tooluniverse-precision-medicine-stratification

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Precision Medicine Patient Stratification

精准医学患者分层

Transform patient genomic and clinical profiles into actionable risk stratification, treatment recommendations, and personalized therapeutic strategies. Integrates germline genetics, somatic alterations, pharmacogenomics, pathway biology, and clinical evidence to produce a quantitative risk score with tiered management recommendations.

KEY PRINCIPLES:

Report-first approach - Create report file FIRST, then populate progressively
Disease-specific logic - Cancer vs metabolic vs rare disease pipelines diverge at Phase 2
Multi-level integration - Germline + somatic + expression + clinical data layers
Evidence-graded - Every finding has an evidence tier (T1-T4)
Quantitative output - Precision Medicine Risk Score (0-100) with transparent components
Pharmacogenomic guidance - Drug selection AND dosing recommendations
Guideline-concordant - Reference NCCN, ACC/AHA, ADA, and other guidelines
Source-referenced - Every statement cites the tool/database source
Completeness checklist - Mandatory section showing data availability and analysis coverage
English-first queries - Always use English terms in tool calls. Respond in user's language

将患者的基因组和临床特征转化为可执行的风险分层、治疗建议和个性化治疗策略。整合种系遗传学、体细胞变异、药物基因组学、通路生物学和临床证据，生成定量风险评分及分层管理建议。

核心原则:

报告优先方法 - 先创建报告文件，再逐步填充内容
疾病特异性逻辑 - 癌症、代谢性疾病和罕见病的分析流程在第2阶段开始分化
多层面整合 - 种系+体细胞+基因表达+临床数据层面
证据分级 - 所有发现均带有证据等级（T1-T4）
定量输出 - 精准医学风险评分（0-100分），且评分构成透明
药物基因组学指导 - 同时提供药物选择和剂量建议
符合指南要求 - 参考NCCN、ACC/AHA、ADA等指南
来源标注 - 所有结论均标注所使用的工具/数据库来源
完整性检查清单 - 必须包含数据可用性和分析覆盖情况的章节
英文优先查询 - 工具调用时始终使用英文术语，以用户语言响应

When to Use

适用场景

Apply when user asks:

"Stratify this breast cancer patient: ER+/HER2-, BRCA1 mutation, stage II"
"What is the risk profile for this diabetes patient with HbA1c 8.5 and CYP2C19 poor metabolizer?"
"NSCLC patient with EGFR L858R, stage IV, TMB 25 - treatment strategy?"
"Predict prognosis and recommend treatment for this cardiovascular patient"
"Patient has Marfan syndrome with FBN1 mutation - risk stratification"
"Alzheimer's risk assessment: APOE e4/e4, family history positive"
"Personalized treatment plan for type 2 diabetes with genetic risk factors"
"Which therapy is best for this patient's molecular profile?"

NOT for (use other skills instead):

Single variant interpretation -> Use

tooluniverse-variant-interpretation

tooluniverse-cancer-variant-interpretation

Immunotherapy-specific prediction -> Use

tooluniverse-immunotherapy-response-prediction

Drug safety profiling only -> Use
```
tooluniverse-adverse-event-detection
```
Target validation -> Use
```
tooluniverse-drug-target-validation
```
Clinical trial search only -> Use
```
tooluniverse-clinical-trial-matching
```
Drug-drug interaction analysis only -> Use
```
tooluniverse-drug-drug-interaction
```
PRS calculation only -> Use
```
tooluniverse-polygenic-risk-score
```

当用户提出以下需求时适用:

"对这位ER+/HER2-、携带BRCA1突变的II期乳腺癌患者进行分层"
"这位HbA1c为8.5且CYP2C19弱代谢型的糖尿病患者，风险特征是什么？"
"携带EGFR L858R突变、TMB为25的IV期NSCLC患者，治疗策略是什么？"
"预测这位心血管疾病患者的预后并推荐治疗方案"
"携带FBN1突变的马凡综合征患者，进行风险分层"
"阿尔茨海默病风险评估：APOE e4/e4基因型，家族史阳性"
"针对携带遗传风险因素的2型糖尿病患者制定个性化治疗计划"
"哪种疗法最适合这位患者的分子特征？"

不适用场景（请使用其他工具）:

单一变异解读 -> 使用

tooluniverse-variant-interpretation

或

tooluniverse-cancer-variant-interpretation

免疫治疗特异性预测 -> 使用

tooluniverse-immunotherapy-response-prediction

仅药物安全性分析 -> 使用
```
tooluniverse-adverse-event-detection
```
靶点验证 -> 使用
```
tooluniverse-drug-target-validation
```
仅临床试验搜索 -> 使用
```
tooluniverse-clinical-trial-matching
```
仅药物相互作用分析 -> 使用
```
tooluniverse-drug-drug-interaction
```
仅PRS计算 -> 使用
```
tooluniverse-polygenic-risk-score
```

Input Parsing

输入解析

Required Input

必填输入

Disease/condition: Free-text disease name (e.g., "breast cancer", "type 2 diabetes", "Marfan syndrome")
At least one of: Germline variants, somatic mutations, gene list, or clinical biomarkers

疾病/病症: 自由文本格式的疾病名称（例如："乳腺癌"、"2型糖尿病"、"马凡综合征"）
至少一项: 种系变异、体细胞突变、基因列表或临床生物标志物

Strongly Recommended

强烈推荐输入

Genomic data: Specific variants (e.g., "BRCA1 c.68_69delAG", "EGFR L858R"), gene names, or expression changes
Clinical parameters: Age, sex, disease stage, biomarkers (HbA1c, PSA, LDL-C)

基因组数据: 具体变异（例如："BRCA1 c.68_69delAG"、"EGFR L858R"）、基因名称或基因表达变化
临床参数: 年龄、性别、疾病分期、生物标志物（HbA1c、PSA、LDL-C）

Optional (improves stratification)

可选输入（可提升分层准确性）

Comorbidities: Other conditions (e.g., "hypertension", "diabetes")
Prior treatments: Previous therapies and responses
Family history: Affected relatives, inheritance pattern
Ethnicity: For population-specific risk calibration
Current medications: For DDI and pharmacogenomic analysis
Stratification goal: Risk assessment, treatment selection, prognosis, prevention

合并症: 其他疾病（例如："高血压"、"糖尿病"）
既往治疗史: 之前接受的治疗及疗效
家族史: 患病亲属、遗传模式
种族: 用于人群特异性风险校准
当前用药: 用于DDI和药物基因组学分析
分层目标: 风险评估、治疗方案选择、预后预测、疾病预防

Input Format Examples

输入格式示例

Format	Example	How to Parse
Cancer + mutations + stage	"Breast cancer, BRCA1 mut, ER+, HER2-, stage II"	disease=breast_cancer, mutations=[BRCA1], biomarkers={ER:+, HER2:-}, stage=II
Metabolic + biomarkers + PGx	"T2D, HbA1c 8.5, CYP2C19 2/2"	disease=T2D, biomarkers={HbA1c:8.5}, pgx={CYP2C19:poor_metabolizer}
CVD risk profile	"High LDL 190, SLCO1B1*5, family hx MI"	disease=CVD, biomarkers={LDL:190}, pgx={SLCO1B1:*5}, family_hx=positive
Rare disease + variant	"Marfan, FBN1 c.4082G>A"	disease=Marfan, mutations=[FBN1 c.4082G>A], disease_type=rare
Neuro risk	"Alzheimer risk, APOE e4/e4, age 55"	disease=AD, genotype={APOE:e4/e4}, clinical={age:55}
Cancer + comprehensive	"NSCLC, EGFR L858R, TMB 25, PD-L1 80%, stage IV"	disease=NSCLC, mutations=[EGFR L858R], biomarkers={TMB:25, PDL1:80}, stage=IV

格式	示例	解析方式
癌症+突变+分期	"乳腺癌，BRCA1突变，ER+，HER2-，II期"	disease=breast_cancer, mutations=[BRCA1], biomarkers={ER:+, HER2:-}, stage=II
代谢性疾病+生物标志物+PGx	"2型糖尿病，HbA1c 8.5，CYP2C19 2/2"	disease=T2D, biomarkers={HbA1c:8.5}, pgx={CYP2C19:poor_metabolizer}
CVD风险特征	"LDL 190，SLCO1B1*5，家族史有心肌梗死"	disease=CVD, biomarkers={LDL:190}, pgx={SLCO1B1:*5}, family_hx=positive
罕见病+变异	"马凡综合征，FBN1 c.4082G>A"	disease=Marfan, mutations=[FBN1 c.4082G>A], disease_type=rare
神经系统疾病风险	"阿尔茨海默病风险，APOE e4/e4，年龄55"	disease=AD, genotype={APOE:e4/e4}, clinical={age:55}
癌症+全面数据	"NSCLC，EGFR L858R，TMB 25，PD-L1 80%，IV期"	disease=NSCLC, mutations=[EGFR L858R], biomarkers={TMB:25, PDL1:80}, stage=IV

Disease Type Classification

疾病类型分类

Classify the disease into one of these categories (determines Phase 2 routing):

Category	Examples	Key Stratification Axes
CANCER	Breast, lung, colorectal, melanoma, prostate	Stage, molecular subtype, TMB, driver mutations, hormone receptors
METABOLIC	Type 2 diabetes, obesity, metabolic syndrome, NAFLD	HbA1c, BMI, genetic risk, comorbidities, CYP genotypes
CARDIOVASCULAR	CAD, heart failure, atrial fibrillation, hypertension	ASCVD risk, LDL, genetic risk, statin PGx, anticoagulant PGx
NEUROLOGICAL	Alzheimer, Parkinson, epilepsy, multiple sclerosis	APOE status, genetic risk, age of onset, PGx for anticonvulsants
RARE/MONOGENIC	Marfan, CF, sickle cell, Huntington, PKU	Causal variant, penetrance, genotype-phenotype correlation
AUTOIMMUNE	RA, lupus, MS, Crohn's, ulcerative colitis	HLA associations, genetic risk, biologics PGx

将疾病归类为以下类别之一（决定第2阶段的分析路径）:

类别	示例	核心分层维度
癌症	乳腺癌、肺癌、结直肠癌、黑色素瘤、前列腺癌	分期、分子亚型、TMB、驱动突变、激素受体
代谢性疾病	2型糖尿病、肥胖、代谢综合征、NAFLD	HbA1c、BMI、遗传风险、合并症、CYP基因型
心血管疾病	冠心病、心力衰竭、心房颤动、高血压	ASCVD风险、LDL、遗传风险、他汀类药物PGx、抗凝药物PGx
神经系统疾病	阿尔茨海默病、帕金森病、癫痫、多发性硬化	APOE状态、遗传风险、发病年龄、抗惊厥药物PGx
罕见/单基因病	马凡综合征、囊性纤维化、镰状细胞病、亨廷顿舞蹈症、苯丙酮尿症	致病性变异、外显率、基因型-表型相关性
自身免疫病	类风湿关节炎、狼疮、多发性硬化、克罗恩病、溃疡性结肠炎	HLA关联、遗传风险、生物制剂PGx

Gene Symbol Normalization

基因符号标准化

Common Alias	Official Symbol	Notes
HER2	ERBB2	Breast cancer biomarker
PD-L1	CD274	Immunotherapy biomarker
EGFR	EGFR	Lung cancer driver
BRCA1/2	BRCA1, BRCA2	Hereditary cancer
CYP2D6	CYP2D6	Drug metabolism
CYP2C19	CYP2C19	Clopidogrel, PPIs
CYP3A4	CYP3A4	Major drug metabolism
VKORC1	VKORC1	Warfarin dosing
SLCO1B1	SLCO1B1	Statin myopathy
DPYD	DPYD	Fluoropyrimidine toxicity
UGT1A1	UGT1A1	Irinotecan toxicity
TPMT	TPMT	Thiopurine toxicity

常用别名	官方符号	说明
HER2	ERBB2	乳腺癌生物标志物
PD-L1	CD274	免疫治疗生物标志物
EGFR	EGFR	肺癌驱动基因
BRCA1/2	BRCA1, BRCA2	遗传性癌症相关基因
CYP2D6	CYP2D6	药物代谢基因
CYP2C19	CYP2C19	氯吡格雷、质子泵抑制剂相关基因
CYP3A4	CYP3A4	主要药物代谢基因
VKORC1	VKORC1	华法林剂量相关基因
SLCO1B1	SLCO1B1	他汀类肌病相关基因
DPYD	DPYD	氟嘧啶毒性相关基因
UGT1A1	UGT1A1	伊立替康毒性相关基因
TPMT	TPMT	硫嘌呤毒性相关基因

Phase 0: Tool Parameter Reference (CRITICAL)

阶段0：工具参数参考（至关重要）

BEFORE calling ANY tool, verify parameters using this reference table.

