vignettes/case-study.Rmd
case-study.RmdIn this vignette, we will use the biocompute package to recreate the example Biocompute Object (HCV1a.json) used in the BCO specification.
name <- "HCV1a ledipasvir resistance SNP detection"
version <- "1.0.0"
review <- data.frame(
"status" = c("approved", "approved"),
"reviewer_comment" = c("Approved by [company name] staff. Waiting for approval from FDA Reviewer", "The revised BCO looks fine"),
"date" = c(
as.POSIXct("2017-11-12T12:30:48", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-12-12T12:30:48", format = "%Y-%m-%dT%H:%M:%S", tz = "America/Los_Angeles")
),
"reviewer_name" = c("Jane Doe", "John Doe"),
"reviewer_affiliation" = c("Seven Bridges Genomics", "U.S. Food and Drug Administration"),
"reviewer_email" = c("example@sevenbridges.com", "example@fda.gov"),
"reviewer_contribution" = c("curatedBy", "curatedBy"),
"reviewer_orcid" = c("https://orcid.org/0000-0000-0000-0000", NA),
stringsAsFactors = FALSE
)
derived_from <- "https://github.com/biocompute-objects/BCO_Specification/blob/1.2.1-beta/HCV1a.json"
obsolete_after <- as.POSIXct("2018-11-12T12:30:48", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
embargo <- c(
"start_time" = as.POSIXct("2017-10-12T12:30:48", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
"end_time" = as.POSIXct("2017-11-12T12:30:48", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
)
created <- as.POSIXct("2017-01-20T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
modified <- as.POSIXct("2019-05-10T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
contributors <- data.frame(
"name" = c("Jane Doe", "John Doe"),
"affiliation" = c("Seven Bridges Genomics", "U.S. Food and Drug Administration"),
"email" = c("example@sevenbridges.com", "example@fda.gov"),
"contribution" = I(list(c("createdBy", "curatedBy"), c("authoredBy"))),
"orcid" = c("https://orcid.org/0000-0000-0000-0000", NA),
stringsAsFactors = FALSE
)
license <- "https://creativecommons.org/licenses/by/4.0/"
provenance <- compose_provenance(
name, version, review, derived_from, obsolete_after,
embargo, created, modified, contributors, license
)
provenance %>% convert_json(){
"name": "HCV1a ledipasvir resistance SNP detection",
"version": "1.0.0",
"review": [
{
"status": "approved",
"reviewer_comment": "Approved by [company name] staff. Waiting for approval from FDA Reviewer",
"date": 1510507848,
"reviewer": [
{
"reviewer_name": "Jane Doe",
"reviewer_affiliation": "Seven Bridges Genomics",
"reviewer_email": "example@sevenbridges.com",
"reviewer_contribution": "curatedBy",
"reviewer_orcid": "https://orcid.org/0000-0000-0000-0000"
}
]
},
{
"status": "approved",
"reviewer_comment": "The revised BCO looks fine",
"date": 1513110648,
"reviewer": [
{
"reviewer_name": "John Doe",
"reviewer_affiliation": "U.S. Food and Drug Administration",
"reviewer_email": "example@fda.gov",
"reviewer_contribution": "curatedBy",
"reviewer_orcid": "NA"
}
]
}
],
"derived_from": "https://github.com/biocompute-objects/BCO_Specification/blob/1.2.1-beta/HCV1a.json",
"obsolete_after": "2018-11-12T12:30:48-0500",
"embargo": ["2017-10-12T12:30:48-0500", "2017-11-12T12:30:48-0500"],
"created": "2017-01-20T09:40:17-0500",
"modified": "2019-05-10T09:40:17-0500",
"contributors": [
{
"name": "Jane Doe",
"affiliation": "Seven Bridges Genomics",
"email": "example@sevenbridges.com",
