msfiddle 0.1.0__py3-none-any.whl

msfiddle/__init__.py

@@ -0,0 +1,44 @@
+"""
+msfiddle: A package for predicting chemical formulas from tandem mass spectra
+"""
+
+__version__ = "0.1.0"
+
+# Import main components to make them available at package level
+from .model_tcn import MS2FNet_tcn, FDRNet
+from .utils.mol_utils import vector_to_formula, formula_to_vector
+from .utils.msms_utils import mass_calculator
+from .utils.refine_utils import formula_refinement
+from .main import test_step, rerank_by_fdr
+from .download import check_models_exist, download_models, get_model_path
+
+# Check if models are available and print a message if not
+import os
+import warnings
+import sys
+
+# Skip the warning if we're running the download command
+is_download_command = any('download-models' in arg for arg in sys.argv)
+
+if not is_download_command and not check_models_exist():
+    warnings.warn(
+        "Pre-trained models not found. To download them, run:\n"
+        "    msfiddle-download-models\n\n"
+        "Or from Python:\n"
+        "    from msfiddle import download_models\n"
+        "    download_models()"
+    )
+
+__all__ = [
+    'MS2FNet_tcn',
+    'FDRNet',
+    'formula_refinement',
+    'mass_calculator',
+    'vector_to_formula',
+    'formula_to_vector',
+    'test_step',
+    'rerank_by_fdr',
+    'download_models',
+    'check_models_exist',
+    'get_model_path',
+]

msfiddle/config/fiddle_tcn_casmi.yml

@@ -0,0 +1,113 @@
+# ------------------------
+# CASMI test 
+# ------------------------
+casmi16: 
+  instrument_type: ['LC-ESI-QFT']
+  instrument: ['Q Exactive Plus Orbitrap Thermo Scientific']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M-H]-']
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 10
+
+casmi17:
+  instrument_type: ['LC-ESI-QTOF']
+  instrument: ['LC-ESI-QTOF']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M-H]-']
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 10
+
+# ------------------------
+# model settings
+# ------------------------
+encoding:
+  resolution: 0.2
+  max_mz: 1500
+  max_atom_num: 300
+  use_simulated_precursor_mz: True
+  precursor_type:
+    '[M+H]+': 1
+    '[M-H]-': 2
+    '[M+Na]+': 3
+    '[M+2H]2+': 4
+    '[2M+H]+': 5
+    '[2M-H]-': 6
+    
+  type2charge: 
+    '[M+H]+': '+1'
+    '[M-H]-': '-1'
+    '[M+Na]+': '+1'
+    '[M+2H]2+': '+2'
+    '[2M+H]+': '+1'
+    '[2M-H]-': '-1'
+    
+    '[M+H-H2O]+': '+1'
+    '[M-H2O+H]+': '+1'
+    '[M+H-2H2O]+': '+1'
+    '[M+H-NH3]+': '+1'
+    '[M+H+NH3]+': '+1'
+    '[M+NH4]+': '+1'
+    '[M+H-CH2O2]+': '+1'
+    '[M+H-CH4O2]+': '+1'
+
+    '[M-H-CO2]-': '-1' 
+    '[M-CHO2]-': '-1' 
+    '[M-H-H2O]-': '-1'
+    '[M-H2O-H]+': '-1'
+
+model: 
+  resolution: 0.2
+  max_mz: 1500
+  padding_dim: 20 # 1500 / 0.2 = 7500; 7500 / 2**5 (# pooling layer) = 234.375; 235 * (2**5) = 7520 
+  num_add: 6
+  input_channels: 1
+
+  tcn_channels: [32, 32, 64, 128, 256, 512]
+  tcn_dilations: [1, 2, 4, 8, 8, 8]
+  tcn_kernel_sizes: [45, 43, 41, 39, 37, 35]
+  tcn_dropout: 0.2
+
+  # metadata_dim: 16 
+  add_embedding_dim: 4
+  ce_embedding_dim: 4
+  mass_embedding_dim: 4
+  embedding_dim: 512
+  
+  formula_decoder_layers: [416, 208, 104, 52, 26, 13]
+  mass_decoder_layers: [416, 208, 104, 26, 13, 1]
+  atomnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  hcnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  output_dim: 13
+
+  fdr_decoder_layers: [416, 208, 104, 26, 13]
+  
+# ------------------------
+# training settings
+# ------------------------
+# unimplemented
+
+# ------------------------
+# postprocessing settings
+# ------------------------
+post_processing: 
+  refine_atom_type: ['C', 'O', 'N', 'H']
+  refine_atom_num: [3, 3, 3, -1]
+
+  mass_tolerance: 5.0 # target space
+  ppm_mode: True
+  time_out: -1 # do not limit the time
+  maxium_miss_atom_num: 50 # search space
+  top_k: 5
+  buddy_fdr_thr: 0.6
+  sirius_score_thr: -5
+