调用任何工具前，请使用此参考表验证参数。

Verified Tool Parameters

已验证工具参数

Tool	Parameters	Response Structure	Notes
`OpenTargets_get_disease_id_description_by_name`	`diseaseName`	`{data: {search: {hits: [{id, name, description}]}}}`	Disease to EFO ID
`OpenTargets_get_drug_id_description_by_name`	`drugName`	`{data: {search: {hits: [{id, name, description}]}}}`	Drug to ChEMBL ID
`OpenTargets_get_associated_drugs_by_disease_efoId`	`efoId` , `size`	`{data: {disease: {knownDrugs: {count, rows}}}}`	Drugs for disease
`OpenTargets_get_associated_targets_by_disease_efoId`	`efoId` , `size`	`{data: {disease: {associatedTargets: {count, rows}}}}`	Genetic associations
`OpenTargets_get_drug_mechanisms_of_action_by_chemblId`	`chemblId`	`{data: {drug: {mechanismsOfAction: {rows}}}}`	Drug MOA
`OpenTargets_get_approved_indications_by_drug_chemblId`	`chemblId`	Approved indications list	Check drug approvals
`OpenTargets_get_drug_adverse_events_by_chemblId`	`chemblId`	`{data: {drug: {adverseEvents: {count, rows}}}}`	Drug safety
`OpenTargets_get_associated_drugs_by_target_ensemblID`	`ensemblId` , `size`	Drug-target associations	Drugs targeting gene
`OpenTargets_get_target_safety_profile_by_ensemblID`	`ensemblId`	Safety profile data	Target safety
`OpenTargets_get_target_tractability_by_ensemblID`	`ensemblId`	Tractability assessment	Druggability
`OpenTargets_get_diseases_phenotypes_by_target_ensembl`	`ensemblId`	Disease-phenotype associations	Gene-disease links
`OpenTargets_target_disease_evidence`	`ensemblId` , `efoId` , `size`	Evidence for target-disease pair	Specific gene-disease evidence
`OpenTargets_search_gwas_studies_by_disease`	`diseaseIds` (array), `size`	`{data: {studies: {count, rows}}}`	GWAS studies
`OpenTargets_drug_pharmacogenomics_data`	`chemblId`	Pharmacogenomic data	Drug PGx
`MyGene_query_genes`	`query` (NOT `q` )	`{hits: [{_id, symbol, name, ensembl: {gene}}]}`	Gene resolution
`ensembl_lookup_gene`	`gene_id` , `species='homo_sapiens'`	`{data: {id, display_name, description, biotype}}`	REQUIRES species
`EnsemblVEP_annotate_rsid`	`variant_id` (NOT `rsid` )	VEP annotation with SIFT/PolyPhen	Variant impact
`EnsemblVEP_annotate_hgvs`	`hgvs_notation` , `species`	VEP annotation	HGVS variant annotation
`ensembl_get_variation`	`variant_id` , `species`	Variant details	rsID lookup
`clinvar_search_variants`	`gene` , `significance` , `limit`	Variant list	Search ClinVar
`clinvar_get_variant_details`	`variant_id`	Variant details with clinical significance	ClinVar details
`clinvar_get_clinical_significance`	`variant_id`	Clinical significance only	Quick pathogenicity
`civic_search_evidence_items`	`therapy_name` , `disease_name`	`{data: {evidenceItems: {nodes}}}`	Clinical evidence
`civic_search_variants`	`name` , `gene_name`	`{data: {variants: {nodes}}}`	Variant clinical significance
`civic_search_assertions`	`therapy_name` , `disease_name`	`{data: {assertions: {nodes}}}`	Clinical assertions
`cBioPortal_get_mutations`	`study_id` , `gene_list` (STRING, not array)	`{status, data: [{...}]}`	Somatic mutation data
`gwas_get_associations_for_trait`	`trait`	GWAS associations	Trait-SNP associations
`gwas_search_associations`	`query`	GWAS associations	Broad GWAS search
`gwas_get_snps_for_gene`	`gene`	SNPs associated with gene	Gene GWAS hits
`GWAS_search_associations_by_gene`	`gene_name`	Gene GWAS associations	Gene-trait links
`PharmGKB_get_clinical_annotations`	`query`	Clinical annotations	Drug-gene-phenotype
`PharmGKB_get_dosing_guidelines`	`query`	Dosing guidelines	PGx dosing
`PharmGKB_search_variants`	`query`	Variant PGx data	PGx variant search
`PharmGKB_get_gene_details`	`query`	Gene PGx details	PGx gene info
`PharmGKB_get_drug_details`	`query`	Drug PGx details	Drug PGx info
`fda_pharmacogenomic_biomarkers`	`drug_name` , `biomarker` , `limit`	`{count, shown, results: [{Drug, Biomarker, ...}]}`	FDA PGx biomarkers
`FDA_get_pharmacogenomics_info_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	FDA PGx label info
`FDA_get_indications_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	FDA indications
`FDA_get_clinical_studies_info_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	Clinical study data
`FDA_get_contraindications_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	Contraindications
`FDA_get_warnings_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	Warnings
`FDA_get_boxed_warning_info_by_drug_name`	`drug_name` , `limit`	May return NOT_FOUND	Boxed warnings
`FDA_get_drug_interactions_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	DDI info
`drugbank_get_drug_basic_info_by_drug_name_or_id`	`query` , `case_sensitive` , `exact_match` , `limit`	Drug basic info	ALL 4 REQUIRED
`drugbank_get_targets_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	Drug targets	ALL 4 REQUIRED
`drugbank_get_pharmacology_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	Pharmacology	ALL 4 REQUIRED
`drugbank_get_indications_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	Indications	ALL 4 REQUIRED
`drugbank_get_drug_interactions_by_drug_name_or_id`	`query` , `case_sensitive` , `exact_match` , `limit`	DDI data	ALL 4 REQUIRED
`drugbank_get_safety_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	Safety data	ALL 4 REQUIRED
`enrichr_gene_enrichment_analysis`	`gene_list` (array), `libs` (array, REQUIRED)	Enrichment results	Key libs: `KEGG_2021_Human` , `Reactome_2022` , `GO_Biological_Process_2023`
`ReactomeAnalysis_pathway_enrichment`	`identifiers` (space-separated string)	`{data: {pathways: [{pathway_id, name, p_value, ...}]}}`	Pathway enrichment
`Reactome_map_uniprot_to_pathways`	`id` (UniProt accession)	List of pathways	Gene-to-pathway
`STRING_get_interaction_partners`	`protein_ids` (array), `species` (9606), `limit`	Interaction partners	PPI network
`STRING_functional_enrichment`	`protein_ids` (array), `species` (9606)	Functional enrichment	Network enrichment
`HPA_get_cancer_prognostics_by_gene`	`gene_name`	Cancer prognostic data	Prognostic markers
`HPA_get_rna_expression_by_source`	`gene_name` , `source_type` , `source_name` (ALL 3)	Expression data	Tissue expression
`gnomad_get_gene_constraints`	`gene_symbol`	Gene constraint metrics	LoF intolerance
`gnomad_get_variant`	`variant_id`	Variant frequency	Population frequency
`clinical_trials_search`	`action='search_studies'` , `condition` , `intervention` , `limit`	`{total_count, studies}`	Trial search
`search_clinical_trials`	`query_term` (REQUIRED), `condition` , `intervention` , `pageSize`	`{studies, total_count}`	Alternative trial search
`PubMed_search_articles`	`query` , `max_results`	Plain list of dicts	Literature
`PubMed_Guidelines_Search`	`query` , `limit` (REQUIRED)	List of guideline articles	Clinical guidelines (may require API key)
`UniProt_get_function_by_accession`	`accession`	List of strings	Protein function
`UniProt_get_disease_variants_by_accession`	`accession`	Disease variants	Known pathogenic variants

工具	参数	响应结构	说明
`OpenTargets_get_disease_id_description_by_name`	`diseaseName`	`{data: {search: {hits: [{id, name, description}]}}}`	疾病转EFO ID
`OpenTargets_get_drug_id_description_by_name`	`drugName`	`{data: {search: {hits: [{id, name, description}]}}}`	药物转ChEMBL ID
`OpenTargets_get_associated_drugs_by_disease_efoId`	`efoId` , `size`	`{data: {disease: {knownDrugs: {count, rows}}}}`	疾病相关药物
`OpenTargets_get_associated_targets_by_disease_efoId`	`efoId` , `size`	`{data: {disease: {associatedTargets: {count, rows}}}}`	遗传关联靶点
`OpenTargets_get_drug_mechanisms_of_action_by_chemblId`	`chemblId`	`{data: {drug: {mechanismsOfAction: {rows}}}}`	药物作用机制
`OpenTargets_get_approved_indications_by_drug_chemblId`	`chemblId`	获批适应症列表	检查药物获批情况
`OpenTargets_get_drug_adverse_events_by_chemblId`	`chemblId`	`{data: {drug: {adverseEvents: {count, rows}}}}`	药物安全性
`OpenTargets_get_associated_drugs_by_target_ensemblID`	`ensemblId` , `size`	药物-靶点关联	靶向该基因的药物
`OpenTargets_get_target_safety_profile_by_ensemblID`	`ensemblId`	靶点安全性数据	靶点安全性
`OpenTargets_get_target_tractability_by_ensemblID`	`ensemblId`	成药性评估	可成药性
`OpenTargets_get_diseases_phenotypes_by_target_ensembl`	`ensemblId`	疾病-表型关联	基因-疾病关联
`OpenTargets_target_disease_evidence`	`ensemblId` , `efoId` , `size`	靶点-疾病对的证据	特定基因-疾病证据
`OpenTargets_search_gwas_studies_by_disease`	`diseaseIds` (数组), `size`	`{data: {studies: {count, rows}}}`	GWAS研究
`OpenTargets_drug_pharmacogenomics_data`	`chemblId`	药物基因组学数据	药物PGx
`MyGene_query_genes`	`query` (非 `q` )	`{hits: [{_id, symbol, name, ensembl: {gene}}]}`	基因解析
`ensembl_lookup_gene`	`gene_id` , `species='homo_sapiens'`	`{data: {id, display_name, description, biotype}}`	必须指定物种
`EnsemblVEP_annotate_rsid`	`variant_id` (非 `rsid` )	包含SIFT/PolyPhen的VEP注释	变异影响
`EnsemblVEP_annotate_hgvs`	`hgvs_notation` , `species`	VEP注释	HGVS变异注释
`ensembl_get_variation`	`variant_id` , `species`	变异详情	rsID查询
`clinvar_search_variants`	`gene` , `significance` , `limit`	变异列表	搜索ClinVar
`clinvar_get_variant_details`	`variant_id`	包含临床意义的变异详情	ClinVar详情
`clinvar_get_clinical_significance`	`variant_id`	仅临床意义	快速致病性判断
`civic_search_evidence_items`	`therapy_name` , `disease_name`	`{data: {evidenceItems: {nodes}}}`	临床证据
`civic_search_variants`	`name` , `gene_name`	`{data: {variants: {nodes}}}`	变异临床意义
`civic_search_assertions`	`therapy_name` , `disease_name`	`{data: {assertions: {nodes}}}`	临床声明
`cBioPortal_get_mutations`	`study_id` , `gene_list` (字符串，非数组)	`{status, data: [{...}]}`	体细胞突变数据
`gwas_get_associations_for_trait`	`trait`	GWAS关联	性状-SNP关联
`gwas_search_associations`	`query`	GWAS关联	广泛GWAS搜索
`gwas_get_snps_for_gene`	`gene`	与基因相关的SNP	基因GWAS位点
`GWAS_search_associations_by_gene`	`gene_name`	基因GWAS关联	基因-性状关联
`PharmGKB_get_clinical_annotations`	`query`	临床注释	药物-基因-表型关联
`PharmGKB_get_dosing_guidelines`	`query`	剂量指南	PGx剂量指南
`PharmGKB_search_variants`	`query`	变异PGx数据	PGx变异搜索
`PharmGKB_get_gene_details`	`query`	基因PGx详情	PGx基因信息
`PharmGKB_get_drug_details`	`query`	药物PGx详情	药物PGx信息
`fda_pharmacogenomic_biomarkers`	`drug_name` , `biomarker` , `limit`	`{count, shown, results: [{Drug, Biomarker, ...}]}`	FDA PGx生物标志物
`FDA_get_pharmacogenomics_info_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	FDA PGx标签信息
`FDA_get_indications_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	FDA适应症
`FDA_get_clinical_studies_info_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	临床研究数据
`FDA_get_contraindications_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	禁忌症
`FDA_get_warnings_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	警告信息
`FDA_get_boxed_warning_info_by_drug_name`	`drug_name` , `limit`	可能返回NOT_FOUND	黑框警告
`FDA_get_drug_interactions_by_drug_name`	`drug_name` , `limit`	`{meta, results}`	DDI信息
`drugbank_get_drug_basic_info_by_drug_name_or_id`	`query` , `case_sensitive` , `exact_match` , `limit`	药物基本信息	4个参数均为必填
`drugbank_get_targets_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	药物靶点	4个参数均为必填
`drugbank_get_pharmacology_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	药理学信息	4个参数均为必填
`drugbank_get_indications_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	适应症	4个参数均为必填
`drugbank_get_drug_interactions_by_drug_name_or_id`	`query` , `case_sensitive` , `exact_match` , `limit`	DDI数据	4个参数均为必填
`drugbank_get_safety_by_drug_name_or_drugbank_id`	`query` , `case_sensitive` , `exact_match` , `limit`	安全性数据	4个参数均为必填
`enrichr_gene_enrichment_analysis`	`gene_list` (数组), `libs` (数组，必填)	富集分析结果	核心数据库： `KEGG_2021_Human` , `Reactome_2022` , `GO_Biological_Process_2023`
`ReactomeAnalysis_pathway_enrichment`	`identifiers` (空格分隔字符串)	`{data: {pathways: [{pathway_id, name, p_value, ...}]}}`	通路富集分析
`Reactome_map_uniprot_to_pathways`	`id` (UniProt编号)	通路列表	基因-通路映射
`STRING_get_interaction_partners`	`protein_ids` (数组), `species` (9606), `limit`	相互作用伙伴	蛋白质相互作用网络
`STRING_functional_enrichment`	`protein_ids` (数组), `species` (9606)	功能富集分析	网络富集分析
`HPA_get_cancer_prognostics_by_gene`	`gene_name`	癌症预后数据	预后标志物
`HPA_get_rna_expression_by_source`	`gene_name` , `source_type` , `source_name` (3个均必填)	表达数据	组织表达
`gnomad_get_gene_constraints`	`gene_symbol`	基因约束指标	功能缺失不耐受性
`gnomad_get_variant`	`variant_id`	变异频率	人群频率
`clinical_trials_search`	`action='search_studies'` , `condition` , `intervention` , `limit`	`{total_count, studies}`	临床试验搜索
`search_clinical_trials`	`query_term` (必填), `condition` , `intervention` , `pageSize`	`{studies, total_count}`	备选临床试验搜索
`PubMed_search_articles`	`query` , `max_results`	字典纯列表	文献检索
`PubMed_Guidelines_Search`	`query` , `limit` (必填)	指南文献列表	临床指南（可能需要API密钥）
`UniProt_get_function_by_accession`	`accession`	字符串列表	蛋白质功能
`UniProt_get_disease_variants_by_accession`	`accession`	疾病相关变异	已知致病性变异

