TypeError while running predict.py

[pailozka]

I tried to run python predict.py --run_type causal_gene_discovery --patient_data disease_simulated --edgelist KG_edgelist_mask.txt --node_map KG_node_map.txt --saved_node_embeddings_path checkpoints/pretrain.ckpt --best_ckpt checkpoints/causal_gene_discovery.ckpt and got this error:

File "../shepherd/samplers.py", line 660, in collate
sim_gene_node_idx, gene_sims, gene_degs, unique_sim_genes = self.get_similar_genes(patient_ids, candidate_gene_node_idx)
File "../shepherd/samplers.py", line 590, in get_similar_genes
p_genes.append(torch.LongTensor([idx for idx, sim in list(self.gene_similarity_dict[int(g)])[:k]]))
TypeError: 'NoneType' object is not subscriptable

Could you please explain how I can fix it?