更新 | gnomAD人群频率库的下载与处理

当前有两个文件可用：

(GATK提供)

_(gnomAD官网)

将并行处理，最后比较。

CHROMPOSIDREFALTQUALFILTERINFO
=3;AF=7.384e-05
=6;AF=0.0001525
=48;AF=0.001223
CHROMPOSIDREFALTQUALFILTERINFO
=0;AC_afr=0;AC_afr_female=0;AC_afr_male=0;AC_amr=0;AC_amr_female=0;AC_amr_male=0;AC_asj=0;AC_asj_female=0;AC_asj_male=0;AC_eas=0;AC_eas_female=0;AC_eas_jpn=0;AC_eas_kor=0;AC_eas_male=0;AC_eas_oea=0;AC_female=0;AC_fin=0;AC_fin_female=0;AC_fin_male=0;AC_male=0;AC_nfe=0;AC_nfe_bgr=0;AC_nfe_est=0;AC_nfe_female=0;AC_nfe_male=0;AC_nfe_nwe=0;AC_nfe_onf=0;AC_nfe_seu=0;AC_nfe_swe=0;AC_oth=0;AC_oth_female=0;AC_oth_male=0;AC_raw=227;AC_sas=0;AC_sas_female=0;AC_sas_male=0;AF_raw=0.0457108;AN=0;AN_afr=0;AN_afr_female=0;AN_afr_male=0;AN_amr=0;AN_amr_female=0;AN_amr_male=0;AN_asj=0;AN_asj_female=0;AN_asj_male=0;AN_eas=0;AN_eas_female=0;AN_eas_jpn=0;AN_eas_kor=0;AN_eas_male=0;AN_eas_oea=0;AN_female=0;AN_fin=0;AN_fin_female=0;AN_fin_male=0;AN_male=0;AN_nfe=0;AN_nfe_bgr=0;AN_nfe_est=0;AN_nfe_female=0;AN_nfe_male=0;AN_nfe_nwe=0;AN_nfe_onf=0;AN_nfe_seu=0;AN_nfe_swe=0;AN_oth=0;AN_oth_female=0;AN_oth_male=0;AN_raw=4966;AN_sas=0;AN_sas_female=0;AN_sas_male=0;BaseQRankSum=0;ClippingRankSum=0.358;DP=9204;FS=0;InbreedingCoeff=0.0098;MQ=23.04;MQRankSum=0.736;OriginalContig=1;OriginalStart=12198;QD=13.95;ReadPosRankSum=0.736;SOR=0.302;VQSLOD=1.01;VQSR_culprit=MQ;ab_hist_alt_bin_freq=0|0|0|0|1|0|2|0|2|0|10|0|1|28|0|3|0|0|0|0;age_hist_het_bin_freq=0|0|0|0|0|0|0|0|0|0;age_hist_het_n_larger=0;age_hist_het_n_smaller=0;age_hist_hom_bin_freq=0|0|0|0|0|0|0|0|0|0;age_hist_hom_n_larger=0;age_hist_hom_n_smaller=0;allele_type=snv;controls_AC=0;controls_AC_afr=0;controls_AC_afr_female=0;controls_AC_afr_male=0;controls_AC_amr=0;controls_AC_amr_female=0;controls_AC_amr_male=0;controls_AC_asj=0;controls_AC_asj_female=0;controls_AC_asj_male=0;controls_AC_eas=0;controls_AC_eas_female=0;controls_AC_eas_jpn=0;controls_AC_eas_kor=0;controls_AC_eas_male=0;controls_AC_eas_oea=0;controls_AC_female=0;controls_AC_fin=0;controls_AC_fin_female=0;controls_AC_fin_male=0;controls_AC_male=0;controls_AC_nfe=0;controls_AC_nfe_bgr=0;controls_AC_nfe_est=0;controls_AC_nfe_female=0;controls_AC_nfe_male=0;controls_AC_nfe_nwe=0;controls_AC_nfe_onf=0;controls_AC_nfe_seu=0;controls_AC_nfe_swe=0;controls_AC_oth=0;controls_AC_oth_female=0;controls_AC_oth_male=0;controls_AC_raw=109;controls_AC_sas=0;controls_AC_sas_female=0;controls_AC_sas_male=0;controls_AF_raw=0.046661;controls_AN=0;controls_AN_afr=0;controls_AN_afr_female=0;controls_AN_afr_male=0;controls_AN_amr=0;controls_AN_amr_female=0;controls_AN_amr_male=0;controls_AN_asj=0;controls_AN_asj_female=0;controls_AN_asj_male=0;controls_AN_eas=0;controls_AN_eas_female=0;controls_AN_eas_jpn=0;controls_AN_eas_kor=0;controls_AN_eas_male=0;controls_AN_eas_oea=0;controls_AN_female=0;controls_AN_fin=0;controls_AN_fin_female=0;controls_AN_fin_male=0;controls_AN_male=0;controls_AN_nfe=0;controls_AN_nfe_bgr=0;controls_AN_nfe_est=0;controls_AN_nfe_female=0;controls_AN_nfe_male=0;controls_AN_nfe_nwe=0;controls_AN_nfe_onf=0;controls_AN_nfe_seu=0;controls_AN_nfe_swe=0;controls_AN_oth=0;controls_AN_oth_female=0;controls_AN_oth_male=0;controls_AN_raw=2336;controls_AN_sas=0;controls_AN_sas_female=0;controls_AN_sas_male=0;controls_faf95=0;controls_faf95_afr=0;controls_faf95_amr=0;controls_faf95_eas=0;controls_faf95_nfe=0;controls_faf95_sas=0;controls_faf99=0;controls_faf99_afr=0;controls_faf99_amr=0;controls_faf99_eas=0;controls_faf99_nfe=0;controls_faf99_sas=0;controls_nhomalt=0;controls_nhomalt_afr=0;controls_nhomalt_afr_female=0;controls_nhomalt_afr_male=0;controls_nhomalt_amr=0;controls_nhomalt_amr_female=0;controls_nhomalt_amr_male=0;controls_nhomalt_asj=0;controls_nhomalt_asj_female=0;controls_nhomalt_asj_male=0;controls_nhomalt_eas=0;controls_nhomalt_eas_female=0;controls_nhomalt_eas_jpn=0;controls_nhomalt_eas_kor=0;controls_nhomalt_eas_male=0;controls_nhomalt_eas_oea=0;controls_nhomalt_female=0;controls_nhomalt_fin=0;controls_nhomalt_fin_female=0;controls_nhomalt_fin_male=0;controls_nhomalt_male=0;controls_nhomalt_nfe=0;controls_nhomalt_nfe_bgr=0;controls_nhomalt_nfe_est=0;controls_nhomalt_nfe_female=0;controls_nhomalt_nfe_male=0;controls_nhomalt_nfe_nwe=0;controls_nhomalt_nfe_onf=0;controls_nhomalt_nfe_seu=0;controls_nhomalt_nfe_swe=0;controls_nhomalt_oth=0;controls_nhomalt_oth_female=0;controls_nhomalt_oth_male=0;controls_nhomalt_raw=44;controls_nhomalt_sas=0;controls_nhomalt_sas_female=0;controls_nhomalt_sas_male=0;dp_hist_all_bin_freq=125724|24|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0;dp_hist_all_n_larger=0;dp_hist_alt_bin_freq=130|7|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0|0;dp_hist_alt_n_larger=0;faf95=0;faf95_afr=0;faf95_amr=0;faf95_eas=0;faf95_nfe=0;faf95_sas=0;faf99=0;faf99_afr=0;faf99_amr=0;faf99_eas=0;faf99_nfe=0;faf99_sas=0;gq_hist_all_bin_freq=1898|511|26|28|8|4|0|5|2|0|0|0|1|0|0|0|0|0|0|0;gq_hist_alt_bin_freq=14|78|1|25|7|4|0|5|2|0|0|0|1|0|0|0|0|0|0|0;n_alt_alleles=1;nhomalt=0;nhomalt_afr=0;nhomalt_afr_female=0;nhomalt_afr_male=0;nhomalt_amr=0;nhomalt_amr_female=0;nhomalt_amr_male=0;nhomalt_asj=0;nhomalt_asj_female=0;nhomalt_asj_male=0;nhomalt_eas=0;nhomalt_eas_female=0;nhomalt_eas_jpn=0;nhomalt_eas_kor=0;nhomalt_eas_male=0;nhomalt_eas_oea=0;nhomalt_female=0;nhomalt_fin=0;nhomalt_fin_female