import json import os import shutil import random import sys from typing import List, Tuple, Optional import Bio.PDB import Bio.SeqUtils import pandas as pd import numpy as np OUTPUT_FOLDER = "/tmp/output" PINDER_ANNOTATIONS = "/tmp/index.parquet" GSUTIL_PATH = "/tmp/google-cloud-sdk/bin/gsutil" MAX_SYSTEMS_FOR_CLUSTER = 2 MAX_LENGTH = 350 MAX_TRIES_OF_METHOD = 5 def do_robust_chain_object_renumber(chain: Bio.PDB.Chain.Chain, new_chain_id: str) -> Optional[Bio.PDB.Chain.Chain]: all_residues = [res for res in chain.get_residues() if "CA" in res and Bio.SeqUtils.seq1(res.get_resname()) not in ("X", "", " ")] if not all_residues: return None res_and_res_id = [(res, res.get_id()[1]) for res in all_residues] min_res_id = min([i[1] for i in res_and_res_id]) if min_res_id < 1: print("Negative res id", chain, min_res_id) factor = -1 * min_res_id + 1 res_and_res_id = [(res, res_id + factor) for res, res_id in res_and_res_id] res_and_res_id_no_collisions = [] for res, res_id in res_and_res_id[::-1]: if res_and_res_id_no_collisions and res_and_res_id_no_collisions[-1][1] == res_id: # there is a collision, usually an insertion residue res_and_res_id_no_collisions = [(i, j + 1) for i, j in res_and_res_id_no_collisions] res_and_res_id_no_collisions.append((res, res_id)) first_res_id = min([i[1] for i in res_and_res_id_no_collisions]) factor = 1 - first_res_id # start from 1 new_chain = Bio.PDB.Chain.Chain(new_chain_id) res_and_res_id_no_collisions.sort(key=lambda x: x[1]) for res, res_id in res_and_res_id_no_collisions: chain.detach_child(res.id) res.id = (" ", res_id + factor, " ") new_chain.add(res) return new_chain def robust_renumber_protein(pdb_path: str, output_path: str): if pdb_path.endswith(".pdb"): pdb_parser = Bio.PDB.PDBParser(QUIET=True) pdb_struct = pdb_parser.get_structure("original_pdb", pdb_path) elif pdb_path.endswith(".cif"): pdb_struct = Bio.PDB.MMCIFParser().get_structure("original_pdb", pdb_path) else: raise ValueError("Unknown file type", pdb_path) assert len(list(pdb_struct)) == 1, "can't extract if more than one model" model = next(iter(pdb_struct)) chains = list(model.get_chains()) new_model = Bio.PDB.Model.Model(0) chain_ids = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789" for chain, chain_id in zip(chains, chain_ids): new_chain = do_robust_chain_object_renumber(chain, chain_id) if new_chain is None: continue new_model.add(new_chain) new_struct = Bio.PDB.Structure.Structure("renumbered_pdb") new_struct.add(new_model) io = Bio.PDB.PDBIO() io.set_structure(new_struct) io.save(output_path) def get_chain_object_to_seq(chain: Bio.PDB.Chain.Chain) -> str: res_id_to_res = {res.get_id()[1]: res for res in chain.get_residues() if "CA" in res} if len(res_id_to_res) == 0: print("skipping empty chain", chain.get_id()) return "" seq = "" for i in range(1, max(res_id_to_res) + 1): if i in res_id_to_res: seq += Bio.SeqUtils.seq1(res_id_to_res[i].get_resname()) else: seq += "X" return seq def get_sequence_from_pdb(pdb_path: str) -> Tuple[str, List[int]]: pdb_parser = Bio.PDB.PDBParser(QUIET=True) pdb_struct = pdb_parser.get_structure("original_pdb", pdb_path) # chain_to_seq = {chain.id: get_chain_object_to_seq(chain) for chain in pdb_struct.get_chains()} all_chain_seqs = [get_chain_object_to_seq(chain) for chain in pdb_struct.get_chains()] chain_lengths = [len(seq) for seq in all_chain_seqs] return ("X" * 20).join(all_chain_seqs), chain_lengths from Bio import PDB from Bio import pairwise2 def extract_sequence(chain): seq = '' residues = [] for res in chain.get_residues(): seq_res = Bio.SeqUtils.seq1(res.get_resname()) if seq_res in ('X', "", " "): continue seq += seq_res