From 43d7264dda8061a024befbc9ca0a89d7159b1e40 Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Fri, 6 Nov 2020 09:52:32 +0000
Subject: UTHSC upload info

---
 doc/blog/using-covid-19-pubseq-part3.org |  3 +-
 scripts/uthsc_samples/.gitignore         |  1 +
 scripts/uthsc_samples/template.yaml      | 35 ++++++++++++++++++++
 scripts/uthsc_samples/uthsc_samples.py   | 57 ++++++++++++++++++++++++++++++++
 4 files changed, 95 insertions(+), 1 deletion(-)
 create mode 100644 scripts/uthsc_samples/.gitignore
 create mode 100644 scripts/uthsc_samples/template.yaml
 create mode 100644 scripts/uthsc_samples/uthsc_samples.py

diff --git a/doc/blog/using-covid-19-pubseq-part3.org b/doc/blog/using-covid-19-pubseq-part3.org
index f3ba073..d0d6c7f 100644
--- a/doc/blog/using-covid-19-pubseq-part3.org
+++ b/doc/blog/using-covid-19-pubseq-part3.org
@@ -255,7 +255,8 @@ more metadata is yummy when stored in RDF. [[https://yummydata.org/][Yummydata]]
 that many of the terms in above example are URIs, such as
 host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606.  We use
 web ontologies for these to make the data less ambiguous and more
-FAIR. Check out the option fields as defined in the schema. If it is not listed
+FAIR. Check out the option fields as defined in the schema. If it is not listed,
+check the [[https://github.com/arvados/bh20-seq-resource/blob/master/semantic_enrichment/labels.ttl][labels.ttl]] file. Also,
 a little bit of web searching may be required or [[./contact][contact]] us.
 
 ** Run the uploader (CLI)
diff --git a/scripts/uthsc_samples/.gitignore b/scripts/uthsc_samples/.gitignore
new file mode 100644
index 0000000..8786e3f
--- /dev/null
+++ b/scripts/uthsc_samples/.gitignore
@@ -0,0 +1 @@
+yaml
diff --git a/scripts/uthsc_samples/template.yaml b/scripts/uthsc_samples/template.yaml
new file mode 100644
index 0000000..1175ac8
--- /dev/null
+++ b/scripts/uthsc_samples/template.yaml
@@ -0,0 +1,35 @@
+id: placeholder
+
+license:
+    license_type: http://creativecommons.org/licenses/by/4.0/
+    title: "$sample_name - $locationx"
+    attribution_name: "Mariah Taylor, Colleen Jonsson"
+    attribution_url: https://www.uthsc.edu/medicine/molecular-sciences/faculty-directory/jonsson.php
+
+host:
+    host_id: "$sample_id"
+    host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606
+
+sample:
+    sample_id: "$sample_id"
+    specimen_source: [http://purl.obolibrary.org/obo/NCIT_C155831]
+    collection_date: "$collection_date"
+    collection_location: $location
+
+virus:
+    virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049
+    virus_strain: "$strain"
+
+technology:
+    sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632]
+    sequence_assembly_method: https://bio.tools/BWA#!
+    additional_technology_information: Oxford Nanopore MiniIon RNA long reads
+
+submitter:
+    authors: [Mariah Taylor, Colleen Jonsson]
+    submitter_name: [Mariah Taylor, Colleen B. Jonsson, Pjotr Prins]
+    submitter_address: UTHSC, Memphis, Tennessee 38163, USA
+    originating_lab: Regional Biocontainment Laboratory, Memphis, TN
+    provider_sample_id: $sample_id
+    submitter_sample_id: $sample_id
+    submitter_orcid: [https://orcid.org/0000-0002-2640-7672,https://orcid.org/0000-0002-8021-9162]
diff --git a/scripts/uthsc_samples/uthsc_samples.py b/scripts/uthsc_samples/uthsc_samples.py
new file mode 100644
index 0000000..5c39398
--- /dev/null
+++ b/scripts/uthsc_samples/uthsc_samples.py
@@ -0,0 +1,57 @@
+import os
+import pandas as pd
+from string import Template
+from dateutil.parser import parse
+import re
+
+import sys
+
+# Metadata in tabular format in a spreadsheet(?!)
+xlsx = '../../test/data/10_samples.xlsx'
+
+# Template in a text file
+template_yaml = 'template.yaml'
+
+dir_output = 'yaml'
+
+if not os.path.exists(dir_output):
+    os.makedirs(dir_output)
+
+table = pd.read_excel(xlsx)
+
+print(table)
+
+for index, row in table.iterrows():
+    sample = row['Sample ID']
+    print(f"Processing sample {sample}...")
+
+    with open(template_yaml) as f:
+      text = Template(f.read())
+      with open(os.path.join(dir_output,f"{sample}.yaml"), 'w') as fw:
+          sample_id = sample
+          sample_name = sample
+          collection_date = parse(str(row['Collection Date'])).strftime('%Y-%m-%d')
+          locationx = row['City']+", "+row['State']+", USA"
+          location = "https://www.wikidata.org/wiki/Q16563" # Memphis by default
+          map = {
+              "Pegram": "https://www.wikidata.org/wiki/Q3289517",
+              "Alexander": "https://www.wikidata.org/wiki/Q79663",
+              "Smithville": "https://www.wikidata.org/wiki/Q2145339",
+              "Nashville": "https://www.wikidata.org/wiki/Q23197",
+              "Madison": "https://www.wikidata.org/wiki/Q494755"
+              }
+
+          for name in map:
+              p = re.compile(name)
+              if p.match(locationx):
+                  location = map[name]
+                  break
+
+          strain = f"SARS-CoV-2/human/USA/{sample}/2020"
+          fw.write(text.substitute(sample_id=sample_id,
+                                   sample_name=sample_name,
+                                   collection_date=collection_date,
+                                   location=location,
+                                   locationx=locationx,
+                                   strain=strain
+                                   ))
-- 
cgit v1.2.3