=0;nhomalt_fin_male=0;nhomalt_male=0;nhomalt_nfe=0;nhomalt_nfe_bgr=0;nhomalt_nfe_est=0;nhomalt_nfe_female=0;nhomalt_nfe_male=0;nhomalt_nfe_nwe=0;nhomalt_nfe_onf=0;nhomalt_nfe_seu=0;nhomalt_nfe_swe=0;nhomalt_oth=0;nhomalt_oth_female=0;nhomalt_oth_male=0;nhomalt_raw=90;nhomalt_sas=0;nhomalt_sas_female=0;nhomalt_sas_male=0;non_cancer_AC=0;non_cancer_AC_afr=0;non_cancer_AC_afr_female=0;non_cancer_AC_afr_male=0;non_cancer_AC_amr=0;non_cancer_AC_amr_female=0;non_cancer_AC_amr_male=0;non_cancer_AC_asj=0;non_cancer_AC_asj_female=0;non_cancer_AC_asj_male=0;non_cancer_AC_eas=0;non_cancer_AC_eas_female=0;non_cancer_AC_eas_jpn=0;non_cancer_AC_eas_kor=0;non_cancer_AC_eas_male=0;non_cancer_AC_eas_oea=0;non_cancer_AC_female=0;non_cancer_AC_fin=0;non_cancer_AC_fin_female=0;non_cancer_AC_fin_male=0;non_cancer_AC_male=0;non_cancer_AC_nfe=0;non_cancer_AC_nfe_bgr=0;non_cancer_AC_nfe_est=0;non_cancer_AC_nfe_female=0;non_cancer_AC_nfe_male=0;non_cancer_AC_nfe_nwe=0;non_cancer_AC_nfe_onf=0;non_cancer_AC_nfe_seu=0;non_cancer_AC_nfe_swe=0;non_cancer_AC_oth=0;non_cancer_AC_oth_female=0;non_cancer_AC_oth_male=0;non_cancer_AC_raw=227;non_cancer_AC_sas=0;non_cancer_AC_sas_female=0;non_cancer_AC_sas_male=0;non_cancer_AF_raw=0.0457293;non_cancer_AN=0;non_cancer_AN_afr=0;non_cancer_AN_afr_female=0;non_cancer_AN_afr_male=0;non_cancer_AN_amr=0;non_cancer_AN_amr_female=0;non_cancer_AN_amr_male=0;non_cancer_AN_asj=0;non_cancer_AN_asj_female=0;non_cancer_AN_asj_male=0;non_cancer_AN_eas=0;non_cancer_AN_eas_female=0;non_cancer_AN_eas_jpn=0;non_cancer_AN_eas_kor=0;non_cancer_AN_eas_male=0;non_cancer_AN_eas_oea=0;non_cancer_AN_female=0;non_cancer_AN_fin=0;non_cancer_AN_fin_female=0;non_cancer_AN_fin_male=0;non_cancer_AN_male=0;non_cancer_AN_nfe=0;non_cancer_AN_nfe_bgr=0;non_cancer_AN_nfe_est=0;non_cancer_AN_nfe_female=0;non_cancer_AN_nfe_male=0;non_cancer_AN_nfe_nwe=0;non_cancer_AN_nfe_onf=0;non_cancer_AN_nfe_seu=0;non_cancer_AN_nfe_swe=0;non_cancer_AN_oth=0;non_cancer_AN_oth_female=0;non_cancer_AN_oth_male=0;non_cancer_AN_raw=4964;non_cancer_AN_sas=0;non_cancer_AN_sas_female=0;non_cancer_AN_sas_male=0;non_cancer_faf95=0;non_cancer_faf95_afr=0;non_cancer_faf95_amr=0;non_cancer_faf95_eas=0;non_cancer_faf95_nfe=0;non_cancer_faf95_sas=0;non_cancer_faf99=0;non_cancer_faf99_afr=0;non_cancer_faf99_amr=0;non_cancer_faf99_eas=0;non_cancer_faf99_nfe=0;non_cancer_faf99_sas=0;non_cancer_nhomalt=0;non_cancer_nhomalt_afr=0;non_cancer_nhomalt_afr_female=0;non_cancer_nhomalt_afr_male=0;non_cancer_nhomalt_amr=0;non_cancer_nhomalt_amr_female=0;non_cancer_nhomalt_amr_male=0;non_cancer_nhomalt_asj=0;non_cancer_nhomalt_asj_female=0;non_cancer_nhomalt