674 lines
30 KiB
Python
674 lines
30 KiB
Python
|
# -*- coding: utf-8 -*-
|
|||
|
|
"""育种统计 Schema（一期 2 个最基础：ABLUP·EBV + 配合力 GCA/SCA）"""
|
|||
|
|
from datetime import datetime
|
|||
|
|
|
|||
|
|
from pydantic import BaseModel, ConfigDict, Field
|
|||
|
|
|
|||
|
|
|
|||
|
|
class RunStatsIn(BaseModel):
|
|||
|
|
"""提交统计任务的入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码（bre_trait.trait_code，如 avg_fruit_weight）")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
fixed_effects: list[str] | None = Field(
|
|||
|
|
None, description="固定效应因子：支持 trial_study(试验/站点) / rootstock(砧木)"
|
|||
|
|
)
|
|||
|
|
covariate: str | None = Field(
|
|||
|
|
None, description="协变量（BLUP 校正）：crop_load(负载量) / competition(空间竞争:相邻株数)"
|
|||
|
|
)
|
|||
|
|
data_gate: bool = Field(
|
|||
|
|
True, description="数据就绪门禁(G1)：每 clone/家系最小 n、系谱完整率、缺失率任一不达标则拒绝运行"
|
|||
|
|
)
|
|||
|
|
min_clone_n: int = Field(
|
|||
|
|
2, ge=0, description="每 clone/家系最小样本量（观测树数低于该值的组列入未达标）"
|
|||
|
|
)
|
|||
|
|
min_pedigree_rate: float = Field(
|
|||
|
|
0.3, ge=0.0, le=1.0, description="系谱完整率下限（有父母或组合亲本的观测树占比）"
|
|||
|
|
)
|
|||
|
|
max_missing_rate: float = Field(
|
|||
|
|
0.8, ge=0.0, le=1.0, description="表型缺失率上限（缺失=有评价记录但无该性状数值）"
|
|||
|
|
)
|
|||
|
|
gxe: bool = Field(
|
|||
|
|
False, description="启用 G×E 交互随机效应（clone×site / 组合×site；year 同理）"
|
|||
|
|
)
|
|||
|
|
gxe_env: str = Field(
|
|||
|
|
"site", description="G×E 环境维度：site(trial_study_id) / year(evaluate_year)"
|
|||
|
|
)
|
|||
|
|
gxr: bool = Field(
|
|||
|
|
False, description="启用砧木×接穗随机互作（G×R）：rootstock 从固定效应移到随机效应，与 gxe 互斥"
|
|||
|
|
)
|
|||
|
|
spatial: bool = Field(
|
|||
|
|
False,
|
|||
|
|
description=(
|
|||
|
|
"启用 AR1×AR1 空间协方差（残差 e~N(0,σ²e·R)，R_ij=ρ^(|Δrow|+|Δcol|)）："
|
|||
|
|
"需观测株均有 bre_tree.row_no/col_no；与 gxe/gxr 互斥"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
spatial_aniso: bool = Field(
|
|||
|
|
False,
|
|||
|
|
description=(
|
|||
|
|
"空间协方差各向异性双参数（需 spatial=True）：R_ij=ρ_row^|Δrow|·ρ_col^|Δcol|，"
|
|||
|
|
"方法 AR1×AR1(aniso)，输出 ρ_row/ρ_col；False 时用单参 ρ（v1 兼容）"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
block: bool = Field(
|
|||
|
|
False,
|
|||
|
|
description=(
|
|||
|
|
"启用区组随机效应（不完全区组/增广/α-格子）：bre_tree.block_no 作第二随机效应，"
|
|||
|
|
"精度收益进入遗传评估；需 ≥2 个区组；与 gxe/gxr/spatial 互斥"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
stage: str | None = Field(
|
|||
|
|
None, description="发育阶段拆分：juvenile(童期)/evaluation(成株)；给定则只取该阶段观测建模并拆独立批次"
|
|||
|
|
)
|
|||
|
|
design_type: str = Field(
|
|||
|
|
"full_diallel",
|
|||
|
|
description=(
|
|||
|
|
"交配设计（配合力分析用）：full_diallel=完全双列(Griffing) / "
|
|||
|
|
"partial_diallel=部分双列 / line_tester=line×tester(NCII 两因素模型) / "
|
|||
|
|
"nciii=NCIII 测交"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class PredictionOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
model_name: str | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
stage: str | None = None
|
|||
|
|
accuracy: float | None = None
|
|||
|
|
train_n: int | None = None
|
|||
|
|
heritability: float | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
is_active: bool | None = None
|
|||
|
|
note: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class PredictionValueOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