msfiddle/config/fiddle_tcn_demo.yml

@@ -0,0 +1,121 @@
+# ------------------------
+# QTOF train & validation 
+# ------------------------
+mona_qtof:
+  instrument_type: ['LC-ESI-QTOF', 
+                    'ESI-QFT'] 
+  instrument: ['Agilent 6530 Q-TOF', 'Waters Xevo G2 Q-Tof', 'Agilent qTOF 6545', 'Agilent 6550 iFunnel']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M+Na]+', '[2M+H]+', # +1
+                    '[M+H-H2O]+', '[M-H2O+H]+', '[M+H-2H2O]+', '[M+H-NH3]+', '[M+H+NH3]+', '[M+NH4]+', '[M+H-CH2O2]+', '[M+H-CH4O2]+', # +1+-neutrue
+                    '[M-H]-', '[2M-H]-', # -1
+                    '[M-H-CO2]-', '[M-CHO2]-', '[M-H-H2O]-', '[M-H2O-H]-', # -1+-neutrue
+                    '[M+2H]2+', ] # +2
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 10
+
+# ------------------------
+# model settings
+# ------------------------
+encoding:
+  resolution: 0.2
+  max_mz: 1500
+  max_atom_num: 300
+  use_simulated_precursor_mz: False
+
+  precursor_type:
+    '[M+H]+': 1
+    '[M-H]-': 2
+    '[M+Na]+': 3
+    '[M+2H]2+': 4
+    '[2M+H]+': 5
+    '[2M-H]-': 6
+    
+  type2charge: 
+    '[M+H]+': '+1'
+    '[M-H]-': '-1'
+    '[M+Na]+': '+1'
+    '[M+2H]2+': '+2'
+    '[2M+H]+': '+1'
+    '[2M-H]-': '-1'
+    
+    '[M+H-H2O]+': '+1'
+    '[M-H2O+H]+': '+1'
+    '[M+H-2H2O]+': '+1'
+    '[M+H-NH3]+': '+1'
+    '[M+H+NH3]+': '+1'
+    '[M+NH4]+': '+1'
+    '[M+H-CH2O2]+': '+1'
+    '[M+H-CH4O2]+': '+1'
+
+    '[M-H-CO2]-': '-1' 
+    '[M-CHO2]-': '-1' 
+    '[M-H-H2O]-': '-1'
+    '[M-H2O-H]+': '-1'
+
+model: 
+  resolution: 0.2
+  max_mz: 1500
+  padding_dim: 20 # 1500 / 0.2 = 7500; 7500 / 2**5 (# pooling layer) = 234.375; 235 * (2**5) = 7520 
+  num_add: 6
+  input_channels: 1
+
+  tcn_channels: [32, 32, 64, 128, 256, 512]
+  tcn_dilations: [1, 2, 4, 8, 8, 8]
+  tcn_kernel_sizes: [45, 43, 41, 39, 37, 35]
+  tcn_dropout: 0.2
+
+  # metadata_dim: 16 
+  add_embedding_dim: 4
+  ce_embedding_dim: 4
+  mass_embedding_dim: 4
+  embedding_dim: 512
+  
+  formula_decoder_layers: [416, 208, 104, 52, 26, 13]
+  mass_decoder_layers: [416, 208, 104, 26, 13, 1]
+  atomnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  hcnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  output_dim: 13
+
+  fdr_decoder_layers: [416, 208, 104, 26, 13]
+
+# ------------------------
+# training settings
+# ------------------------
+train: 
+  epochs: 200
+  batch_size: 128
+  num_workers: 8
+  lr: 0.001
+  weight_decay: 0.01
+  warmup_ratio: 0.1
+  early_stop_step: 10
+  patience: 5
+  noised_times: 3
+  
+train_fdr:
+  epochs: 10
+  batch_size: 128
+  num_workers: 8
+  lr: 0.0001
+  early_stop_step: 10
+
+# ------------------------
+# postprocessing settings
+# ------------------------
+post_processing: 
+  refine_atom_type: ['C', 'O', 'N', 'H']
+  refine_atom_num: [5, 5, 5, -1]
+
+  mass_tolerance: 10.0 # target space
+  ppm_mode: True
+  time_out: -1 # do not limit the time
+  maxium_miss_atom_num: 50 # search space
+  top_k: 5
+  buddy_fdr_thr: 0.6
+  sirius_score_thr: -5