_asj_male=0;non_cancer_nhomalt_eas=0;non_cancer_nhomalt_eas_female=0;non_cancer_nhomalt_eas_jpn=0;non_cancer_nhomalt_eas_kor=0;non_cancer_nhomalt_eas_male=0;non_cancer_nhomalt_eas_oea=0;non_cancer_nhomalt_female=0;non_cancer_nhomalt_fin=0;non_cancer_nhomalt_fin_female=0;non_cancer_nhomalt_fin_male=0;non_cancer_nhomalt_male=0;non_cancer_nhomalt_nfe=0;non_cancer_nhomalt_nfe_bgr=0;non_cancer_nhomalt_nfe_est=0;non_cancer_nhomalt_nfe_female=0;non_cancer_nhomalt_nfe_male=0;non_cancer_nhomalt_nfe_nwe=0;non_cancer_nhomalt_nfe_onf=0;non_cancer_nhomalt_nfe_seu=0;non_cancer_nhomalt_nfe_swe=0;non_cancer_nhomalt_oth=0;non_cancer_nhomalt_oth_female=0;non_cancer_nhomalt_oth_male=0;non_cancer_nhomalt_raw=90;non_cancer_nhomalt_sas=0;non_cancer_nhomalt_sas_female=0;non_cancer_nhomalt_sas_male=0;non_neuro_AC=0;non_neuro_AC_afr=0;non_neuro_AC_afr_female=0;non_neuro_AC_afr_male=0;non_neuro_AC_amr=0;non_neuro_AC_amr_female=0;non_neuro_AC_amr_male=0;non_neuro_AC_asj=0;non_neuro_AC_asj_female=0;non_neuro_AC_asj_male=0;non_neuro_AC_eas=0;non_neuro_AC_eas_female=0;non_neuro_AC_eas_jpn=0;non_neuro_AC_eas_kor=0;non_neuro_AC_eas_male=0;non_neuro_AC_eas_oea=0;non_neuro_AC_female=0;non_neuro_AC_fin=0;non_neuro_AC_fin_female=0;non_neuro_AC_fin_male=0;non_neuro_AC_male=0;non_neuro_AC_nfe=0;non_neuro_AC_nfe_bgr=0;non_neuro_AC_nfe_est=0;non_neuro_AC_nfe_female=0;non_neuro_AC_nfe_male=0;non_neuro_AC_nfe_nwe=0;non_neuro_AC_nfe_onf=0;non_neuro_AC_nfe_seu=0;non_neuro_AC_nfe_swe=0;non_neuro_AC_oth=0;non_neuro_AC_oth_female=0;non_neuro_AC_oth_male=0;non_neuro_AC_raw=225;non_neuro_AC_sas=0;non_neuro_AC_sas_female=0;non_neuro_AC_sas_male=0;non_neuro_AF_raw=0.0470908;non_neuro_AN=0;non_neuro_AN_afr=0;non_neuro_AN_afr_female=0;non_neuro_AN_afr_male=0;non_neuro_AN_amr=0;non_neuro_AN_amr_female=0;non_neuro_AN_amr_male=0;non_neuro_AN_asj=0;non_neuro_AN_asj_female=0;non_neuro_AN_asj_male=0;non_neuro_AN_eas=0;non_neuro_AN_eas_female=0;non_neuro_AN_eas_jpn=0;non_neuro_AN_eas_kor=0;non_neuro_AN_eas_male=0;non_neuro_AN_eas_oea=0;non_neuro_AN_female=0;non_neuro_AN_fin=0;non_neuro_AN_fin_female=0;non_neuro_AN_fin_male=0;non_neuro_AN_male=0;non_neuro_AN_nfe=0;non_neuro_AN_nfe_bgr=0;non_neuro_AN_nfe_est=0;non_neuro_AN_nfe_female=0;non_neuro_AN_nfe_male=0;non_neuro_AN_nfe_nwe=0;non_neuro_AN_nfe_onf=0;non_neuro_AN_nfe_seu=0;non_neuro_AN_nfe_swe=0;non_neuro_AN_oth=0;non_neuro_AN_oth_female=0;non_neuro_AN_oth_male=0;non_neuro_AN_raw=4778;non_neuro_AN_sas=0;non_neuro_AN_sas_female=0;non_neuro_AN_sas_male=0;non_neuro_faf95=0;non_neuro_faf95_afr=0;non_neuro_faf95_amr=0;non_neuro_faf95_eas=0;non_neuro_faf95_nfe=0;non_neuro_faf95_sas=0;non_neuro_faf99=0;non