prediction_id: int
|
|||
|
|
germplasm_id: int | None = None
|
|||
|
|
tree_id: int | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
predicted_value: float | None = None
|
|||
|
|
reliability: float | None = None
|
|||
|
|
pa: float | None = None
|
|||
|
|
rank: int | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CombiningAbilityOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
model_name: str | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
design_type: str | None = None
|
|||
|
|
gca_json: dict | None = None
|
|||
|
|
sca_json: dict | None = None
|
|||
|
|
anova_json: dict | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class StatisticsJobOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
job_type: str | None = None
|
|||
|
|
status: str
|
|||
|
|
params_json: dict | None = None
|
|||
|
|
result_ref: int | None = None
|
|||
|
|
error_msg: str | None = None
|
|||
|
|
started_time: datetime | None = None
|
|||
|
|
finished_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- 纯 Python 统计分析（不依赖 R） ----------
|
|||
|
|
class DescribeStatsIn(BaseModel):
|
|||
|
|
"""描述性统计入参。"""
|
|||
|
|
trait_codes: list[str] | None = Field(None, description="数值性状列名；为空则用全部数值列")
|
|||
|
|
group_by: str = Field("none", description="分组维度：none/year/combination")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CorrelationIn(BaseModel):
|
|||
|
|
"""相关分析入参。"""
|
|||
|
|
trait_codes: list[str] | None = Field(None, description="参与相关的数值性状；至少2个")
|
|||
|
|
mode: str = Field(
|
|||
|
|
"pheno",
|
|||
|
|
description="相关类型：pheno=表型相关（皮尔逊，纯Python）；genetic=遗传相关（成对双性状BLUP REML）",
|
|||
|
|
)
|
|||
|
|
g_method: str = Field(
|
|||
|
|
"mtblup",
|
|||
|
|
description="遗传相关 r_g 来源（仅 mode=genetic）：mtblup=成对双性状BLUP(REML精确)；calo=可靠性校正EBV相关，无生效EBV批次时回退mtblup",
|
|||
|
|
)
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class SelectionIndexIn(BaseModel):
|
|||
|
|
"""选择指数入参。"""
|
|||
|
|
weights: dict[str, float] | None = Field(None, description="性状->权重，缺省等权；自动归一化")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤（仅表型回退路径使用）")
|
|||
|
|
top_n: int = Field(50, description="返回排名前 N 的单株")
|
|||
|
|
batch_ids: dict[str, int] | None = Field(None, description="性状->ABLUP批次id，指定则用该批次的EBV作为指数输入")
|
|||
|
|
use_h2: bool = Field(True, description="有效权重 = 用户权重 × 遗传力(h²) 加权（仅 zsum 模式生效）")
|
|||
|
|
method: str = Field(
|
|||
|
|
"zsum",
|
|||
|
|
description=(
|
|||
|
|
"zsum=加权Z综合（轻量，可表型回退）；"
|
|||
|
|
"smith_hazel=真Smith-Hazel b=P⁻¹Ga（需各性状指定EBV批次且含h²）；"
|
|||
|
|
"restricted=约束指数 b=P⁻¹G(I−M)a（Kempthorne-Nordskog，受限性状 ΔG=0，需 restricted_traits）"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
aggregate: str = Field(
|
|||
|
|
"clone",
|
|||
|
|
description=(
|
|||
|
|
"聚合粒度：clone=无性系级（同系多株可靠加权聚合为一个遗传实体再排名，桃无性繁殖默认）；"
|
|||
|
|
"tree=单株级（旧行为）"
|
|||
|
|
),
|
|||
|
|
)
|
|||
|
|
stage: str | None = Field(
|
|||
|
|
None, description="发育阶段过滤：juvenile(童期)/evaluation(成株)；不传且性状横跨两阶段时返回 stage_warning"
|
|||
|
|
)
|
|||
|
|
g_method: str = Field(
|
|||
|
|
"calo", description="遗传相关 r_g 来源（smith_hazel / restricted 生效）：calo=可靠性校正EBV相关；mtblup=成对双性状BLUP(REML精确估计，单对不收敛回退calo)"
|
|||
|
|
)
|
|||
|
|
auto_weights: bool = Field(
