class ClinicalData(db.Document):
'''
索引方式：project-->subproject-->patient，不可能同一个患者两次出现在同一个subproject
'''
age = db.FloatField(min_value=0.001, max_value=1200) # 单位: 月
age_began_smoking_in_years = db.IntField(min_value=1900, max_value=2999)
alcohol_history_documented = db.BooleanField() # 0: 无饮酒史，1: 有饮酒史
amount_of_alcohol_comsumption_per_day = db.FloatField(min_value=0.01,
max_value=100)
frequency_of_alcohol_consumption = db.IntField(min_value=1, max=7)
gender = db.BooleanField() # 0: 女性 1: 男性
height = db.FloatField(min_value=30, max_value=300)
lymph_node_examined_count = db.FloatField(min_value=0.1, max_value=100)
number_of_lymphnodes_position_by_he = db.FloatField(min_value=0.1,
max_value=100)
number_of_lymphnodes_position_by_ihc = db.FloatField(min_value=0.1,
max_value=100)
number_pack_years_smoked = db.FloatField(min_value=0.01, max_value=100)
OS = db.FloatField(min_value=0.01, max_value=1200)
OS_IND = db.BooleanField()
patient_id = db.StringField(max_length=50, required=True)
project_ref = db.ReferenceField(Project, required=True)
project_name = db.StringField(max_length=30, required=True)
subproject_name = db.StringField(max_length=30, required=True)
RFS = db.FloatField(min_value=0.01, max_value=1200)
RFS_IND = db.BooleanField()
stopped_smoking_year = db.IntField(min_value=1900, max_value=2999)
tobacco_smoking_history = db.BooleanField()
weight = db.FloatField(min_value=1, max_value=500)
class Project(db.Document):
'''
data_file_md5: 可能有多个原始数据文件需要导入，因此设置为List类别
src_project_id: 当前project的数据可能来源于多个原project，因此设置为List类别
src_project对应subproject，用于将多个project聚合成一个project的场景，每次聚合都意味着数据经过了某种处理
'''
analysis_pipeline_ref = db.ReferenceField(AnalysisProgram, required=True)
created_date = db.DateTimeField(required=True)
data_file_md5_lst = db.ListField(db.StringField(max_length=32,
required=True),
required=True)
data_file_name_lst = db.ListField(db.StringField(max_length=255,
required=True),
required=True)
data_type = db.StringField(max_length=10, required=True)
description = db.StringField(max_length=512)
import_data_program_ref = db.ReferenceField(AnalysisProgram, required=True)
normalized = db.BooleanField()
normalized_method = db.StringField(max_length=10, required=True)
num_of_samples = db.IntField(required=True)
project_name = db.StringField(max_length=30, required=True)
src_project_id_ref_lst = db.ListField(db.ReferenceField('Project',
required=True),
required=True)
src_project_name_lst = db.ListField(db.StringField(max_length=30,
required=True),
required=True)
url = db.StringField(max_length=100)
version = db.StringField(max_length=10, required=True)
class TranscriptExpr(db.Document):
'''
索引方式：project-->subproject-->transcript，通过subproject限定检索范围，一个subproject可以唯一确定一个transcript
'''
clinical_data_id_lst = db.ListField(db.ReferenceField('ClinicalData',
required=True),
required=True)
expr_value_lst = db.ListField(db.FloatField(), required=True)
phenotype_data_id_lst = db.ListField(db.ReferenceField('PhenotypeData',
required=True),
required=True)
project_name = db.StringField(max_length=30, required=True)
project_ref = db.ReferenceField(Project, required=True)
samples_data_id_lst = db.ListField(db.ReferenceField('SampleData',
required=True),
required=True)
source_type = db.StringField(max_length=50, required=True)
species = db.StringField(max_length=10, required=True)
subproject_name = db.StringField(max_length=30, required=True)
transcript_ensembl_id = db.StringField(max_length=50, required=True)
class GeneExpr(db.Document):
'''
索引方式：project-->subproject-->gene，通过subproject限定检索范围，一个subproject可以唯一确定一个gene
性能陷阱：sample_id和clinical_data_id等只可用于索引表达值，不可用于检索确定基因，否则将带来性能问题，换而言之，
基因或转录本的唯一确定是由project-subproject决定的，而非样本或患者
'''
clinical_data_id_lst = db.ListField(db.ReferenceField('ClinicalData',
required=True),
required=True)
expr_value_lst = db.ListField(db.FloatField(), required=True)
gene_ensembl_id = db.StringField(max_length=50, required=True)
project_ref = db.ReferenceField(Project, required=True)
project_name = db.StringField(max_length=30, required=True)
subproject_name = db.StringField(max_length=30, required=True)
samples_data_id_lst = db.ListField(db.ReferenceField('SampleData',
required=True),
required=True)
species = db.StringField(max_length=10, required=True)
source_type = db.StringField(max_length=50, required=True)
