gsMap 1.71.1__py3-none-any.whl → 1.72.3__py3-none-any.whl

gsMap/run_all_mode.py

@@ -1,195 +1,235 @@
-import logging
-import time
-from pathlib import Path
-
-from gsMap.cauchy_combination_test import run_Cauchy_combination
-from gsMap.config import GenerateLDScoreConfig, SpatialLDSCConfig, LatentToGeneConfig, \
-    FindLatentRepresentationsConfig, CauchyCombinationConfig, RunAllModeConfig, ReportConfig
-from gsMap.find_latent_representation import run_find_latent_representation
-from gsMap.generate_ldscore import run_generate_ldscore
-from gsMap.latent_to_gene import run_latent_to_gene
-from gsMap.report import run_report
-from gsMap.spatial_ldsc_multiple_sumstats import run_spatial_ldsc
-
-
-
-def format_duration(seconds):
-    hours = int(seconds // 3600)
-    minutes = int((seconds % 3600) // 60)
-    return f"{hours}h {minutes}m"
-
-
-def run_pipeline(config: RunAllModeConfig):
-    # # Set up logging
-    log_file = Path(config.workdir) / config.sample_name / 'gsMap_pipeline.log'
-    log_file.parent.mkdir(parents=True, exist_ok=True)
-    logging.basicConfig(
-        level=logging.INFO,
-        format='[{asctime}] {levelname:.5s} | {name} - {message}',
-        handlers=[
-            logging.FileHandler(log_file),
-        ],
-        style='{'
-    )
-
-    logger = logging.getLogger('gsMap.pipeline')
-    logger.info("Starting pipeline with configuration: %s", config)
-
-    find_latent_config = FindLatentRepresentationsConfig(
-        workdir=config.workdir,
-        input_hdf5_path=config.hdf5_path,
-        sample_name=config.sample_name,
-        annotation=config.annotation,
-        data_layer=config.data_layer
-    )
-
-    latent_to_gene_config = LatentToGeneConfig(
-        workdir=config.workdir,
-        sample_name=config.sample_name,
-        annotation=config.annotation,
-        latent_representation='latent_GVAE',
-        num_neighbour=51,
-        num_neighbour_spatial=201,
-        homolog_file=config.homolog_file
-    )
-
-    ldscore_config = GenerateLDScoreConfig(
-        workdir=config.workdir,
-        sample_name=config.sample_name,
-        chrom='all',
-        # ldscore_save_dir=f"{config.workdir}/{config.sample_name}/generate_ldscore",
-        # mkscore_feather_file=latent_to_gene_config.output_feather_path,
-        bfile_root=config.bfile_root,
-        keep_snp_root=config.keep_snp_root,
-        gtf_annotation_file=config.gtffile,
-        spots_per_chunk=5_000,
-        baseline_annotation_dir=config.baseline_annotation_dir,
-        SNP_gene_pair_dir=config.SNP_gene_pair_dir,
-        ldscore_save_format='quick_mode'
-
-    )
-
-    pipeline_start_time = time.time()
-
-    # Step 1: Find latent representations
-    start_time = time.time()
-    logger.info("Step 1: Finding latent representations")
-    if Path(find_latent_config.hdf5_with_latent_path).exists():
-        logger.info(
-            f"Find latent representations already done. Results saved at {find_latent_config.hdf5_with_latent_path}. Skipping...")
-    else:
-        run_find_latent_representation(find_latent_config)
-    end_time = time.time()
-    logger.info(f"Step 1 completed in {format_duration(end_time - start_time)}.")
-
-    # Step 2: Latent to gene
-    start_time = time.time()
-    logger.info("Step 2: Mapping latent representations to genes")
-    if Path(latent_to_gene_config.mkscore_feather_path).exists():
-        logger.info(
-            f"Latent to gene mapping already done. Results saved at {latent_to_gene_config.mkscore_feather_path}. Skipping...")
-    else:
-        run_latent_to_gene(latent_to_gene_config)
-    end_time = time.time()
-    logger.info(f"Step 2 completed in {format_duration(end_time - start_time)}.")
-
-    # Step 3: Generate LDScores
-    start_time = time.time()
-    logger.info("Step 3: Generating LDScores")
-
-    # check if LDscore has been generated by the done file
-    ldsc_done_file = Path(ldscore_config.ldscore_save_dir) / f"{config.sample_name}_generate_ldscore.done"
-    if ldsc_done_file.exists():
-        logger.info(f"Basic LDScore generation already done. Results saved at {ldscore_config.ldscore_save_dir}. Skipping...")
-    else:
-        run_generate_ldscore(ldscore_config)
-        end_time = time.time()
-        logger.info(f"Step 3 completed in {format_duration(end_time - start_time)}.")