"contribution": ["createdBy", "curatedBy"],
"orcid": "https://orcid.org/0000-0000-0000-0000"
},
{
"name": "John Doe",
"affiliation": "U.S. Food and Drug Administration",
"email": "example@fda.gov",
"contribution": "authoredBy",
"orcid": "NA"
}
],
"license": "https://creativecommons.org/licenses/by/4.0/"
}
text <- c(
"Identify baseline single nucleotide polymorphisms (SNPs)[SO:0000694], (insertions)[SO:0000667], and (deletions)[SO:0000045] that correlate with reduced (ledipasvir)[pubchem.compound:67505836] antiviral drug efficacy in (Hepatitis C virus subtype 1)[taxonomy:31646]",
"Identify treatment emergent amino acid (substitutions)[SO:1000002] that correlate with antiviral drug treatment failure",
"Determine whether the treatment emergent amino acid (substitutions)[SO:1000002] identified correlate with treatment failure involving other drugs against the same virus"
)
usability <- compose_usability(text)
usability %>% convert_json()["Identify baseline single nucleotide polymorphisms (SNPs)[SO:0000694], (insertions)[SO:0000667], and (deletions)[SO:0000045] that correlate with reduced (ledipasvir)[pubchem.compound:67505836] antiviral drug efficacy in (Hepatitis C virus subtype 1)[taxonomy:31646]", "Identify treatment emergent amino acid (substitutions)[SO:1000002] that correlate with antiviral drug treatment failure", "Determine whether the treatment emergent amino acid (substitutions)[SO:1000002] identified correlate with treatment failure involving other drugs against the same virus"]
fhir_endpoint <- "https://fhirtest.uhn.ca/baseDstu3"
fhir_version <- "3"
fhir_resources <- data.frame(
"id" = c("21376", "6288583", "25544", "92440", "4588936"),
"resource" = c(
"Sequence", "DiagnosticReport", "ProcedureRequest",
"Observation", "FamilyMemberHistory"
),
stringsAsFactors = FALSE
)
fhir <- compose_fhir(fhir_endpoint, fhir_version, fhir_resources)
fhir %>% convert_json(){
"fhir_endpoint": "https://fhirtest.uhn.ca/baseDstu3",
"fhir_version": "3",
"fhir_resources": [
[
{
"fhir_id": "21376",
"fhir_resource": "Sequence"
}
],
[
{
"fhir_id": "6288583",
"fhir_resource": "DiagnosticReport"
}
],
[
{
"fhir_id": "25544",
"fhir_resource": "ProcedureRequest"
}
],
[
{
"fhir_id": "92440",
"fhir_resource": "Observation"
}
],
[
{
"fhir_id": "4588936",
"fhir_resource": "FamilyMemberHistory"
}
]
]
}
scm_repository <- "https://github.com/example/repo1"
scm_type <- "git"
scm_commit <- "c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21"
scm_path <- "workflow/hive-viral-mutation-detection.cwl"
scm_preview <- "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
scm <- compose_scm(scm_repository, scm_type, scm_commit, scm_path, scm_preview)
scm %>% convert_json(){
"scm_repository": "https://github.com/example/repo1",
"scm_type": "git",
"scm_commit": "c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21",
"scm_path": "workflow/hive-viral-mutation-detection.cwl",
"scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
}
extension <- compose_extension(fhir, scm)
extension %>% convert_json(){
"fhir_extension": {
"fhir_endpoint": "https://fhirtest.uhn.ca/baseDstu3",
"fhir_version": "3",
"fhir_resources": [
[
{
"fhir_id": "21376",
"fhir_resource": "Sequence"
}
],
[
{
"fhir_id": "6288583",
"fhir_resource": "DiagnosticReport"
}
],
[
{
"fhir_id": "25544",
"fhir_resource": "ProcedureRequest"
}
],
[
{
"fhir_id": "92440",
"fhir_resource": "Observation"
}