|
|||
|
|
False,
|
|||
|
|
description="自动权重：以各性状 default_h2（实测h²优先，兜底0.1）为权重；强制 use_h2=False 防双重相乘",
|
|||
|
|
)
|
|||
|
|
restricted_traits: list[str] | None = Field(
|
|||
|
|
None, description="受限性状列表（仅 method=restricted 生效）：这些性状的遗传增益被约束为 0，其余性状自由响应（Kempthorne-Nordskog 闭式投影）"
|
|||
|
|
)
|
|||
|
|
economic_weights: dict[str, float] | None = Field(
|
|||
|
|
None, description="经济权重（经济价值，绝对尺度不归一化；smith_hazel / restricted 生效）：直接作为聚合基因型系数 a，未列出性状按 0 处理"
|
|||
|
|
)
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class SelectionIndexOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
model_name: str | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
weights_json: dict | None = None
|
|||
|
|
batch_refs_json: dict | None = None
|
|||
|
|
heritability_json: dict | None = None
|
|||
|
|
top_n: int | None = None
|
|||
|
|
result_json: dict | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class SelectionIndexApplyIn(BaseModel):
|
|||
|
|
"""选择指数 -> 决选 入参。"""
|
|||
|
|
top_n: int = Field(50, description="写入前 N 名单株")
|
|||
|
|
selection_year: int | None = Field(None, description="入选年份；为空用当年")
|
|||
|
|
rule_id: int | None = Field(None, description="来源选择规则(决策预览选定,用于溯源 rule_id/from_stage/to_stage)")
|
|||
|
|
min_reliability: float = Field(
|
|||
|
|
0.2, ge=0.0, le=1.0,
|
|||
|
|
description="EBV 可靠性硬门槛：指数引用批次的 EBV 可靠性低于该值的单株跳过(证据不足不入选)",
|
|||
|
|
)
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class KinshipIn(BaseModel):
|
|||
|
|
"""亲缘/近交分析入参。"""
|
|||
|
|
threshold: float = Field(0.25, description="亲缘系数预警阈值（r>A 预警）")
|
|||
|
|
tree_ids: list[int] | None = Field(None, description="限定单株范围；为空用全部活动单株")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class DataQualityIn(BaseModel):
|
|||
|
|
"""数据质量/异常值诊断入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
trial_study_id: int | None = Field(None, description="限定试验/站点(MET)；为空则全部")
|
|||
|
|
dataset_id: int | None = Field(
|
|||
|
|
None, description="基因型数据集：提供时附加孟德尔检验段（最新批次计数+flag树+隔离状态）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GeneticGainIn(BaseModel):
|
|||
|
|
"""ΔG 遗传增益投影入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
prediction_id: int | None = Field(None, description="指定 EBV 批次；为空用该性状最新批次")
|
|||
|
|
top_p: float | None = Field(None, gt=0, lt=1, description="入选比例（0-1，与 top_n 二选一）")
|
|||
|
|
top_n: int | None = Field(None, ge=1, description="入选株数（与 top_p 二选一）")
|
|||
|
|
generation_interval: float = Field(1.0, gt=0, description="世代间隔(年)；年增益=ΔG/L")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class InbreedingDepressionIn(BaseModel):
|
|||
|
|
"""近交衰退分析入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
trial_study_id: int | None = Field(None, description="限定试验/站点(MET)；为空则全部")
|
|||
|
|
min_n: int = Field(10, ge=2, description="回归最小样本量（同时具备 F 与表型的树）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class TrialDesignIn(BaseModel):
|
|||
|
|
"""试验设计生成入参（rcbd / augmented / alpha）。"""
|
|||
|
|
trial_study_id: int = Field(..., description="试验研究点 id（bre_trial_study）")
|
|||
|
|
design_type: str = Field("rcbd", description="设计类型：rcbd=随机完全区组、augmented=增广、alpha=α-格子")
|
|||
|
|
seed: int | None = Field(None, description="随机种子；固定 seed 可复现同一设计")
|
|||
|
|
