{ "app": "Ascorbate Deficiency Long-Read Analyzer", "version": "0.1.7-hardening", "job_id": "adla_20260707_070526_d0551175", "created_at": "2026-07-07T07:05:26+00:00", "reference_build": "GRCh38", "disclaimer": "Anthropological and educational research use only. ADLA does not diagnose scurvy or vitamin C deficiency; interpret genomic, epigenomic, structural-variant, phasing, workflow-import, microbial/context, and ancient-DNA authentication signals alongside archaeological context, preservation quality, osteological/isotopic evidence, historical diet, contamination controls, damage/authenticity metrics, and biochemical data where available.", "input_files": [ { "original_name": "reich_lab_style_demo.auth.json", "stored_name": "reich_lab_style_demo.auth.json", "stored_path": "/home/u649646827/domains/stellanovaeducation.com/public_html/rc/adla/inc/../uploads/adla_20260707_070526_d0551175/reich_lab_style_demo.auth.json", "size_bytes": 1164, "sha256": "26bf624b4a00382d7bed80c83dae34d8f8c8bfcd978c52e75ca204600a6e889f", "extension": "auth.json", "kind": "authentication" } ], "sample_context": { "reference_build": "GRCh38", "sample_age_class": "unknown", "sample_material": "unknown", "sample_type": "", "preservation_context": "", "archaeological_context": "", "osteological_evidence": "", "isotopic_evidence": "", "dietary_evidence": "", "historical_dietary_context": "", "environmental_context": "", "contamination_controls": "", "damage_authenticity_review": "", "intergenerational_question": "", "notes": "", "ascorbate_lab_value": "" }, "qc": [], "variants": { "known_ascorbate_hits": [], "target_region_hits": [], "unclassified_target_hits": [], "summary": [] }, "methylation": { "target_region_summaries": [], "global_summary": [] }, "coverage": { "target_region_depths": [], "summary": [] }, "annotation": { "summaries": [], "clinvar_target_hits": [], "high_impact_target_hits": [], "vep_consequence_counts": [], "clinvar_significance_counts": [] }, "priority": { "variant_priorities": [], "summary": { "prioritized_variant_count": 0, "top_score": 0, "top_priority_bucket": "none", "bucket_counts": [], "callability_counts": { "callable": 0, "low_coverage": 0, "unknown": 0 }, "ruleset_version": "0.1.7-hardening", "boundary": "Anthropological research prioritization only. Scores rank sequencing and authentication findings for review in ancient, historical, modern-intergenerational, or ecological context; they do not diagnose vitamin C deficiency, scurvy, connective-tissue disease, or any medical condition." }, "scoring_policy": { "ruleset_name": "ADLA variant prioritization rules", "ruleset_version": "0.1.7-hardening", "score_range": [ 0, 100 ], "evidence_classes": [ "known_ascorbate_transport_literature", "target_pathway_location", "VEP_consequence_and_impact", "ClinVar_assertion_and_review_status", "dbSNP_rsID_normalization", "sample_variant_support", "target_callability", "anthropological_context", "ancient_or_historical_sample_readiness", "ancient_DNA_authentication_report_import", "damage_deamination_or_PMD_metric", "contamination_estimate_import" ], "priority_buckets": [ { "min_score": 75, "label": "very_high_review_priority", "description": "Strong local evidence stack. Review first, confirm coverage/source dates, and interpret only with clinical/biochemical context." }, { "min_score": 55, "label": "high_review_priority", "description": "Multiple supportive evidence classes or one strong annotation class." }, { "min_score": 35, "label": "moderate_review_priority", "description": "Useful research hit requiring annotation/source review." }, { "min_score": 15, "label": "contextual_review", "description": "Contextual pathway or modifier signal; not enough for strong prioritization." }, { "min_score": 0, "label": "low_priority_or_uncurated", "description": "Weak, missing, or uncurated evidence." } ], "boundary": "Anthropological research prioritization only. Scores rank sequencing and authentication findings for review in ancient, historical, modern-intergenerational, or ecological context; they do not diagnose vitamin C deficiency, scurvy, connective-tissue disease, or any medical condition." } }, "anthropological_context": { "summary": { "sample_age_class": "unknown", "sample_material": "unknown", "preservation_context": "", "anthropological_corroboration_score": 20, "score_components": [ { "component": "authentication_report_imported", "points": 10, "note": "Structured ancient-DNA authentication report(s) were imported." }, { "component": "authentication_damage_metric_present", "points": 10, "note": "Damage/deamination or PMD-style metric was imported." }, { "component": "authentication_contamination_metric_present", "points": 8, "note": "Contamination estimate was imported." }, { "component": "unknown_sample_age_penalty", "points": -8, "note": "Sample age class is unknown, reducing anthropological interpretability." } ], "interpretation_mode": "modern_or_unknown_research_context", "methylation_mode": "direct_modbase_exploratory_when_metadata_complete" }, "evidence_domains": { "genomic_susceptibility": { "status": "not_observed_in_uploaded_inputs", "summary": "0 curated ascorbate-transporter hit(s); 0 target-window variant(s)." }, "modified_base_or_methylation_signal": { "status": "not_available", "summary": "0 target methylation/modified-base summary row(s)." }, "ancient_dna_authenticity": { "status": "not_required_for_modern_context", "summary": "Age class: unknown; material: unknown; imported authentication reports: 1." }, "authentication_imports": { "status": "structured_authentication_evidence_imported", "summary": "Tools: schmutzi; flags: low_contamination_estimate, damage_metric_present, pmd_metric_present, endogenous_fraction_present" }, "osteological_paleopathology": { "status": "not_provided", "summary": "" }, "isotopic_dietary_context": { "status": "not_provided", "summary": "" }, "historical_ethnographic_context": { "status": "not_provided", "summary": "" }, "ecological_or_provisioning_constraint": { "status": "not_provided", "summary": "" }, "intergenerational_context": { "status": "not_specified", "summary": "" } }, "ancient_sample_readiness": { "age_class": "unknown", "material": "unknown", "requires_damage_profile": false, "requires_contamination_estimate": false, "contamination_controls_present": true, "damage_authenticity_review_present": true, "authentication_report_count": 1, "authentication_aggregate": { "report_count": 1, "tools_detected": [ "schmutzi" ], "status": "structured_authentication_evidence_imported", "has_damage_metric": true, "has_contamination_metric": true, "has_endogenous_fraction": true, "has_pmd_metric": true, "max_contamination_percent": 2.8, "metrics": { "contamination_percent": { "count": 1, "min": 2.4, "max": 2.4, "mean": 2.4, "unit": "percent" }, "mitochondrial_contamination_percent": { "count": 1, "min": 2.8, "max": 2.8, "mean": 2.8, "unit": "percent" }, "nuclear_contamination_percent": { "count": 1, "min": 1.9, "max": 1.9, "mean": 1.9, "unit": "percent" }, "endogenous_fraction_percent": { "count": 1, "min": 47.3, "max": 47.3, "mean": 47.3, "unit": "percent" }, "c_to_t_5prime_percent": { "count": 1, "min": 14.2, "max": 14.2, "mean": 14.2, "unit": "percent" }, "g_to_a_3prime_percent": { "count": 1, "min": 11.7, "max": 11.7, "mean": 11.7, "unit": "percent" }, "damage_percent": { "count": 1, "min": 12.9, "max": 12.9, "mean": 12.9, "unit": "percent" }, "mean_pmd_score": { "count": 1, "min": 0.87, "max": 0.87, "mean": 0.87, "unit": "score" }, "pmd_positive_percent": { "count": 1, "min": 68.4, "max": 68.4, "mean": 68.4, "unit": "percent" }, "median_fragment_length_bp": { "count": 1, "min": 68, "max": 68, "mean": 68, "unit": "bp" }, "mean_fragment_length_bp": { "count": 1, "min": 79.5, "max": 79.5, "mean": 79.5, "unit": "bp" }, "short_fragment_percent_le100": { "count": 1, "min": 72.1, "max": 72.1, "mean": 72.1, "unit": "percent" } }, "flags": [ "low_contamination_estimate", "damage_metric_present", "pmd_metric_present", "endogenous_fraction_present" ] }, "fastq_fragment_profiles": [], "readiness_status": "not_an_ancient_sample_mode" }, "messages": [ { "level": "scope", "message": "ADLA is currently framed for anthropological nutritional-stress research, not medical diagnosis. Interpret sequence-derived findings alongside archaeological, osteological, isotopic, ecological, and historical evidence." }, { "level": "gap", "message": "No target callability data were provided. Anthropological interpretation should avoid absence claims until coverage/callability is measured across the panel." } ], "raw_context": { "reference_build": "GRCh38", "sample_age_class": "unknown", "sample_material": "unknown", "sample_type": "", "preservation_context": "", "archaeological_context": "", "osteological_evidence": "", "isotopic_evidence": "", "dietary_evidence": "", "historical_dietary_context": "", "environmental_context": "", "contamination_controls": "", "damage_authenticity_review": "", "intergenerational_question": "", "notes": "", "ascorbate_lab_value": "" }, "boundary": "ADLA evaluates genomic, modified-base, preservation, and contextual evidence relevant to ascorbate stress and scurvy-like vulnerability in anthropological, historical, ancient-remains, and intergenerational research. It does not diagnose vitamin C deficiency or scurvy." }, "authentication": { "summaries": [ { "file": "reich_lab_style_demo.auth.json", "kind": "authentication", "tool_guess": "schmutzi", "standardized_metrics": { "contamination_percent": { "value": 2.4, "unit": "percent", "source_key": "contamination_percent", "raw": "2.4" }, "mitochondrial_contamination_percent": { "value": 2.8, "unit": "percent", "source_key": "mitochondrial_contamination_percent", "raw": "2.8" }, "nuclear_contamination_percent": { "value": 1.9, "unit": "percent", "source_key": "nuclear_contamination_percent", "raw": "1.9" }, "endogenous_fraction_percent": { "value": 47.3, "unit": "percent", "source_key": "endogenous_fraction_percent", "raw": "47.3" }, "c_to_t_5prime_percent": { "value": 14.2, "unit": "percent", "source_key": "damage.c_to_t_5prime_percent", "raw": "14.2" }, "g_to_a_3prime_percent": { "value": 11.7, "unit": "percent", "source_key": "damage.g_to_a_3prime_percent", "raw": "11.7" }, "damage_percent": { "value": 12.9, "unit": "percent", "source_key": "damage.damage_percent", "raw": "12.9" }, "mean_pmd_score": { "value": 0.87, "unit": "score", "source_key": "pmd.mean_pmd_score", "raw": "0.87" }, "pmd_positive_percent": { "value": 68.4, "unit": "percent", "source_key": "pmd.pmd_positive_percent", "raw": "68.4" }, "median_fragment_length_bp": { "value": 68, "unit": "bp", "source_key": "fragments.median_fragment_length_bp", "raw": "68" }, "mean_fragment_length_bp": { "value": 79.5, "unit": "bp", "source_key": "fragments.mean_fragment_length_bp", "raw": "79.5" }, "short_fragment_percent_le100": { "value": 72.1, "unit": "percent", "source_key": "fragments.short_fragment_percent_le100", "raw": "72.1" } }, "metrics": { "mitochondrial_contamination_percent": { "value": 2.8, "unit": "percent", "source_key": "mitochondrial_contamination_percent", "raw": "2.8" }, "nuclear_contamination_percent": { "value": 1.9, "unit": "percent", "source_key": "nuclear_contamination_percent", "raw": "1.9" }, "contamination_percent": { "value": 2.4, "unit": "percent", "source_key": "contamination_percent", "raw": "2.4" }, "endogenous_fraction_percent": { "value": 47.3, "unit": "percent", "source_key": "endogenous_fraction_percent", "raw": "47.3" }, "c_to_t_5prime_percent": { "value": 14.2, "unit": "percent", "source_key": "damage.c_to_t_5prime_percent", "raw": "14.2" }, "g_to_a_3prime_percent": { "value": 11.7, "unit": "percent", "source_key": "damage.g_to_a_3prime_percent", "raw": "11.7" }, "damage_percent": { "value": 12.9, "unit": "percent", "source_key": "damage.damage_percent", "raw": "12.9" }, "mean_pmd_score": { "value": 0.87, "unit": "score", "source_key": "pmd.mean_pmd_score", "raw": "0.87" }, "pmd_positive_percent": { "value": 68.4, "unit": "percent", "source_key": "pmd.pmd_positive_percent", "raw": "68.4" }, "median_fragment_length_bp": { "value": 68, "unit": "bp", "source_key": "fragments.median_fragment_length_bp", "raw": "68" }, "mean_fragment_length_bp": { "value": 79.5, "unit": "bp", "source_key": "fragments.mean_fragment_length_bp", "raw": "79.5" }, "short_fragment_percent_le100": { "value": 72.1, "unit": "percent", "source_key": "fragments.short_fragment_percent_le100", "raw": "72.1" } }, "status": "parsed_structured_metrics", "confidence_flags": [ "low_contamination_estimate", "damage_metric_present", "pmd_metric_present", "endogenous_fraction_present" ], "messages": [ { "level": "parsed", "message": "Structured JSON authentication/QC report was parsed." }, { "level": "supporting", "message": "Imported contamination estimate is low (2.8%), subject to tool assumptions and sample context." }, { "level": "supporting", "message": "Damage/deamination-style metric imported from schmutzi." }, { "level": "supporting", "message": "PMD-style authenticity metric imported from schmutzi." }, { "level": "context", "message": "Endogenous DNA fraction metric imported." }, { "level": "review", "message": "Parse assumptions were recorded. Verify extracted metrics against the original authentication report before publication-quality interpretation." } ], "parse_assumptions": { "routing": "File was routed by filename/content heuristic rather than a formal tool schema.", "metric_extraction": "ADLA extracted JSON leaves, key:value lines, free text, and PMDtools-like tables; original report remains the audit source.", "unit_normalization": "Fractions from keys containing percent/rate/fraction are normalized to percent when values are between 0 and 1." }, "raw_excerpt": "{\n \"tool\": \"schmutzi\",\n \"sample\": \"Reich_Lab_style_ancient_demo_ADLA_test\",\n \"description\": \"Synthetic but realistic authentication summary modeled on typical Reich Lab ancient DNA outputs (schmutzi + ContamLD style). For ADLA testing only. Low contamination, moderate endogenous fraction, classic aDNA damage pattern.\",\n \"mitochondrial_contamination_percent\": 2.8,\n \"nuclear_contamination_percent\": 1.9,\n \"contamination_percent\": 2.4,\n \"endogenous_fraction_percent\": 47.3,\n \"damage\": {\n \"c_to_t_5prime_percent\": 14.2,\n \"g_to_a_3prime_percent\": 11.7,\n \"damage_percent\": 12.9\n },\n \"pmd\": {\n \"mean_pmd_score\": 0.87,\n \"pmd_positive_percent\": 68.4\n },\n \"fragments\": {\n \"median_fragment_length_bp\": 68,\n \"mean_fragment_length_bp\": 79.5,\n \"short_fragment_percent_le100\": 72.1\n },\n \"library\": \"double_stranded_UDG_minus\",\n \"notes\": \"Modeled after typical values from Reich Lab publications using schmutzi and ContamLD on ancient human remains (e.g., Eurasian Bronze Age, Neolithic, or similar contexts). Use for testing ADLA Authentication import and anthropological readiness scoring. Not real data from any specific individual.\"\n}" } ], "aggregate": { "report_count": 1, "tools_detected": [ "schmutzi" ], "status": "structured_authentication_evidence_imported", "has_damage_metric": true, "has_contamination_metric": true, "has_endogenous_fraction": true, "has_pmd_metric": true, "max_contamination_percent": 2.8, "metrics": { "contamination_percent": { "count": 1, "min": 2.4, "max": 2.4, "mean": 2.4, "unit": "percent" }, "mitochondrial_contamination_percent": { "count": 1, "min": 2.8, "max": 2.8, "mean": 2.8, "unit": "percent" }, "nuclear_contamination_percent": { "count": 1, "min": 1.9, "max": 1.9, "mean": 1.9, "unit": "percent" }, "endogenous_fraction_percent": { "count": 1, "min": 47.3, "max": 47.3, "mean": 47.3, "unit": "percent" }, "c_to_t_5prime_percent": { "count": 1, "min": 14.2, "max": 14.2, "mean": 14.2, "unit": "percent" }, "g_to_a_3prime_percent": { "count": 1, "min": 11.7, "max": 11.7, "mean": 11.7, "unit": "percent" }, "damage_percent": { "count": 1, "min": 12.9, "max": 12.9, "mean": 12.9, "unit": "percent" }, "mean_pmd_score": { "count": 1, "min": 0.87, "max": 0.87, "mean": 0.87, "unit": "score" }, "pmd_positive_percent": { "count": 1, "min": 68.4, "max": 68.4, "mean": 68.4, "unit": "percent" }, "median_fragment_length_bp": { "count": 1, "min": 68, "max": 68, "mean": 68, "unit": "bp" }, "mean_fragment_length_bp": { "count": 1, "min": 79.5, "max": 79.5, "mean": 79.5, "unit": "bp" }, "short_fragment_percent_le100": { "count": 1, "min": 72.1, "max": 72.1, "mean": 72.1, "unit": "percent" } }, "flags": [ "low_contamination_estimate", "damage_metric_present", "pmd_metric_present", "endogenous_fraction_present" ] }, "messages": [ { "level": "parsed", "message": "Structured JSON authentication/QC report was parsed." }, { "level": "supporting", "message": "Imported contamination estimate is low (2.8%), subject to tool assumptions and sample context." }, { "level": "supporting", "message": "Damage/deamination-style metric imported from schmutzi." }, { "level": "supporting", "message": "PMD-style authenticity metric imported from schmutzi." }, { "level": "context", "message": "Endogenous DNA fraction metric imported." }, { "level": "review", "message": "Parse assumptions were recorded. Verify extracted metrics against the original authentication report before publication-quality interpretation." } ], "boundary": "Imported ancient-DNA authentication reports support anthropological interpretation only; they do not prove biological deficiency or diagnose disease." }, "tool_profiles": { "registry_version": "0.1.6", "strategy": "Import-first, worker-compatible profiles. Hostinger web mode parses outputs; CLI/worker mode may execute installed tools where licensing, compute, and environment allow.", "profiles": [ { "profile_id": "fastvep", "name": "fastVEP annotation profile", "category": "annotation", "purpose": "Fast local VEP-compatible consequence and supplementary annotation import.", "execution_mode": "worker_or_import", "import_file_hints": [ "fastvep.json", "fastvep.vcf", "CSQ", "ClinVar", "gnomAD" ], "primary_tools": [ { "name": "fastVEP", "purpose": "High-performance Rust variant consequence annotation with VEP-compatible outputs and supplementary database integration.", "license": "Check upstream fastVEP license and bundled database terms before redistribution.", "preferred_local_path": "tools/bin/fastvep", "available": false, "web_exec_safe": false, "notes": "ADLA parses fastVEP JSON/VCF-style imports and can use it as a worker annotation profile." }, { "name": "bcftools", "purpose": "Local VCF normalization, target slicing, indexing-aware filtering, and annotation transfer from ClinVar/dbSNP VCFs.