'Visium_example_data/GWAS/IQ_NG_2018.sumstats.gz' \
+    --trait_name 'IQ'
+```
+
+[gsMap report](https://yanglab.westlake.edu.cn/data/gsMap/Visium_report/coronal/V1_Adult_Mouse_Brain_Coronal_Section_IQ_gsMap_Report.html) for the `IQ` on the adult mouse coronal section Visium data.
+
+## Case2
+
+Data: Visium data of adult mouse sigital section
+Trait: IQ
+
+<span style="color:#31a354"> Required memory: 12G (3289 cells) </span>
+
+```bash
+gsmap quick_mode \
+    --workdir './example_quick_mode/Visium' \
+    --homolog_file 'gsMap_resource/homologs/mouse_human_homologs.txt' \
+    --sample_name 'V1_Mouse_Brain_Sagittal_Posterior_Section' \
+    --gsMap_resource_dir 'gsMap_resource' \
+    --hdf5_path 'Visium_example_data/ST/V1_Mouse_Brain_Sagittal_Posterior_Section.h5ad' \
+    --annotation 'domain' \
+    --data_layer 'count' \
+    --sumstats_file 'Visium_example_data/GWAS/IQ_NG_2018.sumstats.gz' \
+    --trait_name 'IQ'
+```
+
+[gsMap report](https://yanglab.westlake.edu.cn/data/gsMap/Visium_report/saggital/V1_Mouse_Brain_Sagittal_Posterior_Section_IQ_gsMap_Report.html) for the `IQ` on the adult mouse sigital section Visium data.
+
+## Case3
+
+Data: Visium data of adult mouse kindey
+Trait: Serum creatinine
+
+<span style="color:#31a354"> Required memory: 8G (1437 cells) </span>
+
+```bash
+gsmap quick_mode \
+    --workdir './example_quick_mode/Visium' \
+    --homolog_file 'gsMap_resource/homologs/mouse_human_homologs.txt' \
+    --sample_name 'V1_Mouse_Kidney' \
+    --gsMap_resource_dir 'gsMap_resource' \
+    --hdf5_path 'Visium_example_data/ST/V1_Mouse_Kidney.h5ad' \
+    --annotation 'domain' \
+    --data_layer 'count' \
+    --sumstats_file 'Visium_example_data/GWAS/Serum_creatinine.sumstats.gz' \
+    --trait_name 'Serum_creatinine'
+```
+
+[gsMap report](https://yanglab.westlake.edu.cn/data/gsMap/Visium/V1_Mouse_Kidney_Serum_creatinine_gsMap_Report.html) for the `Serum creatinine` on the adult mouse kindey Visium data.

{gsmap-1.73.0 → gsmap-1.73.2}/docs/source/advanced_usage.md

@@ -44,7 +44,7 @@ do
         --chrom $CHROM \
         --bfile_root 'gsMap_resource/LD_Reference_Panel/1000G_EUR_Phase3_plink/1000G.EUR.QC' \
         --keep_snp_root 'gsMap_resource/LDSC_resource/hapmap3_snps/hm' \
-        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v39lift37.annotation.gtf' \
+        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v46lift37.basic.annotation.gtf' \
         --gene_window_size 50000 \
         --additional_baseline_annotation 'gsMap_additional_annotation'
 done

{gsmap-1.73.0 → gsmap-1.73.2}/docs/source/step_by_step.md

@@ -132,7 +132,7 @@ do
         --chrom $CHROM \
         --bfile_root 'gsMap_resource/LD_Reference_Panel/1000G_EUR_Phase3_plink/1000G.EUR.QC' \
         --keep_snp_root 'gsMap_resource/LDSC_resource/hapmap3_snps/hm' \
-        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v39lift37.annotation.gtf' \
+        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v46lift37.basic.annotation.gtf' \
         --gene_window_size 50000
 done
 ```
@@ -150,7 +150,7 @@ do
         --chrom $CHROM \
         --bfile_root 'gsMap_resource/LD_Reference_Panel/1000G_EUR_Phase3_plink/1000G.EUR.QC' \
         --keep_snp_root 'gsMap_resource/LDSC_resource/hapmap3_snps/hm' \
-        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v39lift37.annotation.gtf' \
+        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v46lift37.basic.annotation.gtf' \
         --enhancer_annotation_file 'gsMap_resource/genome_annotation/enhancer/by_tissue/ALL/ABC_roadmap_merged.bed' \
         --snp_multiple_enhancer_strategy 'max_mkscore' \
         --gene_window_enhancer_priority 'enhancer_only'
@@ -170,7 +170,7 @@ do
         --chrom $CHROM \
         --bfile_root 'gsMap_resource/LD_Reference_Panel/1000G_EUR_Phase3_plink/1000G.EUR.QC' \
         --keep_snp_root 'gsMap_resource/LDSC_resource/hapmap3_snps/hm' \
-        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v39lift37.annotation.gtf' \