phenotype_data_id_lst = db.ListField(db.ReferenceField('PhenotypeData',
required=True),
required=True)
class AnalysisProgram(db.Document):
created_author = db.StringField(max_length=20, required=True)
created_date = db.DateTimeField(required=True)
description = db.StringField(max_length=500, required=False)
document_file = db.StringField(max_length=255, required=True)
md5 = db.StringField(max_length=32, required=True)
path = db.StringField(max_length=255, required=True)
program_name = db.StringField(max_length=100, required=True)
class SampleData(db.Document):
'''
索引方式：project-->subproject-->sample，不可能同一个样本两次出现在同一个subproject
'''
clinical_data_id_ref = db.ReferenceField(ClinicalData, required=True)
concentration = db.FloatField(min_value=0.001, max_value=1000)
ERCC = db.StringField(max_length=10)
FFPE = db.BooleanField()
histological_type = db.StringField(max_length=30, required=True)
od260_280 = db.FloatField(min_value=0.001, max_value=1000)
primary_site = db.StringField(max_length=30, required=True)
project_ref = db.ReferenceField(Project, required=True)
project_name = db.StringField(max_length=30, required=True)
subproject_name = db.StringField(max_length=30, required=True)
reads = db.FloatField(min_value=0.01, max_value=1000)
rin = db.FloatField(min_value=0.001, max_value=1000)
sample_id = db.StringField(max_length=50, required=True)
source = db.StringField(max_length=30, required=True)
species = db.StringField(max_length=10, required=True)
tissue_histological_subtype = db.StringField(max_length=30, required=False)
tissue_molecular_subtype = db.StringField(max_length=30, required=False)
volume = db.FloatField(min_value=0.001, max_value=1000)
weight = db.FloatField(min_value=0.001, max_value=1000)
yields = db.FloatField(min_value=0.01, max_value=1000)
class ExprInfo(db.Document):
'''
临时资源，用于多ID查询的场景
'''
clinical_data_id_lst = db.ListField(
db.ReferenceField('ClinicalData', required=True))
expr_value_lst = db.ListField(db.FloatField(), required=True)
transcript_ensembl_id_lst = db.ListField(
db.StringField(max_length=50, required=True))
gene_ensembl_id_lst = db.ListField(
db.StringField(max_length=50, required=True))
project_ref = db.ReferenceField(Project, required=True)
subproject_name_lst = db.ListField(
db.StringField(max_length=30, required=True))
project_name = db.StringField(max_length=30, required=True)
samples_data_id_lst = db.ListField(
db.ReferenceField('SampleData', required=True))
species_lst = db.ListField(db.StringField(max_length=10, required=True))
source_type_lst = db.ListField(db.StringField(max_length=50,
required=True),
required=True)
phenotype_data_id_lst = db.ListField(
db.ReferenceField('PhenotypeData', required=True))
query_condition_md5 = db.StringField(max_length=128, required=True)
class Mutation(db.Document):
chromosome = db.StringField(max_length=10, required=True)
clinical_data_id_lst = db.ListField(db.ReferenceField('ClinicalData',
required=True),
required=True)
dbsnp_rs = db.StringField(max_length=50, required=True)
end_position = db.StringField(max_length=50, required=True)
gene_ensembl_id = db.StringField(max_length=50, required=True)
transcript_ensembl_id = db.StringField(max_length=50, required=True)
phenotype_data_id_lst = db.ListField(db.ReferenceField('PhenotypeData',
required=True),
required=True)
project_name = db.StringField(max_length=30, required=True)
project_ref = db.ReferenceField(Project, required=True)
protein_change = db.StringField(max_length=50, required=True)
reference_allele = db.StringField(max_length=50, required=True)
samples_data_id_lst = db.ListField(db.ReferenceField('SampleData',
required=True),
required=True)
source_type = db.StringField(max_length=50, required=True)
species = db.StringField(max_length=10, required=True)
start_position = db.StringField(max_length=50, required=True)
subproject_name = db.StringField(max_length=30, required=True)
transcript_strand = db.StringField(max_length=50, required=True)
tumor_sample_barcode = db.StringField(max_length=50, required=True)
tumor_seq_allele1 = db.StringField(max_length=50, required=True)
tumor_seq_allele2 = db.StringField(max_length=50, required=True)
variant_classification = db.StringField(max_length=50, required=True)
variant_type = db.StringField(max_length=50, required=True)