msfiddle/config/fiddle_tcn_demo_wo_da.yml

@@ -0,0 +1,121 @@
+# ------------------------
+# QTOF train & validation 
+# ------------------------
+mona_qtof:
+  instrument_type: ['LC-ESI-QTOF', 
+                    'ESI-QFT'] 
+  instrument: ['Agilent 6530 Q-TOF', 'Waters Xevo G2 Q-Tof', 'Agilent qTOF 6545', 'Agilent 6550 iFunnel']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M+Na]+', '[2M+H]+', # +1
+                    '[M+H-H2O]+', '[M-H2O+H]+', '[M+H-2H2O]+', '[M+H-NH3]+', '[M+H+NH3]+', '[M+NH4]+', '[M+H-CH2O2]+', '[M+H-CH4O2]+', # +1+-neutrue
+                    '[M-H]-', '[2M-H]-', # -1
+                    '[M-H-CO2]-', '[M-CHO2]-', '[M-H-H2O]-', '[M-H2O-H]-', # -1+-neutrue
+                    '[M+2H]2+', ] # +2
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 10
+
+# ------------------------
+# model settings
+# ------------------------
+encoding:
+  resolution: 0.2
+  max_mz: 1500
+  max_atom_num: 300
+  use_simulated_precursor_mz: True
+
+  precursor_type:
+    '[M+H]+': 1
+    '[M-H]-': 2
+    '[M+Na]+': 3
+    '[M+2H]2+': 4
+    '[2M+H]+': 5
+    '[2M-H]-': 6
+    
+  type2charge: 
+    '[M+H]+': '+1'
+    '[M-H]-': '-1'
+    '[M+Na]+': '+1'
+    '[M+2H]2+': '+2'
+    '[2M+H]+': '+1'
+    '[2M-H]-': '-1'
+    
+    '[M+H-H2O]+': '+1'
+    '[M-H2O+H]+': '+1'
+    '[M+H-2H2O]+': '+1'
+    '[M+H-NH3]+': '+1'
+    '[M+H+NH3]+': '+1'
+    '[M+NH4]+': '+1'
+    '[M+H-CH2O2]+': '+1'
+    '[M+H-CH4O2]+': '+1'
+
+    '[M-H-CO2]-': '-1' 
+    '[M-CHO2]-': '-1' 
+    '[M-H-H2O]-': '-1'
+    '[M-H2O-H]+': '-1'
+
+model: 
+  resolution: 0.2
+  max_mz: 1500
+  padding_dim: 20 # 1500 / 0.2 = 7500; 7500 / 2**5 (# pooling layer) = 234.375; 235 * (2**5) = 7520 
+  num_add: 6
+  input_channels: 1
+
+  tcn_channels: [32, 32, 64, 128, 256, 512]
+  tcn_dilations: [1, 2, 4, 8, 8, 8]
+  tcn_kernel_sizes: [45, 43, 41, 39, 37, 35]
+  tcn_dropout: 0.2
+
+  # metadata_dim: 16 
+  add_embedding_dim: 4
+  ce_embedding_dim: 4
+  mass_embedding_dim: 4
+  embedding_dim: 512
+  
+  formula_decoder_layers: [416, 208, 104, 52, 26, 13]
+  mass_decoder_layers: [416, 208, 104, 26, 13, 1]
+  atomnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  hcnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  output_dim: 13
+
+  fdr_decoder_layers: [416, 208, 104, 26, 13]
+
+# ------------------------
+# training settings
+# ------------------------
+train: 
+  epochs: 200
+  batch_size: 128
+  num_workers: 8
+  lr: 0.001
+  weight_decay: 0.01
+  warmup_ratio: 0.1
+  early_stop_step: 10
+  patience: 5
+  noised_times: 0
+  
+train_fdr:
+  epochs: 10
+  batch_size: 128
+  num_workers: 8
+  lr: 0.0001
+  early_stop_step: 10
+
+# ------------------------
+# postprocessing settings
+# ------------------------
+post_processing: 
+  refine_atom_type: ['C', 'O', 'N', 'H']
+  refine_atom_num: [5, 5, 5, -1]
+
+  mass_tolerance: 10.0 # target space
+  ppm_mode: True
+  time_out: -1 # do not limit the time
+  maxium_miss_atom_num: 50 # search space
+  top_k: 5
+  buddy_fdr_thr: 0.6
+  sirius_score_thr: -5