Response Format Notes

响应格式说明

OpenTargets: Always nested
```
{data: {entity: {field: ...}}}
```
structure

FDA label tools: Return

{meta: {disclaimer, terms, license, ...}, results: [...]}

. Access via

result['results'][0]['field']

DrugBank: ALL tools require 4 params:
```
query
```
,
```
case_sensitive
```
(bool),
```
exact_match
```
(bool),
```
limit
```
(int)
PharmGKB: Returns complex nested objects. Check for
```
data
```
wrapper
PubMed_search_articles: Returns a plain list of dicts, NOT
```
{articles: [...]}
```
ClinVar:
```
clinvar_search_variants
```
returns list of variants with clinical significance
gnomAD: May return "Service overloaded" - treat as transient, retry or skip
fda_pharmacogenomic_biomarkers: Default limit=10, use
```
limit=1000
```
to get all
cBioPortal_get_mutations:
```
gene_list
```
is a STRING, not array. cBioPortal tools may have URL bugs
ClinVar: May return either a plain list or
```
{status, data: {esearchresult: {count, idlist}}}
```
- handle both
EnsemblVEP: May return either a list
```
[{...}]
```
or
```
{data: {...}, metadata: {...}}
```
- handle both
PubMed_Guidelines_Search: Requires
```
limit
```
parameter (NOT
```
max_results
```
), may require API key. Use
```
PubMed_search_articles
```
as fallback
gwas_get_associations_for_trait: May return errors; use
```
gwas_search_associations
```
instead
MyGene CYP2D6: First result may be LOC110740340; always filter by
```
symbol
```
match

OpenTargets: 始终为嵌套
```
{data: {entity: {field: ...}}}
```
结构

FDA标签工具: 返回

{meta: {disclaimer, terms, license, ...}, results: [...]}

。通过

result['results'][0]['field']

访问数据

DrugBank: 所有工具均需4个参数：
```
query
```
,
```
case_sensitive
```
(布尔值),
```
exact_match
```
(布尔值),
```
limit
```
(整数)
PharmGKB: 返回复杂嵌套对象，需检查是否有
```
data
```
包装层
PubMed_search_articles: 返回字典纯列表，而非
```
{articles: [...]}
```
ClinVar:
```
clinvar_search_variants
```
返回包含临床意义的变异列表
gnomAD: 可能返回"Service overloaded" - 视为临时问题，可重试或跳过
fda_pharmacogenomic_biomarkers: 默认limit=10，使用
```
limit=1000
```
获取全部结果
cBioPortal_get_mutations:
```
gene_list
```
为字符串，非数组。cBioPortal工具可能存在URL问题
ClinVar: 可能返回纯列表或
```
{status, data: {esearchresult: {count, idlist}}}
```
- 需兼容两种格式
EnsemblVEP: 可能返回列表
```
[{...}]
```
或
```
{data: {...}, metadata: {...}}
```
- 需兼容两种格式
PubMed_Guidelines_Search: 需
```
limit
```
参数（非
```
max_results
```
），可能需要API密钥。可使用
```
PubMed_search_articles
```
作为备选
gwas_get_associations_for_trait: 可能返回错误；可使用
```
gwas_search_associations
```
替代
MyGene CYP2D6: 第一个结果可能为LOC110740340；需始终按
```
symbol
```
匹配过滤

Workflow Overview

工作流程概述

Input: Disease + Genomic data + Clinical parameters + Stratification goal

Phase 1: Disease Disambiguation & Profile Standardization
  - Resolve disease to EFO/MONDO IDs
  - Classify disease type (cancer/metabolic/CVD/neuro/rare/autoimmune)
  - Parse genomic data (variants, genes, expression)
  - Resolve gene IDs (Ensembl, Entrez, UniProt)

Phase 2: Genetic Risk Assessment
  - Germline variant pathogenicity (ClinVar, VEP)
  - Gene-disease association strength (OpenTargets)
  - GWAS-based polygenic risk estimation
  - Population frequency (gnomAD)
  - Gene constraint/intolerance (gnomAD)

Phase 3: Disease-Specific Molecular Stratification
  CANCER PATH:
    - Molecular subtyping (driver mutations, receptor status)
    - Prognostic markers (stage + grade + molecular)
    - TMB/MSI/HRD assessment
    - Somatic mutation landscape (cBioPortal)
  METABOLIC PATH:
    - Genetic risk + clinical risk integration
    - Complication risk (nephropathy, neuropathy, CVD)
    - Monogenic subtypes (MODY, lipodystrophy)
  CVD PATH:
    - ASCVD risk integration
    - Familial hypercholesterolemia genes
    - Statin/anticoagulant PGx
  RARE DISEASE PATH:
    - Causal variant identification
    - Genotype-phenotype correlation
    - Penetrance estimation

Phase 4: Pharmacogenomic Profiling
  - Drug-metabolizing enzyme genotypes (CYP2D6, CYP2C19, CYP3A4)
  - Drug transporter variants (SLCO1B1, ABCB1)
  - Drug target variants (VKORC1, DPYD, UGT1A1)
  - HLA alleles (drug hypersensitivity risk)
  - PharmGKB clinical annotations
  - FDA pharmacogenomic biomarkers

Phase 5: Comorbidity & Drug Interaction Risk
  - Disease-disease genetic overlap
  - Impact on treatment selection
  - Drug-drug interaction risk
  - Pharmacogenomic DDI amplification

Phase 6: Molecular Pathway Analysis
  - Dysregulated pathway identification (Reactome, KEGG)
  - Network disruption analysis (STRING)
  - Druggable pathway targets
  - Pathway-based therapeutic opportunities

Phase 7: Clinical Evidence & Guidelines
  - Guideline-based risk categories (NCCN, ACC/AHA, ADA)
  - FDA-approved therapies for patient profile
  - Literature evidence (PubMed)
  - Biomarker-guided treatment evidence

Phase 8: Clinical Trial Matching
  - Trials matching molecular profile
  - Biomarker-driven trials
  - Precision medicine basket/umbrella trials
  - Risk-adapted trials

Phase 9: Integrated Scoring & Recommendations
  - Calculate Precision Medicine Risk Score (0-100)
  - Risk tier assignment (Low/Int/High/Very High)
  - Treatment algorithm (1st/2nd/3rd line)
  - Monitoring plan
  - Outcome predictions

输入: 疾病 + 基因组数据 + 临床参数 + 分层目标

阶段1：疾病明确诊断与特征标准化
  - 将疾病解析为EFO/MONDO ID
  - 疾病类型分类（癌症/代谢性疾病/CVD/神经系统疾病/罕见病/自身免疫病）
  - 解析基因组数据（变异、基因、表达）
  - 解析基因ID（Ensembl、Entrez、UniProt）

阶段2：遗传风险评估
  - 种系变异致病性（ClinVar、VEP）
  - 基因-疾病关联强度（OpenTargets）
  - 基于GWAS的多基因风险估计
  - 人群频率（gnomAD）
  - 基因约束/不耐受性（gnomAD）

阶段3：疾病特异性分子分层
  癌症路径:
    - 分子亚型划分（驱动突变、受体状态）
    - 预后标志物（分期+分级+分子特征）
    - TMB/MSI/HRD评估
    - 体细胞突变图谱（cBioPortal）
  代谢性疾病路径:
    - 遗传风险+临床风险整合
    - 并发症风险（肾病、神经病变、CVD）
    - 单基因亚型（MODY、脂肪营养不良）
  CVD路径:
    - ASCVD风险整合
    - 家族性高胆固醇血症相关基因
    - 他汀类/抗凝药物PGx
  罕见病路径:
    - 致病性变异识别
    - 基因型-表型相关性
    - 外显率估计

阶段4：药物基因组学分析
  - 药物代谢酶基因型（CYP2D6、CYP2C19、CYP3A4）
  - 药物转运体变异（SLCO1B1、ABCB1）
  - 药物靶点变异（VKORC1、DPYD、UGT1A1）
  - HLA等位基因（药物超敏反应风险）
  - PharmGKB临床注释
  - FDA药物基因组学生物标志物

阶段5：合并症与药物相互作用风险
  - 疾病-疾病遗传重叠
  - 对治疗方案选择的影响
  - 药物-药物相互作用风险
  - 药物基因组学放大的DDI风险

阶段6：分子通路分析
  - 失调通路识别（Reactome、KEGG）
  - 网络破坏分析（STRING）
  - 可成药通路靶点
  - 基于通路的治疗机会

阶段7：临床证据与指南匹配
   - 基于指南的风险分类（NCCN、ACC/AHA、ADA）
   - 适用于患者特征的FDA获批疗法
   - 文献证据（PubMed）
   - 生物标志物指导治疗的证据

阶段8：临床试验匹配
   - 匹配分子特征的试验
   - 生物标志物驱动的试验
   - 精准医学篮式/伞式试验
   - 风险适应性试验

阶段9：综合评分与建议
   - 计算精准医学风险评分（0-100）
   - 风险等级划分（低/中/高/极高）
   - 治疗算法（一线/二线/三线）
   - 监测计划
   - 预后预测

Phase 1: Disease Disambiguation & Profile Standardization

阶段1：疾病明确诊断与特征标准化

Step 1.1: Resolve Disease to EFO ID

步骤1.1：将疾病解析为EFO ID

python

undefined

python

undefined

Get disease EFO ID

获取疾病EFO ID

result = tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName='breast cancer')

-> {data: {search: {hits: [{id: 'EFO_0000305', name: 'breast carcinoma', description: '...'}]}}}

efo_id = result['data']['search']['hits'][0]['id']


