scPlantLLM — Foundation Model Tutorial¶

import omicverse as ov
import scanpy as sc
import os
import warnings
warnings.filterwarnings('ignore')

ov.plot_set()

info = ov.fm.describe_model("scplantllm")

print("=== Model Info ===")
print(f"Name: {info['model']['name']}")
print(f"Version: {info['model']['version']}")
print(f"Tasks: {info['model']['tasks']}")
print(f"Species: {info['model']['species']}")
print(f"Embedding dim: {info['model']['embedding_dim']}")
print(f"Differentiator: {info['model']['differentiator']}")

print("\n=== Input Contract ===")
print(f"Gene ID scheme: {info['input_contract']['gene_id_scheme']}")
print(f"Preprocessing: {info['input_contract']['preprocessing']}")

print("\n=== Output Contract ===")
print(f"Embedding key: {info['output_contract']['embedding_key']}")
print(f"Embedding dim: {info['output_contract']['embedding_dim']}")

# scPlantLLM requires plant scRNA-seq data.
# Replace with your own plant dataset:
# adata = sc.read_h5ad('arabidopsis_root.h5ad')
#
# Supported species: Arabidopsis thaliana, Oryza sativa (rice),
# Zea mays (maize), and other plant species.

# For demonstration, we show the API pattern with PBMC RNA data.
# The validation step will correctly flag the species mismatch.
adata = sc.datasets.pbmc3k()
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)
adata.write_h5ad('pbmc3k_scplantllm.h5ad')
print(f'Dataset: {adata.n_obs} cells x {adata.n_vars} genes')
print('Note: This is human data — scPlantLLM will flag incompatibility.')

profile = ov.fm.profile_data("pbmc3k_scplantllm.h5ad")

print("=== Data Profile ===")
print(f"Species: {profile['species']}")
print(f"Gene scheme: {profile['gene_scheme']}")
print(f"Modality: {profile['modality']}")
print(f"Cells: {profile['n_cells']:,}")
print(f"Genes: {profile['n_genes']:,}")

# Validate compatibility
validation = ov.fm.preprocess_validate("pbmc3k_scplantllm.h5ad", "scplantllm", "embed")
print(f"\n=== Validation: {validation['status']} ===")
for d in validation.get("diagnostics", []):
    print(f"  [{d['severity']}] {d['message']}")
if validation.get("auto_fixes"):
    print("\nSuggested fixes:")
    for fix in validation["auto_fixes"]:
        print(f"  - {fix}")

result = ov.fm.run(
    task="embed",
    model_name="scplantllm",
    adata_path="pbmc3k_scplantllm.h5ad",
    output_path="pbmc3k_scplantllm_out.h5ad",
    device="auto",
)

if "error" in result:
    print(f"Error: {result['error']}")
    if "suggestion" in result:
        print(f"Suggestion: {result['suggestion']}")
else:
    print(f"Status: {result['status']}")
    print(f"Output keys: {result.get('output_keys', [])}")
    print(f"Cells processed: {result.get('n_cells', 0)}")

if os.path.exists("pbmc3k_scplantllm_out.h5ad"):
    adata_out = sc.read_h5ad("pbmc3k_scplantllm_out.h5ad")
    emb_key = "X_scplantllm"
    
    if emb_key in adata_out.obsm:
        print(f"Embedding shape: {adata_out.obsm[emb_key].shape}")
        
        # UMAP visualization
        sc.pp.neighbors(adata_out, use_rep=emb_key)
        sc.tl.umap(adata_out)
        sc.tl.leiden(adata_out, resolution=0.5)
        sc.pl.umap(adata_out, color=["leiden"],
                   title="scPlantLLM Embedding (PBMC 3k)")
        
        # QA metrics
        interpretation = ov.fm.interpret_results("pbmc3k_scplantllm_out.h5ad", task="embed")
        if "embeddings" in interpretation["metrics"]:
            for k, v in interpretation["metrics"]["embeddings"].items():
                print(f"\n{k}: dim={v['dim']}", end="")
                if "silhouette" in v:
                    print(f", silhouette={v['silhouette']:.4f}", end="")
                print()
    else:
        print(f"Embedding key {emb_key} not found.")
        print(f"Available keys: {list(adata_out.obsm.keys())}")
else:
    print("Output file not found — check model installation and adapter status.")
    print("See the Guide page for installation instructions.")