_neuro_faf99_afr=0;non_neuro_faf99_amr=0;non_neuro_faf99_eas=0;non_neuro_faf99_nfe=0;non_neuro_faf99_sas=0;non_neuro_nhomalt=0;non_neuro_nhomalt_afr=0;non_neuro_nhomalt_afr_female=0;non_neuro_nhomalt_afr_male=0;non_neuro_nhomalt_amr=0;non_neuro_nhomalt_amr_female=0;non_neuro_nhomalt_amr_male=0;non_neuro_nhomalt_asj=0;non_neuro_nhomalt_asj_female=0;non_neuro_nhomalt_asj_male=0;non_neuro_nhomalt_eas=0;non_neuro_nhomalt_eas_female=0;non_neuro_nhomalt_eas_jpn=0;non_neuro_nhomalt_eas_kor=0;non_neuro_nhomalt_eas_male=0;non_neuro_nhomalt_eas_oea=0;non_neuro_nhomalt_female=0;non_neuro_nhomalt_fin=0;non_neuro_nhomalt_fin_female=0;non_neuro_nhomalt_fin_male=0;non_neuro_nhomalt_male=0;non_neuro_nhomalt_nfe=0;non_neuro_nhomalt_nfe_bgr=0;non_neuro_nhomalt_nfe_est=0;non_neuro_nhomalt_nfe_female=0;non_neuro_nhomalt_nfe_male=0;non_neuro_nhomalt_nfe_nwe=0;non_neuro_nhomalt_nfe_onf=0;non_neuro_nhomalt_nfe_seu=0;non_neuro_nhomalt_nfe_swe=0;non_neuro_nhomalt_oth=0;non_neuro_nhomalt_oth_female=0;non_neuro_nhomalt_oth_male=0;non_neuro_nhomalt_raw=89;non_neuro_nhomalt_sas=0;non_neuro_nhomalt_sas_female=0;non_neuro_nhomalt_sas_male=0;non_topmed_AC=0;non_topmed_AC_afr=0;non_topmed_AC_afr_female=0;non_topmed_AC_afr_male=0;non_topmed_AC_amr=0;non_topmed_AC_amr_female=0;non_topmed_AC_amr_male=0;non_topmed_AC_asj=0;non_topmed_AC_asj_female=0;non_topmed_AC_asj_male=0;non_topmed_AC_eas=0;non_topmed_AC_eas_female=0;non_topmed_AC_eas_jpn=0;non_topmed_AC_eas_kor=0;non_topmed_AC_eas_male=0;non_topmed_AC_eas_oea=0;non_topmed_AC_female=0;non_topmed_AC_fin=0;non_topmed_AC_fin_female=0;non_topmed_AC_fin_male=0;non_topmed_AC_male=0;non_topmed_AC_nfe=0;non_topmed_AC_nfe_bgr=0;non_topmed_AC_nfe_est=0;non_topmed_AC_nfe_female=0;non_topmed_AC_nfe_male=0;non_topmed_AC_nfe_nwe=0;non_topmed_AC_nfe_onf=0;non_topmed_AC_nfe_seu=0;non_topmed_AC_nfe_swe=0;non_topmed_AC_oth=0;non_topmed_AC_oth_female=0;non_topmed_AC_oth_male=0;non_topmed_AC_raw=218;non_topmed_AC_sas=0;non_topmed_AC_sas_female=0;non_topmed_AC_sas_male=0;non_topmed_AF_raw=0.0459334;non_topmed_AN=0;non_topmed_AN_afr=0;non_topmed_AN_afr_female=0;non_topmed_AN_afr_male=0;non_topmed_AN_amr=0;non_topmed_AN_amr_female=0;non_topmed_AN_amr_male=0;non_topmed_AN_asj=0;non_topmed_AN_asj_female=0;non_topmed_AN_asj_male=0;non_topmed_AN_eas=0;non_topmed_AN_eas_female=0;non_topmed_AN_eas_jpn=0;non_topmed_AN_eas_kor=0;non_topmed_AN_eas_male=0;non_topmed_AN_eas_oea=0;non_topmed_AN_female=0;non_topmed_AN_fin=0;non_topmed_AN_fin_female=0;non_topmed_AN_fin_male=0;non_topmed_AN_male=0;non_topmed_AN_nfe=0;non_topmed_AN_nfe_bgr=0;non_topmed_AN_nfe_est=0;non_topmed_AN_nfe_female=0;non_topmed_AN_nfe_male