residues.append(res) return seq, residues def map_residues(alignment, residues_gt, residues_pred): idx_gt = 0 idx_pred = 0 mapping = [] for i in range(len(alignment.seqA)): aa_gt = alignment.seqA[i] aa_pred = alignment.seqB[i] res_gt = None res_pred = None if aa_gt != '-': res_gt = residues_gt[idx_gt] idx_gt += 1 if aa_pred != '-': res_pred = residues_pred[idx_pred] idx_pred += 1 if res_gt and res_pred: mapping.append((res_gt, res_pred)) return mapping class ResidueSelect(PDB.Select): def __init__(self, residues_to_select): self.residues_to_select = set(residues_to_select) def accept_residue(self, residue): return residue in self.residues_to_select def count_gapped_single_aa(alignment): count_non_gap = 0 count_fully_gapped = 0 for i in range(1, len(alignment.seqA) - 1): if alignment.seqA[i] != '-': count_non_gap += 1 if alignment.seqA[i - 1] == '-' and alignment.seqA[i + 1] == '-': count_fully_gapped += 1 top_ratio = count_fully_gapped / count_non_gap count_non_gap = 0 count_fully_gapped = 0 for i in range(1, len(alignment.seqB) - 1): if alignment.seqA[i] != '-': count_non_gap += 1 if alignment.seqA[i - 1] == '-' and alignment.seqA[i + 1] == '-': count_fully_gapped += 1 if count_fully_gapped / count_non_gap > top_ratio: top_ratio = count_fully_gapped / count_non_gap return top_ratio def copy_residue_numbering(gt_pdb_path, input_pdb_path): parser = PDB.PDBParser(QUIET=True) gt_structure = parser.get_structure('gt', gt_pdb_path) input_structure = parser.get_structure('input', input_pdb_path) for res in list(input_structure.get_residues()): res.id = (' ', res.get_id()[1] + 10000, ' ') for gt_res, input_res in zip(gt_structure.get_residues(), input_structure.get_residues()): input_res.id = gt_res.id io = PDB.PDBIO() io.set_structure(input_structure) io.save(input_pdb_path) def align_gt_and_input(gt_pdb_path, input_pdb_path, output_gt_path, output_input_path): # print("aligning", gt_pdb_path, input_pdb_path, output_gt_path, output_input_path) parser = PDB.PDBParser(QUIET=True) gt_structure = parser.get_structure('gt', gt_pdb_path) pred_structure = parser.get_structure('pred', input_pdb_path) matched_residues_gt = [] matched_residues_pred = [] total_gt_size = len([res for res in gt_structure.get_residues() if "CA" in res]) used_chain_pred = [] total_mapping_size = 0 for chain_gt in gt_structure.get_chains(): seq_gt, residues_gt = extract_sequence(chain_gt) best_alignment = None best_chain_pred = None best_score = -1 best_residues_pred = None # Find the best matching chain in pred for chain_pred in pred_structure.get_chains(): # print("checking", chain_pred.get_id(), chain_gt.get_id()) if chain_pred in used_chain_pred: continue seq_pred, residues_pred = extract_sequence(chain_pred) # print(seq_gt) # print(seq_pred) # alignments = pairwise2.align.globalxx(seq_gt, seq_pred, one_alignment_only=True) alignments = pairwise2.align.globalms(seq_gt, seq_pred, 2, -10000, -1, 0, one_alignment_only=True) if not alignments: continue # print("checking2", chain_pred.get_id(), chain_gt.get_id()) alignment = alignments[0] score = alignment.score if score > best_score: best_score = score best_alignment = alignment best_chain_pred = chain_pred best_residues_pred = residues_pred if best_alignment and count_gapped_single_aa(best_alignment) < 0.2: mapping = map_residues(best_alignment, residues_gt, best_residues_pred) total_mapping_size += len(mapping) used_chain_pred.append(best_chain_pred) for res_gt, res_pred in mapping: matched_residues_gt.append(res_gt) matched_residues_pred.append(res_pred) else: print(f"No matching chain found for chain {chain_gt.get_id()}") assert total_mapping_size / total_gt_size > 0.8, \ f"Mapping size too low ({total_mapping_size}/{total_gt_size}), skipping" print(f"Total mapping size: {total_mapping_size}") # Write new PDB files with only matched residues io = PDB.PDBIO() io.set_structure(gt_structure) io.save(output_gt_path, ResidueSelect(matched_residues_gt)) io = PDB.PDBIO() io.set_structure(pred_structure) io.save(output_input_path, ResidueSelect(matched_residues_pred)) copy_residue_numbering(output_gt_path, output_input_path) def validate_matching_input_gt(gt_pdb_path, input_pdb_path): gt_residues = [res for res in PDB.PDBParser().get_structure('gt', gt_pdb_path).get_residues()] input_residues = [res for res in PDB.PDBParser().get_structure('input', input_pdb_path).get_residues()] if len(gt_residues) != len(input_residues): print(f"Residue count mismatch: {len(gt_residues)} vs {len(input_residues)}") return -1 for res_gt, res_input in zip(gt_residues, input_residues): if res_gt.get_resname() != res_input.get_resname(): print(f"Residue name mismatch: {res_gt.get_resname()} vs {res_input.get_resname()}") return -1 return len(input_residues) def download_pdb(pdb_name, output_folder): output_path = os.path.join(output_folder, pdb_name) if os.path.exists(output_path): return output_path print("downloading", pdb_name) os.system(f'{GSUTIL_PATH} -m -q cp "gs://pinder/2024-02/pdbs/{pdb_name}" {output_path}') return output_path INTERFACE_MIN_ATOM_DIST = 5 def get_filtered_res(gt_r_res, gt_l_res, max_length: int): gt_r_ca = np.array([res["CA"].coord for res in gt_r_res]) gt_l_ca = np.array([res["CA"].coord for res in gt_l_res]) if len(gt_r_res) + len(gt_l_res) < max_length: # continue without cropping print("no cropping needed", len(gt_r_res), len(gt_l_res)) return gt_r_res, gt_l_res # close_residues = np.argwhere(scipy.spatial.distance.cdist(gt_r_ca, gt_l_ca) < INTERFACE_MIN_ATOM_DIST) # gt_r_interface, gt_l_interface = set(), set() # for i, j in close_residues: # gt_r_interface.add(gt_r_res[i].id[1]) # gt_l_interface.add(gt_l_res[j].id[1]) inter_dists = gt_r_ca[:, np.newaxis, :] - gt_l_ca[np.newaxis, :, :] inter_dists = np.sqrt((inter_dists ** 2).sum(-1)) min_inter_dist_per_gt_l_res = inter_dists.min(axis=0) min_inter_dist_per_gt_r_res = inter_dists.min(axis=1) assert min_inter_dist_per_gt_l_res.shape[0] == len(gt_l_res) assert min_inter_dist_per_gt_r_res.shape[0] == len(gt_r_res) min_r_res, max_r_res = min(min_inter_dist_per_gt_r_res), max(min_inter_dist_per_gt_r_res) min_l_res, max_l_res = min(min_inter_dist_per_gt_l_res), max(min_inter_dist_per_gt_l_res) r_pocket = [res for res in gt_r_res if min_r_res <= res.id[1] <= max_r_res] l_pocket = [res for res in gt_l_res if min_l_res <= res.id[1] <= max_l_res] if len(r_pocket) + len(l_pocket) < max_length: # add extra residues to both chains to get a total of max_length res_r_before = [res for res in gt_r_res if res.id[1] < min_r_res] res_r_after = [res for res in gt_r_res if res.id[1] > max_r_res] res_l_before = [res for res in gt_l_res if res.id[1] < min_l_res] res_l_after = [res for res in gt_l_res if res.id[1] > max_l_res] extra_to_add = max_length - len(r_pocket) - len(l_pocket) actions = [] if len(res_r_before) > 0: actions.append("add_r_before") if len(res_r_after) > 0: actions.append("add_r_after") if len(res_l_before) > 0: actions.append("add_l_before") if len(res_l_after) > 0: actions.append("add_l_after") while extra_to_add > 0 and actions: action = random.choice(actions) if action == "add_r_before": r_pocket.insert(0, res_r_before.pop()) if not len(res_r_before): actions.remove("add_r_before") elif action == "add_r_after": r_pocket.append(res_r_after.pop()) if not