# Configuration for inference on SE(3) diffusion experiments.
defaults:
  - base
  - _self_

inference:

  # Use this to write with date-time stamp.
  name: run_${now:%Y-%m-%d}_${now:%H-%M}
  seed: 123
  ckpt_path: ckpt/se3-fm/dnmt-full-unconditioned/2024-09-26_00-42-38/epoch29.ckpt
  #output_dir: inference_outputs/dnmt-guided-tests-fixed-residues/
  output_dir: inference_outputs/more-sample/

  # Directories
  pmpnn_dir: ./ProteinMPNN/

  use_gpu: True
  num_gpus: 1

  interpolant:
    min_t: 1e-2
    rots:
      corrupt: True
      sample_schedule: exp
      exp_rate: 10
    trans:
      corrupt: True
      sample_schedule: linear
    sampling:
      num_timesteps: 100
    self_condition: True

  samples:

    # Number of backbone samples per sequence length.
    samples_per_length: 1000

    # Minimum sequence length to sample.
    min_length: 196

    # Maximum sequence length to sample.
    max_length: 286

    # gap between lengths to sample. i.e. this script will sample all lengths
    # in range(min_length, max_length, length_step)
    length_step: 1

    # Subset of lengths to sample. If null, sample all targets.
    # length_subset: [60, 80, 100, 112, 128, 196, 256, 512]
    length_subset: [196, 256, 286]
    # ESM and ProteinMPNN samples
    seq_per_sample: 8

    overwrite: False
  
  classifier:
    ckpt_path: classifier_ckpt/se3-classifier/new-classifier-full/2025-02-24_01-37-28/epoch=90-step=728000.ckpt
    node_embed_size: 128
    edge_embed_size: 128
    symmetric: false
    node_features:
      c_s: ${model.node_embed_size}
      c_pos_emb: 128
      c_timestep_emb: 128
      embed_diffuse_mask: false
      max_num_res: 2000
      timestep_int: 1000
    edge_features:
      single_bias_transition_n: 2
      c_s: ${model.node_embed_size}
      c_p: ${model.edge_embed_size}
      relpos_k: 64
      use_rbf: true
      num_rbf: 32
      feat_dim: 64
      num_bins: 22
      self_condition: true
    ipa:
      c_s: ${model.node_embed_size}
      c_z: ${model.edge_embed_size}
      c_hidden: 128
      no_heads: 4
      no_qk_points: 4
      no_v_points: 2
      seq_tfmr_num_heads: 2
      seq_tfmr_num_layers: 1
      num_blocks: 2

fixed_inference:
  flag: True
  input_pdb: 6F57_A.pdb
  #fixed_residues: [639,640,641,642,643,644,645,646,647,664,665,686,687,688,888,889,890,891,892,893,894,895]
  fixed_residues: [639, 640, 641, 642, 643, 644, 645, 646, 647, 648, 649, 650, 651, 652, 653, 654, 655, 656, 657, 658, 659, 660, 661, 662, 663, 664, 665, 666, 667, 668, 669, 670, 671, 672, 673, 674, 675, 676, 677, 678, 679, 680, 681, 682, 683, 684, 685, 686, 687, 688, 689, 690, 691, 692, 693, 694, 695, 696, 697, 698, 699, 700, 701, 702, 703, 704, 705, 706, 707, 708, 709, 710, 711, 712, 713, 714, 715, 716, 717, 718, 719, 720, 721, 722, 723, 724, 725, 726, 727, 728, 729, 730, 731, 732, 733, 734, 735, 736, 737, 738, 739, 740, 741, 742, 743, 744, 745, 746, 747, 748, 749, 750, 751, 752, 753, 754, 755, 756, 757, 758, 759, 760, 761, 762, 763, 764, 765, 766, 767, 768, 769, 770, 771, 772, 773, 774, 775, 776, 777, 778, 779, 780, 781, 782, 783, 784, 785, 786, 787, 788, 789, 790, 791, 792, 793, 794, 795, 796, 797, 798, 799, 800, 801, 802, 803, 804, 805, 806, 807, 808, 809, 810, 811, 812, 813, 814, 815, 816, 817, 818, 819, 820, 821, 822, 823, 824, 825, 826, 827, 828, 829, 830]
  num_samples: 5