Ramachandran and side-chain outlier¶

def get_outlier_data(pdb_id):
    """
    This function will GET the outlier data from
    the PDBe API using the make_request() function

    :param pdb_id: String
    :return: JSON
    """
    # Check if the provided PDB id is valid
    # There is no point in making an API call
    # with bad PDB ids
    if not re.match("[0-9][A-Za-z][A-Za-z0-9]{2}", pdb_id):
        print("Invalid PDB id")
        return None

    # GET the outlier data
    outlier_data = make_request(outlier_data_url, "get", pdb_id)

    # Check if there is data
    if not outlier_data:
        print("No data found")
        return None

    return outlier_data

def list_number_of_outliers_per_model(pdb_id):
    """
    This function calls get_outlier_data() and
    then list the number of Ramachandran and
    side-chain outliers per model in the PDB entry

    :param pdb_id: String,
    :return: None
    """
    # We will collect the number of outlier
    # residues per model
    outliers = {"ramachandran_outliers": {}, "sidechain_outliers": {}}

    # Getting outlier data
    outlier_data = get_outlier_data(pdb_id)

    # If there is no data, return None
    if not outlier_data:
        return None

    # Iterate through both Ramachandran and
    # side-chain outliers
    for key in outliers.keys():
        for i in range(len(outlier_data[pdb_id][key])):
            # Grab the model id
            model_id = outlier_data[pdb_id][key][i]["model_id"]
            # If the model id was not observed before, add to
            # the outliers dictionary with the corresponding
            # outlier type, otherwise increase the count by one
            if model_id not in outliers[key].keys():
                outliers[key][model_id] = 1
            else:
                outliers[key][model_id] += 1

    print("Ramachandran outliers:")
    for model in outliers["ramachandran_outliers"].keys():
        print("Model %i has %i Ramachandran outliers" % (model,
                                                         outliers["ramachandran_outliers"][model]))
    print()
    print("Side-chain outliers:")
    for model in outliers["sidechain_outliers"].keys():
        print("Model %i has %i Side-chain outliers" % (model,
                                                       outliers["sidechain_outliers"][model]))

list_number_of_outliers_per_model("2aqa")

def list_outlier_residues_of_model(pdb_id, model_id):
    """
    This function calls get_outlier_data()
    and lists all outlier residues of a
    specific model

    :param pdb_id: String,
    :param model_id: Integer,
    :return: None
    """

    outlier_data = get_outlier_data(pdb_id)

    # If there is no data, return None
    if not outlier_data:
        return None

    # Iterate thourgh the outlier types
    for outlier_type in outlier_data[pdb_id].keys():
        # Loop through all the residue-level outlier information
        for i in range(len(outlier_data[pdb_id][outlier_type])):
            outlier_information = outlier_data[pdb_id][outlier_type][i]
            # Only process outlier information that corresponds to
            # the model id of interest
            if outlier_information["model_id"] != model_id:
                continue

            # Set outlier type labels
            if outlier_type == "ramachandran_outliers":
                label = "Ramachandran"
            else:
                label = "side-chain"

            residue = outlier_information["residue_number"]
            chain = outlier_information["chain_id"]
            entity = outlier_information["entity_id"]
            print ("Residue %i in chain %s of entity %i is a %s outlier" % (residue,
                                                                            chain,
                                                                            entity,
                                                                            label))

print("Listing outlier residues for Model #7 of PDB entry 2aqa:")
list_outlier_residues_of_model("2aqa", 7)