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/bcftools", "available": false, "web_exec_safe": false, "notes": "Primary lightweight engine for offline ClinVar/dbSNP annotation and ADLA target-slice generation." }, { "name": "tabix", "purpose": "Index bgzip-compressed VCF/BED annotation files for local random access.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/tabix", "available": false, "web_exec_safe": false, "notes": "Required for indexed ClinVar/dbSNP VCF usage." }, { "name": "bgzip", "purpose": "Block gzip compression for VCF/BED files that need tabix indexing.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/bgzip", "available": false, "web_exec_safe": false, "notes": "Used by annotation prep scripts when normalizing or slicing local reference VCFs." } ], "tools_available": 0, "tool_count": 4, "status": "import_ready", "notes": "Use as a fast local annotation path; VEP remains a conservative reference path." }, { "profile_id": "longhap", "name": "LongHap methylation-aware phasing profile", "category": "phasing", "purpose": "Import or execute haplotype phasing that integrates long-read methylation evidence.", "execution_mode": "worker_or_import", "import_file_hints": [ "longhap", "phased.vcf", "haplotagged", "phase_set" ], "primary_tools": [ { "name": "LongHap", "purpose": "Read-based phasing that integrates native long-read methylation signals with variant calls.", "license": "MIT per upstream repository at time of review; verify before redistribution.", "preferred_local_path": "tools/bin/longhap", "available": false, "web_exec_safe": false, "notes": "Import phased VCF/summary outputs for haplotype-aware ascorbate-pathway interpretation." } ], "tools_available": 0, "tool_count": 1, "status": "import_ready", "notes": "High value for intergenerational and haplotype-context interpretation." }, { "profile_id": "longphase", "name": "LongPhase co-phasing profile", "category": "phasing", "purpose": "Co-phase SNPs, indels, SVs, and 5mC modifications from long reads.", "execution_mode": "worker_or_import", "import_file_hints": [ "longphase", "phase_set", "haplotype block", "5mC" ], "primary_tools": [ { "name": "LongPhase", "purpose": "Co-phase SNPs, small indels, SVs, and 5mC modifications from Nanopore/PacBio long reads.", "license": "GPL-3.0; verify upstream and redistribution requirements.", "preferred_local_path": "tools/bin/longphase", "available": false, "web_exec_safe": false, "notes": "Use as optional worker profile for haplotype and modification co-phasing." } ], "tools_available": 0, "tool_count": 1, "status": "import_ready", "notes": "Useful for broad long-read haplotype context." }, { "profile_id": "wf-human-variation", "name": "EPI2ME wf-human-variation import profile", "category": "ont_reference_workflow", "purpose": "Import ONT workflow outputs for small variants, SVs, CNVs, STRs, modified bases, and phasing.", "execution_mode": "external_worker_import", "import_file_hints": [ "wf-human-variation", "epi2me", "nextflow", "small variants", "structural variant", "modified bases" ], "primary_tools": [ { "name": "wf-human-variation", "purpose": "EPI2ME Nextflow workflow for ONT human small variants, SVs, CNVs, STRs, modified bases, and phasing.", "license": "Check Oxford Nanopore/EPI2ME workflow terms and dependencies before redistribution.", "preferred_local_path": "tools/workflows/wf-human-variation", "available": false, "web_exec_safe": false, "notes": "Run externally or via worker; ADLA imports derived reports, VCFs, BAM summaries, and bedMethyl outputs." }, { "name": "Dorado", "purpose": "ONT basecalling, demultiplexing, alignment support, and modified-base calling from POD5/FAST5 inputs.", "license": "Oxford Nanopore Technologies license; verify redistribution terms before bundling.", "preferred_local_path": "tools/bin/dorado", "available": false, "web_exec_safe": false, "notes": "Use from CLI or worker first. GPU/CPU needs may exceed shared hosting constraints. Dorado 2.x includes modified-base workflows and newer small variant capabilities." }, { "name": "Modkit", "purpose": "Summarize modified-base BAM/modBAM into bedMethyl and per-region modification reports.", "license": "Check upstream nanoporetech/modkit license before redistribution.", "preferred_local_path": "tools/bin/modkit", "available": false, "web_exec_safe": false, "notes": "Primary engine for methylation/modified-base evidence. Output bedMethyl can be parsed by PHP web mode." }, { "name": "Sniffles2", "purpose": "Long-read structural variant calling from ONT/PacBio alignments.", "license": "MIT; verify upstream repository.", "preferred_local_path": "tools/bin/sniffles", "available": false, "web_exec_safe": false, "notes": "Adds large-deletion/insertion context for pathway and differential diagnosis genes." } ], "tools_available": 0, "tool_count": 4, "status": "import_ready", "notes": "Too heavy for shared hosting; import reports and derived VCF/bedMethyl outputs." }, { "profile_id": "pastforward", "name": "PastForward historical/aDNA profile", "category": "ancient_dna_workflow", "purpose": "Import historical/ancient-DNA mapping, contamination, coverage, and damage-rescaling summaries.", "execution_mode": "external_worker_import", "import_file_hints": [ "pastforward", "damage rescaled", "contamination", "endogenous" ], "primary_tools": [ { "name": "PastForward", "purpose": "Snakemake pipeline for historical/ancient DNA processing, QC, contamination, coverage, and damage rescaling.", "license": "MIT in current upstream repository; verify before redistribution.", "preferred_local_path": "tools/workflows/PastForward", "available": false, "web_exec_safe": false, "notes": "ADLA imports PastForward summaries to strengthen ancient/historical readiness." }, { "name": "mapDamage2", "purpose": "Ancient DNA nucleotide misincorporation and fragmentation pattern assessment for authenticity/damage review.", "license": "Check upstream license and dependencies before redistribution.", "preferred_local_path": "tools/bin/mapDamage", "available": false, "web_exec_safe": false, "notes": "Optional aDNA authentication support. ADLA v0.1.4 records damage/authenticity metadata but does not execute mapDamage in web mode. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." }, { "name": "schmutzi", "purpose": "Mitochondrial contamination estimation and endogenous consensus support for ancient human DNA.", "license": "Check upstream license and database terms before redistribution.", "preferred_local_path": "tools/bin/schmutzi", "available": false, "web_exec_safe": false, "notes": "Optional contamination/authenticity workflow; output can be summarized in ADLA anthropological context fields. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." } ], "tools_available": 0, "tool_count": 3, "status": "import_ready", "notes": "Strengthens anthropological readiness and authenticity review." }, { "profile_id": "mapache", "name": "Mapache aDNA mapping profile", "category": "ancient_dna_workflow", "purpose": "Import ancient-DNA mapping/QC/imputation workflow summaries.", "execution_mode": "external_worker_import", "import_file_hints": [ "mapache", "snakemake", "mapped reads", "damage rescaling" ], "primary_tools": [ { "name": "Mapache", "purpose": "Snakemake ancient-DNA mapping workflow supporting reproducible mapping/QC/imputation context.", "license": "GPL-3.0; verify redistribution requirements.", "preferred_local_path": "tools/workflows/mapache", "available": false, "web_exec_safe": false, "notes": "ADLA imports Mapache summaries and links them to authentication/context fields." }, { "name": "mapDamage2", "purpose": "Ancient DNA nucleotide misincorporation and fragmentation pattern assessment for authenticity/damage review.", "license": "Check upstream license and dependencies before redistribution.", "preferred_local_path": "tools/bin/mapDamage", "available": false, "web_exec_safe": false, "notes": "Optional aDNA authentication support. ADLA v0.1.4 records damage/authenticity metadata but does not execute mapDamage in web mode. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." } ], "tools_available": 0, "tool_count": 2, "status": "import_ready", "notes": "Supports reproducible mapping context for older remains." }, { "profile_id": "ameta", "name": "aMeta ancient metagenomics profile", "category": "microbial_context", "purpose": "Import ancient microbiome/pathogen/burial-context summaries from aMeta/MALT/KrakenUniq/MaltExtract.", "execution_mode": "external_worker_import", "import_file_hints": [ "ameta", "krakenuniq", "malt", "maltextract", "microbial", "pathogen", "taxa" ], "primary_tools": [ { "name": "aMeta", "purpose": "Ancient metagenomic profiling workflow using trimming/QC, KrakenUniq, Bowtie2 pathogen screening, MapDamage2, MALT, and MaltExtract.", "license": "Check upstream workflow and database terms before redistribution.", "preferred_local_path": "tools/workflows/aMeta", "available": false, "web_exec_safe": false, "notes": "ADLA imports aMeta outputs for microbial, pathogen, oral/gut, and burial-context interpretation." }, { "name": "KrakenUniq", "purpose": "K-mer-based taxonomic classification used in ancient metagenomic workflows such as aMeta.", "license": "Check upstream license and database terms.", "preferred_local_path": "tools/bin/krakenuniq", "available": false, "web_exec_safe": false, "notes": "Contextual microbial/burial evidence only." }, { "name": "MALT", "purpose": "MEGAN Alignment Tool for metagenomic alignment/LCA workflows used in ancient microbial authentication.", "license": "Check upstream MEGAN/MALT terms.", "preferred_local_path": "tools/bin/malt-run", "available": false, "web_exec_safe": false, "notes": "Use through external aMeta/MALT workflows; import summaries into ADLA." }, { "name": "MaltExtract", "purpose": "Authentication and validation of microbial species detected in ancient metagenomic workflows.", "license": "Check upstream license and database terms.", "preferred_local_path": "tools/bin/MaltExtract", "available": false, "web_exec_safe": false, "notes": "Import output summaries into ADLA microbial context." }, { "name": "mapDamage2", "purpose": "Ancient DNA nucleotide misincorporation and fragmentation pattern assessment for authenticity/damage review.", "license": "Check upstream license and dependencies before redistribution.", "preferred_local_path": "tools/bin/mapDamage", "available": false, "web_exec_safe": false, "notes": "Optional aDNA authentication support. ADLA v0.1.4 records damage/authenticity metadata but does not execute mapDamage in web mode. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." } ], "tools_available": 0, "tool_count": 5, "status": "import_ready", "notes": "Contextual evidence only; useful for preservation, oral/gut/pathogen/burial signals." }, { "profile_id": "sv_consensus", "name": "Sniffles2/cuteSV structural variant profile", "category": "structural_variants", "purpose": "Import long-read SV calls and compare target-window overlaps.", "execution_mode": "worker_or_import", "import_file_hints": [ "sniffles", "cutesv", "SVTYPE", "structural variant" ], "primary_tools": [ { "name": "Sniffles2", "purpose": "Long-read structural variant calling from ONT/PacBio alignments.", "license": "MIT; verify upstream repository.", "preferred_local_path": "tools/bin/sniffles", "available": false, "web_exec_safe": false, "notes": "Adds large-deletion/insertion context for pathway and differential diagnosis genes." }, { "name": "cuteSV", "purpose": "Long-read structural variant caller for ONT/PacBio datasets; useful as an alternate/concordance SV caller with Sniffles2.", "license": "Check upstream license before redistribution.", "preferred_local_path": "tools/bin/cuteSV", "available": false, "web_exec_safe": false, "notes": "Upload cuteSV VCFs to populate ADLA structural-variant target overlaps." } ], "tools_available": 0, "tool_count": 2, "status": "import_ready", "notes": "Caller concordance is preferred before strong SV interpretation." } ] }, "external_workflows": { "imports": [], "summary": { "import_count": 0, "profiles_observed": [], "metric_categories": [], "registry_version": "0.1.6", "interpretation": "No external workflow outputs were imported." }, "messages": [] }, "phasing": { "summaries": [], "target_haplotype_links": [], "summary": { "summary_count": 0, "reported_phased_variant_count": 0, "reported_phase_set_count": 0, "target_phased_variant_count": 0, "boundary": "Phasing/haplotype evidence supports lineage and allele-context interpretation; it does not make a deficiency call." } }, "structural_variants": { "target_overlaps": [], "summary": { "summary_count": 0, "reported_sv_count": 0, "target_overlap_count": 0, "svtype_counts": [], "boundary": "SV overlaps are candidate contextual findings. Confirm with read-level inspection and caller concordance." } }, "microbial_context": { "summaries": [], "flagged_taxa": [], "summary": { "summary_count": 0, "flagged_taxa_count": 0, "boundary": "Microbial/pathogen/burial context can corroborate preservation, infection, oral/gut environment, or contamination hypotheses; it is not direct ascorbate evidence." }, "boundary": "Microbial and burial-context imports are contextual evidence; they do not establish nutritional deficiency by themselves." }, "tool_status": [ { "name": "Dorado", "purpose": "ONT basecalling, demultiplexing, alignment support, and modified-base calling from POD5/FAST5 inputs.", "license": "Oxford Nanopore Technologies license; verify redistribution terms before bundling.", "preferred_local_path": "tools/bin/dorado", "available": false, "web_exec_safe": false, "notes": "Use from CLI or worker first. GPU/CPU needs may exceed shared hosting constraints. Dorado 2.x includes modified-base workflows and newer small variant capabilities." }, { "name": "Modkit", "purpose": "Summarize modified-base BAM/modBAM into bedMethyl and per-region modification reports.", "license": "Check upstream nanoporetech/modkit license before redistribution.", "preferred_local_path": "tools/bin/modkit", "available": false, "web_exec_safe": false, "notes": "Primary engine for methylation/modified-base evidence. Output bedMethyl can be parsed by PHP web mode." }, { "name": "NanoPlot", "purpose": "Long-read QC plots and HTML summaries for FASTQ/BAM/sequencing_summary inputs.", "license": "MIT", "preferred_local_path": "tools/bin/NanoPlot", "available": false, "web_exec_safe": false, "notes": "Python dependency stack may be large; can run from CLI worker and cache HTML outputs." }, { "name": "chopper", "purpose": "Fast ONT read filtering by length, quality, and GC thresholds.", "license": "MIT/Apache-style Rust ecosystem dependencies; verify upstream repository.", "preferred_local_path": "tools/bin/chopper", "available": false, "web_exec_safe": false, "notes": "Good candidate for vendored binary mode if Hostinger permits executable files." }, { "name": "minimap2", "purpose": "Long-read alignment to reference genomes.", "license": "MIT-like; verify upstream LICENSE.txt.", "preferred_local_path": "tools/bin/minimap2", "available": false, "web_exec_safe": false, "notes": "Use -x map-ont for ONT reads. Alignment should generally run in CLI/worker mode." }, { "name": "samtools", "purpose": "BAM/SAM sorting, indexing, and summary statistics.", "license": "MIT/BSD-style; verify htslib/samtools license.", "preferred_local_path": "tools/bin/samtools", "available": false, "web_exec_safe": false, "notes": "Core dependency for BAM preparation." }, { "name": "mosdepth", "purpose": "Fast BAM/CRAM depth summaries and target coverage/callability checks.", "license": "MIT; verify upstream repository.", "preferred_local_path": "tools/bin/mosdepth", "available": false, "web_exec_safe": false, "notes": "Important for proving whether target genes/windows were callable." }, { "name": "Clair3", "purpose": "Long-read germline small variant calling, including ONT models.", "license": "Check upstream HKU-BAL/Clair3 license and model terms.", "preferred_local_path": "tools/bin/run_clair3.sh", "available": false, "web_exec_safe": false, "notes": "Use as worker/CLI stage. Outputs VCF that web mode can parse." }, { "name": "Sniffles2", "purpose": "Long-read structural variant calling from ONT/PacBio alignments.", "license": "MIT; verify upstream repository.", "preferred_local_path": "tools/bin/sniffles", "available": false, "web_exec_safe": false, "notes": "Adds large-deletion/insertion context for pathway and differential diagnosis genes." }, { "name": "Ensembl VEP", "purpose": "Offline/cache-based variant consequence annotation with transcript/protein effects, consequence terms, frequencies, and plugin support.", "license": "Apache 2.0 for Ensembl API code; data cache terms vary. Verify before redistribution.", "preferred_local_path": "tools/bin/vep", "available": false, "web_exec_safe": false, "notes": "Use --offline --cache --assembly GRCh38 with a local cache under tools/annotations/vep_cache. ADLA parses VEP CSQ fields from annotated VCFs." }, { "name": "bcftools", "purpose": "Local VCF normalization, target slicing, indexing-aware filtering, and annotation transfer from ClinVar/dbSNP VCFs.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/bcftools", "available": false, "web_exec_safe": false, "notes": "Primary lightweight engine for offline ClinVar/dbSNP annotation and ADLA target-slice generation." }, { "name": "tabix", "purpose": "Index bgzip-compressed VCF/BED annotation files for local random access.