AlphaBase

import alphabase

# Chemical constants and calculations
from alphabase.constants.aa import AA_ASCII_MASS, calc_AA_masses
from alphabase.constants.atom import MASS_PROTON, calc_mass_from_formula
from alphabase.constants.modification import MOD_DF, add_new_modifications

# Fragment and precursor calculations
from alphabase.peptide.fragment import get_charged_frag_types, create_fragment_mz_dataframe
from alphabase.peptide.precursor import update_precursor_mz, calc_precursor_isotope_info
from alphabase.peptide.mobility import ccs_to_mobility_for_df, mobility_to_ccs_for_df

# Spectral library operations
from alphabase.spectral_library.base import SpecLibBase
from alphabase.spectral_library.decoy import SpecLibDecoy, DIANNDecoyGenerator
from alphabase.spectral_library.flat import SpecLibFlat

# PSM reading from various search engines
from alphabase.psm_reader import MaxQuantReader, DiannReader, SpectronautReader

# Quantification data processing
from alphabase.quantification.quant_reader.quant_reader_manager import import_data
from alphabase.quantification.quant_reader.longformat_reader import LongFormatReader

# SMILES and cheminformatics
from alphabase.smiles.peptide import PeptideSmilesEncoder
from alphabase.smiles.smiles import AminoAcidModifier

# High-performance I/O
from alphabase.io.hdf import HDF_File
from alphabase.io.tempmmap import array, zeros

import pandas as pd
from alphabase.constants.aa import calc_AA_masses
from alphabase.constants.modification import calc_modification_mass
from alphabase.peptide.fragment import create_fragment_mz_dataframe
from alphabase.spectral_library.base import SpecLibBase

# Calculate amino acid masses for peptide sequences
sequences = ['PEPTIDE', 'SEQUENCE', 'EXAMPLE']
aa_masses = calc_AA_masses(sequences)

# Calculate modification masses
mod_sequences = ['PEPTIDE[Oxidation (M)]', 'SEQUENCE[Phospho (STY)]']
mod_masses = calc_modification_mass(mod_sequences)

# Create a spectral library
spec_lib = SpecLibBase()

# Load precursor data
precursor_df = pd.DataFrame({
    'sequence': ['PEPTIDE', 'SEQUENCE'],
    'mods': ['', 'Phospho (STY)@2'],
    'charge': [2, 3],
    'proteins': ['P12345', 'P67890']
})

spec_lib.precursor_df = precursor_df
spec_lib.refine_df()

# Calculate precursor m/z values
spec_lib.calc_precursor_mz()

# Generate fragment m/z dataframe
frag_types = ['b++', 'y++', 'b+', 'y+']
spec_lib.calc_fragment_mz_df(frag_types)

print(f"Created spectral library with {len(spec_lib.precursor_df)} precursors")

# Core constants
AA_ASCII_MASS: np.ndarray  # 128-length array of AA masses
MASS_PROTON: float = 1.00727646688
MOD_DF: pd.DataFrame  # Complete modification database

# Mass calculation functions
def calc_AA_masses(sequences: List[str]) -> np.ndarray: ...
def calc_mass_from_formula(formula: str) -> float: ...
def calc_modification_mass(mod_sequences: List[str]) -> np.ndarray: ...

def get_charged_frag_types(frag_types: List[str], charges: List[int]) -> List[str]: ...
def create_fragment_mz_dataframe(precursor_df: pd.DataFrame, frag_types: List[str]) -> pd.DataFrame: ...
def calc_b_y_and_peptide_masses_for_same_len_seqs(sequences: List[str]) -> tuple: ...

class SpecLibBase:
    precursor_df: pd.DataFrame
    fragment_mz_df: pd.DataFrame
    fragment_intensity_df: pd.DataFrame
    
    def copy(self) -> 'SpecLibBase': ...
    def append(self, other: 'SpecLibBase') -> None: ...
    def calc_precursor_mz(self) -> None: ...
    def calc_fragment_mz_df(self, frag_types: List[str]) -> None: ...
    def save_hdf(self, filepath: str) -> None: ...
    def load_hdf(self, filepath: str) -> None: ...

class PSMReaderBase:
    def import_file(self, filepath: str) -> pd.DataFrame: ...
    def get_modification_mapping(self) -> dict: ...

# Available readers
class MaxQuantReader(PSMReaderBase): ...
class DiannReader(PSMReaderBase): ...
class SpectronautReader(PSMReaderBase): ...
# ... and 7 more search engine readers

class HDF_File:
    def __init__(self, filepath: str, mode: str = 'r'): ...
    def __getitem__(self, key: str): ...
    def __setitem__(self, key: str, value): ...

def array(shape: tuple, dtype=np.float64) -> np.ndarray: ...
def zeros(shape: tuple, dtype=np.float64) -> np.ndarray: ...
def clear() -> None: ...

def import_data(data_path: str, data_type: str = None, config_dict: dict = None) -> pd.DataFrame: ...
class LongFormatReader: ...
class WideFormatReader: ...
class ConfigDictLoader: ...

def update_precursor_mz(precursor_df: pd.DataFrame, batch_size: int = 100000) -> None: ...
def calc_precursor_isotope_info(precursor_df: pd.DataFrame, max_isotope: int = 6) -> None: ...
def ccs_to_mobility_for_df(precursor_df: pd.DataFrame, vendor_type: str = 'bruker') -> None: ...
def hash_precursor_df(precursor_df: pd.DataFrame, seed: int = 42) -> None: ...

class SpecLibDecoy: ...
class DIANNDecoyGenerator: ...
class SpecLibFlat: ...
class LibraryReaderBase: ...
class Schema: ...

class AminoAcidModifier: ...
class PeptideSmilesEncoder: ...
def calculate_molecular_descriptors(smiles: str) -> dict: ...
def predict_retention_time_from_smiles(smiles: str, model_type: str = 'krokhin') -> float: ...

def read_fasta_file(filepath: str) -> Iterator[tuple[str, str]]: ...
def get_uniprot_gene_name(description: str) -> str: ...