check_germplasm_ids: list[int] = Field(default_factory=list,
|
|||
|
|
description="增广设计对照种质 id 列表（每区组重复）")
|
|||
|
|
block_size: int | None = Field(None, description="α-格子区组大小 k（每重复区组块大小）")
|
|||
|
|
reps: int | None = Field(None, description="α-格子重复数 r（平方格子缺省 k+1）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MatingRecommendIn(BaseModel):
|
|||
|
|
"""主动选配推荐入参。"""
|
|||
|
|
candidate_germplasm_ids: list[int] = Field(..., description="候选亲本种质 id 集合（≥2）")
|
|||
|
|
prediction_id: int | None = Field(None, description="EBV 批次；为空用最新 ABLUP/GBLUP 批次")
|
|||
|
|
kinship_threshold: float = Field(0.25, description="亲缘惩罚阈值（r>阈值开始扣分）")
|
|||
|
|
w_ebv: float = Field(1.0, ge=0, description="EBV 互补权重")
|
|||
|
|
w_kin: float = Field(1.0, ge=0, description="近交惩罚权重")
|
|||
|
|
max_pairs: int = Field(20, ge=1, le=500, description="返回 top N 配对")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class OcsIn(BaseModel):
|
|||
|
|
"""最优贡献选择（OCS）入参。"""
|
|||
|
|
candidate_germplasm_ids: list[int] = Field(..., description="候选亲本种质 id 集合")
|
|||
|
|
n_select: int = Field(5, ge=1, description="选择数量（贡献总和 Σc=n_select）")
|
|||
|
|
lam: float = Field(0.1, ge=0, description="近交约束权重 λ：越大越压低子代平均亲缘（avg_kinship 单调非增），0=无近交约束（满额投最高 EBV 单亲）")
|
|||
|
|
prediction_id: int | None = Field(None, description="EBV 批次；为空用最新 ABLUP/GBLUP 批次")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MabcIn(BaseModel):
|
|||
|
|
"""MABC 标记辅助回交进度入参。"""
|
|||
|
|
candidate_tree_ids: list[int] = Field(..., description="候选回交单株树 id 集合（BC 世代分离群体）")
|
|||
|
|
foreground_panel_ids: list[int] = Field(..., description="前景选择面板 id（目标性状 MAS 面板）")
|
|||
|
|
background_panel_ids: list[int] = Field(..., description="背景恢复面板 id（全基因组标记面板）")
|
|||
|
|
recurrent_parent_tree_id: int = Field(..., description="轮回亲本树 id（背景纯合一致对照）")
|
|||
|
|
foreground_min_hits: int = Field(1, ge=1, description="前景通过阈值（有利剂量命中标记数 ≥ 此值，stage 无关、童期可用）")
|
|||
|
|
generation: str = Field("BC1", description="候选当前回交代（F1/BC1/BC2/BC3），用于晋级建议")
|
|||
|
|
background_target: float = Field(90.0, gt=0, le=100, description="背景恢复目标 %（达到则建议晋级下一回交代）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class AnovaIn(BaseModel):
|
|||
|
|
"""ANOVA / 广义遗传力 H² 入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
block: bool = Field(
|
|||
|
|
False, description="RCBD 设计基 ANOVA：True=从残差析出区组效应(SS_block/F_block/p_block)，遗传差异为区组校正后；需观测株 bre_tree.block_no")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class AnovaOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
model_name: str | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
result_json: dict | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CvRunIn(BaseModel):
|
|||
|
|
"""k-fold 交叉验证入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
fixed_effects: list[str] | None = Field(
|
|||
|
|
None, description="固定效应因子：trial_study(试验/站点) / rootstock(砧木)"
|
|||
|
|
)
|
|||
|
|
covariate: str | None = Field(
|
|||
|
|
None, description="协变量：crop_load(负载量) / competition(空间竞争)"
|
|||
|
|
)
|
|||
|
|
gxe: bool = Field(False, description="启用 G×E 交互随机效应")
|
|||
|
|
gxe_env: str = Field("site", description="G×E 环境维度：site / year")
|
|||
|
|
k: int = Field(5, ge=2, le=10, description="折数")
|
|||
|
|
