admin管理员组

文章数量:1027628

内容复习

作者，Evil Genius

今天我们复习，banksy。

随着经验积累的不断增多，回头看一些方法又会有不一样的理解。

我们分享了很多邻域的分析，主要集中在细胞的细胞邻域，而banksy主要集中在细胞的分子邻域。

就是一个细胞周围环境细胞的基因表达的平均值，作为该细胞的特征进行聚类分析。

针对的平台包括MERFISH, CosMX, CODEX，Xenium等，但是随着panel数量的增多，banksy也慢慢退出舞台了。说明其核心是一种数据增强的方法。

其中Seurat的HD教程也采用了banksy（8um）分析，说明HD本身数据信息不够，要进行一定程度的数据增强。

核心原理如下

核心就是考虑邻域的分子环境。数据增强之后对于本身的聚类分析是有好处的。

其中最核心的地方就是，依据分子邻域特征区分细胞亚型。

最后看看代码，我们现在基本都要转向Python版本了。

代码语言：javascript代码运行次数：0运行复制
import os
import numpy as np
import warnings
warnings.filterwarnings("ignore")

import scanpy as sc
sc.logging.print_header()
sc.set_figure_params(facecolor="white", figsize=(8, 8))
sc.settings.verbosity = 1 # errors (0), warnings (1), info (2), hints (3)

import random
# Note that BANKSY itself is deterministic, here the seeds affect the umap clusters and leiden partition
seed = 0
np.random.seed(seed)
random.seed(seed)

# %%
# Define File paths
file_path = os.path.join("data", "slide_seq", "v1")
gcm_filename = "Cerebellum_MappedDGEForR.csv"

# (Optional) Arguments for load_data only if annadata is not present
locations_filename = "locations.csv"
adata_filename = "spatial.h5ad"

from banksy_utils.load_data import load_adata

# To either load data from .h5ad directly or convert raw data to .h5ad format
load_adata_directly = True

# Keys to specify coordinate indexes in the anndata Object
coord_keys = ('xcoord', 'ycoord', 'coord_xy')

raw_y, raw_x, adata = load_adata(file_path,
                                     load_adata_directly, 
                                     adata_filename, 
                                     gcm_filename, 
                                     locations_filename,
                                     coord_keys)

# %%
adata.var_names_make_unique()
adata.var["mt"] = adata.var_names.str.startswith("MT-")

# Calulates QC metrics and put them in place to the adata object
sc.pp.calculate_qc_metrics(adata, 
                           qc_vars=["mt"], 
                           log1p=True, 
                           inplace=True)


# %%
from banksy_utils.filter_utils import filter_cells

# Filter cells with each respective filters
adata = filter_cells(adata, 
             min_count=40, 
             max_count=1000, 
             MT_filter=20, 
             gene_filter=10)

# %%
from banksy_utils.filter_utils import normalize_total, filter_hvg

# Normalizes the anndata dataset
adata = normalize_total(adata)

# %%
adata, adata_allgenes = filter_hvg(adata,
            n_top_genes = 2000,
            flavor="seurat")

# %%
from banksy.main import median_dist_to_nearest_neighbour

# set params
# ==========
plot_graph_weights = True
k_geom = 15 # only for fixed type
max_m = 1 # azumithal transform up to kth order
nbr_weight_decay = "scaled_gaussian" # can also be "reciprocal", "uniform" or "ranked"

# Find median distance to closest neighbours, the median distance will be `sigma`
nbrs = median_dist_to_nearest_neighbour(adata, key = coord_keys[2])

from banksy.initialize_banksy import initialize_banksy

banksy_dict = initialize_banksy(adata,
                coord_keys,
                k_geom,
                nbr_weight_decay = nbr_weight_decay,
                max_m = max_m,
                plt_edge_hist = True,
                plt_nbr_weights = True,
                plt_agf_angles = False 
                )

from banksy.main import concatenate_all
from banksy.embed_banksy import generate_banksy_matrix

# The following are the main hyperparameters for BANKSY
resolutions = [0.7] # clustering resolution for UMAP
pca_dims = [20] # Dimensionality in which PCA reduces to
lambda_list = [0.2] # list of lambda parameters

banksy_dict, banksy_matrix = generate_banksy_matrix(adata,
                                                    banksy_dict,
                                                    lambda_list,
                                                    max_m)

banksy_dict["nonspatial"] = {
    # Here we simply append the nonspatial matrix (adata.X) to obtain the nonspatial clustering results
    0.0: {"adata": concatenate_all([adata.X], 0, adata=adata), }
}

print(banksy_dict['nonspatial'][0.0]['adata'])

from banksy_utils.umap_pca import pca_umap

pca_umap(banksy_dict,
         pca_dims = pca_dims,
         add_umap = True
         )


from banksy.cluster_methods import run_Leiden_partition

results_df, max_num_labels = run_Leiden_partition(
    banksy_dict,
    resolutions,
    num_nn = 50,
    num_iterations = -1,
    partition_seed = 1234,
    match_labels = True,
)


from banksy.plot_banksy import plot_results

c_map =  'tab20' # specify color map
weights_graph =  banksy_dict['scaled_gaussian']['weights'][1]

plot_results(
    results_df,
    weights_graph,
    c_map,
    match_labels = True,
    coord_keys = coord_keys,
    max_num_labels  =  max_num_labels, 
    save_path = os.path.join(file_path, 'tmp_png'),
    save_fig = False, # Save Spatial Plot Only
    save_fullfig = True # Save Full Plot
)