],
[
{
"fhir_id": "4588936",
"fhir_resource": "FamilyMemberHistory"
}
]
]
},
"scm_extension": {
"scm_repository": "https://github.com/example/repo1",
"scm_type": "git",
"scm_commit": "c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21",
"scm_path": "workflow/hive-viral-mutation-detection.cwl",
"scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
}
}
keywords <- c("HCV1a", "Ledipasvir", "antiviral resistance", "SNP", "amino acid substitutions")
xref <- data.frame(
"namespace" = c("pubchem.compound", "pubmed", "so", "taxonomy"),
"name" = c("PubChem-compound", "PubMed", "Sequence Ontology", "Taxonomy"),
"ids" = I(list(
"67505836",
"26508693",
c("SO:000002", "SO:0000694", "SO:0000667", "SO:0000045"),
"31646"
)),
"access_time" = c(
as.POSIXct("2017-01-20T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-21T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-22T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-23T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
platform <- "Seven Bridges Platform"
pipeline_meta <- data.frame(
"step_number" = c("1"),
"name" = c("HIVE-hexagon"),
"description" = c("Alignment of reads to a set of references"),
"version" = c("1.3"),
stringsAsFactors = FALSE
)
pipeline_prerequisite <- data.frame(
"step_number" = rep("1", 5),
"name" = c(
"Hepatitis C virus genotype 1",
"Hepatitis C virus type 1b complete genome",
"Hepatitis C virus (isolate JFH-1) genomic RNA",
"Hepatitis C virus clone J8CF, complete genome",
"Hepatitis C virus S52 polyprotein gene"
),
"uri" = c(
"https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"https://www.ncbi.nlm.nih.gov/nuccore/5420376",
"https://www.ncbi.nlm.nih.gov/nuccore/13122261",
"https://www.ncbi.nlm.nih.gov/nuccore/386646758",
"https://www.ncbi.nlm.nih.gov/nuccore/295311559"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
pipeline_input <- data.frame(
"step_number" = rep("1", 2),
"uri" = c(
"https://example.com/dna.cgi?cmd=objFile&ids=514683",
"https://example.com/dna.cgi?cmd=objFile&ids=514682"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
pipeline_output <- data.frame(
"step_number" = rep("1", 2),
"uri" = c(
"https://example.com/data/514769/allCount-aligned.csv",
"https://example.com/data/514801/SNPProfile*.csv"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
description <- compose_description(
keywords, xref, platform,
pipeline_meta, pipeline_prerequisite, pipeline_input, pipeline_output
)
description %>% convert_json(){
"keywords": ["HCV1a", "Ledipasvir", "antiviral resistance", "SNP", "amino acid substitutions"],
"xref": [
{
"namespace": "pubchem.compound",
"name": "PubChem-compound",
"ids": "67505836",
"access_time": "2017-01-20T09:40:17-0500"
},
{
"namespace": "pubmed",
"name": "PubMed",
"ids": "26508693",
"access_time": "2017-01-21T09:40:17-0500"
},
{
"namespace": "so",
"name": "Sequence Ontology",
"ids": ["SO:000002", "SO:0000694", "SO:0000667", "SO:0000045"],
"access_time": "2017-01-22T09:40:17-0500"
},
{
"namespace": "taxonomy",
"name": "Taxonomy",
"ids": "31646",
"access_time": "2017-01-23T09:40:17-0500"
}
],
"platform": [
"Seven Bridges Platform"
],
"pipeline_steps": [
{
"step_number": "1",
"name": "HIVE-hexagon",
"description": "Alignment of reads to a set of references",
"version": "1.3",
"prerequisite": [
{
