# GATK HaplotypeCaller (傳統)
gatk HaplotypeCaller \
  -R hg38.fa \
  -I input.bam \
  -O gatk_output.vcf

# Google DeepVariant (AI)
docker run google/deepvariant:latest \
  --model_type=WGS \
  --ref=hg38.fa \
  --reads=input.bam \
  --output_vcf=deepvariant_output.vcf

# Google BigQuery Genomics
SELECT
  reference_name, start_position, 
  COUNT(*) as variant_count
FROM `bigquery-public-data.human_genome_variants.1000_genomes_phase_3_variants`
WHERE reference_name = 'chr17'
GROUP BY reference_name, start_position

# vs GATK + Spark 處理 VCF

# 1. 下載測試資料
wget https://storage.googleapis.com/deepvariant/case-study-testdata/HG001_NA12878.bam

# 2. GATK 環境
docker pull broadinstitute/gatk:latest

# 3. DeepVariant 環境
docker pull google/deepvariant:latest

# Step 1: GATK HaplotypeCaller (CPU)
time gatk HaplotypeCaller \
  -R hg38.fa \
  -I HG001.bam \
  -O gatk_output.vcf \
  --native-pair-hmm-threads 32

# Step 2: DeepVariant (GPU)
time docker run --gpus all google/deepvariant:latest \
  --model_type=WGS \
  --ref=hg38.fa \
  --reads=HG001.bam \
  --output_vcf=deepvariant_output.vcf \
  --num_shards=32

# Step 3: 對比結果
bcftools isec gatk_output.vcf deepvariant_output.vcf -p comparison/

# 使用 Google 的 Variant Transforms
docker run gcr.io/gcp-variant-transforms/gcp-variant-transforms \
  --input_pattern "gs://mybucket/*.vcf" \
  --output_table project:dataset.variants

# 然後可以用 SQL 查詢

from transformers import AutoTokenizer, AutoModelForSequenceClassification

# 載入模型
model = AutoModelForSequenceClassification.from_pretrained(
    "neuralbioinfo/prokbert-mini-long-promoter"
)
tokenizer = AutoTokenizer.from_pretrained(
    "neuralbioinfo/prokbert-mini-long-promoter"
)

# 預測啟動子
sequence = "ATGCGATCGATCG..."  # DNA序列
inputs = tokenizer(sequence, return_tensors="pt")
outputs = model(**inputs)
prediction = outputs.logits.argmax(-1)

import gradio as gr
from transformers import pipeline

# 載入模型
classifier = pipeline("text-classification", 
                     model="neuralbioinfo/prokbert-mini-long-promoter")

def predict_promoter(dna_sequence):
    result = classifier(dna_sequence)
    return result[0]['label'], result[0]['score']

# Gradio 介面
interface = gr.Interface(
    fn=predict_promoter,
    inputs=gr.Textbox(label="輸入DNA序列", placeholder="ATGC..."),
    outputs=[
        gr.Textbox(label="預測結果"),
        gr.Number(label="置信度")
    ],
    title="啟動子預測工具",
    description="使用 ProkBERT 預測原核生物啟動子"
)

interface.launch()

def predict_pathogenicity(gene, position, ref, alt):
    # 獲取上下文序列
    context = get_sequence(gene, position-50, position+50)
    # 用 DNABERT 預測
    wildtype_score = model(context)
    # 替換變異
    mutant_context = context.replace(ref, alt)
    mutant_score = model(mutant_context)
    # 計算影響
    delta = abs(wildtype_score - mutant_score)
    return "Pathogenic" if delta > threshold else "Benign"

def explain_variant(vcf_line, model="BioGPT"):
    # 解析 VCF
    chrom, pos, ref, alt, gene, consequence = parse_vcf(vcf_line)

    # 生成提示
    prompt = f"""
    變異資訊：
    - 染色體: {chrom}
    - 位置: {pos}
    - 基因: {gene}
    - 改變: {ref}>{alt}
    - 後果: {consequence}

    請用中文解釋這個變異的臨床意義：
    """

    # 呼叫 LLM
    explanation = llm.generate(prompt)
    return explanation

更新日期: 2026-01-29

下一步: 開始 DeepVariant vs GATK 對比測試