-        # create a done file
-        ldsc_done_file.touch()
-
-    # Step 4: Spatial LDSC
-    start_time = time.time()
-    logger.info("Step 4: Running spatial LDSC")
-
-    sumstats_config = config.sumstats_config_dict
-    for trait_name in sumstats_config:
-        logger.info("Running spatial LDSC for trait: %s", trait_name)
-        # detect if the spatial LDSC has been done:
-        spatial_ldsc_result_file = Path(config.ldsc_save_dir) / f"{config.sample_name}_{trait_name}.csv.gz"
-
-        if spatial_ldsc_result_file.exists():
-            logger.info(
-                f"Spatial LDSC already done for trait {trait_name}. Results saved at {spatial_ldsc_result_file}. Skipping...")
-            continue
-
-        spatial_ldsc_config_trait = SpatialLDSCConfig(
-            workdir=config.workdir,
-            sumstats_file=sumstats_config[trait_name],
-            trait_name=trait_name,
-            w_file=config.w_file,
-            sample_name=config.sample_name,
-            # ldscore_save_dir=spatial_ldsc_config.ldscore_save_dir,
-            # ldsc_save_dir=spatial_ldsc_config.ldsc_save_dir,
-            num_processes=config.max_processes,
-            ldscore_save_format='quick_mode',
-            snp_gene_weight_adata_path=config.snp_gene_weight_adata_path,
-        )
-        run_spatial_ldsc(spatial_ldsc_config_trait)
-    end_time = time.time()
-    logger.info(f"Step 4 completed in {format_duration(end_time - start_time)}.")
-
-    # Step 5: Cauchy combination test
-    start_time = time.time()
-    logger.info("Step 6: Running Cauchy combination test")
-    '/storage/yangjianLab/chenwenhao/projects/202312_GPS/test/20240817_vanilla_pipeline_mouse_embryo_v4/E16.5_E1S1.MOSTA/cauchy_combination/E16.5_E1S1.MOSTA_Depression_2023_NatureMed.Cauchy.csv.gz'
-    for trait_name in sumstats_config:
-        # check if the cauchy combination has been done
-        cauchy_result_file = config.get_cauchy_result_file(trait_name)
-        if cauchy_result_file.exists():
-            logger.info(
-                f"Cauchy combination already done for trait {trait_name}. Results saved at {cauchy_result_file}. Skipping...")
-            continue
-        cauchy_config = CauchyCombinationConfig(
-            workdir=config.workdir,
-            sample_name=config.sample_name,
-            annotation=config.annotation,
-            trait_name=trait_name,
-        )
-        run_Cauchy_combination(cauchy_config)
-    end_time = time.time()
-    logger.info(f"Step 5 completed in {format_duration(end_time - start_time)}.")
-
-    # Step 6: Generate final report
-    for trait_name in sumstats_config:
-        logger.info("Running final report generation for trait: %s", trait_name)
-        report_config = ReportConfig(
-            workdir=config.workdir,
-            sample_name=config.sample_name,
-            annotation=config.annotation,
-            trait_name=trait_name,
-            plot_type='all',
-            top_corr_genes=50,
-            selected_genes=None,
-            sumstats_file=sumstats_config[trait_name],
-        )
-        # Create the run parameters dictionary for each trait
-        run_parameter_dict = {
-            "Sample Name": config.sample_name,
-            "Trait Name": trait_name,
-            "Summary Statistics File": sumstats_config[trait_name],
-            "HDF5 Path": config.hdf5_path,
-            "Annotation": config.annotation,
-            "Number of Processes": config.max_processes,
-            "Spatial LDSC Save Directory": config.ldsc_save_dir,
-            "Cauchy Directory": config.cauchy_save_dir,
-            "Report Directory": config.get_report_dir(trait_name),
-            "gsMap Report File": config.get_gsMap_report_file(trait_name),
-            "Gene Diagnostic Info File": config.get_gene_diagnostic_info_save_path(trait_name),
-            "Spending Time": format_duration(time.time() - pipeline_start_time),
-        }
-
-        # Pass the run parameter dictionary to the report generation function
-        run_report(report_config, run_parameters=run_parameter_dict)
-
-    logger.info("Pipeline completed successfully.")
