import seqcore as sc

# DNA sequences - efficient 2-bit encoding
dna = sc.DNAArray("ACGTACGTACGT" * 1_000_000)

# Batch operations
sequences = sc.DNAArray([
    "ACGTACGT",
    "TGCATGCA",
    "GGGGCCCC",
])

# Vectorized operations
gc = sc.gc_content(sequences)
lengths = sc.length(sequences)
rev_comp = sc.reverse_complement(sequences)

# Translation
proteins = sc.translate(sequences)

# GC content, molecular weight, length
gc = sc.gc_content(dna)
mw = sc.molecular_weight(protein)

# Transcription and translation
rna = sc.transcribe(dna)
protein = sc.translate(dna, frame=0)

# K-mer operations
kmers = sc.extract_kmers(sequences, k=21)
kmer_counts = sc.count_kmers(sequences, k=21)

# Pairwise alignment
result = sc.align(query, reference)
print(result.score, result.identity, result.cigar)

# Distance matrices
dm = sc.pairwise_distance(sequences, metric="edit")

# Pattern matching
matches = sc.find_pattern(sequences, "ATG[ACGT]{30,100}TAA")

# Auto-detect format
data = sc.read("sequences.fasta")
data = sc.read("structure.pdb")
data = sc.read("reads.fastq.gz")

# Streaming for large files
for batch in sc.read_stream("huge.fastq.gz", batch_size=100_000):
    results = process(batch)

# Database fetching
seq = sc.fetch("NP_000509")      # NCBI/UniProt
structure = sc.fetch("1ABC")     # PDB

# Load structure
structure = sc.read("protein.pdb")

# Access data
print(structure.chains)      # ['A', 'B']
print(structure.n_residues)  # 265

# Distance matrix
dm = sc.distance_matrix(structure, selection="CA")

# Find contacts
contacts = sc.find_contacts(structure, cutoff=4.0)

# RMSD calculation
rmsd = sc.rmsd(structure1, structure2, align=True)

# Surface analysis
sasa = sc.sasa(structure)
surface = sc.surface_residues(structure, threshold=25.0)

# Binding pockets
pockets = sc.find_pockets(structure)

# Small molecules
mol = sc.Molecule.from_smiles("CCO")

# Molecular properties
mw = sc.molecular_weight(molecules)
logp = sc.logp(molecules)
hbd = sc.h_bond_donors(molecules)

# ADMET filters
passes_lipinski = sc.lipinski_filter(molecules)
bbb_permeable = sc.bbb_filter(molecules)

# Fingerprints and similarity
fps = sc.morgan_fingerprint(molecules, radius=2)
similarity = sc.tanimoto_similarity(fps)

# Substructure search
matches = sc.substructure_search(molecules, "c1ccccc1")

# Tree construction
tree = sc.neighbor_joining(sequences)
tree = sc.upgma(sequences)

# Tree operations
print(tree.newick())
dist = tree.distance("Species_A", "Species_B")
subtree = tree.prune(["A", "B", "C"])

# Variant analysis
variants = sc.read("variants.vcf")
af = sc.allele_frequency(variants)
maf = sc.minor_allele_frequency(variants)

# Population statistics
fst = sc.fst(pop1, pop2)
pi = sc.nucleotide_diversity(sequences)
d = sc.tajimas_d(sequences)

# Linkage disequilibrium
ld = sc.linkage_disequilibrium(variants)

# Check GPU availability
if sc.gpu_available():
    print(sc.gpu_info())

# Device context
with sc.device("cuda:0"):
    result = sc.align(sequences, reference)

# Memory management
sc.set_memory_limit("8GB")
sc.clear_gpu_cache()

# Timing
with sc.timer() as t:
    result = sc.align(sequences, reference)
print(f"Completed in {t.elapsed:.2f}s")

# NumPy
arr = sequences.to_numpy()
sequences = sc.DNAArray.from_numpy(arr)

# pandas
df = sequences.to_dataframe()
df = structure.to_dataframe()

# Biopython
bio_seq = sequences[0].to_biopython()
sc_seq = sc.DNAArray.from_biopython(bio_seq)

# RDKit
rdkit_mol = molecule.to_rdkit()
sc_mol = sc.Molecule.from_rdkit(rdkit_mol)