dataset_id: int | None = Field(
|
|||
|
|
None, description="基因型数据集 id；给定则走 GS 交叉验证（GBLUP/ssGBLUP/rrBLUP/BayesB）"
|
|||
|
|
)
|
|||
|
|
method: str | None = Field(
|
|||
|
|
None, description="GS 方法：gblup / ssgblup / rrblup / bayesb（仅 dataset_id 给定时生效）"
|
|||
|
|
)
|
|||
|
|
maf_min: float = Field(0.05, description="MAF 下限（GS 交叉验证用）")
|
|||
|
|
split: str = Field(
|
|||
|
|
"random", description="GS 折划分：random=固定种子随机分层（默认）/ family=家系阻塞折（同父半同胞同折，防亲缘泄漏）"
|
|||
|
|
)
|
|||
|
|
seed: int = Field(20260805, description="BayesB 随机种子（折划分与 Gibbs 共用，固定可复现）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CvResultOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
trait_code: str | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
k: int | None = None
|
|||
|
|
n_total: int | None = None
|
|||
|
|
n_individuals: int | None = None
|
|||
|
|
mean_pearson: float | None = None
|
|||
|
|
mean_rmse: float | None = None
|
|||
|
|
pooled_pearson: float | None = None
|
|||
|
|
pooled_rmse: float | None = None
|
|||
|
|
cv_accuracy: float | None = None
|
|||
|
|
h2: float | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
note: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class CvFoldOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
cv_result_id: int
|
|||
|
|
fold_idx: int | None = None
|
|||
|
|
n_train: int | None = None
|
|||
|
|
n_test: int | None = None
|
|||
|
|
n_eval: int | None = None
|
|||
|
|
pearson: float | None = None
|
|||
|
|
rmse: float | None = None
|
|||
|
|
error: str | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class DecisionPreviewIn(BaseModel):
|
|||
|
|
"""选择规则 × 表型/EBV/标记(MAS) 决策预览入参。"""
|
|||
|
|
rule_ids: list[int] | None = Field(None, description="指定规则；为空用全部启用规则")
|
|||
|
|
prediction_id: int | None = Field(None, description="EBV 源批次；为空用最新 ABLUP 批次")
|
|||
|
|
year: int | None = Field(None, description="表型均值年份过滤")
|
|||
|
|
min_reliability: float = Field(
|
|||
|
|
0.2, ge=0.0, le=1.0,
|
|||
|
|
description="EBV 可靠性门槛：单株 EBV 可靠性低于该值视为证据不足，不参与晋级/淘汰判定；"
|
|||
|
|
"ebv 条件内可配 min_reliability 逐性状覆盖",
|
|||
|
|
)
|
|||
|
|
stage: str | None = Field(
|
|||
|
|
None, description="发育阶段过滤：juvenile(童期)/evaluation(成株)；不传且规则引用性状横跨两阶段时返回 stage_warning"
|
|||
|
|
)
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class DecisionPreviewOut(BaseModel):
|
|||
|
|
rule_id: int | None = None
|
|||
|
|
rule_name: str | None = None
|
|||
|
|
action: str | None = None
|
|||
|
|
stage: str | None = None
|
|||
|
|
matched: bool | None = None
|
|||
|
|
reasons: list[str] | None = None
|
|||
|
|
tree_id: int | None = None
|
|||
|
|
tree_no: str | None = None
|
|||
|
|
combination_id: int | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- AMMI / Finlay-Wilkinson 稳定性（§8.18） ----------
|
|||
|
|
class StabilityRunIn(BaseModel):
|
|||
|
|
"""稳定性分析入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
gxe_env: str = Field("site", description="环境维度：site(trial_study_id) / year(evaluate_year)")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
methods: list[str] = Field(
|
|||
|
|
["ammi", "finlay"], description="分析方法：ammi / finlay，可多选"
|
|||
|
|
)
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class StabilityOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