+import logging
+import time
+from pathlib import Path
+
+from gsMap.cauchy_combination_test import run_Cauchy_combination
+from gsMap.config import (
+    CauchyCombinationConfig,
+    FindLatentRepresentationsConfig,
+    GenerateLDScoreConfig,
+    LatentToGeneConfig,
+    ReportConfig,
+    RunAllModeConfig,
+    SpatialLDSCConfig,
+)
+from gsMap.find_latent_representation import run_find_latent_representation
+from gsMap.generate_ldscore import run_generate_ldscore
+from gsMap.latent_to_gene import run_latent_to_gene
+from gsMap.report import run_report
+from gsMap.spatial_ldsc_multiple_sumstats import run_spatial_ldsc
+
+
+def format_duration(seconds):
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    return f"{hours}h {minutes}m"
+
+
+def run_pipeline(config: RunAllModeConfig):
+    # # Set up logging
+    _current_datatime = time.strftime("%Y%m%d_%H%M%S")
+    log_file = (
+        Path(config.workdir)
+        / config.sample_name
+        / f"gsMap_pipeline_{config.sample_name}_{_current_datatime}.log"
+    )
+    log_file.parent.mkdir(parents=True, exist_ok=True)
+    logging.basicConfig(
+        level=logging.INFO,
+        format="[{asctime}] {levelname:.5s} | {name} - {message}",
+        handlers=[
+            logging.FileHandler(log_file),
+        ],
+        style="{",
+    )
+
+    logger = logging.getLogger("gsMap.pipeline")
+    logger.info("Starting pipeline with configuration: %s", config)
+    pipeline_start_time = time.time()
+
+    # Step 1: Find latent representations
+    if config.latent_representation is not None:
+        logger.warning(
+            f"Using the provided latent representation: {config.latent_representation} in {config.hdf5_path}. This would skip the Find_latent_representations step."
+        )
+        logger.info(
+            "Skipping step 1: Find latent representations, as latent representation is provided."
+        )
+        latent_to_gene_input_hdf5_path = config.hdf5_path
+    else:
+        latent_to_gene_input_hdf5_path = None
+        logger.info(
+            "No latent representation provided. Will run the Find_latent_representations step."
+        )
+        find_latent_config = FindLatentRepresentationsConfig(
+            workdir=config.workdir,
+            input_hdf5_path=config.hdf5_path,
+            sample_name=config.sample_name,
+            annotation=config.annotation,
+            data_layer=config.data_layer,
+        )
+
+        # Step 1: Find latent representations
+        start_time = time.time()
+
+        logger.info("Step 1: Finding latent representations")
+        if Path(find_latent_config.hdf5_with_latent_path).exists():
+            logger.info(
+                f"Find latent representations already done. Results saved at {find_latent_config.hdf5_with_latent_path}. Skipping..."
+            )
+        else:
+            run_find_latent_representation(find_latent_config)
+        end_time = time.time()
+        logger.info(f"Step 1 completed in {format_duration(end_time - start_time)}.")
+
+    latent_to_gene_config = LatentToGeneConfig(
+        input_hdf5_path=latent_to_gene_input_hdf5_path,
+        workdir=config.workdir,
+        sample_name=config.sample_name,
+        annotation=config.annotation,
+        latent_representation=config.latent_representation,
+        num_neighbour=config.num_neighbour,
+        num_neighbour_spatial=config.num_neighbour_spatial,
+        homolog_file=config.homolog_file,
+        gM_slices=config.gM_slices,
+    )
+
+    ldscore_config = GenerateLDScoreConfig(
+        workdir=config.workdir,
+        sample_name=config.sample_name,
+        chrom="all",
+        bfile_root=config.bfile_root,
+        keep_snp_root=config.keep_snp_root,
+        gtf_annotation_file=config.gtffile,
+        spots_per_chunk=5_000,
+        baseline_annotation_dir=config.baseline_annotation_dir,
+        SNP_gene_pair_dir=config.SNP_gene_pair_dir,
+        ldscore_save_format="quick_mode",
+    )
+
+    # Step 2: Latent to gene
+    start_time = time.time()
+    logger.info("Step 2: Mapping latent representations to genes")
+    if Path(latent_to_gene_config.mkscore_feather_path).exists():
+        logger.info(
+            f"Latent to gene mapping already done. Results saved at {latent_to_gene_config.mkscore_feather_path}. Skipping..."
+        )
+    else:
+        run_latent_to_gene(latent_to_gene_config)
+    end_time = time.time()
+    logger.info(f"Step 2 completed in {format_duration(end_time - start_time)}.")
+
+    # Step 3: Generate LDScores
+    start_time = time.time()
+    logger.info("Step 3: Generating LDScores")
+
+    # check if LDscore has been generated by the done file
+    ldsc_done_file = (
+        Path(ldscore_config.ldscore_save_dir) / f"{config.sample_name}_generate_ldscore.done"
+    )
+    if ldsc_done_file.exists():
+        logger.info(
+            f"Basic LDScore generation already done. Results saved at {ldscore_config.ldscore_save_dir}. Skipping..."