**Common Disease EFO IDs** (for reference):

| Disease | EFO ID | Category |
|---------|--------|----------|
| Breast carcinoma | EFO_0000305 | CANCER |
| Non-small cell lung carcinoma | EFO_0003060 | CANCER |
| Colorectal cancer | EFO_0000365 | CANCER |
| Melanoma | EFO_0000756 | CANCER |
| Prostate carcinoma | EFO_0001663 | CANCER |
| Type 2 diabetes | EFO_0001360 | METABOLIC |
| Coronary artery disease | EFO_0001645 | CVD |
| Atrial fibrillation | EFO_0000275 | CVD |
| Alzheimer disease | MONDO_0004975 | NEUROLOGICAL |
| Parkinson disease | EFO_0002508 | NEUROLOGICAL |
| Rheumatoid arthritis | EFO_0000685 | AUTOIMMUNE |
| Marfan syndrome | Orphanet_558 | RARE |
| Cystic fibrosis | EFO_0000508 | RARE |

efo_id = result['data']['search']['hits'][0]['id']


**常见疾病EFO ID**（参考用）:

| 疾病 | EFO ID | 类别 |
|---------|--------|----------|
| 乳腺癌 | EFO_0000305 | 癌症 |
| 非小细胞肺癌 | EFO_0003060 | 癌症 |
| 结直肠癌 | EFO_0000365 | 癌症 |
| 黑色素瘤 | EFO_0000756 | 癌症 |
| 前列腺癌 | EFO_0001663 | 癌症 |
| 2型糖尿病 | EFO_0001360 | 代谢性疾病 |
| 冠心病 | EFO_0001645 | CVD |
| 心房颤动 | EFO_0000275 | CVD |
| 阿尔茨海默病 | MONDO_0004975 | 神经系统疾病 |
| 帕金森病 | EFO_0002508 | 神经系统疾病 |
| 类风湿关节炎 | EFO_0000685 | 自身免疫病 |
| 马凡综合征 | Orphanet_558 | 罕见病 |
| 囊性纤维化 | EFO_0000508 | 罕见病 |

Step 1.2: Classify Disease Type

步骤1.2：疾病类型分类

Based on disease name and EFO ID, classify into: CANCER, METABOLIC, CVD, NEUROLOGICAL, RARE, AUTOIMMUNE. This determines the Phase 3 routing.

根据疾病名称和EFO ID，将疾病归类为：癌症、代谢性疾病、CVD、神经系统疾病、罕见病、自身免疫病。这将决定阶段3的分析路径。

Step 1.3: Parse Genomic Data

步骤1.3：解析基因组数据

Parse each variant/gene into structured format:

"BRCA1 c.68_69delAG" -> {gene: "BRCA1", variant: "c.68_69delAG", type: "frameshift"}
"EGFR L858R" -> {gene: "EGFR", variant: "L858R", type: "missense"}
"CYP2C19 *2/*2" -> {gene: "CYP2C19", genotype: "*2/*2", metabolizer_status: "poor"}
"APOE e4/e4" -> {gene: "APOE", genotype: "e4/e4", risk_allele: "e4"}

将每个变异/基因解析为结构化格式:

"BRCA1 c.68_69delAG" -> {gene: "BRCA1", variant: "c.68_69delAG", type: "移码突变"}
"EGFR L858R" -> {gene: "EGFR", variant: "L858R", type: "错义突变"}
"CYP2C19 *2/*2" -> {gene: "CYP2C19", genotype: "*2/*2", metabolizer_status: "弱代谢型"}
"APOE e4/e4" -> {gene: "APOE", genotype: "e4/e4", risk_allele: "e4"}

Step 1.4: Resolve Gene IDs

步骤1.4：解析基因ID

python

undefined

python

undefined

For each gene in profile

针对特征中的每个基因

result = tu.tools.MyGene_query_genes(query='BRCA1')

-> hits[0]: {_id: '672', symbol: 'BRCA1', ensembl: {gene: 'ENSG00000012048'}}

ensembl_id = result['hits'][0]['ensembl']['gene'] entrez_id = result['hits'][0]['_id']


**Critical Gene IDs** (pre-resolved):

| Gene | Ensembl ID | Entrez ID | Category |
|------|-----------|-----------|----------|
| BRCA1 | ENSG00000012048 | 672 | Cancer predisposition |
| BRCA2 | ENSG00000139618 | 675 | Cancer predisposition |
| TP53 | ENSG00000141510 | 7157 | Tumor suppressor |
| EGFR | ENSG00000146648 | 1956 | Cancer driver |
| BRAF | ENSG00000157764 | 673 | Cancer driver |
| KRAS | ENSG00000133703 | 3845 | Cancer driver |
| CYP2D6 | ENSG00000100197 | 1565 | Pharmacogenomics |
| CYP2C19 | ENSG00000165841 | 1557 | Pharmacogenomics |
| SLCO1B1 | ENSG00000134538 | 10599 | Pharmacogenomics |
| VKORC1 | ENSG00000167397 | 79001 | Pharmacogenomics |
| DPYD | ENSG00000188641 | 1806 | Pharmacogenomics |
| APOE | ENSG00000130203 | 348 | Neurological risk |
| LDLR | ENSG00000130164 | 3949 | CVD risk |
| PCSK9 | ENSG00000169174 | 255738 | CVD risk |
| FBN1 | ENSG00000166147 | 2200 | Marfan syndrome |
| CFTR | ENSG00000001626 | 1080 | Cystic fibrosis |

---

ensembl_id = result['hits'][0]['ensembl']['gene'] entrez_id = result['hits'][0]['_id']


**关键基因ID**（预解析）:

| 基因 | Ensembl ID | Entrez ID | 类别 |
|------|-----------|-----------|----------|
| BRCA1 | ENSG00000012048 | 672 | 癌症易感基因 |
| BRCA2 | ENSG00000139618 | 675 | 癌症易感基因 |
| TP53 | ENSG00000141510 | 7157 | 抑癌基因 |
| EGFR | ENSG00000146648 | 1956 | 癌症驱动基因 |
| BRAF | ENSG00000157764 | 673 | 癌症驱动基因 |
| KRAS | ENSG00000133703 | 3845 | 癌症驱动基因 |
| CYP2D6 | ENSG00000100197 | 1565 | 药物基因组学 |
| CYP2C19 | ENSG00000165841 | 1557 | 药物基因组学 |
| SLCO1B1 | ENSG00000134538 | 10599 | 药物基因组学 |
| VKORC1 | ENSG00000167397 | 79001 | 药物基因组学 |
| DPYD | ENSG00000188641 | 1806 | 药物基因组学 |
| APOE | ENSG00000130203 | 348 | 神经系统疾病风险 |
| LDLR | ENSG00000130164 | 3949 | CVD风险 |
| PCSK9 | ENSG00000169174 | 255738 | CVD风险 |
| FBN1 | ENSG00000166147 | 2200 | 马凡综合征 |
| CFTR | ENSG00000001626 | 1080 | 囊性纤维化 |

---

Phase 2: Genetic Risk Assessment

阶段2：遗传风险评估

Step 2.1: Germline Variant Pathogenicity

步骤2.1：种系变异致病性

For each germline variant provided:

python

undefined

针对每个提供的种系变异:

python

undefined

Search ClinVar for variant pathogenicity

在ClinVar中搜索变异致病性

result = tu.tools.clinvar_search_variants(gene='BRCA1', significance='pathogenic', limit=50)

Check if patient's specific variant is in ClinVar

检查患者的特定变异是否存在于ClinVar中

For rsID variants, get VEP annotation

针对rsID变异，获取VEP注释

result = tu.tools.EnsemblVEP_annotate_rsid(variant_id='rs80357906')

Returns SIFT, PolyPhen predictions, consequence type

返回SIFT、PolyPhen预测结果、变异类型

For HGVS variants

针对HGVS变异

result = tu.tools.EnsemblVEP_annotate_hgvs(hgvs_notation='ENST00000357654.9:c.5266dupC', species='homo_sapiens')


**Pathogenicity Classification** (ACMG-aligned):

| Classification | ClinVar Term | Risk Score Points |
|---------------|-------------|-------------------|
| Pathogenic | Pathogenic | 25 (molecular component) |
| Likely pathogenic | Likely pathogenic | 20 |
| VUS | Uncertain significance | 10 (conservative) |
| Likely benign | Likely benign | 2 |
| Benign | Benign | 0 |

result = tu.tools.EnsemblVEP_annotate_hgvs(hgvs_notation='ENST00000357654.9:c.5266dupC', species='homo_sapiens')


**致病性分类**（符合ACMG标准）:

| 分类 | ClinVar术语 | 风险评分点数 |
|---------------|-------------|-------------------|
| 致病性 | Pathogenic | 25分（分子组分） |
| 可能致病性 | Likely pathogenic | 20分 |
| 意义不明确 | Uncertain significance | 10分（保守值） |
| 可能良性 | Likely benign | 2分 |
| 良性 | Benign | 0分 |

Step 2.2: Gene-Disease Association Strength

步骤2.2：基因-疾病关联强度

python

undefined

python

undefined

Get genetic evidence for gene-disease pair

获取基因-疾病对的遗传证据

result = tu.tools.OpenTargets_target_disease_evidence( ensemblId='ENSG00000012048', # BRCA1 efoId='EFO_0000305', # breast cancer size=20 )

result = tu.tools.OpenTargets_target_disease_evidence( ensemblId='ENSG00000012048', # BRCA1 efoId='EFO_0000305', # 乳腺癌 size=20 )

Returns evidence items with scores

返回带评分的证据条目

undefined

undefined

Step 2.3: GWAS-Based Polygenic Risk

步骤2.3：基于GWAS的多基因风险

python

undefined

python

undefined

Search GWAS associations for disease

搜索疾病相关GWAS关联

result = tu.tools.gwas_get_associations_for_trait(trait='breast cancer')

Returns associated SNPs with effect sizes

返回带效应量的关联SNP

Search GWAS studies via OpenTargets

通过OpenTargets搜索GWAS研究

result = tu.tools.OpenTargets_search_gwas_studies_by_disease( diseaseIds=['EFO_0000305'], size=25 )

For specific genes, check GWAS hits

针对特定基因，检查GWAS位点

result = tu.tools.GWAS_search_associations_by_gene(gene_name='BRCA1')


**PRS Estimation** (from available GWAS data):

| PRS Percentile | Risk Category | Score Points (0-35) |
|---------------|--------------|---------------------|
| >95th percentile | Very high genetic risk | 35 |
| 90-95th | High genetic risk | 30 |
| 75-90th | Elevated genetic risk | 25 |
| 50-75th | Average-high | 18 |
| 25-50th | Average-low | 12 |
| 10-25th | Below average | 8 |
| <10th | Low genetic risk | 5 |

**Note**: With user-provided variants only (not full genotype), estimate approximate PRS by counting known risk alleles and their effect sizes from GWAS catalog. Flag as "estimated - full genotyping recommended for precise PRS."

result = tu.tools.GWAS_search_associations_by_gene(gene_name='BRCA1')


**PRS估计**（基于可用GWAS数据）:

| PRS百分位数 | 风险类别 | 评分点数（0-35） |
|---------------|--------------|---------------------|
| >95百分位 | 极高遗传风险 | 35分 |
| 90-95百分位 | 高遗传风险 | 30分 |
| 75-90百分位 | 升高的遗传风险 | 25分 |
| 50-75百分位 | 中高风险 | 18分 |
| 25-50百分位 | 中低风险 | 12分 |
| 10-25百分位 | 低于平均风险 | 8分 |
| <10百分位 | 低遗传风险 | 5分 |

**注意**: 若仅提供用户的变异（而非全基因型），可通过统计已知风险等位基因及其来自GWAS数据库的效应量来近似估计PRS。需标注“为估计值 - 如需精确PRS，建议进行全基因分型”。

Step 2.4: Population Frequency

步骤2.4：人群频率

python

undefined

python

undefined

Check variant frequency in gnomAD

在gnomAD中检查变异频率

result = tu.tools.gnomad_get_variant(variant_id='1-55505647-G-T')

Returns allele frequency across populations

返回各人群的等位基因频率

undefined

undefined

Step 2.5: Gene Constraint

步骤2.5：基因约束

python

undefined

python

undefined

Gene intolerance to loss of function

基因功能缺失不耐受性

result = tu.tools.gnomad_get_gene_constraints(gene_symbol='BRCA1')