trait_code: str | None = None
|
|||
|
|
env_dim: str | None = None
|
|||
|
|
methods: str | None = None
|
|||
|
|
detail_json: dict | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
note: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- 遗传相关矩阵（MT-BLUP，§8.18） ----------
|
|||
|
|
class GeneticCorrIn(BaseModel):
|
|||
|
|
"""遗传相关矩阵入参。"""
|
|||
|
|
trait_ids: list[int] = Field(..., description="参与遗传相关的性状 id（≥2）")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
full_mtblup: bool = Field(
|
|||
|
|
False, description="True=全多变量 EM-REML（一次估计完整 G0⊗A，替代逐对 bivariate）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GeneticCorrOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
trait_ids_json: dict | None = None
|
|||
|
|
matrix_json: dict | None = None
|
|||
|
|
sigma_a_json: dict | None = None
|
|||
|
|
heritability_json: dict | None = None
|
|||
|
|
pairs_json: dict | None = None
|
|||
|
|
n_common: int | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
note: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- Type-B 多环境遗传相关（§8.27） ----------
|
|||
|
|
class TypeBIn(BaseModel):
|
|||
|
|
"""Type-B 多环境遗传相关入参。"""
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait，数值型）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
env_dim: str = Field("site", description="环境维度：site(研究点 trial_study_id) / year(评价年份) / stage(发育阶段：juvenile童期 vs evaluation成株，估幼年-成年遗传相关)")
|
|||
|
|
method: str = Field(
|
|||
|
|
"reml", description="方法：reml=环境互为性状逐对REML双性状BLUP(默认)；calo=分环境EBV相关/√rel(无环境级EBV时回退reml)"
|
|||
|
|
)
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class TypeBOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
trait_code: str | None = None
|
|||
|
|
env_dim: str | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
envs_json: dict | None = None
|
|||
|
|
matrix_json: dict | None = None
|
|||
|
|
pairs_json: dict | None = None
|
|||
|
|
n_common: int | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
note: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- UPGMA 聚类（§8.27，计算端点不落库） ----------
|
|||
|
|
class ClusterIn(BaseModel):
|
|||
|
|
"""UPGMA 聚类入参（实体=单株或无性系，按多性状轮廓聚类）。"""
|
|||
|
|
trait_ids: list[int] = Field(..., description="参与聚类的数值性状 id（≥2）")
|
|||
|
|
entity_type: str = Field("tree", description="聚类实体：tree=单株；clone=无性系(同系多株均值聚合)")
|
|||
|
|
mode: str = Field("pheno", description="值来源：pheno=表型均值；genetic=EBV(无生效批次回退表型)")
|
|||
|
|
distance: str = Field(
|
|||
|
|
"corr", description="实体距离：corr=1-|皮尔逊r|(轮廓相似)；euclidean=标准化欧氏距离"
|
|||
|
|
)
|
|||
|
|
k: int | None = Field(None, description="聚成 k 类；为空按合并距离最大跳变自动选择")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- GBLUP / ssGBLUP 基因组选择（§8.18） ----------
|
|||
|
|
class GblupRunIn(BaseModel):
|
|||
|
|
"""GBLUP/ssGBLUP/rrBLUP/BayesB 基因组选择入参（§8.18）。"""
|
|||
|
|
dataset_id: int = Field(..., description="基因型数据集 id（bre_genotyping_dataset）")
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
method: str = Field("gblup", description="gblup（仅基因型株）/ ssgblup（单步法，含非基因型亲属）/ rrblup（岭回归逐标记，输出 marker effects）/ bayesb（贝叶斯可变选择，固定 seed 可复现）")
|
|||
|
|
maf_min: float = Field(0.05, ge=0.0, lt=0.5, description="MAF 过滤下限")
|
|||
|
|
