def compute_protein_coverage(experiment1:Experiment,experiment2:Experiment,progress_bar:bool=True)->Dict[str,Dict[str,np.ndarray]]:
""" Compute the difference in protein coverage among the two input experiments
Args:
experiment1 (Experiment): The first experiment containing the protein and peptides derived from the first HLA-set
experiment2 (Experiment): The second experiment containing the protein and peptides derived from the second HLA-set
progress_bar (bool): A boolean flag for controlling the progress bar, if true, a progress bar is shown, defaults to True.
Returns:
Dict[str,Dict[str,np.ndarray]]: Returns a nested dict containing protein identifiers as a keys and a dict as a value, the dict contain two arrays as values,\
the first contain protein coverage in the first HLA-Set and the second contain the coverage in the second HLA-set.\
The results dictionary only contain coverage for proteins observed in the two sets.
"""
protein_experiment_one:List[str]=experiment1.get_proteins()
protein_experiment_two:List[str]=experiment2.get_proteins()
present_in_both:List[str]=protein_experiment_one.intersection(protein_experiment_two)
results:Dict[str,Dict[str,np.ndarray]]=dict()
if progress_bar:
for protein in present_in_both:
temp_dict={
'_'.join(experiment1.get_hla_set().get_names()):experiment1.get_mapped_protein(protein),
'_'.join(experiment2.get_hla_set().get_names()):experiment2.get_mapped_protein(protein)
}
results.update({protein:temp_dict})
else:
for protein in present_in_both:
temp_dict={
'_'.join(experiment1.get_hla_set().get_names()):experiment1.get_mapped_protein(protein),
'_'.join(experiment2.get_hla_set().get_names()):experiment2.get_mapped_protein(protein)
}
results.update({protein:temp_dict})
return results
def get_binnary_protein_overlap(exp1:Experiment, exp2:Experiment)->Proteins:
"""compare the protein overlap between two experimental objects.
:param exp1: an instance of class Experiment.
:type exp1: Experiment
:param exp2: an instance of class Experiment.
:type exp2: Experiment
:return: a list of proteins that have been identified or inferred in both experiments.
:rtype: Proteins
"""
protein_one=exp1.get_proteins()
protein_two=exp2.get_proteins()
return list(protein_one.intersection(protein_two))
def compute_jaccard_index(exp1:Experiment,exp2:Experiment, level:str='peptide')->float:
"""Compute Jaccard index between samples two samples
Args:
exp1 (Experiment): The first experimental instance
exp2 (Experiment): The first experimental instance
level (str): The level of computing the overlap between samples, can be any of peptide or protein
Returns:
float: Jaccard index computed with regard to the to provide level
"""
if level != 'peptide' and level != 'protein':
raise ValueError(f"Level: {level} is not supported, currently only level, peptide and protein are supported")
if level=='peptide':
return (len(exp1.get_peptides().intersection(exp2.get_peptides())) / len(exp1.get_peptides().union(exp2.get_peptides())))
if level=='protein':
return (len(exp1.get_proteins().intersection(exp2.get_proteins())) / len(exp1.get_proteins().union(exp2.get_proteins())))
def compute_expression_correlation(exp1: Experiment,
exp2: Experiment) -> float:
"""compute the correlation in the gene expression between two experiments by constructing a union
of all the proteins expressed in the first and second experiments, extract the gene expression
of these genes and then compute the correlation using SciPy stat module.
:param exp1: The first experimental object
:type exp1: Experiment
:param exp2: The second experimental object
:type exp2: Experiment
:return: the correlation in gene expression of the proteins inferred in the provided pair of experiment
:rtype: float
"""
# get the expression tables
protein_exp1: Set[str] = set(exp1.get_proteins())
protein_exp2: Set[str] = set(exp2.get_proteins())
unique_proteins = list(protein_exp1.union(protein_exp2))
# get the gene id
prot2Ense: pd.DataFrame = map_from_uniprot_gene(unique_proteins)
# allocate lists to hold the results
gene_expression_exp1: List[float] = []
gene_expression_exp2: List[float] = []
# get the expression from experiment one
for prot in unique_proteins:
temp_df: pd.DataFrame = prot2Ense.loc[prot2Ense.iloc[:, 0] == prot]
if temp_df.shape[0] == 1: # we got only one match
gene_id: str = temp_df['Gene-ID'].tolist()[0]
try:
gene_expression_exp1.append(
exp1.get_tissue().get_expression_profile(
).get_gene_id_expression(gene_id=gene_id))
except KeyError:
gene_expression_exp1.append(-1)
else:
temp_gene_expression: List[float] = []
for gene in temp_df.iloc[:, 1].tolist():
try:
temp_gene_expression.append(
exp1.get_tissue().get_expression_profile(
).get_gene_id_expression(gene_id=gene))
except KeyError:
temp_gene_expression.append(-1)
# filter the temp_genes for default value
temp_gene_process: List[str] = [
elem for elem in temp_gene_expression if elem != -1
]
# add the gene expression as the average if all values have been filtered
if len(temp_gene_process) == 0:
gene_expression_exp1.append(-1)
else:
gene_expression_exp1.append(np.mean(temp_gene_process))
# ge the expression from exp2:
for prot in unique_proteins:
temp_df: pd.DataFrame = prot2Ense.loc[prot2Ense.iloc[:, 0] == prot]
if temp_df.shape[0] == 1: # we got only one match
gene_id: str = temp_df['Gene-ID'].tolist()[0]
try:
gene_expression_exp2.append(
exp2.get_tissue().get_expression_profile(
).get_gene_id_expression(gene_id=gene_id))
except KeyError:
gene_expression_exp2.append(-1)
else:
temp_gene_expression: List[float] = []
for gene in temp_df.iloc[:, 1].tolist():
try:
temp_gene_expression.append(
exp2.get_tissue().get_expression_profile(
).get_gene_id_expression(gene_id=gene))
except KeyError:
temp_gene_expression.append(-1)
# filter the temp_genes for default value
temp_gene_process: List[str] = [
elem for elem in temp_gene_expression if elem != -1
]
# add the gene expression as the average
if len(temp_gene_process) == 0:
gene_expression_exp2.append(-1)
else:
gene_expression_exp2.append(np.mean(temp_gene_process))
# compute construct a dataframe
temp_paired_exp_df: pd.DataFrame = pd.DataFrame({
'exp2':
gene_expression_exp1,
'exp1':
gene_expression_exp2
})
# filter the un-mapped from exp1
temp_paired_exp_df = temp_paired_exp_df.loc[
temp_paired_exp_df.iloc[:, 0] != -1, ]
# filter the unmapped from exp2
temp_paired_exp_df = temp_paired_exp_df.loc[
temp_paired_exp_df.iloc[:, 1] != -1, ]
# compute the correlation
return pearsonr(temp_paired_exp_df.iloc[:, 0],
temp_paired_exp_df.iloc[:, 1])[0]