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/tabix", "available": false, "web_exec_safe": false, "notes": "Required for indexed ClinVar/dbSNP VCF usage." }, { "name": "bgzip", "purpose": "Block gzip compression for VCF/BED files that need tabix indexing.", "license": "MIT/BSD-style htslib/samtools family; verify upstream version.", "preferred_local_path": "tools/bin/bgzip", "available": false, "web_exec_safe": false, "notes": "Used by annotation prep scripts when normalizing or slicing local reference VCFs." }, { "name": "SnpEff", "purpose": "Alternative local variant effect annotation when VEP cache is not installed.", "license": "Verify current SnpEff license before redistributing jar files.", "preferred_local_path": "tools/bin/snpEff.jar", "available": false, "web_exec_safe": false, "notes": "Java runtime required. Use as optional alternative to VEP, not as the primary ADLA consequence engine." }, { "name": "SnpSift", "purpose": "Annotate/filter VCFs using local ClinVar, dbSNP, dbNSFP, and other indexed files.", "license": "Verify current SnpSift/SnpEff license before redistributing jar files.", "preferred_local_path": "tools/bin/SnpSift.jar", "available": false, "web_exec_safe": false, "notes": "Useful fallback for ClinVar/dbSNP enrichment and field extraction." }, { "name": "clinvcf", "purpose": "Optional ClinVar XML-to-enhanced-VCF builder supporting GRCh37/GRCh38; useful if raw ClinVar VCF is insufficient for local interpretation workflows.", "license": "Check upstream SeqOne/clinvcf license before redistribution.", "preferred_local_path": "tools/bin/clinvcf", "available": false, "web_exec_safe": false, "notes": "Optional advanced curation path. ADLA can operate from official ClinVar VCF without this tool." }, { "name": "mapDamage2", "purpose": "Ancient DNA nucleotide misincorporation and fragmentation pattern assessment for authenticity/damage review.", "license": "Check upstream license and dependencies before redistribution.", "preferred_local_path": "tools/bin/mapDamage", "available": false, "web_exec_safe": false, "notes": "Optional aDNA authentication support. ADLA v0.1.4 records damage/authenticity metadata but does not execute mapDamage in web mode. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." }, { "name": "PMDtools", "purpose": "Post-mortem damage score support for ancient DNA read filtering/authenticity workflows.", "license": "Check upstream license before redistribution.", "preferred_local_path": "tools/bin/pmdtools", "available": false, "web_exec_safe": false, "notes": "Optional ancient/historical sample readiness component for CLI/worker mode. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." }, { "name": "schmutzi", "purpose": "Mitochondrial contamination estimation and endogenous consensus support for ancient human DNA.", "license": "Check upstream license and database terms before redistribution.", "preferred_local_path": "tools/bin/schmutzi", "available": false, "web_exec_safe": false, "notes": "Optional contamination/authenticity workflow; output can be summarized in ADLA anthropological context fields. ADLA v0.1.5 imports summary outputs into the Authentication tab when reports are uploaded." }, { "name": "ContamLD", "purpose": "Autosomal ancient-DNA contamination estimation using linkage disequilibrium breakdown; useful as an advanced nuclear-contamination context layer.", "license": "Check upstream Reich Lab/ContamLD terms before redistribution.", "preferred_local_path": "tools/bin/contamLD", "available": false, "web_exec_safe": false, "notes": "Optional future CLI/worker tool. ADLA v0.1.5 can import contamination summary outputs when provided as text/JSON." }, { "name": "ANGSD", "purpose": "Genotype-likelihood framework used in low-coverage and ancient DNA contexts, including chromosome-X contamination estimation workflows for applicable samples.", "license": "Check upstream ANGSD license before redistribution.", "preferred_local_path": "tools/bin/angsd", "available": false, "web_exec_safe": false, "notes": "Optional future CLI/worker tool. Requires careful setup, population frequency sites, and sex/chromosome applicability review." }, { "name": "hapCon", "purpose": "Ancient DNA contamination estimation for male X-chromosome workflows; useful where applicable and when reference panels/metadata are appropriate.", "license": "Check upstream terms and reference-data requirements before redistribution.", "preferred_local_path": "tools/bin/hapCon", "available": false, "web_exec_safe": false, "notes": "Optional future CLI/worker tool. ADLA can import summary metrics but does not execute it in web mode." }, { "name": "fastVEP", "purpose": "High-performance Rust variant consequence annotation with VEP-compatible outputs and supplementary database integration.", "license": "Check upstream fastVEP license and bundled database terms before redistribution.", "preferred_local_path": "tools/bin/fastvep", "available": false, "web_exec_safe": false, "notes": "ADLA parses fastVEP JSON/VCF-style imports and can use it as a worker annotation profile." }, { "name": "LongHap", "purpose": "Read-based phasing that integrates native long-read methylation signals with variant calls.", "license": "MIT per upstream repository at time of review; verify before redistribution.", "preferred_local_path": "tools/bin/longhap", "available": false, "web_exec_safe": false, "notes": "Import phased VCF/summary outputs for haplotype-aware ascorbate-pathway interpretation." }, { "name": "LongPhase", "purpose": "Co-phase SNPs, small indels, SVs, and 5mC modifications from Nanopore/PacBio long reads.", "license": "GPL-3.0; verify upstream and redistribution requirements.", "preferred_local_path": "tools/bin/longphase", "available": false, "web_exec_safe": false, "notes": "Use as optional worker profile for