Returns pLI, LOEUF scores - high pLI/low LOEUF = haploinsufficiency

返回pLI、LOEUF评分 - pLI高/LOEUF低 = 单倍体不足


**Genetic Risk Score Component** (0-35 points):

Combine pathogenicity + gene-disease association + PRS:
- Pathogenic variant in disease gene: 25+ points
- Strong GWAS associations (multiple risk alleles): up to 35 points
- VUS in relevant gene: 10-15 points
- No known pathogenic variants but some risk alleles: 5-15 points

---


**遗传风险评分组分**（0-35分）:

结合致病性+基因-疾病关联+PRS:
- 疾病基因中的致病性变异：25+分
- 强GWAS关联（多个风险等位基因）：最高35分
- 相关基因中的意义不明确变异：10-15分
- 无已知致病性变异但存在部分风险等位基因：5-15分

---

Phase 3: Disease-Specific Molecular Stratification

阶段3：疾病特异性分子分层

CANCER PATH (Phase 3C)

癌症路径（阶段3C）

Step 3C.1: Molecular Subtyping

步骤3C.1：分子亚型划分

python

undefined

python

undefined

Get somatic mutation landscape from cBioPortal

从cBioPortal获取体细胞突变图谱

result = tu.tools.cBioPortal_get_mutations( study_id='brca_tcga_pub', # breast cancer TCGA gene_list='BRCA1 BRCA2 TP53 PIK3CA ESR1 ERBB2' # STRING, not array )

result = tu.tools.cBioPortal_get_mutations( study_id='brca_tcga_pub', # 乳腺癌TCGA研究 gene_list='BRCA1 BRCA2 TP53 PIK3CA ESR1 ERBB2' # 字符串，非数组 )

Returns mutation frequencies, types

返回突变频率、类型

Check cancer prognostic markers

检查癌症预后标志物

result = tu.tools.HPA_get_cancer_prognostics_by_gene(gene_name='ESR1')

Returns prognostic data for breast cancer

返回乳腺癌预后数据


**Cancer-Specific Subtype Definitions**:

| Cancer | Subtype System | Key Markers | High-Risk Features |
|--------|---------------|-------------|-------------------|
| Breast | Luminal A/B, HER2+, TNBC | ER, PR, HER2, Ki67 | TNBC, high Ki67, TP53 mut |
| NSCLC | Adenocarcinoma, squamous | EGFR, ALK, ROS1, KRAS, PD-L1 | KRAS G12C, no driver = chemoIO |
| CRC | MSI-H vs MSS, CMS1-4 | KRAS, BRAF, MSI, CMS | BRAF V600E, MSS |
| Melanoma | BRAF-mut, NRAS-mut, wild-type | BRAF, NRAS, KIT, NF1 | NRAS, uveal |
| Prostate | Luminal vs basal, BRCA status | AR, BRCA1/2, SPOP, TMPRSS2:ERG | BRCA2, neuroendocrine |


**癌症特异性亚型定义**:

| 癌症 | 亚型系统 | 关键标志物 | 高风险特征 |
|--------|---------------|-------------|-------------------|
| 乳腺癌 | Luminal A/B、HER2+、TNBC | ER、PR、HER2、Ki67 | TNBC、高Ki67、TP53突变 |
| NSCLC | 腺癌、鳞癌 | EGFR、ALK、ROS1、KRAS、PD-L1 | KRAS G12C、无驱动突变=化疗联合免疫治疗 |
| CRC | MSI-H vs MSS、CMS1-4 | KRAS、BRAF、MSI、CMS | BRAF V600E、MSS |
| 黑色素瘤 | BRAF突变型、NRAS突变型、野生型 | BRAF、NRAS、KIT、NF1 | NRAS突变、葡萄膜黑色素瘤 |
| 前列腺癌 | Luminal vs basal、BRCA状态 | AR、BRCA1/2、SPOP、TMPRSS2:ERG | BRCA2突变、神经内分泌型 |

Step 3C.2: TMB/MSI/HRD Assessment

步骤3C.2：TMB/MSI/HRD评估

If TMB provided:

python

undefined

若提供TMB:

python

undefined

Check FDA TMB-H approvals

检查FDA TMB-H获批情况

result = tu.tools.fda_pharmacogenomic_biomarkers(drug_name='pembrolizumab', limit=100)

Look for "Tumor Mutational Burden" in Biomarker field

在Biomarker字段中查找"Tumor Mutational Burden"


| Biomarker | High-Risk Threshold | Clinical Significance |
|-----------|-------------------|----------------------|
| TMB | >= 10 mut/Mb (FDA cutoff) | Pembrolizumab eligible (tissue-agnostic) |
| MSI-H | MSI-high or dMMR | Pembrolizumab/nivolumab eligible |
| HRD | HRD-positive | PARP inhibitor eligible |


| 生物标志物 | 高风险阈值 | 临床意义 |
|-----------|-------------------|----------------------|
| TMB | >=10突变/Mb（FDA cutoff值） | 符合帕博利珠单抗使用条件（泛癌种） |
| MSI-H | MSI高或dMMR | 符合帕博利珠单抗/纳武利尤单抗使用条件 |
| HRD | HRD阳性 | 符合PARP抑制剂使用条件 |

Step 3C.3: Prognostic Stratification

步骤3C.3：预后分层

Combine stage + molecular features:

Stage	Low-Risk Molecular	High-Risk Molecular	Score (0-30 clinical)
I	Favorable subtype	Unfavorable subtype	5-10
II	Favorable subtype	Unfavorable subtype	10-18
III	Any	Any	18-25
IV	Any	Any	25-30

结合分期+分子特征:

分期	低风险分子特征	高风险分子特征	评分（0-30，临床组分）
I	良好亚型	不良亚型	5-10分
II	良好亚型	不良亚型	10-18分
III	任意	任意	18-25分
IV	任意	任意	25-30分

METABOLIC PATH (Phase 3M)

代谢性疾病路径（阶段3M）

Step 3M.1: Clinical Risk Integration

步骤3M.1：临床风险整合

python

undefined

python

undefined

Check genetic risk factors for T2D

检查2型糖尿病的遗传风险因素

result = tu.tools.GWAS_search_associations_by_gene(gene_name='TCF7L2')

TCF7L2 is strongest T2D risk gene

TCF7L2是2型糖尿病最强风险基因

Check monogenic diabetes genes

检查单基因糖尿病基因

result = tu.tools.OpenTargets_target_disease_evidence( ensemblId='ENSG00000148737', # TCF7L2 efoId='EFO_0001360', # T2D size=20 )


**T2D Stratification**:

| Risk Factor | Low Risk | Moderate Risk | High Risk | Score Points |
|-------------|----------|---------------|-----------|-------------|
| HbA1c | <6.5% | 6.5-8.0% | >8.0% | 5-30 |
| Genetic risk | No risk alleles | 1-3 risk alleles | MODY gene/many risk alleles | 5-25 |
| Complications | None | Microalbuminuria | Retinopathy, neuropathy | 0-20 |
| Duration | <5 years | 5-15 years | >15 years | 0-10 |

result = tu.tools.OpenTargets_target_disease_evidence( ensemblId='ENSG00000148737', # TCF7L2 efoId='EFO_0001360', # 2型糖尿病 size=20 )


**2型糖尿病分层**:

| 风险因素 | 低风险 | 中风险 | 高风险 | 评分点数 |
|-------------|----------|---------------|-----------|-------------|
| HbA1c | <6.5% | 6.5-8.0% | >8.0% | 5-30分 |
| 遗传风险 | 无风险等位基因 | 1-3个风险等位基因 | MODY基因/多个风险等位基因 | 5-25分 |
| 并发症 | 无 | 微量白蛋白尿 | 视网膜病变、神经病变 | 0-20分 |
| 病程 | <5年 | 5-15年 | >15年 | 0-10分 |

CVD PATH (Phase 3V)

CVD路径（阶段3V）

python

undefined

python

undefined

Check PCSK9 and LDLR variants

检查PCSK9和LDLR变异

result = tu.tools.clinvar_search_variants(gene='LDLR', significance='pathogenic', limit=20)

Familial hypercholesterolemia check

家族性高胆固醇血症检查

Check statin-relevant PGx

检查他汀类药物相关PGx

result = tu.tools.PharmGKB_get_clinical_annotations(query='SLCO1B1')

SLCO1B1 *5 -> increased statin myopathy risk

SLCO1B1 *5 -> 他汀类肌病风险升高


**CVD Risk Integration**:

| Factor | Score Points |
|--------|-------------|
| LDL >190 mg/dL | 15 |
| FH gene mutation (LDLR/APOB/PCSK9) | 20 |
| ASCVD >20% 10-year risk | 30 |
| Family hx premature CVD | 10 |
| Lipoprotein(a) elevated | 8 |
| Multiple GWAS risk alleles | 5-15 |


**CVD风险整合**:

| 因素 | 评分点数 |
|--------|-------------|
| LDL >190 mg/dL | 15分 |
| FH基因突变（LDLR/APOB/PCSK9） | 20分 |
| ASCVD 10年风险 >20% | 30分 |
| 早发CVD家族史 | 10分 |
| 脂蛋白(a)升高 | 8分 |
| 多个GWAS风险等位基因 | 5-15分 |

RARE DISEASE PATH (Phase 3R)

罕见病路径（阶段3R）

python

undefined

python

undefined

Check causal variant in disease gene

检查疾病基因中的致病性变异

result = tu.tools.clinvar_search_variants(gene='FBN1', significance='pathogenic', limit=50)

Marfan syndrome - FBN1 pathogenic variants

马凡综合征 - FBN1致病性变异

Genotype-phenotype correlation

基因型-表型相关性

result = tu.tools.UniProt_get_disease_variants_by_accession(accession='P35555') # FBN1 UniProt

result = tu.tools.UniProt_get_disease_variants_by_accession(accession='P35555') # FBN1 UniProt编号

Known disease variants and their phenotypes

已知疾病变异及其表型


**Rare Disease Risk Assessment**:

| Finding | Risk Level | Score Points |
|---------|-----------|-------------|
| Pathogenic variant in causal gene | Definitive | 30 |
| Likely pathogenic in causal gene | Strong | 25 |
| VUS in causal gene | Moderate | 15 |
| Family history + partial phenotype | Suggestive | 10 |
| Single phenotype feature only | Low | 5 |

---


**罕见病风险评估**:

| 发现 | 风险等级 | 评分点数 |
|---------|-----------|-------------|
| 致病基因中的致病性变异 | 确诊 | 30分 |
| 致病基因中的可能致病性变异 | 高度疑似 | 25分 |
| 致病基因中的意义不明确变异 | 中度疑似 | 15分 |
| 家族史+部分表型 | 提示性 | 10分 |
| 仅单一表型特征 | 低风险 | 5分 |

---

Phase 4: Pharmacogenomic Profiling

阶段4：药物基因组学分析

Step 4.1: Drug-Metabolizing Enzyme Genotypes

步骤4.1：药物代谢酶基因型

python

undefined

python

undefined

PharmGKB clinical annotations for CYP2C19

CYP2C19的PharmGKB临床注释

result = tu.tools.PharmGKB_get_clinical_annotations(query='CYP2C19')

Returns drug-gene pairs with clinical annotation levels

返回带临床注释等级的药物-基因对

FDA pharmacogenomic biomarkers

FDA药物基因组学生物标志物

result = tu.tools.fda_pharmacogenomic_biomarkers(drug_name='clopidogrel', limit=50)

CYP2C19 poor metabolizer -> reduced clopidogrel efficacy

CYP2C19弱代谢型 -> 氯吡格雷疗效降低

PharmGKB dosing guidelines

PharmGKB剂量指南

result = tu.tools.PharmGKB_get_dosing_guidelines(query='CYP2C19')

CPIC dosing guidelines

CPIC剂量指南


**Key Pharmacogenes and Clinical Impact**:

| Gene | Star Alleles | Metabolizer Status | Clinical Impact | Score Points |
|------|-------------|-------------------|----------------|-------------|
| CYP2D6 | *4/*4, *5/*5 | Poor metabolizer | Codeine, tamoxifen, many antidepressants | 8 |
| CYP2C19 | *2/*2, *2/*3 | Poor metabolizer | Clopidogrel, voriconazole, PPIs | 8 |
| CYP2C9 | *2/*3, *3/*3 | Poor metabolizer | Warfarin, NSAIDs, phenytoin | 5 |
| SLCO1B1 | *5/*5 | Decreased function | Statin myopathy (simvastatin) | 5 |
| DPYD | *2A | DPD deficient | 5-FU/capecitabine severe toxicity | 10 |
| VKORC1 | -1639G>A | Warfarin sensitive | Lower warfarin dose needed | 5 |
| UGT1A1 | *28/*28 | Poor glucuronidator | Irinotecan toxicity | 5 |
| TPMT | *2, *3A, *3C | Poor metabolizer | Thiopurine toxicity | 8 |
| HLA-B*5701 | Present | N/A | Abacavir hypersensitivity | 10 |
| HLA-B*1502 | Present | N/A | Carbamazepine SJS/TEN | 10 |