=0;non_topmed_AN_nfe_nwe=0;non_topmed_AN_nfe_onf=0;non_topmed_AN_nfe_seu=0;non_topmed_AN_nfe_swe=0;non_topmed_AN_oth=0;non_topmed_AN_oth_female=0;non_topmed_AN_oth_male=0;non_topmed_AN_raw=4746;non_topmed_AN_sas=0;non_topmed_AN_sas_female=0;non_topmed_AN_sas_male=0;non_topmed_faf95=0;non_topmed_faf95_afr=0;non_topmed_faf95_amr=0;non_topmed_faf95_eas=0;non_topmed_faf95_nfe=0;non_topmed_faf95_sas=0;non_topmed_faf99=0;non_topmed_faf99_afr=0;non_topmed_faf99_amr=0;non_topmed_faf99_eas=0;non_topmed_faf99_nfe=0;non_topmed_faf99_sas=0;non_topmed_nhomalt=0;non_topmed_nhomalt_afr=0;non_topmed_nhomalt_afr_female=0;non_topmed_nhomalt_afr_male=0;non_topmed_nhomalt_amr=0;non_topmed_nhomalt_amr_female=0;non_topmed_nhomalt_amr_male=0;non_topmed_nhomalt_asj=0;non_topmed_nhomalt_asj_female=0;non_topmed_nhomalt_asj_male=0;non_topmed_nhomalt_eas=0;non_topmed_nhomalt_eas_female=0;non_topmed_nhomalt_eas_jpn=0;non_topmed_nhomalt_eas_kor=0;non_topmed_nhomalt_eas_male=0;non_topmed_nhomalt_eas_oea=0;non_topmed_nhomalt_female=0;non_topmed_nhomalt_fin=0;non_topmed_nhomalt_fin_female=0;non_topmed_nhomalt_fin_male=0;non_topmed_nhomalt_male=0;non_topmed_nhomalt_nfe=0;non_topmed_nhomalt_nfe_bgr=0;non_topmed_nhomalt_nfe_est=0;non_topmed_nhomalt_nfe_female=0;non_topmed_nhomalt_nfe_male=0;non_topmed_nhomalt_nfe_nwe=0;non_topmed_nhomalt_nfe_onf=0;non_topmed_nhomalt_nfe_seu=0;non_topmed_nhomalt_nfe_swe=0;non_topmed_nhomalt_oth=0;non_topmed_nhomalt_oth_female=0;non_topmed_nhomalt_oth_male=0;non_topmed_nhomalt_raw=87;non_topmed_nhomalt_sas=0;non_topmed_nhomalt_sas_female=0;non_topmed_nhomalt_sas_male=0;pab_max=1;rf_label=FP;rf_negative_label;rf_tp_probability=0.836542;rf_train;segdup;variant_type=snv;vep=C|downstream_gene_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000423562|unprocessed_pseudogene||||||||||rs62635282|1|2165|-1||SNV|1|HGNC|38034||||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000438504|unprocessed_pseudogene||||||||||rs62635282|1|2165|-1||SNV|1|HGNC|38034|YES|||||||||||||||||||||||||||||||||||||||||,C|non_coding_transcript_exon_variantnon_coding_transcript_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000450305|transcribed_unprocessed_pseudogene|2/6||:||68|||||rs62635282|1||1||SNV|1|HGNC|37102||||||||||||||||||||||||||||||||||||||||||,C|non_coding_transcript_exon_variantnon_coding_transcript_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000456328|processed_transcript|1/3||:||330|||||rs62635282|1||1||SNV|1|HGNC|37102|YES|||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000488147|unprocessed_pseudogene||||||||||rs62635282|1|2206|-1||SNV|1|HGNC|38034||||||||||||||||||||||||||||||