So I’m pretty sure that what’s happening here is that your json schema isn’t consistent with what the plugin is doing. Admittedly, it’s not really easy to add new VEP plugins in our current config file model. I am pasting a few lines of the log below:
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field flags at <root>.transcript_consequences[element] for value JArray(List(JString(cds_start_NF)))
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field mutationassessor_pred at <root>.transcript_consequences[element] for value JString(M)
2020-06-09 16:47:18 root: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field mutationassessor_pred at <root>.transcript_consequences[element] for value JString(M)
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field lrt_pred at <root>.transcript_consequences[element] for value JString(U)
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field mutationassessor_score at <root>.transcript_consequences[element] for value JDouble(2.215)
2020-06-09 16:47:18 root: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field mutationassessor_score at <root>.transcript_consequences[element] for value JDouble(2.215)
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field polyphen2_hdiv_pred at <root>.transcript_consequences[element] for value JString(D)
2020-06-09 16:47:18 root: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field polyphen2_hdiv_pred at <root>.transcript_consequences[element] for value JString(D)
2020-06-09 16:47:18 Hail: WARN: struct{allele_num: int32, amino_acids: str, biotype: str, canonical: int32, ccds: str, cdna_start: int32, cdna_end: int32, cds_end: int32, cds_start: int32, codons: str, consequence_terms: array<str>, distance: int32, domains: array<struct{db: str, name: str}>, exon: str, gene_id: str, gene_pheno: int32, symbol: str, symbol_source: str, hgnc_id: str, hgvsc: str, hgvsp: str, hgvs_offset: int32, impact: str, intron: str, lof: str, lof_flags: str, lof_filter: str, lof_info: str, minimised: int32, polyphen_prediction: str, polyphen_score: float64, protein_end: int32, protein_start: int32, protein_id: str, sift_prediction: str, sift_score: float64, strand: int32, swissprot: str, transcript_id: str, trembl: str, uniparc: str, variant_allele: str, SIFT_score: float64, SIFT_pred: str, Polyphen2_HDIV_score: float64, Polyphen2_HDIV_pred: str, Polyphen2_HVAR_score: float64, Polyphen2_HVAR_pred: str, LRT_score: float64, LRT_pred: str, MutationTaster_score: float64, MutationTaster_pred: str, MutationAssessor_score: float64, MutationAssessor_pred: str, PROVEAN_score: float64, PROVEAN_pred: str} has no field mutationtaster_score at <root>.transcript_consequences[element] for value JDouble(0.999949)
if you look at the end of the lines, it’s complaining that, for example, the json schema has no field called polyphen2_hvar_pred
. That’s because you called it " Polyphen2_HVAR_pred
. I think if you keep changing names in your schema to squash these warnings in the logs, that’ll fix your problem.