seed: int = Field(20260805, description="BayesB 随机种子（固定保证可复现；MLOps 铁律）")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GenotypingDatasetOut(BaseModel):
|
|||
|
|
id: int
|
|||
|
|
dataset_name: str | None = None
|
|||
|
|
platform: str | None = None
|
|||
|
|
panel: str | None = None
|
|||
|
|
purpose: str | None = None
|
|||
|
|
run_date: datetime | None = None
|
|||
|
|
n_samples: int | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
# ---------- GWAS / QTL / MAS 标记辅助选择（§8.22） ----------
|
|||
|
|
class GwasRunIn(BaseModel):
|
|||
|
|
"""GWAS 关联分析入参（GLM+PC 首版）。"""
|
|||
|
|
dataset_id: int = Field(..., description="基因型数据集 id（bre_genotyping_dataset）")
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
method: str = Field("gwas", description="gwas（GLM+PC）/ emmax（混合模型 EMMAX）/ ssgwas（单步 GWAS）")
|
|||
|
|
maf_min: float = Field(0.05, ge=0.0, lt=0.5, description="MAF 过滤下限")
|
|||
|
|
n_pc: int = Field(3, ge=1, le=10, description="群体结构主成分数")
|
|||
|
|
sig_level: float = Field(0.05, gt=0.0, le=1.0, description="显著性水平")
|
|||
|
|
qtl_window: int = Field(1_000_000, ge=1, description="QTL 合并窗口(bp)")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GwasQtlXEIn(BaseModel):
|
|||
|
|
"""QTL×E 入参（按环境分层 GWAS + 稳定性判定，计算端点不建表）。"""
|
|||
|
|
dataset_id: int = Field(..., description="基因型数据集 id（bre_genotyping_dataset）")
|
|||
|
|
trait_id: int = Field(..., description="性状 id（bre_trait）")
|
|||
|
|
trait_code: str = Field(..., description="性状编码")
|
|||
|
|
year: int | None = Field(None, description="评价年份过滤；为空则全部")
|
|||
|
|
method: str = Field("gwas", description="gwas（GLM+PC）/ emmax（混合模型 EMMAX）")
|
|||
|
|
maf_min: float = Field(0.05, ge=0.0, lt=0.5, description="MAF 过滤下限")
|
|||
|
|
n_pc: int = Field(3, ge=1, le=10, description="群体结构主成分数")
|
|||
|
|
sig_level: float = Field(0.05, gt=0.0, le=1.0, description="显著性水平")
|
|||
|
|
qtl_window: int = Field(1_000_000, ge=1, description="QTL 合并窗口(bp)")
|
|||
|
|
env_dim: str = Field("site", description="环境维度：site(trial_study_id) / year(evaluate_year)")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GwasResultOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
dataset_id: int | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
trait_code: str | None = None
|
|||
|
|
method: str | None = None
|
|||
|
|
n_individuals: int | None = None
|
|||
|
|
n_markers: int | None = None
|
|||
|
|
m_after_maf: int | None = None
|
|||
|
|
maf_min: float | None = None
|
|||
|
|
n_pc: int | None = None
|
|||
|
|
sig_level: float | None = None
|
|||
|
|
threshold_bonf: float | None = None
|
|||
|
|
n_sig_bonf: int | None = None
|
|||
|
|
n_sig_fdr: int | None = None
|
|||
|
|
n_qtl: int | None = None
|
|||
|
|
data_version: str | None = None
|
|||
|
|
input_hash: str | None = None
|
|||
|
|
engine_version: str | None = None
|
|||
|
|
remark: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class GwasSnpOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
gwas_result_id: int
|
|||
|
|
marker_id: int | None = None
|
|||
|
|
marker_name: str | None = None
|
|||
|
|
chromosome: str | None = None
|
|||
|
|
position: int | None = None
|
|||
|
|
maf: float | None = None
|
|||
|
|
effect: float | None = None
|
|||
|
|
se: float | None = None
