SYMBOL INDEX (103 symbols across 7 files)

FILE: cpa/api.py
  class API (line 23) | class API:
    method __init__ (line 28) | def __init__(
    method load_from_old (line 196) | def load_from_old(self, pretrained):
    method print_args (line 210) | def print_args(self):
    method load (line 213) | def load(self, pretrained):
    method train (line 226) | def train(
    method save (line 355) | def save(self, filename):
    method _init_pert_embeddings (line 366) | def _init_pert_embeddings(self):
    method get_drug_embeddings (line 378) | def get_drug_embeddings(self, dose=1.0, return_anndata=True):
    method _init_covars_embeddings (line 409) | def _init_covars_embeddings(self):
    method get_covars_embeddings_combined (line 438) | def get_covars_embeddings_combined(self, return_anndata=True):
    method get_covars_embeddings (line 456) | def get_covars_embeddings(self, covars_tgt, return_anndata=True):
    method _get_drug_encoding (line 477) | def _get_drug_encoding(self, drugs, doses=None):
    method mix_drugs (line 506) | def mix_drugs(self, drugs_list, doses_list=None, return_anndata=True):
    method latent_dose_response (line 550) | def latent_dose_response(
    method latent_dose_response2D (line 613) | def latent_dose_response2D(
    method compute_comb_emb (line 687) | def compute_comb_emb(self, thrh=30):
    method compute_uncertainty (line 746) | def compute_uncertainty(self, cov, pert, dose, thrh=30):
    method predict (line 803) | def predict(
    method get_latent (line 973) | def get_latent(
    method get_response (line 1073) | def get_response(
    method get_response_reference (line 1164) | def get_response_reference(self, perturbations=None):
    method get_response2D (line 1222) | def get_response2D(
    method evaluate_r2 (line 1332) | def evaluate_r2(self, dataset, genes_control, adata_random=None):
  function get_reference_from_combo (line 1432) | def get_reference_from_combo(perturbations_list, datasets, splits=["trai...
  function linear_interp (line 1466) | def linear_interp(y1, y2, x1, x2, x):
  function evaluate_r2_benchmark (line 1473) | def evaluate_r2_benchmark(cpa_api, datasets, pert_category, pert_categor...

FILE: cpa/data.py
  function ranks_to_df (line 18) | def ranks_to_df(data, key="rank_genes_groups"):
  function check_adata (line 42) | def check_adata(adata, special_fields):
  class Dataset (line 65) | class Dataset:
    method __init__ (line 66) | def __init__(
    method subset (line 292) | def subset(self, split, condition="all"):
    method __getitem__ (line 296) | def __getitem__(self, i):
    method __len__ (line 303) | def __len__(self):
  class SubDataset (line 307) | class SubDataset:
    method __init__ (line 312) | def __init__(self, dataset, indices):
    method __getitem__ (line 339) | def __getitem__(self, i):
    method subset_condition (line 346) | def subset_condition(self, control=True):
    method __len__ (line 350) | def __len__(self):
  function load_dataset_splits (line 354) | def load_dataset_splits(

FILE: cpa/helper.py
  function _convert_mean_disp_to_counts_logits (line 21) | def _convert_mean_disp_to_counts_logits(mu, theta, eps=1e-6):
  function rank_genes_groups_by_cov (line 45) | def rank_genes_groups_by_cov(
  function rank_genes_groups (line 136) | def rank_genes_groups(
  function evaluate_r2_ (line 254) | def evaluate_r2_(adata, pred_adata, condition_key, sampled=False, de_gen...
  function evaluate_mmd (line 295) | def evaluate_mmd(adata, pred_adata, condition_key, de_genes_dict=None):
  function evaluate_emd (line 321) | def evaluate_emd(adata, pred_adata, condition_key, de_genes_dict=None):
  function pairwise_distance (line 354) | def pairwise_distance(x, y):
  function gaussian_kernel_matrix (line 362) | def gaussian_kernel_matrix(x, y, alphas):
  function mmd_loss_calc (line 387) | def mmd_loss_calc(source_features, target_features):