"name": "Hepatitis C virus genotype 1",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus type 1b complete genome",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/5420376",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus (isolate JFH-1) genomic RNA",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/13122261",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus clone J8CF, complete genome",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/386646758",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus S52 polyprotein gene",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/295311559",
"access_time": "2017-01-24 09:40:17"
}
}
],
"input_list": [
{
"uri": "https://example.com/dna.cgi?cmd=objFile&ids=514683",
"access_time": "2017-01-24 09:40:17"
},
{
"uri": "https://example.com/dna.cgi?cmd=objFile&ids=514682",
"access_time": "2017-01-24 09:40:17"
}
],
"output_list": [
{
"uri": "https://example.com/data/514769/allCount-aligned.csv",
"access_time": "2017-01-24 09:40:17"
},
{
"uri": "https://example.com/data/514801/SNPProfile*.csv",
"access_time": "2017-01-24 09:40:17"
}
]
}
]
}
script <- "https://example.com/workflows/antiviral_resistance_detection_hive.py"
script_driver <- "shell"
software_prerequisites <- data.frame(
"name" = c("HIVE-hexagon", "HIVE-heptagon"),
"version" = c("babajanian.1", "albinoni.2"),
"uri" = c(
"https://example.com/dna.cgi?cmd=dna-hexagon&cmdMode=-",
"https://example.com/dna.cgi?cmd=dna-heptagon&cmdMode=-"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
"sha1_chksum" = c("d60f506cddac09e9e816531e7905ca1ca6641e3c", NA),
stringsAsFactors = FALSE
)
external_data_endpoints <- data.frame(
"name" = c("generic name", "access to ftp server", "access to e-utils web service"),
"url" = c(
"protocol://domain:port/application/path",
"ftp://data.example.com:21/",
"https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
),
stringsAsFactors = FALSE
)
environment_variables <- data.frame(
"key" = c("HOSTTYPE", "EDITOR"),
"value" = c("x86_64-linux", "vim")
)
execution <- compose_execution(
script, script_driver, software_prerequisites, external_data_endpoints, environment_variables
)
execution %>% convert_json(){
"script": [
"https://example.com/workflows/antiviral_resistance_detection_hive.py"
],
"script_driver": "shell",
"software_prerequisites": [
{
"name": "HIVE-hexagon",
"version": "babajanian.1",
"uri": [
{
"uri": "https://example.com/dna.cgi?cmd=dna-hexagon&cmdMode=-",
"access_time": "2017-01-24 09:40:17",
"sha1_chksum": "d60f506cddac09e9e816531e7905ca1ca6641e3c"
}
]
},
{
"name": "HIVE-heptagon",
"version": "albinoni.2",
"uri": [
{
"uri": "https://example.com/dna.cgi?cmd=dna-heptagon&cmdMode=-",
"access_time": "2017-01-24 09:40:17",
"sha1_chksum": "NA"
}
]
}
],
"external_data_endpoints": [
[
{
"name": "generic name",
"url": "protocol://domain:port/application/path"
}
],
[
{
"name": "access to ftp server",
"url": "ftp://data.example.com:21/"
}
],
[
{
"name": "access to e-utils web service",
"url": "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
}
]
],
"environment_variables": {
"HOSTTYPE": "x86_64-linux",
"EDITOR": "vim"
}
}
df_parametric <- data.frame(
"param" = c(
"seed", "minimum_match_len",
"divergence_threshold_percent",
"minimum_coverage", "freq_cutoff"
),
"value" = c("14", "66", "0.30", "15", "0.10"),
"step" = c(1, 1, 1, 2, 2),
stringsAsFactors = FALSE
)
parametric <- compose_parametric(df_parametric)
parametric %>% convert_json()[
{