|
|||
|
|
t_value: float | None = None
|
|||
|
|
p_value: float | None = None
|
|||
|
|
neg_log10p: float | None = None
|
|||
|
|
q_value: float | None = None
|
|||
|
|
sig_bonf: bool | None = None
|
|||
|
|
sig_fdr: bool | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class QtlIn(BaseModel):
|
|||
|
|
"""已知 QTL 录入（source=known）入参。"""
|
|||
|
|
trait_id: int | None = Field(None, description="性状 id（bre_trait）")
|
|||
|
|
chromosome: str | None = Field(None, description="染色体")
|
|||
|
|
start_bp: int | None = Field(None, description="区间起点(bp)")
|
|||
|
|
end_bp: int | None = Field(None, description="区间终点(bp)")
|
|||
|
|
peak_marker_id: int | None = Field(None, description="峰标记 id（bre_marker）")
|
|||
|
|
peak_p: float | None = Field(None, description="峰标记 p 值")
|
|||
|
|
n_markers: int | None = Field(None, description="区间显著标记数")
|
|||
|
|
effect: float | None = Field(None, description="峰效应")
|
|||
|
|
remark: str | None = Field(None, description="备注")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class QtlOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
chromosome: str | None = None
|
|||
|
|
start_bp: int | None = None
|
|||
|
|
end_bp: int | None = None
|
|||
|
|
peak_marker_id: int | None = None
|
|||
|
|
peak_marker_name: str | None = None
|
|||
|
|
peak_p: float | None = None
|
|||
|
|
n_markers: int | None = None
|
|||
|
|
effect: float | None = None
|
|||
|
|
source: str | None = None
|
|||
|
|
gwas_result_id: int | None = None
|
|||
|
|
remark: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MasPanelIn(BaseModel):
|
|||
|
|
"""MAS 标记辅助选择面板入参。"""
|
|||
|
|
panel_name: str = Field(..., description="面板名称")
|
|||
|
|
trait_id: int | None = Field(None, description="目标性状 id（bre_trait）")
|
|||
|
|
remark: str | None = Field(None, description="备注")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MasPanelOut(BaseModel):
|
|||
|
|
model_config = ConfigDict(from_attributes=True)
|
|||
|
|
id: int
|
|||
|
|
panel_name: str | None = None
|
|||
|
|
trait_id: int | None = None
|
|||
|
|
n_markers: int | None = None
|
|||
|
|
remark: str | None = None
|
|||
|
|
created_time: datetime | None = None
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MasPanelMarkerIn(BaseModel):
|
|||
|
|
"""面板标记（有利剂量 + 方向 + 基因作用模式）。"""
|
|||
|
|
marker_id: int | None = Field(None, description="标记 id（bre_marker）")
|
|||
|
|
favorable_dose: int | None = Field(None, description="有利剂量(0/1/2)")
|
|||
|
|
effect: float | None = Field(None, description="效应(参考)")
|
|||
|
|
direction: str | None = Field("high", description="high=剂量≥favorable_dose命中 / low=剂量≤命中")
|
|||
|
|
mode: str | None = Field("additive", description="基因作用模式：additive/dominance/recessive/allele/haplotype")
|
|||
|
|
favorable_allele: str | None = Field(None, description="有利等位(allele/haplotype 模式用，SSR 等位索引)")
|
|||
|
|
haplotype_group: str | None = Field(None, description="单倍型组(haplotype 模式：同组标记全命中才计 1)")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|
|||
|
|
|
|||
|
|
|
|||
|
|
class MasPanelSetMarkersIn(BaseModel):
|
|||
|
|
"""面板标记全量替换入参。"""
|
|||
|
|
markers: list[MasPanelMarkerIn] = Field(default_factory=list, description="面板标记列表")
|
|||
|
|
model_config = ConfigDict(extra="ignore")
|