FILE: cpa/model.py
  class NBLoss (line 11) | class NBLoss(torch.nn.Module):
    method __init__ (line 12) | def __init__(self):
    method forward (line 15) | def forward(self, mu, y, theta, eps=1e-8):
  function _nan2inf (line 46) | def _nan2inf(x):
  class MLP (line 49) | class MLP(torch.nn.Module):
    method __init__ (line 54) | def __init__(self, sizes, batch_norm=True, last_layer_act="linear"):
    method forward (line 77) | def forward(self, x):
  class GeneralizedSigmoid (line 85) | class GeneralizedSigmoid(torch.nn.Module):
    method __init__ (line 91) | def __init__(self, dim, device, nonlin="sigmoid"):
    method forward (line 107) | def forward(self, x):
    method one_drug (line 117) | def one_drug(self, x, i):
  class CPA (line 128) | class CPA(torch.nn.Module):
    method __init__ (line 133) | def __init__(
    method set_hparams_ (line 286) | def set_hparams_(self, hparams):
    method move_inputs_ (line 322) | def move_inputs_(self, genes, drugs, covariates):
    method compute_drug_embeddings_ (line 334) | def compute_drug_embeddings_(self, drugs):
    method predict (line 349) | def predict(
    method early_stopping (line 403) | def early_stopping(self, score):
    method update (line 419) | def update(self, genes, drugs, covariates):
    method defaults (line 509) | def defaults(self):

FILE: cpa/plotting.py
  class CPAVisuals (line 23) | class CPAVisuals:
    method __init__ (line 30) | def __init__(
    method plot_latent_embeddings (line 90) | def plot_latent_embeddings(
    method plot_contvar_response2D (line 165) | def plot_contvar_response2D(
    method plot_contvar_response (line 274) | def plot_contvar_response(
    method plot_scatter (line 366) | def plot_scatter(
  function log10_with0 (line 435) | def log10_with0(x):
  function get_palette (line 441) | def get_palette(n_colors, palette_name="Set1"):
  function fast_dimred (line 454) | def fast_dimred(emb, method="KernelPCA"):
  function plot_dose_response (line 478) | def plot_dose_response(
  function plot_uncertainty_comb_dose (line 640) | def plot_uncertainty_comb_dose(
  function plot_uncertainty_dose (line 771) | def plot_uncertainty_dose(
  function save_to_file (line 882) | def save_to_file(fig, file_name, file_format=None):
  function plot_embedding (line 897) | def plot_embedding(
  function get_colors (line 1011) | def get_colors(labels, palette=None, palette_name=None):
  function plot_similarity (line 1019) | def plot_similarity(
  function mean_plot (line 1074) | def mean_plot(
  function plot_r2_matrix (line 1211) | def plot_r2_matrix(pred, adata, de_genes=None, **kwds):
  function arrange_history (line 1268) | def arrange_history(history):
  class CPAHistory (line 1273) | class CPAHistory:
    method __init__ (line 1278) | def __init__(self, cpa_api, fileprefix=None):
    method print_time (line 1326) | def print_time(self):
    method plot_losses (line 1329) | def plot_losses(self, filename=None):
    method plot_r2_metrics (line 1363) | def plot_r2_metrics(self, epoch_min=0, filename=None):
    method plot_disentanglement_metrics (line 1409) | def plot_disentanglement_metrics(self, epoch_min=0, filename=None):

FILE: cpa/train.py
  function pjson (line 19) | def pjson(s):
  function _convert_mean_disp_to_counts_logits (line 25) | def _convert_mean_disp_to_counts_logits(mu, theta, eps=1e-6):
  function evaluate_disentanglement (line 48) | def evaluate_disentanglement(autoencoder, dataset):
  function evaluate_r2 (line 117) | def evaluate_r2(autoencoder, dataset, genes_control):
  function evaluate (line 199) | def evaluate(autoencoder, datasets):
  function prepare_cpa (line 243) | def prepare_cpa(args, state_dict=None):
  function train_cpa (line 277) | def train_cpa(args, return_model=False):
  function parse_arguments (line 368) | def parse_arguments():

FILE: tests/test.py
  function sim_adata (line 10) | def sim_adata():