"param": "seed",
"value": "14",
"step": "1"
},
{
"param": "minimum_match_len",
"value": "66",
"step": "1"
},
{
"param": "divergence_threshold_percent",
"value": "0.30",
"step": "1"
},
{
"param": "minimum_coverage",
"value": "15",
"step": "2"
},
{
"param": "freq_cutoff",
"value": "0.10",
"step": "2"
}
]
input_subdomain <- data.frame(
"filename" = c(
"Hepatitis C virus genotype 1",
"Hepatitis C virus type 1b complete genome"
),
"uri" = c(
"https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"https://www.ncbi.nlm.nih.gov/nuccore/5420376"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
output_subdomain <- data.frame(
"mediatype" = c("text/csv", "text/csv"),
"uri" = c(
"https://example.com/data/514769/dnaAccessionBased.csv",
"https://example.com/data/514801/SNPProfile*.csv"
),
"access_time" = c(
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST"),
as.POSIXct("2017-01-24T09:40:17", format = "%Y-%m-%dT%H:%M:%S", tz = "EST")
),
stringsAsFactors = FALSE
)
io <- compose_io(input_subdomain, output_subdomain)
io %>% convert_json(){
"input_subdomain": [
{
"uri": [
{
"filename": "Hepatitis C virus genotype 1",
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"access_time": "2017-01-24T09:40:17-0500"
}
]
},
{
"uri": [
{
"filename": "Hepatitis C virus type 1b complete genome",
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/5420376",
"access_time": "2017-01-24T09:40:17-0500"
}
]
}
],
"output_subdomain": [
{
"mediatype": "text/csv",
"uri": [
{
"uri": "https://example.com/data/514769/dnaAccessionBased.csv",
"access_time": "2017-01-24T09:40:17-0500"
}
]
},
{
"mediatype": "text/csv",
"uri": [
{
"uri": "https://example.com/data/514801/SNPProfile*.csv",
"access_time": "2017-01-24T09:40:17-0500"
}
]
}
]
}
empirical <- data.frame(
"key" = c("false_negative_alignment_hits", "false_discovery"),
"value" = c("<0.0010", "<0.05"),
stringsAsFactors = FALSE
)
algorithmic <- data.frame(
"key" = c("false_positive_mutation_calls", "false_discovery"),
"value" = c("<0.00005", "0.005"),
stringsAsFactors = FALSE
)
error <- compose_error(empirical, algorithmic)
error %>% convert_json(){
"empirical_error": {
"false_negative_alignment_hits": "<0.0010",
"false_discovery": "<0.05"
},
"algorithmic_error": {
"false_positive_mutation_calls": "<0.00005",
"false_discovery": "0.005"
}
}
tlf <- compose_tlf(
provenance, usability, extension, description,
execution, parametric, io, error
)
tlf %>% convert_json()["https://w3id.org/biocompute/1.4.2/", "https://biocompute.sbgenomics.com/bco/c9ef66e4-41cb-4a56-a6ba-cf8356fd062c", "d18deb41a97a3108e743231af5fec0055dac321b945a569ca58bf33503ec526b"]
bco <- biocompute::compose(
tlf, provenance, usability, extension, description,
execution, parametric, io, error
)
bco %>% convert_json(){
"spec_version": "https://w3id.org/biocompute/1.4.2/",
"object_id": "https://biocompute.sbgenomics.com/bco/c9ef66e4-41cb-4a56-a6ba-cf8356fd062c",
"etag": "d18deb41a97a3108e743231af5fec0055dac321b945a569ca58bf33503ec526b",
"provenance_domain": {
"name": "HCV1a ledipasvir resistance SNP detection",
"version": "1.0.0",
"review": [
{
"status": "approved",
"reviewer_comment": "Approved by [company name] staff. Waiting for approval from FDA Reviewer",
"date": 1510507848,
"reviewer": [
{
"reviewer_name": "Jane Doe",
"reviewer_affiliation": "Seven Bridges Genomics",
"reviewer_email": "example@sevenbridges.com",