||||||||||||,C|non_coding_transcript_exon_variantnon_coding_transcript_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000515242|transcribed_unprocessed_pseudogene|1/3||:||327|||||rs62635282|1||1||SNV|1|HGNC|37102||||||||||||||||||||||||||||||||||||||||||,C|non_coding_transcript_exon_variantnon_coding_transcript_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000518655|transcribed_unprocessed_pseudogene|1/4||:||325|||||rs62635282|1||1||SNV|1|HGNC|37102||||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000538476|unprocessed_pseudogene||||||||||rs62635282|1|2213|-1||SNV|1|HGNC|38034||||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000541675|unprocessed_pseudogene||||||||||rs62635282|1|2165|-1||SNV|1|HGNC|38034||||||||||||||||||||||||||||||||||||||||||,C|regulatory_region_variant|MODIFIER|||RegulatoryFeature|ENSR00001576075|CTCF_binding_site||||||||||rs62635282|1||||SNV|1||||||||||||||||||||||||||||||||||||||||||||
bcftoolsannotate-x^INFO/AC,^INFO/AN,^INFO/AF,^INFO/AF_raw,^INFO/AF__|\grep-v"^"|head-n20
CHROMPOSIDREFALTQUALFILTERINFO
=0;AF_raw=0.0457108;AN=0
=0;AF_raw=0.000440995;AN=0
=0;AF=0;AF_raw=0.000155788;AN=2
=0;AF_raw=0.00434708;AN=0
=0;AF=0;AF_raw=0.00430126;AN=2
;RFAC=0;AF=0;AF_raw=0.000294357;AN=3038
=14;AF=0.00472654;AF_raw=0.00287838;AN=2962
=2;AF=0.000476644;AF_raw=0.000172585;AN=4196
=2;AF=0.000558971;AF_raw=6.50675e-05;AN=3578
=0;AF=0;AF_raw=2.17855e-05;AN=2952
=8;AF=0.00275103;AF_raw=0.0010003;AN=2908
=0;AF=0;AF_raw=2.18036e-05;AN=2830
;RFAC=0;AF=0;AF_raw=4.02609e-05;AN=5600
=1;AF=0.000174825;AF_raw=5.98205e-05;AN=5720
=7;AF=0.00106093;AF_raw=0.001232;AN=6598
=20;AF=0.00291971;AF_raw=0.00295915;AN=6850
=13;AF=0.00200803;AF_raw=0.00194156;AN=6474
=10;AF=0.0014339;AF_raw=0.0019007;AN=6974
=6;AF=0.000839396;AF_raw=0.000667608;AN=7148
bcftoolsannotate-x^INFO/AC,^INFO/AN,^INFO/_|grep-v"^"|head-n20|sed's/\t//g'
查看结果：_
chr113417rs777038595CCGGGA0
数据库文件对多等位基因位点似乎已经拆分完毕：
bcftoolsannotate-x^INFO/_|head-n5000|grep-wrs777038595
+07PASSAF=1.49898e-05
+07PASSAF=0.112528
+07AC0AF=0
+07PASSAF=1.49898e-05
(含多等位基因位点)
bcftoolsannotate-x^INFO/|bcftoolsnorm-f/db/gatk/hg38/Homo_sapiens_|grep-v"^"|cut-f1,2,3,4,5,8|sed's/AF=//g'
上图dbSNP的"GnomAD_exome"的值来自：
_grch38
比较：行数
17,201,297
_
290,331,359
82,985,813a1000G//chr/
比较：标准化历程
Linestotal/split/realigned/skipped:17201296/0/6/0
Linestotal/split/realigned/skipped:268225276/15895112/9642331/0
比较：内容
，带"chr"，含补丁染色体
|\grep-P'chr1\t10140\t'
多等位基因位点拆分前：
CCCTAACA,GCCCTAAC6752.26PASSAC=25,4;AF=0.0006338,0.0001014
对于
AN,Totalnumberofallelesinsamples(AN=0：测序没有测到，或质控后均无基因型)
AC,Alternateallelecountforsamples
不含AC=0|\head-n20000000|grep'AC=0'查看_