**关键药物基因组基因及临床影响**:

| 基因 | 星号等位基因 | 代谢型 | 临床影响 | 评分点数 |
|------|-------------|-------------------|----------------|-------------|
| CYP2D6 | *4/*4、*5/*5 | 弱代谢型 | 可待因、他莫昔芬、多种抗抑郁药 | 8分 |
| CYP2C19 | *2/*2、*2/*3 | 弱代谢型 | 氯吡格雷、伏立康唑、质子泵抑制剂 | 8分 |
| CYP2C9 | *2/*3、*3/*3 | 弱代谢型 | 华法林、NSAIDs、苯妥英 | 5分 |
| SLCO1B1 | *5/*5 | 功能降低 | 他汀类肌病（辛伐他汀） | 5分 |
| DPYD | *2A | DPD缺陷 | 5-FU/卡培他滨严重毒性 | 10分 |
| VKORC1 | -1639G>A | 华法林敏感型 | 需降低华法林剂量 | 5分 |
| UGT1A1 | *28/*28 | 弱葡萄糖醛酸化型 | 伊立替康毒性 | 5分 |
| TPMT | *2、*3A、*3C | 弱代谢型 | 硫嘌呤毒性 | 8分 |
| HLA-B*5701 | 存在 | N/A | 阿巴卡韦超敏反应 | 10分 |
| HLA-B*1502 | 存在 | N/A | 卡马西平SJS/TEN | 10分 |

Step 4.2: Treatment-Specific PGx

步骤4.2：治疗特异性PGx

python

undefined

python

undefined

For the specific disease, identify relevant drugs and check PGx

针对特定疾病，识别相关药物并检查PGx

Example: breast cancer -> tamoxifen -> CYP2D6

示例：乳腺癌 -> 他莫昔芬 -> CYP2D6

result = tu.tools.PharmGKB_get_drug_details(query='tamoxifen')

Returns PGx annotations for tamoxifen

返回他莫昔芬的PGx注释

Get FDA PGx biomarkers for disease area

获取疾病领域的FDA PGx生物标志物

result = tu.tools.fda_pharmacogenomic_biomarkers(biomarker='CYP2D6', limit=100)

All drugs with CYP2D6 PGx in FDA labels

FDA标签中所有与CYP2D6相关的药物

undefined

undefined

Step 4.3: Drug Target Variants

步骤4.3：药物靶点变异

python

undefined

python

undefined

Check if patient has variants in drug targets

检查患者是否存在药物靶点变异

result = tu.tools.PharmGKB_search_variants(query='VKORC1')

VKORC1 variants affecting warfarin response

VKORC1变异影响华法林反应


**Pharmacogenomic Risk Score** (0-10 points):
- Poor metabolizer for treatment-relevant CYP: 8-10 points
- Intermediate metabolizer: 4-5 points
- High-risk HLA allele: 8-10 points
- Drug target variant: 3-5 points
- Normal metabolizer, no actionable PGx: 0 points

---


**药物基因组学风险评分**（0-10分）:
- 治疗相关CYP弱代谢型：8-10分
- 中间代谢型：4-5分
- 高风险HLA等位基因：8-10分
- 药物靶点变异：3-5分
- 正常代谢型，无可行动PGx发现：0分

---

Phase 5: Comorbidity & Drug Interaction Risk

阶段5：合并症与药物相互作用风险

Step 5.1: Comorbidity Analysis

步骤5.1：合并症分析

python

undefined

python

undefined

Check disease-disease overlap via shared genetic targets

通过共享遗传靶点检查疾病-疾病重叠

result = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId( efoId='EFO_0001360', # T2D size=50 )

result = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId( efoId='EFO_0001360', # 2型糖尿病 size=50 )

Compare top targets between primary disease and comorbidities

比较原发疾病与合并症的顶级靶点

Literature on comorbidity

合并症相关文献

result = tu.tools.PubMed_search_articles( query='type 2 diabetes cardiovascular comorbidity risk', max_results=5 )

undefined

result = tu.tools.PubMed_search_articles( query='type 2 diabetes cardiovascular comorbidity risk', max_results=5 )

undefined

Step 5.2: Drug-Drug Interaction Risk

步骤5.2：药物-药物相互作用风险

python

undefined

python

undefined

If current medications provided, check DDI

若提供当前用药，检查DDI

result = tu.tools.drugbank_get_drug_interactions_by_drug_name_or_id( query='metformin', case_sensitive=False, exact_match=False, limit=20 )

FDA DDI data

FDA DDI数据

result = tu.tools.FDA_get_drug_interactions_by_drug_name(drug_name='metformin', limit=5)

undefined

result = tu.tools.FDA_get_drug_interactions_by_drug_name(drug_name='metformin', limit=5)

undefined

Step 5.3: PGx-Amplified DDI Risk

步骤5.3：PGx放大的DDI风险

If patient is a CYP2D6 poor metabolizer AND taking a CYP2D6 inhibitor -> compounded risk.

Interaction Type	Risk Level	Management
PGx PM + CYP inhibitor	Very high	Alternative drug or dose reduction
PGx IM + CYP inhibitor	High	Monitor closely, possible dose reduction
PGx normal + CYP inhibitor	Moderate	Standard monitoring
No interacting drugs	Low	Standard care

若患者为CYP2D6弱代谢型且同时服用CYP2D6抑制剂 -> 风险叠加。

相互作用类型	风险等级	管理方案
PGx弱代谢型 + CYP抑制剂	极高	更换药物或降低剂量
PGx中间代谢型 + CYP抑制剂	高	密切监测，可能需要降低剂量
PGx正常代谢型 + CYP抑制剂	中	标准监测
无相互作用药物	低	标准护理

Phase 6: Molecular Pathway Analysis

阶段6：分子通路分析

Step 6.1: Dysregulated Pathways

步骤6.1：失调通路

python

undefined

python

undefined

Pathway enrichment for affected genes

受影响基因的通路富集

gene_list = ['BRCA1', 'TP53', 'PIK3CA'] # from patient mutations result = tu.tools.enrichr_gene_enrichment_analysis( gene_list=gene_list, libs=['KEGG_2021_Human', 'Reactome_2022'] )

gene_list = ['BRCA1', 'TP53', 'PIK3CA'] # 来自患者突变 result = tu.tools.enrichr_gene_enrichment_analysis( gene_list=gene_list, libs=['KEGG_2021_Human', 'Reactome_2022'] )

Returns enriched pathways with p-values

返回带p值的富集通路

Reactome pathway analysis

Reactome通路分析

First get UniProt IDs, then map to pathways

先获取UniProt编号，再映射到通路

result = tu.tools.Reactome_map_uniprot_to_pathways(id='P38398') # BRCA1 UniProt

result = tu.tools.Reactome_map_uniprot_to_pathways(id='P38398') # BRCA1 UniProt编号

Returns list of pathways involving BRCA1

返回BRCA1参与的通路列表

undefined

undefined

Step 6.2: Network Analysis

步骤6.2：网络分析

python

undefined

python

undefined

Protein-protein interaction network

蛋白质-蛋白质相互作用网络

result = tu.tools.STRING_get_interaction_partners( protein_ids=['BRCA1', 'TP53'], species=9606, limit=20 )

Functional enrichment of network

网络功能富集分析

result = tu.tools.STRING_functional_enrichment( protein_ids=['BRCA1', 'TP53', 'PALB2', 'RAD51'], species=9606 )

undefined

result = tu.tools.STRING_functional_enrichment( protein_ids=['BRCA1', 'TP53', 'PALB2', 'RAD51'], species=9606 )

undefined

Step 6.3: Druggable Pathway Targets

步骤6.3：可成药通路靶点

python

undefined

python

undefined

Check tractability of pathway nodes

检查通路节点的成药性

for gene in pathway_genes: result = tu.tools.OpenTargets_get_target_tractability_by_ensemblID(ensemblId=ensembl_id) # Returns small molecule, antibody, PROTAC tractability


**Key Druggable Pathways**:

| Pathway | Key Nodes | Drug Classes | Cancer Relevance |
|---------|-----------|-------------|-----------------|
| PI3K/AKT/mTOR | PIK3CA, AKT1, MTOR | PI3K inhibitors, mTOR inhibitors | Breast, endometrial |
| RAS/MAPK | KRAS, BRAF, MEK1/2 | KRAS G12C inhibitors, BRAF inhibitors | Lung, CRC, melanoma |
| DNA damage repair | BRCA1/2, ATM, PALB2 | PARP inhibitors | Breast, ovarian, prostate |
| Cell cycle | CDK4/6, RB1, CCND1 | CDK4/6 inhibitors | Breast |
| Immunocheckpoint | PD-1, PD-L1, CTLA-4 | ICIs | Pan-cancer |
| Wnt/beta-catenin | APC, CTNNB1, TCF | Wnt inhibitors (investigational) | CRC |

---

for gene in pathway_genes: result = tu.tools.OpenTargets_get_target_tractability_by_ensemblID(ensemblId=ensembl_id) # 返回小分子、抗体、PROTAC成药性


**关键可成药通路**:

| 通路 | 关键节点 | 药物类别 | 癌症相关性 |
|---------|-----------|-------------|-----------------|
| PI3K/AKT/mTOR | PIK3CA、AKT1、MTOR | PI3K抑制剂、mTOR抑制剂 | 乳腺癌、子宫内膜癌 |
| RAS/MAPK | KRAS、BRAF、MEK1/2 | KRAS G12C抑制剂、BRAF抑制剂 | 肺癌、CRC、黑色素瘤 |
| DNA损伤修复 | BRCA1/2、ATM、PALB2 | PARP抑制剂 | 乳腺癌、卵巢癌、前列腺癌 |
| 细胞周期 | CDK4/6、RB1、CCND1 | CDK4/6抑制剂 | 乳腺癌 |
| 免疫检查点 | PD-1、PD-L1、CTLA-4 | 免疫检查点抑制剂 | 泛癌种 |
| Wnt/β-catenin | APC、CTNNB1、TCF | Wnt抑制剂（研究阶段） | CRC |

---

Phase 7: Clinical Evidence & Guidelines

阶段7：临床证据与指南

Step 7.1: Guideline-Based Risk Categories

步骤7.1：基于指南的风险分类

python

undefined

python

undefined

Search clinical guidelines in PubMed

在PubMed中搜索临床指南

result = tu.tools.PubMed_Guidelines_Search( query='NCCN breast cancer BRCA1 treatment guidelines', max_results=5 )

Search general evidence

搜索一般证据

result = tu.tools.PubMed_search_articles( query='BRCA1 breast cancer treatment stratification', max_results=10 )


**Guideline References by Disease**:

| Disease Category | Guidelines | Key Stratification |
|-----------------|-----------|-------------------|
| Breast cancer | NCCN, ASCO, St. Gallen | Luminal A/B, HER2+, TNBC, BRCA status |
| NSCLC | NCCN, ESMO | Driver mutation status, PD-L1, TMB |
| CRC | NCCN | MSI, RAS/BRAF, sidedness |
| T2D | ADA Standards | HbA1c, CVD risk, CKD stage |
| CVD | ACC/AHA | ASCVD risk score, LDL goals, PGx |
| AF | ACC/AHA/HRS | CHA2DS2-VASc, anticoagulant selection |
| Rare disease | ACMG/AMP | Variant classification, genetic counseling |

result = tu.tools.PubMed_search_articles( query='BRCA1 breast cancer treatment stratification', max_results=10 )


**按疾病分类的指南参考**:

| 疾病类别 | 指南 | 核心分层依据 |
|-----------------|-----------|-------------------|
| 乳腺癌 | NCCN、ASCO、St. Gallen | Luminal A/B、HER2+、TNBC、BRCA状态 |
| NSCLC | NCCN、ESMO | 驱动突变状态、PD-L1、TMB |
| CRC | NCCN | MSI、RAS/BRAF、肿瘤部位 |
| 2型糖尿病 | ADA标准 | HbA1c、CVD风险、CKD分期 |
| CVD | ACC/AHA | ASCVD风险评分、LDL目标、PGx |
| AF | ACC/AHA/HRS | CHA2DS2-VASc、抗凝药物选择 |
| 罕见病 | ACMG/AMP | 变异分类、遗传咨询 |