len(res_r_after): actions.remove("add_r_after") elif action == "add_l_before": l_pocket.insert(0, res_l_before.pop()) if not len(res_l_before): actions.remove("add_l_before") elif action == "add_l_after": l_pocket.append(res_l_after.pop()) if not len(res_l_after): actions.remove("add_l_after") extra_to_add -= 1 print("Extended pocket sizes", len(r_pocket), len(l_pocket), "extra_to_add", extra_to_add) return r_pocket, l_pocket print("cropping simply") # remove residues that are farthest from the interface res_and_dist_r = [(res, min_inter_dist_per_gt_r_res[res_idx]) for res_idx, res in enumerate(gt_r_res)] res_and_dist_l = [(res, min_inter_dist_per_gt_l_res[res_idx]) for res_idx, res in enumerate(gt_l_res)] res_and_dist_r = [(res, dist) for res, dist in res_and_dist_r if res in r_pocket] res_and_dist_l = [(res, dist) for res, dist in res_and_dist_l if res in l_pocket] res_and_dist_r = sorted(res_and_dist_r, key=lambda x: x[1], reverse=True) res_and_dist_l = sorted(res_and_dist_l, key=lambda x: x[1], reverse=True) while len(res_and_dist_r) + len(res_and_dist_l) > max_length: if res_and_dist_r[0][1] > res_and_dist_l[0][1]: res_and_dist_r.pop(0) else: res_and_dist_l.pop(0) return [res for res, _ in res_and_dist_r], [res for res, _ in res_and_dist_l] def prepare_holo(row, tmp_dir_path, max_length: int): tmp_gt_r_pdb = os.path.join(tmp_dir_path, f"tmp_{row.id}_gt_r.pdb") tmp_gt_l_pdb = os.path.join(tmp_dir_path, f"tmp_{row.id}_gt_l.pdb") if os.path.exists(tmp_gt_r_pdb) and os.path.exists(tmp_gt_l_pdb): return tmp_gt_r_pdb, tmp_gt_l_pdb holo_r_pdb = download_pdb(row.holo_R_pdb, tmp_dir_path) holo_l_pdb = download_pdb(row.holo_L_pdb, tmp_dir_path) # make gt and apo that matches robust_renumber_protein(holo_r_pdb, tmp_gt_r_pdb) robust_renumber_protein(holo_l_pdb, tmp_gt_l_pdb) parser = PDB.PDBParser(QUIET=True) gt_r_prot = parser.get_structure('r', tmp_gt_r_pdb) gt_l_prot = parser.get_structure('l', tmp_gt_l_pdb) assert len(list(gt_r_prot.get_chains())) == 1, "can't extract if more than one chain" assert len(list(gt_l_prot.get_chains())) == 1, "can't extract if more than one chain" gt_r_res = [res for res in gt_r_prot.get_residues() if "CA" in res] gt_l_res = [res for res in gt_l_prot.get_residues() if "CA" in res] to_keep_r, to_keep_l = get_filtered_res(gt_r_res, gt_l_res, max_length) io = PDB.PDBIO() io.set_structure(gt_r_prot) io.save(tmp_gt_r_pdb, ResidueSelect(to_keep_r)) io = PDB.PDBIO() io.set_structure(gt_l_prot) io.save(tmp_gt_l_pdb, ResidueSelect(to_keep_l)) return tmp_gt_r_pdb, tmp_gt_l_pdb def generate_input_pdbs(tmp_input_r_pdb, tmp_input_l_pdb, tmp_gt_r_pdb, tmp_gt_l_pdb, input_r_output_pdb, input_l_output_pdb, gt_r_output_pdb, gt_l_output_pdb): # print("preparing input pdbs", gt_r_output_pdb) if not os.path.exists(tmp_input_r_pdb) or not os.path.exists(tmp_input_l_pdb): raise False try: align_gt_and_input(tmp_gt_r_pdb, tmp_input_r_pdb, gt_r_output_pdb, input_r_output_pdb) protein_size_r = validate_matching_input_gt(gt_r_output_pdb, input_r_output_pdb) assert protein_size_r > -1, "Failed to validate matching input and gt" align_gt_and_input(tmp_gt_l_pdb, tmp_input_l_pdb, gt_l_output_pdb, input_l_output_pdb) protein_size_l = validate_matching_input_gt(gt_l_output_pdb, input_l_output_pdb) assert protein_size_l > -1, "Failed to validate matching input and gt" except Exception as e: print("Failed to align", e) if os.path.exists(gt_r_output_pdb): os.remove(gt_r_output_pdb) if os.path.exists(gt_l_output_pdb): os.remove(gt_l_output_pdb) if os.path.exists(input_r_output_pdb): os.remove(input_r_output_pdb) if os.path.exists(input_l_output_pdb): os.remove(input_l_output_pdb) return False return True def _get_rel_path(abs_path): return os.path.join(os.path.basename(os.path.dirname(abs_path)), os.path.basename(abs_path)) def main(start_ind: Optional[int] = None, end_ind: Optional[int] = None): print("running with", start_ind, end_ind) os.makedirs(OUTPUT_FOLDER, exist_ok=True) output_models_folder = os.path.join(OUTPUT_FOLDER, "pinder_models") output_train_jsons_folder = os.path.join(OUTPUT_FOLDER, "pinder_jsons_train") output_val_jsons_folder = os.path.join(OUTPUT_FOLDER, "pinder_jsons_val") output_test_jsons_folder = os.path.join(OUTPUT_FOLDER, "pinder_jsons_test") output_info = os.path.join(OUTPUT_FOLDER, "pinder_generation_info.csv") os.makedirs(output_models_folder, exist_ok=True) os.makedirs(output_train_jsons_folder, exist_ok=True) os.makedirs(output_val_jsons_folder, exist_ok=True) os.makedirs(output_test_jsons_folder, exist_ok=True) split_to_folder = { "train": output_train_jsons_folder, "val": output_val_jsons_folder, "test": output_test_jsons_folder } # output_info_file = open(output_info, "a+") systems = pd.read_parquet(PINDER_ANNOTATIONS) systems = systems[systems.split.isin(['train', 'val', 'test'])] cluster_ids = systems["cluster_id"].value_counts() cluster_ids = cluster_ids[cluster_ids >= 1] print("There are", len(cluster_ids), "clusters") # clusters_with_data = 0 # for cluster_id in cluster_ids.index: # cluster_systems = systems[systems["cluster_id"] == cluster_id] # with_apo = cluster_systems[cluster_systems.apo_R & cluster_systems.apo_L] # if len(with_apo) > 0: # print("Cluster", cluster_id, "has", len(with_apo), "systems with apo") # clusters_with_data += 1 # continue # with_pred = cluster_systems[cluster_systems.predicted_R & cluster_systems.predicted_L] # if len(with_pred) > 0: # print("Cluster", cluster_id, "has", len(with_pred), "systems with pred") # clusters_with_data += 1 # continue # print("There are", clusters_with_data, "clusters with data out of", len(cluster_ids)) for cluster_ind, cluster_id in enumerate(sorted(cluster_ids.index)): if (start_ind is not None and cluster_ind < start_ind) or (end_ind is not None and cluster_ind >= end_ind): continue # if cluster_id != "cluster_10004_p": # continue tmp_dir_path = os.path.join(OUTPUT_FOLDER, "tmp_" + cluster_id) os.makedirs(tmp_dir_path, exist_ok=True) system_id_to_method = {} cluster_systems = systems[systems["cluster_id"] == cluster_id] print("--- Starting cluster", cluster_ind, cluster_id, "size", cluster_systems.shape) with_apo = cluster_systems[cluster_systems.apo_R & cluster_systems.apo_L] print("*** APO *** Cluster", cluster_id, "has", len(with_apo), "systems with apo") for try_counter, row in enumerate(with_apo.itertuples()): if row.split not in ("test", "val") \ and (try_counter >= MAX_TRIES_OF_METHOD or len(system_id_to_method) >= MAX_SYSTEMS_FOR_CLUSTER): continue print("-- Trying to prepare apo", row.id, row.split) try: tmp_gt_r_pdb, tmp_gt_l_pdb = prepare_holo(row, tmp_dir_path, MAX_LENGTH) gt_r_output_path = os.path.join(output_models_folder, f"{row.id}_gt_r.pdb") gt_l_output_path = os.path.join(output_models_folder, f"{row.id}_gt_l.pdb") input_r_output_path = os.path.join(output_models_folder, f"{row.id}_input_r.pdb") input_l_output_path = os.path.join(output_models_folder, f"{row.id}_input_l.pdb") input_r_pdb_path = download_pdb(row.apo_R_pdb, tmp_dir_path) input_l_pdb_path = download_pdb(row.apo_L_pdb, tmp_dir_path) if generate_input_pdbs(input_r_pdb_path, input_l_pdb_path, tmp_gt_r_pdb, tmp_gt_l_pdb, input_r_output_path, input_l_output_path, gt_r_output_path, gt_l_output_path): system_id_to_method[row.id] = "apo" except Exception as e: print("Failed to prepare apo", row.id, e) continue