chr112198GClowAN

chr112237GAlowAN

chr112259GClowAN

chr112266GAlowAN

chr112272GAlowAN

chr130524GAlowAN

chr130528CTlowAN

__|grep-v""|head-n100000|_|grep-v""|head-n100000|sed's/AF_raw=/\t/g'|cut-f9|sed's/;/\t/g'|_|grep-v""|head-n100000|sed's/AF=/\t/g'|cut-f9|sed's/;/\t/g'|_|grep-v""|head|grep-w10109|grep"AC=\|AF=\|AF_raw=\|AC_raw="

查看几个有rsID的ClinVar位点，比较AF值

cut-f10,13variant_summary_|\nl|grep-v-P'\-1'|grep-wPathogenic|head

可见，仍有很多致病位点在已发表的大量AF数据库中没有人群频率。因此，筛选致病位点时：1.可以对AF使用排除法(排除有AF、且AF值较大的位点)；2.无条件纳入ClinVar/OMIM等已报告的致病位点；3.当CADDScore极高时也可纳入(如50，即使无AF值)。

awk'BEGIN{OFS=FS="\t"}{if($21000000)print$0}'_|awk'BEGIN{OFS=FS="\t"}{if($21000000)print$0}'*test*tail*test*

比较差异的位点数量

71,842

66,454

全基因组chr1:1-1,000,000中，含有AF值的总变异数目约7万(~7%)，前者多出5,388。

各自特有的位点：

awk'BEGIN{OFS=FS="\t"}ARGIND==1{var["_"$1"_"$2"_"$4"_"$5"_"]=1}ARGIND==2{if(var["_"$1"_"$2"_"$4"_"$5"_"]=="")print$0}'\|wc-l

5,594

awk'BEGIN{OFS=FS="\t"}ARGIND==1{var["_"$1"_"$2"_"$4"_"$5"_"]=1}ARGIND==2{if(var["_"$1"_"$2"_"$4"_"$5"_"]=="")print$0}'\|wc-l

190

可使用af-only-gnomad的全基因组AF，使用的全外显子组AF。

最终待合并与使用的文件名

_

共3.1亿个短变异的人群频率