Step 7.2: FDA-Approved Therapies

步骤7.2：FDA获批疗法

python

undefined

python

undefined

Get approved drugs for disease

获取疾病相关获批药物

result = tu.tools.OpenTargets_get_associated_drugs_by_disease_efoId( efoId='EFO_0000305', # breast cancer size=50 )

result = tu.tools.OpenTargets_get_associated_drugs_by_disease_efoId( efoId='EFO_0000305', # 乳腺癌 size=50 )

Returns all known drugs with clinical status

返回所有已知药物及其临床状态

Check specific drug FDA info

检查特定药物的FDA信息

result = tu.tools.FDA_get_indications_by_drug_name(drug_name='olaparib', limit=5)

PARP inhibitor for BRCA-mutated breast cancer

针对BRCA突变乳腺癌的PARP抑制剂

Get drug mechanism

获取药物作用机制

result = tu.tools.FDA_get_mechanism_of_action_by_drug_name(drug_name='olaparib', limit=5)

undefined

result = tu.tools.FDA_get_mechanism_of_action_by_drug_name(drug_name='olaparib', limit=5)

undefined

Step 7.3: Biomarker-Drug Evidence

步骤7.3：生物标志物-药物证据

python

undefined

python

undefined

CIViC evidence for biomarker-drug pair

生物标志物-药物对的CIViC证据

result = tu.tools.civic_search_evidence_items( therapy_name='olaparib', disease_name='breast cancer' )

Returns clinical evidence items with evidence levels

返回带证据等级的临床证据条目

DrugBank for drug details

DrugBank药物详情

result = tu.tools.drugbank_get_drug_basic_info_by_drug_name_or_id( query='olaparib', case_sensitive=False, exact_match=False, limit=5 )

---

result = tu.tools.drugbank_get_drug_basic_info_by_drug_name_or_id( query='olaparib', case_sensitive=False, exact_match=False, limit=5 )

---

Phase 8: Clinical Trial Matching

阶段8：临床试验匹配

Step 8.1: Biomarker-Driven Trials

步骤8.1：生物标志物驱动的试验

python

undefined

python

undefined

Search trials matching molecular profile

搜索匹配分子特征的试验

result = tu.tools.clinical_trials_search( action='search_studies', condition='breast cancer', intervention='PARP inhibitor', limit=10 )

Returns {total_count, studies: [{nctId, title, status, conditions}]}

返回{total_count, studies: [{nctId, title, status, conditions}]}

Alternative search

备选搜索

result = tu.tools.search_clinical_trials( query_term='BRCA1 breast cancer', condition='breast cancer', intervention='olaparib', pageSize=10 )

undefined

result = tu.tools.search_clinical_trials( query_term='BRCA1 breast cancer', condition='breast cancer', intervention='olaparib', pageSize=10 )

undefined

Step 8.2: Precision Medicine Trials

步骤8.2：精准医学试验

python

undefined

python

undefined

Search basket/umbrella trials

搜索篮式/伞式试验

result = tu.tools.search_clinical_trials( query_term='precision medicine biomarker-driven', condition='breast cancer', pageSize=10 )

Search risk-adapted trials

搜索风险适应性试验

result = tu.tools.search_clinical_trials( query_term='high risk BRCA1', condition='breast cancer', pageSize=10 )

undefined

result = tu.tools.search_clinical_trials( query_term='high risk BRCA1', condition='breast cancer', pageSize=10 )

undefined

Step 8.3: Trial Details

步骤8.3：试验详情

python

undefined

python

undefined

Get details for promising trials

获取有潜力的试验详情

result = tu.tools.clinical_trials_get_details( action='get_study_details', nct_id='NCT03344965' )

Returns full study protocol

返回完整研究方案

---

---

Phase 9: Integrated Scoring & Recommendations

阶段9：综合评分与建议

Precision Medicine Risk Score (0-100)

精准医学风险评分（0-100）

Score Components

评分组分

Genetic Risk Component (0-35 points):

Scenario	Points
Pathogenic variant in high-penetrance disease gene (BRCA1, LDLR, FBN1)	30-35
Multiple moderate-risk variants (GWAS hits + moderate penetrance)	20-28
High PRS (>90th percentile) with no known pathogenic variants	25-30
Single moderate-risk variant	12-18
VUS in relevant gene	8-12
Average PRS, no pathogenic variants	5-10
Low genetic risk (low PRS, no risk alleles)	0-5

Clinical Risk Component (0-30 points):

Disease Type	Factor	Low (0-8)	Moderate (10-20)	High (22-30)
Cancer	Stage	I	II-III	IV
T2D	HbA1c	<7%	7-9%	>9%
CVD	ASCVD 10-yr	<10%	10-20%	>20%
Neuro	Biomarker status	No biomarkers	Mild changes	Established
Rare	Phenotype match	Partial	Moderate	Full phenotype

Molecular Features Component (0-25 points):

Feature	Points
Cancer: High-risk driver mutations (TP53+PIK3CA, KRAS G12C)	20-25
Cancer: Actionable mutation (EGFR, BRAF V600E)	15-20
Cancer: High TMB or MSI-H (favorable for ICI)	10-15
Metabolic: Monogenic form (MODY, FH)	20-25
Metabolic: Multiple metabolic risk variants	10-15
CVD: FH gene mutation	20-25
Rare: Complete genotype-phenotype match	20-25
VUS requiring further workup	5-10

Pharmacogenomic Risk Component (0-10 points):

Finding	Points
Poor metabolizer for treatment-critical CYP + high-risk HLA	10
Poor metabolizer for treatment-critical CYP	7-8
Intermediate metabolizer for relevant CYP	4-5
Drug target variant (e.g., VKORC1 for warfarin)	3-5
No actionable PGx findings	0-2

遗传风险组分（0-35分）:

场景	点数
高外显率疾病基因中的致病性变异（BRCA1、LDLR、FBN1）	30-35分
多个中风险变异（GWAS位点+中外显率）	20-28分
高PRS（>90百分位）且无已知致病性变异	25-30分
单一中风险变异	12-18分
相关基因中的意义不明确变异	8-12分
平均PRS，无致病性变异	5-10分
低遗传风险（低PRS，无风险等位基因）	0-5分

临床风险组分（0-30分）:

疾病类型	因素	低风险（0-8）	中风险（10-20）	高风险（22-30）
癌症	分期	I期	II-III期	IV期
2型糖尿病	HbA1c	<7%	7-9%	>9%
CVD	ASCVD 10年风险	<10%	10-20%	>20%
神经系统疾病	生物标志物状态	无生物标志物异常	轻度异常	确诊
罕见病	表型匹配度	部分匹配	中度匹配	完全匹配

分子特征组分（0-25分）:

特征	点数
癌症：高风险驱动突变（TP53+PIK3CA、KRAS G12C）	20-25分
癌症：可行动突变（EGFR、BRAF V600E）	15-20分
癌症：高TMB或MSI-H（免疫治疗获益）	10-15分
代谢性疾病：单基因类型（MODY、FH）	20-25分
代谢性疾病：多个代谢风险变异	10-15分
CVD：FH基因突变	20-25分
罕见病：完全基因型-表型匹配	20-25分
需进一步检查的意义不明确变异	5-10分

药物基因组学风险组分（0-10分）:

发现	点数
治疗关键CYP弱代谢型 + 高风险HLA等位基因	10分
治疗关键CYP弱代谢型	7-8分
相关CYP中间代谢型	4-5分
药物靶点变异（如华法林相关VKORC1）	3-5分
无可行动PGx发现	0-2分

Risk Tier Assignment

风险等级划分

Total Score	Risk Tier	Management Intensity
75-100	VERY HIGH	Intensive treatment, subspecialty referral, clinical trial enrollment
50-74	HIGH	Aggressive treatment, close monitoring, molecular tumor board
25-49	INTERMEDIATE	Standard treatment, guideline-based care, PGx-guided dosing
0-24	LOW	Surveillance, prevention, risk factor modification

总评分	风险等级	管理强度
75-100	极高	强化治疗、专科转诊、临床试验入组
50-74	高	积极治疗、密切监测、分子肿瘤会诊
25-49	中	标准治疗、指南导向护理、PGx指导剂量
0-24	低	监测、预防、风险因素干预

Treatment Algorithm

治疗算法

Based on disease type + risk tier + molecular profile + PGx:

基于疾病类型+风险等级+分子特征+PGx:

Cancer Treatment Algorithm

癌症治疗算法

IF actionable mutation present:
  1st line: Targeted therapy (e.g., EGFR TKI, BRAF inhibitor, PARP inhibitor)
  2nd line: Immunotherapy (if TMB-H or MSI-H) OR chemotherapy
  3rd line: Clinical trial OR alternative targeted therapy

IF no actionable mutation:
  IF TMB-H or MSI-H:
    1st line: Immunotherapy (pembrolizumab)
    2nd line: Chemotherapy
  ELSE:
    1st line: Standard chemotherapy (disease-specific)
    2nd line: Consider clinical trials

PGx adjustments:
  - DPYD deficient -> AVOID fluoropyrimidines or reduce dose 50%
  - UGT1A1 *28/*28 -> Reduce irinotecan dose
  - CYP2D6 PM + tamoxifen -> Switch to aromatase inhibitor

若存在可行动突变:
  一线：靶向治疗（如EGFR TKI、BRAF抑制剂、PARP抑制剂）
  二线：免疫治疗（若TMB-H或MSI-H）或化疗
  三线：临床试验或备选靶向治疗

若无可行行动突变:
  若TMB-H或MSI-H:
    一线：免疫治疗（帕博利珠单抗）
    二线：化疗
  否则:
    一线：标准化疗（疾病特异性）
    二线：考虑临床试验

PGx调整:
  - DPYD缺陷 -> 避免氟嘧啶类或剂量降低50%
  - UGT1A1 *28/*28 -> 降低伊立替康剂量
  - CYP2D6弱代谢型 + 他莫昔芬 -> 更换为芳香化酶抑制剂

Metabolic/CVD Treatment Algorithm

代谢性/CVD治疗算法

IF monogenic form (MODY, FH):
  Disease-specific therapy (e.g., sulfonylureas for HNF1A-MODY, PCSK9i for FH)

IF polygenic risk:
  Standard guidelines (ADA, ACC/AHA)
  PGx-guided drug selection:
    - CYP2C19 PM -> Alternative to clopidogrel (ticagrelor, prasugrel)
    - SLCO1B1 *5 -> Lower statin dose or alternative statin
    - VKORC1 variant -> Warfarin dose adjustment or DOAC

若为单基因类型（MODY、FH）:
  疾病特异性治疗（如HNF1A-MODY用磺脲类、FH用PCSK9抑制剂）

若为多基因风险:
  遵循标准指南（ADA、ACC/AHA）
  PGx指导药物选择:
    - CYP2C19弱代谢型 -> 替代氯吡格雷（替格瑞洛、普拉格雷）
    - SLCO1B1 *5 -> 降低他汀剂量或更换他汀
    - VKORC1变异 -> 调整华法林剂量或使用DOAC

Monitoring Plan

监测计划

Component	Frequency	Method
Molecular biomarkers	Per guideline	Liquid biopsy, tissue biopsy
Clinical markers	3-6 months	Labs, imaging
PGx-guided drug levels	As needed	TDM
Disease progression	Per stage/risk	Imaging, biomarkers
Comorbidity screening	Annually	Labs, risk calculators

组分	频率	方法
分子生物标志物	按指南	液体活检、组织活检
临床标志物	3-6个月	实验室检查、影像学
PGx指导的药物浓度	按需	治疗药物监测（TDM）
疾病进展	按分期/风险	影像学、生物标志物
合并症筛查	每年	实验室检查、风险计算器

Output Report Structure

输出报告结构

Generate a comprehensive markdown report saved to:

[PATIENT_ID]_precision_medicine_report.md

生成全面的markdown报告，保存至：

[PATIENT_ID]_precision_medicine_report.md

Required Sections

必填章节

markdown

undefined

markdown

undefined

Precision Medicine Stratification Report

精准医学分层报告

Executive Summary

执行摘要

Patient Profile: [Disease, key features]
Precision Medicine Risk Score: [X]/100
Risk Tier: [LOW / INTERMEDIATE / HIGH / VERY HIGH]
Key Finding: [One-line summary of most actionable finding]
Primary Recommendation: [One-line treatment recommendation]

患者特征: [疾病、关键特征]
精准医学风险评分: [X]/100
风险等级: [低 / 中 / 高 / 极高]
关键发现: [最具可行动性发现的单行总结]
首要建议: [单行治疗建议]

1. Patient Profile

1. 患者特征

Disease Classification

疾病分类

Genomic Data Summary

基因组数据摘要

Clinical Parameters

临床参数

2. Genetic Risk Assessment

2. 遗传风险评估

Germline Variant Analysis

种系变异分析

Gene-Disease Association Evidence

基因-疾病关联证据

Polygenic Risk Estimation

多基因风险估计

Population Frequency Data

人群频率数据

3. Disease-Specific Stratification

3. 疾病特异性分层

[Cancer: Molecular Subtype / Metabolic: Risk Integration / etc.]

