|
- ###
- # Casanovo configuration.
- # Blank entries are interpreted as "None"
- ###
-
- # Random seed to ensure reproducible results.
- random_seed: 454
-
- # Spectrum processing options.
- n_peaks: 150
- min_mz: 50.0
- max_mz: 2500.0
- min_intensity: 0.01
- remove_precursor_tol: 2.0 # Da
- max_charge: 10
- precursor_mass_tol: 50 # ppm
- isotope_error_range: [0, 1]
-
- # Model architecture options.
- dim_model: 512
- n_head: 8
- dim_feedforward: 1024
- n_layers: 9
- decoder_dim_model: 768
- decoder_n_head: 8
- decoder_dim_feedforward: 1024
- decoder_n_layers: 9
- dropout: 0.0
- dim_intensity:
- custom_encoder:
- max_length: 100
- residues:
- "-17.027": -17.026549 # NH3 loss
- "+43.006-17.027": 25.980265
- "A": 71.037114
- "L": 113.084064
- "G": 57.021464
- "V": 99.068414
- "S": 87.032028
- "R": 156.101111
- "E": 129.042593
- "D": 115.026943
- "T": 101.047670
- "I": 113.084064
- "P": 97.052764
- "K": 128.094963
- "F": 147.068414
- "Q": 128.058578
- "N": 114.042927
- "Y": 163.063329
- "M": 131.040485
- "H": 137.058912
- "W": 186.079313
- "C+57.021": 160.030649 # 103.009185 + 57.021464
- # Amino acid modifications.
- "M+15.995": 147.035400 # Met oxidation: 131.040485 + 15.994915
- "N+0.984": 115.026943 # Asn deamidation: 114.042927 + 0.984016
- "Q+0.984": 129.042594 # Gln deamidation: 128.058578 + 0.984016
- # N-terminal modifications.
- "+42.011": 42.010565 # Acetylation
- "+43.006": 43.005814 # Carbamylation
- n_log: 1
- tb_summarywriter:
- warmup_iters: 100_000
- max_iters: 600_000
- learning_rate: 1e-4
- weight_decay: 1e-5
-
- # Training/inference options.
- train_batch_size: 4
- predict_batch_size: 1024
-
- logger:
- max_epochs: 40
- num_sanity_val_steps: 0
-
- train_from_scratch: True
-
- save_model: True
- model_save_folder_path: "exp_small_t5"
- save_weights_only: True
- every_n_epochs: 1
-
- #{'-17.027': 1, '+43.006-17.027': 2, 'A': 3, 'L': 4, 'G': 5, 'V': 6, 'S': 7, 'R': 8, 'E': 9, 'D': 10, 'T': 11, 'I': 12, 'P': 13, 'K': 14, 'F': 15, 'Q': 16, 'N': 17, 'Y': 18, 'M': 19, 'H': 20, 'W': 21, 'C+57.021': 22, 'M+15.995': 23, 'N+0.984': 24, 'Q+0.984': 25, '+42.011': 26, '+43.006': 27, '$': 28}
- #T5
- # {'</s>': 1, '<unk>': 2, '▁A': 3, '▁L': 4, '▁G': 5, '▁V': 6, '▁S': 7, '▁R': 8, '▁E': 9, '▁D': 10, '▁T': 11, '▁I': 12, '▁P': 13, '▁K': 14, '▁F': 15, '▁Q': 16, '▁N': 17, '▁Y': 18, '▁M': 19, '▁H': 20, '▁W': 21, '▁C': 22, '▁X': 23, '▁B': 24, '▁O': 25, '▁U': 26, '▁Z': 27}
|