"reviewer_contribution": "curatedBy",
"reviewer_orcid": "https://orcid.org/0000-0000-0000-0000"
}
]
},
{
"status": "approved",
"reviewer_comment": "The revised BCO looks fine",
"date": 1513110648,
"reviewer": [
{
"reviewer_name": "John Doe",
"reviewer_affiliation": "U.S. Food and Drug Administration",
"reviewer_email": "example@fda.gov",
"reviewer_contribution": "curatedBy",
"reviewer_orcid": "NA"
}
]
}
],
"derived_from": "https://github.com/biocompute-objects/BCO_Specification/blob/1.2.1-beta/HCV1a.json",
"obsolete_after": "2018-11-12T12:30:48-0500",
"embargo": ["2017-10-12T12:30:48-0500", "2017-11-12T12:30:48-0500"],
"created": "2017-01-20T09:40:17-0500",
"modified": "2019-05-10T09:40:17-0500",
"contributors": [
{
"name": "Jane Doe",
"affiliation": "Seven Bridges Genomics",
"email": "example@sevenbridges.com",
"contribution": ["createdBy", "curatedBy"],
"orcid": "https://orcid.org/0000-0000-0000-0000"
},
{
"name": "John Doe",
"affiliation": "U.S. Food and Drug Administration",
"email": "example@fda.gov",
"contribution": "authoredBy",
"orcid": "NA"
}
],
"license": "https://creativecommons.org/licenses/by/4.0/"
},
"usability_domain": ["Identify baseline single nucleotide polymorphisms (SNPs)[SO:0000694], (insertions)[SO:0000667], and (deletions)[SO:0000045] that correlate with reduced (ledipasvir)[pubchem.compound:67505836] antiviral drug efficacy in (Hepatitis C virus subtype 1)[taxonomy:31646]", "Identify treatment emergent amino acid (substitutions)[SO:1000002] that correlate with antiviral drug treatment failure", "Determine whether the treatment emergent amino acid (substitutions)[SO:1000002] identified correlate with treatment failure involving other drugs against the same virus"],
"extension_domain": {
"fhir_extension": {
"fhir_endpoint": "https://fhirtest.uhn.ca/baseDstu3",
"fhir_version": "3",
"fhir_resources": [
[
{
"fhir_id": "21376",
"fhir_resource": "Sequence"
}
],
[
{
"fhir_id": "6288583",
"fhir_resource": "DiagnosticReport"
}
],
[
{
"fhir_id": "25544",
"fhir_resource": "ProcedureRequest"
}
],
[
{
"fhir_id": "92440",
"fhir_resource": "Observation"
}
],
[
{
"fhir_id": "4588936",
"fhir_resource": "FamilyMemberHistory"
}
]
]
},
"scm_extension": {
"scm_repository": "https://github.com/example/repo1",
"scm_type": "git",
"scm_commit": "c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21",
"scm_path": "workflow/hive-viral-mutation-detection.cwl",
"scm_preview": "https://github.com/example/repo1/blob/c9ffea0b60fa3bcf8e138af7c99ca141a6b8fb21/workflow/hive-viral-mutation-detection.cwl"
}
},
"description_domain": {
"keywords": ["HCV1a", "Ledipasvir", "antiviral resistance", "SNP", "amino acid substitutions"],
"xref": [
{
"namespace": "pubchem.compound",
"name": "PubChem-compound",
"ids": "67505836",
"access_time": "2017-01-20T09:40:17-0500"
},
{
"namespace": "pubmed",
"name": "PubMed",
"ids": "26508693",
"access_time": "2017-01-21T09:40:17-0500"
},
{
"namespace": "so",
"name": "Sequence Ontology",
"ids": ["SO:000002", "SO:0000694", "SO:0000667", "SO:0000045"],
"access_time": "2017-01-22T09:40:17-0500"
},
{
"namespace": "taxonomy",
"name": "Taxonomy",
"ids": "31646",
"access_time": "2017-01-23T09:40:17-0500"
}
],
"platform": [
"Seven Bridges Platform"
],
"pipeline_steps": [
{
"step_number": "1",
"name": "HIVE-hexagon",
"description": "Alignment of reads to a set of references",
"version": "1.3",
"prerequisite": [