+        --gtf_annotation_file 'gsMap_resource/genome_annotation/gtf/gencode.v46lift37.basic.annotation.gtf' \
         --gene_window_size 50000 \
         --enhancer_annotation_file 'gsMap_resource/genome_annotation/enhancer/by_tissue/ALL/ABC_roadmap_merged.bed' \
         --snp_multiple_enhancer_strategy 'max_mkscore' \

{gsmap-1.73.0 → gsmap-1.73.2}/docs/source/tutorials.rst

@@ -27,4 +27,5 @@ The tutorials are organized as follows:
     quick_mode.md
     step_by_step.md
     advanced_usage.md
+    10x.md
     data_format.md

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/GNN/train.py

@@ -17,7 +17,7 @@ def reconstruction_loss(decoded, x):
 
 def label_loss(pred_label, true_label):
     """Compute the cross-entropy loss."""
-    return F.cross_entropy(pred_label, true_label)
+    return F.cross_entropy(pred_label, true_label.long())
 
 
 class ModelTrainer:

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/__init__.py

@@ -2,4 +2,4 @@
 Genetics-informed pathogenic spatial mapping
 """
 
-__version__ = "1.73.0"
+__version__ = "1.73.2"

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/config.py

@@ -232,6 +232,9 @@ def add_find_latent_representations_args(parser):
         action="store_true",
         help="Enable hierarchical latent representation finding.",
     )
+    parser.add_argument(
+        "--pearson_residuals", action="store_true", help="Using the pearson residuals."
+    )
 
 
 def chrom_choice(value):
@@ -308,7 +311,7 @@ def add_generate_ldscore_args(parser):
         help="Root path for genotype plink bfiles (.bim, .bed, .fam).",
     )
     parser.add_argument(
-        "--keep_snp_root", type=str, required=True, help="Root path for SNP files."
+        "--keep_snp_root", type=str, required=False, help="Root path for SNP files"
     )
     parser.add_argument(
         "--gtf_annotation_file", type=str, required=True, help="Path to GTF annotation file."
@@ -357,7 +360,11 @@ def add_spatial_ldsc_args(parser):
         "--sumstats_file", type=str, required=True, help="Path to GWAS summary statistics file."
     )
     parser.add_argument(
-        "--w_file", type=str, required=True, help="Path to regression weight file."
+        "--w_file",
+        type=str,
+        required=False,
+        default=None,
+        help="Path to regression weight file. If not provided, will use weights generated in the generate_ldscore step.",
     )
     parser.add_argument(
         "--trait_name", type=str, required=True, help="Name of the trait being analyzed."
@@ -678,6 +685,9 @@ def add_run_all_mode_args(parser):
     parser.add_argument(
         "--gM_slices", type=str, default=None, help="Path to the slice mean file (optional)."
     )
+    parser.add_argument(
+        "--pearson_residuals", action="store_true", help="Using the pearson residuals."
+    )
 
 
 def ensure_path_exists(func):
@@ -854,6 +864,7 @@ class FindLatentRepresentationsConfig(ConfigWithAutoPaths):
     var: bool = False
     convergence_threshold: float = 1e-4
     hierarchically: bool = False
+    pearson_residuals: bool = False
 
     def __post_init__(self):
         # self.output_hdf5_path = self.hdf5_with_latent_path
@@ -942,11 +953,11 @@ class GenerateLDScoreConfig(ConfigWithAutoPaths):
     chrom: int | str
 
     bfile_root: str
-    keep_snp_root: str | None
 
     # annotation by gene distance
     gtf_annotation_file: str
     gene_window_size: int = 50000
+    keep_snp_root: str | None = None
 
     # annotation by enhancer
     enhancer_annotation_file: str = None
@@ -1055,7 +1066,7 @@ class GenerateLDScoreConfig(ConfigWithAutoPaths):
 
 @dataclass
 class SpatialLDSCConfig(ConfigWithAutoPaths):
-    w_file: str
+    w_file: str | None = None
     # ldscore_save_dir: str
     use_additional_baseline_annotation: bool = True
     trait_name: str | None = None
@@ -1105,8 +1116,19 @@ class SpatialLDSCConfig(ConfigWithAutoPaths):
         for sumstats_file in self.sumstats_config_dict.values():
             assert Path(sumstats_file).exists(), f"{sumstats_file} does not exist."