with_pred = cluster_systems[cluster_systems.predicted_R & cluster_systems.predicted_L] print("*** Pred *** Cluster", cluster_id, "has", len(with_pred), "systems with pred") for try_counter, row in enumerate(with_pred.itertuples()): if row.id in system_id_to_method: continue if row.split not in ("test", "val") \ and (try_counter >= MAX_TRIES_OF_METHOD or len(system_id_to_method) >= MAX_SYSTEMS_FOR_CLUSTER): continue print("-- Trying to prepare pred", row.id, row.split) try: tmp_gt_r_pdb, tmp_gt_l_pdb = prepare_holo(row, tmp_dir_path, MAX_LENGTH) gt_r_output_path = os.path.join(output_models_folder, f"{row.id}_gt_r.pdb") gt_l_output_path = os.path.join(output_models_folder, f"{row.id}_gt_l.pdb") input_r_output_path = os.path.join(output_models_folder, f"{row.id}_input_r.pdb") input_l_output_path = os.path.join(output_models_folder, f"{row.id}_input_l.pdb") input_r_pdb_path = download_pdb(row.predicted_R_pdb, tmp_dir_path) input_l_pdb_path = download_pdb(row.predicted_L_pdb, tmp_dir_path) if generate_input_pdbs(input_r_pdb_path, input_l_pdb_path, tmp_gt_r_pdb, tmp_gt_l_pdb, input_r_output_path, input_l_output_path, gt_r_output_path, gt_l_output_path): system_id_to_method[row.id] = "pred" except Exception as e: print("Failed to prepare pred", row.id, e) # default - use gt print("*** GT *** ") for row in cluster_systems.itertuples(): if row.id in system_id_to_method: continue if row.split not in ("test", "val") and len(system_id_to_method) >= MAX_SYSTEMS_FOR_CLUSTER: continue try: tmp_gt_r_pdb, tmp_gt_l_pdb = prepare_holo(row, tmp_dir_path, MAX_LENGTH) gt_r_output_path = os.path.join(output_models_folder, f"{row.id}_gt_r.pdb") gt_l_output_path = os.path.join(output_models_folder, f"{row.id}_gt_l.pdb") input_r_output_path = os.path.join(output_models_folder, f"{row.id}_input_r.pdb") input_l_output_path = os.path.join(output_models_folder, f"{row.id}_input_l.pdb") shutil.copyfile(tmp_gt_r_pdb, gt_r_output_path) shutil.copyfile(tmp_gt_r_pdb, input_r_output_path) shutil.copyfile(tmp_gt_l_pdb, gt_l_output_path) shutil.copyfile(tmp_gt_l_pdb, input_l_output_path) system_id_to_method[row.id] = "gt" except Exception as e: print("Failed to prepare gt", row.id, e) # save jsons for row in cluster_systems.itertuples(): if row.id not in system_id_to_method: continue output_json_path = os.path.join(split_to_folder[row.split], f"{row.id}.json") gt_r_output_path = os.path.join(output_models_folder, f"{row.id}_gt_r.pdb") gt_l_output_path = os.path.join(output_models_folder, f"{row.id}_gt_l.pdb") input_r_output_path = os.path.join(output_models_folder, f"{row.id}_input_r.pdb") input_l_output_path = os.path.join(output_models_folder, f"{row.id}_input_l.pdb") protein_r_seq_len = validate_matching_input_gt(gt_r_output_path, input_r_output_path) protein_l_seq_len = validate_matching_input_gt(gt_l_output_path, input_l_output_path) json_data = { "input_r_structure": _get_rel_path(input_r_output_path), "input_l_structure": _get_rel_path(input_l_output_path), "gt_r_structure": _get_rel_path(gt_r_output_path), "gt_l_structure": _get_rel_path(gt_l_output_path), "resolution": 1.0, "protein_r_seq_len": protein_r_seq_len, "protein_l_seq_len": protein_l_seq_len, "uniprot_r": row.uniprot_R, "uniprot_l": row.uniprot_L, "cluster": row.cluster_id, "input_protein_source": system_id_to_method[row.id], "pdb_id": row.id, } open(output_json_path, "w").write(json.dumps(json_data, indent=4)) print("******* saved", row.id, system_id_to_method[row.id], flush=True) shutil.rmtree(tmp_dir_path) print("total systems", len(systems)) if __name__ == '__main__': if len(sys.argv) == 3: main(int(sys.argv[1]), int(sys.argv[2])) else: main()