msfiddle/config/fiddle_tcn_embl.yml

@@ -0,0 +1,100 @@
+# ------------------------
+# EMBL MCF 2.0 
+# ------------------------
+embl:  
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M+Na]+', '[2M+H]+', # +1
+                    '[M+H-H2O]+', '[M-H2O+H]+', '[M+H-2H2O]+', '[M+H-NH3]+', '[M+H+NH3]+', '[M+NH4]+', '[M+H-CH2O2]+', '[M+H-CH4O2]+', # +1+-neutrue
+                    '[M-H]-', '[2M-H]-', # -1
+                    '[M-H-CO2]-', '[M-CHO2]-', '[M-H-H2O]-', '[M-H2O-H]-', # -1+-neutrue
+                    '[M+2H]2+', ]
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 50
+
+# ------------------------
+# model settings
+# ------------------------
+encoding:
+  resolution: 0.2
+  max_mz: 1500
+  max_atom_num: 300
+  use_simulated_precursor_mz: False
+  precursor_type:
+    '[M+H]+': 1
+    '[M-H]-': 2
+    '[M+Na]+': 3
+    '[M+2H]2+': 4
+    '[2M+H]+': 5
+    '[2M-H]-': 6
+    
+  type2charge: 
+    '[M+H]+': '+1'
+    '[M-H]-': '-1'
+    '[M+Na]+': '+1'
+    '[M+2H]2+': '+2'
+    '[2M+H]+': '+1'
+    '[2M-H]-': '-1'
+    
+    '[M+H-H2O]+': '+1'
+    '[M-H2O+H]+': '+1'
+    '[M+H-2H2O]+': '+1'
+    '[M+H-NH3]+': '+1'
+    '[M+H+NH3]+': '+1'
+    '[M+NH4]+': '+1'
+    '[M+H-CH2O2]+': '+1'
+    '[M+H-CH4O2]+': '+1'
+
+    '[M-H-CO2]-': '-1' 
+    '[M-CHO2]-': '-1' 
+    '[M-H-H2O]-': '-1'
+    '[M-H2O-H]+': '-1'
+
+model: 
+  resolution: 0.2
+  max_mz: 1500
+  padding_dim: 20 # 1500 / 0.2 = 7500; 7500 / 2**5 (# pooling layer) = 234.375; 235 * (2**5) = 7520 
+  num_add: 6
+  input_channels: 1
+
+  tcn_channels: [32, 32, 64, 128, 256, 512]
+  tcn_dilations: [1, 2, 4, 8, 8, 8]
+  tcn_kernel_sizes: [45, 43, 41, 39, 37, 35]
+  tcn_dropout: 0.2
+
+  # metadata_dim: 16 
+  add_embedding_dim: 4
+  ce_embedding_dim: 4
+  mass_embedding_dim: 4
+  embedding_dim: 512
+  
+  formula_decoder_layers: [416, 208, 104, 52, 26, 13]
+  mass_decoder_layers: [416, 208, 104, 26, 13, 1]
+  atomnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  hcnum_decoder_layers: [416, 208, 104, 26, 13, 1]
+  output_dim: 13
+
+  fdr_decoder_layers: [416, 208, 104, 26, 13]
+  
+# ------------------------
+# training settings
+# ------------------------
+# unimplemented
+
+# ------------------------
+# postprocessing settings
+# ------------------------
+post_processing: 
+  refine_atom_type: ['C', 'O', 'N', 'H']
+  refine_atom_num: [3, 3, 3, -1]
+
+  mass_tolerance: 10.0 # target space
+  ppm_mode: True
+  time_out: -1 # do not limit the time
+  maxium_miss_atom_num: 50 # search space
+  top_k: 5
+  buddy_fdr_thr: 0.6
+  sirius_score_thr: -5