 
-        # check if additional baseline annotation is exist
-        # self.use_additional_baseline_annotation = False
+        # Handle w_file
+        if self.w_file is None:
+            w_ld_dir = Path(self.ldscore_save_dir) / "w_ld"
+            if w_ld_dir.exists():
+                self.w_file = str(w_ld_dir / "weights.")
+                logger.info(f"Using weights generated in the generate_ldscore step: {self.w_file}")
+            else:
+                raise ValueError(
+                    "No w_file provided and no weights found in generate_ldscore output. "
+                    "Either provide --w_file or run generate_ldscore first."
+                )
+        else:
+            logger.info(f"Using provided weights file: {self.w_file}")
 
         if self.use_additional_baseline_annotation:
             self.process_additional_baseline_annotation()
@@ -1117,16 +1139,6 @@ class SpatialLDSCConfig(ConfigWithAutoPaths):
 
         if not dir_exists:
             self.use_additional_baseline_annotation = False
-            # if self.use_additional_baseline_annotation:
-            #     logger.warning(f"additional_baseline directory is not found in {self.ldscore_save_dir}.")
-            #     print('''\
-            #         if you want to use additional baseline annotation,
-            #         please provide additional baseline annotation when calculating ld score.
-            #         ''')
-            #     raise FileNotFoundError(
-            #         f'additional_baseline directory is not found.')
-            # return
-            # self.use_additional_baseline_annotation = self.use_additional_baseline_annotation or True
         else:
             logger.info(
                 "------Additional baseline annotation is provided. It will be used with the default baseline annotation."
@@ -1227,6 +1239,7 @@ class RunAllModeConfig(ConfigWithAutoPaths):
 
     # == Find Latent Representation PARAMETERS ==
     n_comps: int = 300
+    pearson_residuals: bool = False
 
     # == latent 2 Gene PARAMETERS ==
     gM_slices: str | None = None

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/create_slice_mean.py

@@ -23,6 +23,7 @@ def get_common_genes(h5ad_files, config: CreateSliceMeanConfig):
     common_genes = None
     for file in tqdm(h5ad_files, desc="Finding common genes"):
         adata = sc.read_h5ad(file)
+        sc.pp.filter_genes(adata, min_cells=1)
         adata.var_names_make_unique()
         if common_genes is None:
             common_genes = adata.var_names

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/diagnosis.py

@@ -49,7 +49,10 @@ def compute_gene_diagnostic_info(config: DiagnosisConfig):
 
     # Align marker scores with trait LDSC results
     mk_score = mk_score.loc[trait_ldsc_result.index]
-    mk_score = mk_score.loc[:, mk_score.sum(axis=0) != 0]
+
+    # Filter out genes with no variation
+    has_variation = (~mk_score.eq(mk_score.iloc[0], axis=1)).any()
+    mk_score = mk_score.loc[:, has_variation]
 
     logger.info("Calculating correlation between gene marker scores and trait logp-values...")
     corr = mk_score.corrwith(trait_ldsc_result["logp"])
@@ -66,10 +69,6 @@ def compute_gene_diagnostic_info(config: DiagnosisConfig):
         }
     )
 
-    # Filter based on median GSS score
-    high_GSS_Gene_annotation_pair = high_GSS_Gene_annotation_pair[
-        high_GSS_Gene_annotation_pair["Median_GSS"] >= 1.0
-    ]
     high_GSS_Gene_annotation_pair = high_GSS_Gene_annotation_pair.merge(
         corr, left_on="Gene", right_index=True
     )
@@ -88,19 +87,6 @@ def compute_gene_diagnostic_info(config: DiagnosisConfig):
     gene_diagnostic_info.to_csv(gene_diagnostic_info_save_path, index=False)
     logger.info(f"Gene diagnostic information saved to {gene_diagnostic_info_save_path}.")