[癌症：分子亚型 / 代谢性疾病：风险整合 / 等]

Prognostic Markers

预后标志物

Risk Group Assignment

风险分组

4. Pharmacogenomic Profile

4. 药物基因组学特征

Drug-Metabolizing Enzymes

药物代谢酶

Drug Target Variants

药物靶点变异

Treatment-Specific PGx Recommendations

治疗特异性PGx建议

FDA PGx Biomarker Status

FDA PGx生物标志物状态

5. Comorbidity & Drug Interaction Risk

5. 合并症与药物相互作用风险

Disease-Disease Overlap

疾病-疾病重叠

Drug-Drug Interactions

药物-药物相互作用

PGx-Amplified DDI Risk

PGx放大的DDI风险

6. Dysregulated Pathways

6. 失调通路

Key Pathways Affected

受影响的关键通路

Druggable Targets

可成药靶点

Network Analysis

网络分析

7. Clinical Evidence & Guidelines

7. 临床证据与指南

Guideline-Based Classification

指南导向分类

FDA-Approved Therapies

FDA获批疗法

Biomarker-Drug Evidence

生物标志物-药物证据

8. Clinical Trial Matches

8. 临床试验匹配

Biomarker-Driven Trials

生物标志物驱动的试验

Precision Medicine Trials

精准医学试验

Risk-Adapted Trials

风险适应性试验

9. Integrated Risk Score

9. 综合风险评分

Score Breakdown

评分细分

Component	Points	Max	Basis
Genetic Risk	X	35	[Details]
Clinical Risk	X	30	[Details]
Molecular Features	X	25	[Details]
Pharmacogenomic Risk	X	10	[Details]
TOTAL	X	100

组分	点数	满分	依据
遗传风险	X	35	[详情]
临床风险	X	30	[详情]
分子特征	X	25	[详情]
药物基因组学风险	X	10	[详情]
总计	X	100

Risk Tier: [TIER]

风险等级: [等级]

Confidence Level: [HIGH/MODERATE/LOW]

置信水平: [高/中/低]

10. Treatment Algorithm

10. 治疗算法

1st Line Recommendation

一线建议

2nd Line Options

二线选项

3rd Line / Investigational

三线 / 研究阶段

PGx Dose Adjustments

PGx剂量调整

11. Monitoring Plan

11. 监测计划

Biomarker Surveillance

生物标志物监测

Imaging Schedule

影像学 schedule

Risk Reassessment Timeline

风险重新评估时间线

12. Outcome Predictions

12. 预后预测

Disease-Specific Prognosis

疾病特异性预后

Treatment Response Prediction

治疗反应预测

Projected Timeline

预期时间线

Completeness Checklist

完整性检查清单

Data Layer	Available	Analyzed	Key Finding
Disease disambiguation	Y/N	Y/N	[EFO ID]
Germline variants	Y/N	Y/N	[Pathogenicity]
Somatic mutations	Y/N	Y/N	[Drivers]
Gene expression	Y/N	Y/N	[Subtype]
PGx genotypes	Y/N	Y/N	[Metabolizer status]
Clinical biomarkers	Y/N	Y/N	[Key values]
GWAS/PRS	Y/N	Y/N	[Risk percentile]
Pathway analysis	Y/N	Y/N	[Key pathways]
Clinical trials	Y/N	Y/N	[N matches]
Guidelines	Y/N	Y/N	[Guideline tier]

数据层面	可用	已分析	关键发现
疾病明确诊断	是/否	是/否	[EFO ID]
种系变异	是/否	是/否	[致病性]
体细胞突变	是/否	是/否	[驱动突变]
基因表达	是/否	是/否	[亚型]
PGx基因型	是/否	是/否	[代谢型状态]
临床生物标志物	是/否	是/否	[关键数值]
GWAS/PRS	是/否	是/否	[风险百分位]
通路分析	是/否	是/否	[关键通路]
临床试验	是/否	是/否	[匹配数量]
指南	是/否	是/否	[指南等级]

Evidence Sources

证据来源

[List all databases and tools used with specific citations]

---

[列出所有使用的数据库和工具，并标注具体引用]

---

Evidence Grading

证据分级

All findings must be graded:

Tier	Level	Sources	Weight
T1	Clinical/regulatory evidence	FDA labels, NCCN guidelines, PharmGKB Level 1A/1B, ClinVar pathogenic	Highest
T2	Strong experimental evidence	CIViC Level A/B, OpenTargets high-score, GWAS p<5e-8, clinical trials	High
T3	Moderate evidence	PharmGKB Level 2, CIViC Level C, GWAS suggestive, preclinical data	Moderate
T4	Computational/predicted	VEP predictions, pathway inference, network analysis, PRS estimates	Supportive

所有发现必须进行分级:

等级	水平	来源	权重
T1	临床/监管证据	FDA标签、NCCN指南、PharmGKB Level 1A/1B、ClinVar致病性	最高
T2	强实验证据	CIViC Level A/B、OpenTargets高分、GWAS p<5e-8、临床试验	高
T3	中等证据	PharmGKB Level 2、CIViC Level C、GWAS提示性、临床前数据	中等
T4	计算/预测性	VEP预测、通路推断、网络分析、PRS估计	支持性

Completeness Requirements

完整性要求

Minimum deliverables for a valid stratification report:

Disease resolved to EFO/ontology ID
At least one genetic risk assessment completed (germline OR somatic OR PRS)
Disease-specific stratification with risk group
At least one pharmacogenomic assessment (even if "no actionable findings")
Pathway analysis with at least one pathway identified
Treatment recommendation with evidence tier
At least one clinical trial match attempted
Precision Medicine Risk Score calculated with all available components
Risk tier assigned
Monitoring plan outlined

有效分层报告的最低交付要求:

疾病解析为EFO/本体ID
至少完成一项遗传风险评估（种系/体细胞/PRS）
疾病特异性分层并划分风险组
至少完成一项药物基因组学评估（即使结果为“无可行动发现”）
通路分析且至少识别一条通路
带证据等级的治疗建议
至少尝试匹配一项临床试验
利用所有可用组分计算精准医学风险评分
划分风险等级
制定监测计划

Common Use Patterns

常见使用模式

Pattern 1: Cancer Patient with Actionable Mutation

模式1：携带可行动突变的癌症患者

Input: "Breast cancer, BRCA1 pathogenic variant, ER+/HER2-, stage IIA, age 45" Key phases: Phase 1 (cancer classification) -> Phase 2 (BRCA1 pathogenicity) -> Phase 3C (molecular subtype = Luminal B, BRCA+) -> Phase 4 (check CYP2D6 for tamoxifen) -> Phase 7 (NCCN guidelines: PARP inhibitor eligible) -> Phase 8 (PARP inhibitor trials) -> Phase 9 (Risk Score ~55-65, HIGH tier)

输入: "乳腺癌，BRCA1致病性变异，ER+/HER2-，IIA期，年龄45" 核心阶段: 阶段1（癌症分类）-> 阶段2（BRCA1致病性）-> 阶段3C（分子亚型=Luminal B、BRCA+）-> 阶段4（检查他莫昔芬相关CYP2D6）-> 阶段7（NCCN指南：符合PARP抑制剂使用条件）-> 阶段8（PARP抑制剂试验）-> 阶段9（风险评分~55-65，高等级）

Pattern 2: Metabolic Disease with PGx Concern

模式2：存在PGx顾虑的代谢性疾病患者

Input: "Type 2 diabetes, HbA1c 8.5%, CYP2C19 *2/*2, on clopidogrel for CAD stent" Key phases: Phase 1 (T2D + CAD) -> Phase 2 (T2D genetic risk) -> Phase 3M (HbA1c-based risk) -> Phase 4 (CYP2C19 PM: clopidogrel ineffective!) -> Phase 5 (T2D-CAD comorbidity) -> Phase 9 (Risk Score ~50-60, HIGH, clopidogrel switch urgent)

输入: "2型糖尿病，HbA1c 8.5%，CYP2C19 *2/*2，因CAD支架术后服用氯吡格雷" 核心阶段: 阶段1（2型糖尿病+CAD）-> 阶段2（2型糖尿病遗传风险）-> 阶段3M（基于HbA1c的风险）-> 阶段4（CYP2C19弱代谢型：氯吡格雷无效！）-> 阶段5（2型糖尿病-CAD合并症）-> 阶段9（风险评分~50-60，高等级，需紧急更换氯吡格雷）

Pattern 3: CVD Risk Stratification

模式3：CVD风险分层

Input: "LDL 190 mg/dL, SLCO1B1*5 heterozygous, family history of MI at age 48" Key phases: Phase 1 (CVD/FH evaluation) -> Phase 2 (FH gene check: LDLR, APOB, PCSK9) -> Phase 3V (ASCVD risk) -> Phase 4 (SLCO1B1 *5: statin myopathy risk) -> Phase 7 (ACC/AHA guidelines) -> Phase 9 (Risk Score ~45-55, statin dose reduction or rosuvastatin)

输入: "LDL 190 mg/dL，SLCO1B1*5杂合型，父亲48岁时患心肌梗死" 核心阶段: 阶段1（CVD/FH评估）-> 阶段2（FH基因检查：LDLR、APOB、PCSK9）-> 阶段3V（ASCVD风险）-> 阶段4（SLCO1B1 *5：他汀类肌病风险）-> 阶段7（ACC/AHA指南）-> 阶段9（风险评分~45-55，需降低他汀剂量或使用瑞舒伐他汀）

Pattern 4: Rare Disease Diagnosis

模式4：罕见病诊断

Input: "Marfan syndrome suspected, FBN1 c.4082G>A, tall stature, aortic root dilation" Key phases: Phase 1 (Marfan/rare) -> Phase 2 (FBN1 variant pathogenicity) -> Phase 3R (genotype-phenotype match) -> Phase 7 (Ghent criteria) -> Phase 9 (Risk Score depends on aortic involvement)

输入: "疑似马凡综合征，FBN1 c.4082G>A，身材高大，主动脉根部扩张" 核心阶段: 阶段1（马凡综合征/罕见病）-> 阶段2（FBN1变异致病性）-> 阶段3R（基因型-表型匹配）-> 阶段7（Ghent标准）-> 阶段9（风险评分取决于主动脉受累情况）

Pattern 5: Neurological Risk Assessment

模式5：神经系统疾病风险评估

Input: "Family history of Alzheimer's, APOE e4/e4, age 55" Key phases: Phase 1 (AD/neuro) -> Phase 2 (APOE e4/e4 = highest genetic risk) -> Phase 3 (AD-specific risk) -> Phase 4 (PGx for potential treatments) -> Phase 7 (guidelines) -> Phase 9 (Risk Score ~60-75, HIGH)

输入: "阿尔茨海默病家族史，APOE e4/e4，年龄55" 核心阶段: 阶段1（AD/神经系统疾病）-> 阶段2（APOE e4/e4=最高遗传风险）-> 阶段3（AD特异性风险）-> 阶段4（潜在治疗的PGx）-> 阶段7（指南）-> 阶段9（风险评分~60-75，高等级）

Pattern 6: Comprehensive Cancer with Full Molecular

模式6：具备完整分子数据的全面癌症患者

Input: "NSCLC, EGFR L858R, TMB 25 mut/Mb, PD-L1 80%, stage IV, no EGFR T790M" Key phases: All phases. Phase 3C critical: EGFR L858R = EGFR TKI eligible, high TMB + PD-L1 = ICI eligible. Treatment algorithm: 1st line osimertinib (EGFR TKI), 2nd line ICI (if progression). Risk Score ~70-80 (VERY HIGH due to stage IV).

输入: "NSCLC，EGFR L858R，TMB 25 mut/Mb，PD-L1 80%，IV期，无EGFR T790M" 核心阶段: 所有阶段。阶段3C至关重要：EGFR L858R=符合EGFR TKI使用条件，高TMB+PD-L1=符合免疫治疗使用条件。治疗算法：一线奥希替尼（EGFR TKI），二线免疫治疗（若进展）。风险评分~70-80（因IV期为极高等级）