haplotype and modification co-phasing." }, { "name": "wf-human-variation", "purpose": "EPI2ME Nextflow workflow for ONT human small variants, SVs, CNVs, STRs, modified bases, and phasing.", "license": "Check Oxford Nanopore/EPI2ME workflow terms and dependencies before redistribution.", "preferred_local_path": "tools/workflows/wf-human-variation", "available": false, "web_exec_safe": false, "notes": "Run externally or via worker; ADLA imports derived reports, VCFs, BAM summaries, and bedMethyl outputs." }, { "name": "PastForward", "purpose": "Snakemake pipeline for historical/ancient DNA processing, QC, contamination, coverage, and damage rescaling.", "license": "MIT in current upstream repository; verify before redistribution.", "preferred_local_path": "tools/workflows/PastForward", "available": false, "web_exec_safe": false, "notes": "ADLA imports PastForward summaries to strengthen ancient/historical readiness." }, { "name": "Mapache", "purpose": "Snakemake ancient-DNA mapping workflow supporting reproducible mapping/QC/imputation context.", "license": "GPL-3.0; verify redistribution requirements.", "preferred_local_path": "tools/workflows/mapache", "available": false, "web_exec_safe": false, "notes": "ADLA imports Mapache summaries and links them to authentication/context fields." }, { "name": "aMeta", "purpose": "Ancient metagenomic profiling workflow using trimming/QC, KrakenUniq, Bowtie2 pathogen screening, MapDamage2, MALT, and MaltExtract.", "license": "Check upstream workflow and database terms before redistribution.", "preferred_local_path": "tools/workflows/aMeta", "available": false, "web_exec_safe": false, "notes": "ADLA imports aMeta outputs for microbial, pathogen, oral/gut, and burial-context interpretation." }, { "name": "cuteSV", "purpose": "Long-read structural variant caller for ONT/PacBio datasets; useful as an alternate/concordance SV caller with Sniffles2.", "license": "Check upstream license before redistribution.", "preferred_local_path": "tools/bin/cuteSV", "available": false, "web_exec_safe": false, "notes": "Upload cuteSV VCFs to populate ADLA structural-variant target overlaps." }, { "name": "KrakenUniq", "purpose": "K-mer-based taxonomic classification used in ancient metagenomic workflows such as aMeta.", "license": "Check upstream license and database terms.", "preferred_local_path": "tools/bin/krakenuniq", "available": false, "web_exec_safe": false, "notes": "Contextual microbial/burial evidence only." }, { "name": "MALT", "purpose": "MEGAN Alignment Tool for metagenomic alignment/LCA workflows used in ancient microbial authentication.", "license": "Check upstream MEGAN/MALT terms.", "preferred_local_path": "tools/bin/malt-run", "available": false, "web_exec_safe": false, "notes": "Use through external aMeta/MALT workflows; import summaries into ADLA." }, { "name": "MaltExtract", "purpose": "Authentication and validation of microbial species detected in ancient metagenomic workflows.", "license": "Check upstream license and database terms.", "preferred_local_path": "tools/bin/MaltExtract", "available": false, "web_exec_safe": false, "notes": "Import output summaries into ADLA microbial context." } ], "interpretation": { "overall_confidence": "insufficient_for_deficiency_call", "messages": [ { "class": "anthropological_boundary", "level": "required", "message": "Sequencing cannot directly measure vitamin C status. In ADLA, genomic and epigenomic findings are anthropological research signals that require archaeological, osteological, isotopic, ecological, historical, and preservation context before interpretation." }, { "class": "anthropological_context", "level": "context", "message": "Anthropological context mode: modern or unknown research context; corroboration score 20/100." }, { "class": "ancient_dna_authentication", "level": "context", "message": "ADLA imported 1 ancient-DNA authentication/QC report(s). Status: structured authentication evidence imported. These metrics support sample-readiness review, not deficiency diagnosis." }, { "class": "genetic_transport", "level": "neutral", "message": "No curated ascorbate-transporter rsID hits were detected in parsed VCF inputs. This is not proof of absence unless target regions were callable." }, { "class": "target_callability", "level": "not_available", "message": "No mosdepth/coverage target report was parsed. Variant absence and methylation absence should be treated as unknown until target callability is measured." }, { "class": "modified_base", "level": "not_available", "message": "No target-region modified-base summaries were available. Upload Modkit bedMethyl or run modkit from modBAM through the CLI pipeline." } ], "recommended_next_steps": [ "Confirm sample type, reference build, and target-region coverage/callability using the generated BED panel.", "Pair sequencing output with osteological/paleopathological, isotopic, ecological, and historical dietary evidence; use biochemical ascorbate only when modern/historical sample context makes it available.", "Run the offline annotation stage with VEP cache, ClinVar VCF, dbSNP VCF, and/or SnpSift/bcftools before interpreting unclassified target-region variants.", "Review the ADLA priority score only as a triage/ranking aid; inspect the evidence components and source dates for every high-scoring hit.", "Use matched controls and method-specific ancient/modern methylation workflows before interpreting methylation directionality.", "When available, import fastVEP/VEP, LongHap/LongPhase, Sniffles2/cuteSV, wf-human-variation, PastForward/Mapache, and aMeta outputs so ADLA can connect annotation, phasing, SVs, authentication, and microbial context." ], "scientific_boundary": "ADLA evaluates genomic, modified-base, preservation, and contextual evidence relevant to ascorbate stress and scurvy-like vulnerability in anthropological, historical, ancient-remains, and intergenerational research. It does not diagnose vitamin C deficiency or scurvy." }, "notes": [] }