msfiddle/config/fiddle_tcn_orbitrap.yml

@@ -0,0 +1,163 @@
+# ------------------------
+# Orbitrap train & validation 
+# ------------------------
+nist20_orbitrap: 
+  instrument_type: HCD
+  instrument: ['Thermo Finnigan Elite Orbitrap']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M+Na]+', '[2M+H]+', # +1
+                    '[M+H-H2O]+', '[M-H2O+H]+', '[M+H-2H2O]+', '[M+H-NH3]+', '[M+H+NH3]+', '[M+NH4]+', '[M+H-CH2O2]+', '[M+H-CH4O2]+', # +1+-neutrue
+                    '[M-H]-', '[2M-H]-', # -1
+                    '[M-H-CO2]-', '[M-CHO2]-', '[M-H-H2O]-', '[M-H2O-H]-', # -1+-neutrue
+                    '[M+2H]2+', ] # +2
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 5
+
+nist23_orbitrap: 
+  instrument_type: HCD
+  instrument: ['Thermo Finnigan Elite Orbitrap']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M+Na]+', '[2M+H]+', # +1
+                    '[M+H-H2O]+', '[M-H2O+H]+', '[M+H-2H2O]+', '[M+H-NH3]+', '[M+H+NH3]+', '[M+NH4]+', '[M+H-CH2O2]+', '[M+H-CH4O2]+', # +1+-neutrue
+                    '[M-H]-', '[2M-H]-', # -1
+                    '[M-H-CO2]-', '[M-CHO2]-', '[M-H-H2O]-', '[M-H2O-H]-', # -1+-neutrue
+                    '[M+2H]2+', ] # +2
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 5
+
+mona_orbitrap: 
+  intrument_type: ['LC-ESI-QFT', 'LC-ESI-Q-Orbitrap']
+  instrument: ['Thermo Q Exactive HF', 'Q Exactive Orbitrap (Thermo Scientific)', 'Q Exactive Plus Orbitrap Thermo Scientific']
+  ms_level: 'MS2'
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M-H]-', '[M+H-H2O]+', '[M+Na]+', '[M+2H]2+', '[2M+H]+', '[2M-H]-', '[M-H2O+H]+', '[M-H2O-H]-']
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 5
+
+gnps_orbitrap: 
+  instrument_type: ['hcd']
+  instrument: ['orbitrap']
+  atom_type: ['C', 'O', 'N', 'H', 'P', 'S', 'F', 'Cl', 'B', 'Br', 'I', 'Na', 'K']
+  precursor_type: ['[M+H]+', '[M-H]-', '[M+H-H2O]+', '[M+Na]+', '[M+2H]2+', '[2M+H]+', '[2M-H]-', '[M-H2O+H]+', '[M-H2O-H]-']
+  min_mz: 50
+  max_mz: 1500
+  min_peak_num: 5
+  max_atom_num: 300
+  min_atom_num: 10
+  ppm_tolerance: 5
+
+# ------------------------
+# model settings
+# ------------------------