+        )
+    else:
+        run_generate_ldscore(ldscore_config)
+        end_time = time.time()
+        logger.info(f"Step 3 completed in {format_duration(end_time - start_time)}.")
+        # create a done file
+        ldsc_done_file.touch()
+
+    # Step 4: Spatial LDSC
+    start_time = time.time()
+    logger.info("Step 4: Running spatial LDSC")
+
+    sumstats_config = config.sumstats_config_dict
+    for trait_name in sumstats_config:
+        logger.info("Running spatial LDSC for trait: %s", trait_name)
+        # detect if the spatial LDSC has been done:
+        spatial_ldsc_result_file = (
+            Path(config.ldsc_save_dir) / f"{config.sample_name}_{trait_name}.csv.gz"
+        )
+
+        if spatial_ldsc_result_file.exists():
+            logger.info(
+                f"Spatial LDSC already done for trait {trait_name}. Results saved at {spatial_ldsc_result_file}. Skipping..."
+            )
+            continue
+
+        spatial_ldsc_config_trait = SpatialLDSCConfig(
+            workdir=config.workdir,
+            sumstats_file=sumstats_config[trait_name],
+            trait_name=trait_name,
+            w_file=config.w_file,
+            sample_name=config.sample_name,
+            # ldscore_save_dir=spatial_ldsc_config.ldscore_save_dir,
+            # ldsc_save_dir=spatial_ldsc_config.ldsc_save_dir,
+            num_processes=config.max_processes,
+            ldscore_save_format="quick_mode",
+            snp_gene_weight_adata_path=config.snp_gene_weight_adata_path,
+        )
+        run_spatial_ldsc(spatial_ldsc_config_trait)
+    end_time = time.time()
+    logger.info(f"Step 4 completed in {format_duration(end_time - start_time)}.")
+
+    # Step 5: Cauchy combination test
+    start_time = time.time()
+    logger.info("Step 6: Running Cauchy combination test")
+    for trait_name in sumstats_config:
+        # check if the cauchy combination has been done
+        cauchy_result_file = config.get_cauchy_result_file(trait_name)
+        if cauchy_result_file.exists():
+            logger.info(
+                f"Cauchy combination already done for trait {trait_name}. Results saved at {cauchy_result_file}. Skipping..."
+            )
+            continue
+        cauchy_config = CauchyCombinationConfig(
+            workdir=config.workdir,
+            sample_name=config.sample_name,
+            annotation=config.annotation,
+            trait_name=trait_name,
+        )
+        run_Cauchy_combination(cauchy_config)
+    end_time = time.time()
+    logger.info(f"Step 5 completed in {format_duration(end_time - start_time)}.")
+
+    # Step 6: Generate final report
+    for trait_name in sumstats_config:
+        logger.info("Running final report generation for trait: %s", trait_name)
+        report_config = ReportConfig(
+            workdir=config.workdir,
+            sample_name=config.sample_name,
+            annotation=config.annotation,
+            trait_name=trait_name,
+            plot_type="all",
+            top_corr_genes=50,
+            selected_genes=None,
+            sumstats_file=sumstats_config[trait_name],
+        )
+        gsMap_report_file = report_config.get_gsMap_report_file(trait_name)
+        if Path(gsMap_report_file).exists():
+            logger.info(
+                f"Final report already generated for trait {trait_name}. Results saved at {gsMap_report_file}. Skipping..."
+            )
+            continue
+
+        # Create the run parameters dictionary for each trait
+        run_parameter_dict = {
+            "Sample Name": config.sample_name,
+            "Trait Name": trait_name,
+            "Summary Statistics File": sumstats_config[trait_name],
+            "HDF5 Path": config.hdf5_path,
+            "Annotation": config.annotation,
+            "Number of Processes": config.max_processes,
+            "Spatial LDSC Save Directory": config.ldsc_save_dir,
+            "Cauchy Directory": config.cauchy_save_dir,
+            "Report Directory": config.get_report_dir(trait_name),
+            "gsMap Report File": config.get_gsMap_report_file(trait_name),
+            "Gene Diagnostic Info File": config.get_gene_diagnostic_info_save_path(trait_name),
+            "Spending Time": format_duration(time.time() - pipeline_start_time),
+        }
+
+        # Pass the run parameter dictionary to the report generation function
+        run_report(report_config, run_parameters=run_parameter_dict)
+
+    logger.info("Pipeline completed successfully.")

gsMap/setup.py

@@ -2,4 +2,4 @@
 import setuptools
 
 if __name__ == "__main__":
-    setuptools.setup(name='gsMap')
+    setuptools.setup(name="gsMap")