生活很好，有你更好

内容复习

作者，Evil Genius

今天我们复习，banksy。

随着经验积累的不断增多，回头看一些方法又会有不一样的理解。

我们分享了很多邻域的分析，主要集中在细胞的细胞邻域，而banksy主要集中在细胞的分子邻域。

就是一个细胞周围环境细胞的基因表达的平均值，作为该细胞的特征进行聚类分析。

针对的平台包括MERFISH, CosMX, CODEX，Xenium等，但是随着panel数量的增多，banksy也慢慢退出舞台了。说明其核心是一种数据增强的方法。

其中Seurat的HD教程也采用了banksy（8um）分析，说明HD本身数据信息不够，要进行一定程度的数据增强。

核心原理如下

核心就是考虑邻域的分子环境。数据增强之后对于本身的聚类分析是有好处的。

其中最核心的地方就是，依据分子邻域特征区分细胞亚型。

最后看看代码，我们现在基本都要转向Python版本了。

代码语言：javascript代码运行次数：0运行复制
import os
import numpy as np
import warnings
warnings.filterwarnings("ignore")

import scanpy as sc
sc.logging.print_header()
sc.set_figure_params(facecolor="white", figsize=(8, 8))
sc.settings.verbosity = 1 # errors (0), warnings (1), info (2), hints (3)

import random
# Note that BANKSY itself is deterministic, here the seeds affect the umap clusters and leiden partition
seed = 0
np.random.seed(seed)
random.seed(seed)

# %%
# Define File paths
file_path = os.path.join("data", "slide_seq", "v1")
gcm_filename = "Cerebellum_MappedDGEForR.csv"

# (Optional) Arguments for load_data only if annadata is not present
locations_filename = "locations.csv"
adata_filename = "spatial.h5ad"

from banksy_utils.load_data import load_adata

# To either load data from .h5ad directly or convert raw data to .h5ad format
load_adata_directly = True

# Keys to specify coordinate indexes in the anndata Object
coord_keys = ('xcoord', 'ycoord', 'coord_xy')

raw_y, raw_x, adata = load_adata(file_path,
                                     load_adata_directly, 
                                     adata_filename, 
                                     gcm_filename, 
                                     locations_filename,
                                     coord_keys)

# %%
adata.var_names_make_unique()
adata.var["mt"] = adata.var_names.str.startswith("MT-")

# Calulates QC metrics and put them in place to the adata object
sc.pp.calculate_qc_metrics(adata, 
                           qc_vars=["mt"], 
                           log1p=True, 
                           inplace=True)


# %%
from banksy_utils.filter_utils import filter_cells

# Filter cells with each respective filters
adata = filter_cells(adata, 
             min_count=40, 
             max_count=1000, 
             MT_filter=20, 
             gene_filter=10)

# %%
from banksy_utils.filter_utils import normalize_total, filter_hvg

# Normalizes the anndata dataset
adata = normalize_total(adata)

# %%
adata, adata_allgenes = filter_hvg(adata,
            n_top_genes = 2000,
            flavor="seurat")

# %%
from banksy.main import median_dist_to_nearest_neighbour

# set params
# ==========
plot_graph_weights = True
k_geom = 15 # only for fixed type
max_m = 1 # azumithal transform up to kth order
nbr_weight_decay = "scaled_gaussian" # can also be "reciprocal", "uniform" or "ranked"

# Find median distance to closest neighbours, the median distance will be `sigma`
nbrs = median_dist_to_nearest_neighbour(adata, key = coord_keys[2])

from banksy.initialize_banksy import initialize_banksy

banksy_dict = initialize_banksy(adata,
                coord_keys,
                k_geom,
                nbr_weight_decay = nbr_weight_decay,
                max_m = max_m,
                plt_edge_hist = True,
                plt_nbr_weights = True,
                plt_agf_angles = False 
                )

from banksy.main import concatenate_all
from banksy.embed_banksy import generate_banksy_matrix

# The following are the main hyperparameters for BANKSY
resolutions = [0.7] # clustering resolution for UMAP
pca_dims = [20] # Dimensionality in which PCA reduces to
lambda_list = [0.2] # list of lambda parameters

banksy_dict, banksy_matrix = generate_banksy_matrix(adata,
                                                    banksy_dict,
                                                    lambda_list,
                                                    max_m)

banksy_dict["nonspatial"] = {
    # Here we simply append the nonspatial matrix (adata.X) to obtain the nonspatial clustering results
    0.0: {"adata": concatenate_all([adata.X], 0, adata=adata), }
}

print(banksy_dict['nonspatial'][0.0]['adata'])

from banksy_utils.umap_pca import pca_umap

pca_umap(banksy_dict,
         pca_dims = pca_dims,
         add_umap = True
         )


from banksy.cluster_methods import run_Leiden_partition

results_df, max_num_labels = run_Leiden_partition(
    banksy_dict,
    resolutions,
    num_nn = 50,
    num_iterations = -1,
    partition_seed = 1234,
    match_labels = True,
)


from banksy.plot_banksy import plot_results

c_map =  'tab20' # specify color map
weights_graph =  banksy_dict['scaled_gaussian']['weights'][1]

plot_results(
    results_df,
    weights_graph,
    c_map,
    match_labels = True,
    coord_keys = coord_keys,
    max_num_labels  =  max_num_labels, 
    save_path = os.path.join(file_path, 'tmp_png'),
    save_fig = False, # Save Spatial Plot Only
    save_fullfig = True # Save Full Plot
)

生活很好，有你更好

本文标签： 内容复习

版权声明：本文标题：内容复习 内容由热心网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：http://it.en369.cn/jiaocheng/1747424490a2165720.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。