+encoding:
+  resolution: 0.2
+  max_mz: 1500
+  max_peak_num: 512
+  max_atom_num: 300
+  use_simulated_precursor_mz: False
+
+  precursor_type:
+    '[M+H]+': 1
+    '[M-H]-': 2
+    '[M+Na]+': 3
+    '[M+2H]2+': 4
+    '[2M+H]+': 5
+    '[2M-H]-': 6
+  type2charge: 
+    '[M+H]+': '+1'
+    '[M-H]-': '-1'
+    '[M+Na]+': '+1'
+    '[M+2H]2+': '+2'
+    '[2M+H]+': '+1'
+    '[2M-H]-': '-1'
+    
+    '[M+H-H2O]+': '+1'
+    '[M-H2O+H]+': '+1'
+    '[M+H-2H2O]+': '+1'
+    '[M+H-NH3]+': '+1'
+    '[M+H+NH3]+': '+1'
+    '[M+NH4]+': '+1'
+    '[M+H-CH2O2]+': '+1'
+    '[M+H-CH4O2]+': '+1'
+
+    '[M-H-CO2]-': '-1' 
+    '[M-CHO2]-': '-1' 
+    '[M-H-H2O]-': '-1'
+    '[M-H2O-H]+': '-1'
+
+model: 
+  resolution: 0.2
+  max_mz: 1500
+  padding_dim: 20 # 1500 / 0.2 = 7500; 7500 / 2**5 (# pooling layer) = 234.375; 235 * (2**5) = 7520 
+  num_add: 6
+  input_channels: 1
+
+  tcn_channels: [32, 32, 64, 128, 256, 512]
+  tcn_dilations: [1, 2, 4, 8, 8, 8]
+  tcn_kernel_sizes: [45, 43, 41, 39, 37, 35]
+  tcn_dropout: 0.2
+
+  # metadata_dim: 16 
+  add_embedding_dim: 4
+  ce_embedding_dim: 4
+  mass_embedding_dim: 4
+  embedding_dim: 512
+  
+  formula_decoder_layers: [416, 208, 104, 52, 26]
+  mass_decoder_layers: [416, 208, 104, 26, 13]
+  atomnum_decoder_layers: [416, 208, 104, 26, 13]
+  hcnum_decoder_layers: [416, 208, 104, 26, 13]
+  output_dim: 13
+
+  fdr_decoder_layers: [416, 208, 104, 26, 13]
+  
+# ------------------------
+# training settings
+# ------------------------
+train: 
+  epochs: 500
+  batch_size: 512 # 128
+  num_workers: 8
+  lr: 0.002 # 0.001
+  weight_decay: 0.01
+  warmup_ratio: 0.1
+  early_stop_step: 10
+  patience: 5
+  noised_times: 0
+  
+train_fdr:
+  epochs: 100
+  batch_size: 128
+  num_workers: 8
+  lr: 0.0001
+  early_stop_step: 10
+  
+# ------------------------
+# postprocessing settings
+# ------------------------
+post_processing: 
+  # Orbitrap
+  refine_atom_type: ['C', 'O', 'N', 'H']
+  refine_atom_num: [3, 3, 3, -1]
+
+  mass_tolerance: 20.0 # target space
+  ppm_mode: True
+  time_out: 300
+  maxium_miss_atom_num: 20 # search space
+  top_k: 5
+  buddy_fdr_thr: 0.6
+  sirius_score_thr: -5