 
-    # TODO: A new script is needed to save the gene diagnostic info to adata.var and trait_ldsc_result to adata.obs when running multiple traits
-    # # Save to adata.var with the trait_name prefix
-    # logger.info('Saving gene diagnostic info to adata.var...')
-    # gene_diagnostic_info.set_index('Gene', inplace=True)  # Use 'Gene' as the index to align with adata.var
-    # adata.var[f'{config.trait_name}_Annotation'] = gene_diagnostic_info['Annotation']
-    # adata.var[f'{config.trait_name}_Median_GSS'] = gene_diagnostic_info['Median_GSS']
-    # adata.var[f'{config.trait_name}_PCC'] = gene_diagnostic_info['PCC']
-    #
-    # # Save trait_ldsc_result to adata.obs
-    # logger.info(f'Saving trait LDSC results to adata.obs as gsMap_{config.trait_name}_p_value...')
-    # adata.obs[f'gsMap_{config.trait_name}_p_value'] = trait_ldsc_result['p']
-    # adata.write(config.hdf5_with_latent_path, )
-
     return gene_diagnostic_info.reset_index()
 
 
@@ -171,6 +157,20 @@ def generate_manhattan_plot(config: DiagnosisConfig):
         + gwas_data_to_plot["Annotation"].astype(str)
     )
 
+    # Verify data integrity
+    if gwas_data_with_gene_annotation_sort.empty:
+        logger.error("Filtered GWAS data is empty, cannot create Manhattan plot")
+        return
+
+    if len(gwas_data_to_plot) == 0:
+        logger.error("No SNPs passed filtering criteria for Manhattan plot")
+        return
+
+    # Log some diagnostic information
+    logger.info(f"Creating Manhattan plot with {len(gwas_data_to_plot)} SNPs")
+    logger.info(f"Columns available: {list(gwas_data_to_plot.columns)}")
+    logger.info(f"Chromosome column values: {gwas_data_to_plot['CHR'].unique()}")
+
     fig = ManhattanPlot(
         dataframe=gwas_data_to_plot,
         title="gsMap Diagnosis Manhattan Plot",

{gsmap-1.73.0 → gsmap-1.73.2}/src/gsMap/find_latent_representation.py

@@ -50,6 +50,15 @@ def preprocess_data(adata, params):
         # HVGs based on count
         logger.info("Dealing with count data...")
         sc.pp.highly_variable_genes(adata, flavor="seurat_v3", n_top_genes=params.feat_cell)
+
+        # Get the pearson residuals
+        if params.pearson_residuals:
+            sc.experimental.pp.normalize_pearson_residuals(adata, inplace=False)
+            pearson_residuals = sc.experimental.pp.normalize_pearson_residuals(
+                adata, inplace=False, clip=10
+            )
+            adata.layers["pearson_residuals"] = pearson_residuals["X"]
+
         # Normalize the data
         sc.pp.normalize_total(adata, target_sum=1e4)
         sc.pp.log1p(adata)
@@ -64,8 +73,13 @@ class LatentRepresentationFinder:
     def __init__(self, adata, args: FindLatentRepresentationsConfig):
         self.params = args
 
-        self.expression_array = adata[:, adata.var.highly_variable].X.copy()
-        self.expression_array = sc.pp.scale(self.expression_array, max_value=10)
+        if "pearson_residuals" in adata.layers:
+            self.expression_array = (
+                adata[:, adata.var.highly_variable].layers["pearson_residuals"].copy()
+            )
+        else:
+            self.expression_array = adata[:, adata.var.highly_variable].X.copy()
+            self.expression_array = sc.pp.scale(self.expression_array, max_value=10)
 
         # Construct the neighboring graph
         self.graph_dict = construct_adjacency_matrix(adata, self.params)
@@ -103,6 +117,8 @@ def run_find_latent_representation(args: FindLatentRepresentationsConfig):
     # Load the ST data
     logger.info(f"Loading ST data of {args.sample_name}...")
     adata = sc.read_h5ad(args.input_hdf5_path)
+    sc.pp.filter_genes(adata, min_cells=1)
+
     logger.info(f"The ST data contains {adata.shape[0]} cells, {adata.shape[1]} genes.")
 
     # Load the cell type annotation