读取pandas datafram中的序列化json

2024-10-02 00:22:16 发布

您现在位置:Python中文网/ 问答频道 /正文

我想从pandas数据框中的文件中读取双重序列化的json对象。 下面是json的示例

{"input":"8\t140630920\t.\tC\tT\t840.948\t.","assembly_name":"GRCh37","end":140630920,"seq_region_name":"8","transcript_consequences":[{"source":"Ensembl","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"ENST00000520439","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"RefSeq","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"NM_016601.2","cds_start":706,"gene_id":51305,"protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"RefSeq","variant_allele":"T","cdna_end":764,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":764,"transcript_id":"XM_005250954.1","cds_start":706,"gene_id":51305,"protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"source":"Ensembl","variant_allele":"T","cdna_end":755,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":755,"transcript_id":"ENST00000522317","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant","NMD_transcript_variant"],"impact":"MODERATE"},{"source":"Ensembl","variant_allele":"T","cdna_end":770,"phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"codons":"Ggg/Agg","protein_end":236,"strand":-1,"amino_acids":"G/R","cdna_start":770,"transcript_id":"ENST00000303015","cds_start":706,"gene_id":"ENSG00000169427","protein_start":236,"cds_end":706,"consequence_terms":["missense_variant"],"impact":"MODERATE"},{"gene_id":"ENSG00000169427","source":"Ensembl","distance":1672,"variant_allele":"T","phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"consequence_terms":["upstream_gene_variant"],"strand":-1,"transcript_id":"ENST00000523477","impact":"MODIFIER"},{"gene_id":"ENSG00000169427","source":"Ensembl","distance":2630,"variant_allele":"T","phenotypes":[{"source":"MIM_disease","end":140715299,"seq_region_name":"8","attrib_type":"Gene","external_id":612292,"strand":"-","phenotype":"BIRK-BAREL MENTAL RETARDATION DYSMORPHISM SYNDROME","type":"Gene","id":"ENSG00000169427","start":140613081},{"source":"OMIM","risk_allele":1,"end":140630920,"seq_region_name":"8","strand":"+","phenotype":"BIRK-BAREL SYNDROME","associated_gene":"KCNK9","variation_names":"rs121908332","type":"Variation","id":"rs121908332","start":140630920},{"source":"ClinVar","clinvar_clin_sig":"pathogenic","review_status":"no assertion criteria provided","risk_allele":"T","end":140630920,"seq_region_name":"8","external_id":"RCV000005007.1","associated_gene":"KCNK9","phenotype":"Birk Barel mental retardation dysmorphism syndrome","strand":"+","type":"Variation","id":"rs121908332","start":140630920}],"consequence_terms":["upstream_gene_variant"],"strand":-1,"transcript_id":"ENST00000519923","impact":"MODIFIER"}],"strand":1,"id":"8_140630920_C/T","allele_string":"C/T","most_severe_consequence":"missense_variant","start":140630920}

在pandas数据框中读到这个

^{pr2}$

结果如下表所示, Table generated by pandas read-json

但是,我想从['transcript_consequences']列提取信息,也从['transcript_consequences']列中的['phenotypes']提取信息。

如何在熊猫数据框中实现这一点?


Tags: nameidsourcetypestartseqregionend
1条回答
网友
1楼 · 发布于 2024-10-02 00:22:16

一个选项可以是:

>>> import pandas as pd
>>> jsona = pd.read_json('jsona.json') #here the file is named 'jsona.json'
>>> transcript_consequences = jsona['transcript_consequences'].apply(pd.Series)

这里我不确定这是否是有意的,但似乎transcript_consequences[0]与{}是相同的。在

您可以执行以下操作:

^{pr2}$

相关问题 更多 >

    热门问题