{
"name": "Hepatitis C virus genotype 1",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus type 1b complete genome",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/5420376",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus (isolate JFH-1) genomic RNA",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/13122261",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus clone J8CF, complete genome",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/386646758",
"access_time": "2017-01-24 09:40:17"
}
},
{
"name": "Hepatitis C virus S52 polyprotein gene",
"uri": {
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/295311559",
"access_time": "2017-01-24 09:40:17"
}
}
],
"input_list": [
{
"uri": "https://example.com/dna.cgi?cmd=objFile&ids=514683",
"access_time": "2017-01-24 09:40:17"
},
{
"uri": "https://example.com/dna.cgi?cmd=objFile&ids=514682",
"access_time": "2017-01-24 09:40:17"
}
],
"output_list": [
{
"uri": "https://example.com/data/514769/allCount-aligned.csv",
"access_time": "2017-01-24 09:40:17"
},
{
"uri": "https://example.com/data/514801/SNPProfile*.csv",
"access_time": "2017-01-24 09:40:17"
}
]
}
]
},
"execution_domain": {
"script": [
"https://example.com/workflows/antiviral_resistance_detection_hive.py"
],
"script_driver": "shell",
"software_prerequisites": [
{
"name": "HIVE-hexagon",
"version": "babajanian.1",
"uri": [
{
"uri": "https://example.com/dna.cgi?cmd=dna-hexagon&cmdMode=-",
"access_time": "2017-01-24 09:40:17",
"sha1_chksum": "d60f506cddac09e9e816531e7905ca1ca6641e3c"
}
]
},
{
"name": "HIVE-heptagon",
"version": "albinoni.2",
"uri": [
{
"uri": "https://example.com/dna.cgi?cmd=dna-heptagon&cmdMode=-",
"access_time": "2017-01-24 09:40:17",
"sha1_chksum": "NA"
}
]
}
],
"external_data_endpoints": [
[
{
"name": "generic name",
"url": "protocol://domain:port/application/path"
}
],
[
{
"name": "access to ftp server",
"url": "ftp://data.example.com:21/"
}
],
[
{
"name": "access to e-utils web service",
"url": "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
}
]
],
"environment_variables": {
"HOSTTYPE": "x86_64-linux",
"EDITOR": "vim"
}
},
"parametric_domain": [
{
"param": "seed",
"value": "14",
"step": "1"
},
{
"param": "minimum_match_len",
"value": "66",
"step": "1"
},
{
"param": "divergence_threshold_percent",
"value": "0.30",
"step": "1"
},
{
"param": "minimum_coverage",
"value": "15",
"step": "2"
},
{
"param": "freq_cutoff",
"value": "0.10",
"step": "2"
}
],
"io_domain": {
"input_subdomain": [
{
"uri": [
{
"filename": "Hepatitis C virus genotype 1",
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/22129792",
"access_time": "2017-01-24T09:40:17-0500"
}
]
},
{
"uri": [
{
"filename": "Hepatitis C virus type 1b complete genome",
"uri": "https://www.ncbi.nlm.nih.gov/nuccore/5420376",
"access_time": "2017-01-24T09:40:17-0500"
}
]
}
],
"output_subdomain": [
{
"mediatype": "text/csv",
"uri": [
{
"uri": "https://example.com/data/514769/dnaAccessionBased.csv",
"access_time": "2017-01-24T09:40:17-0500"
}
]
},
{
"mediatype": "text/csv",
"uri": [
{
"uri": "https://example.com/data/514801/SNPProfile*.csv",
"access_time": "2017-01-24T09:40:17-0500"
}
]
}
]
},
"error_domain": {
"empirical_error": {
"false_negative_alignment_hits": "<0.0010",
"false_discovery": "<0.05"
},
"algorithmic_error": {
"false_positive_mutation_calls": "<0.00005",
"false_discovery": "0.005"
}
}
}