From b7ceab8473160070507cbb7c9bf6da1e78e4b1a3 Mon Sep 17 00:00:00 2001
From: Ulthran <ctbushman@gmail.com>
Date: Tue, 6 Aug 2024 15:08:29 -0400
Subject: [PATCH] Adjust tests for vsearch

---
 .tests/e2e/test_full_run.py | 43 ++++++-------------------------------
 README.md                   |  6 ++++--
 config.yml                  |  2 +-
 sbx_vsearch.smk             |  2 +-
 4 files changed, 13 insertions(+), 40 deletions(-)

diff --git a/.tests/e2e/test_full_run.py b/.tests/e2e/test_full_run.py
index aeb0d2e..d51d976 100644
--- a/.tests/e2e/test_full_run.py
+++ b/.tests/e2e/test_full_run.py
@@ -9,8 +9,7 @@
 @pytest.fixture
 def setup(tmpdir):
     reads_fp = Path(".tests/data/reads/").resolve()
-    hosts_fp = Path(".tests/data/hosts/").resolve()
-    db_fp = Path(".tests/data/db/").resolve()
+    db_fp = Path(".tests/data/ref/").resolve()
 
     project_dir = tmpdir / "project"
 
@@ -18,20 +17,7 @@ def setup(tmpdir):
 
     config_fp = project_dir / "sunbeam_config.yml"
 
-    config_str = f"sbx_kraken: {{kraken_db_fp: {db_fp}}}"
-    sp.check_output(
-        [
-            "sunbeam",
-            "config",
-            "modify",
-            "-i",
-            "-s",
-            f"{config_str}",
-            f"{config_fp}",
-        ]
-    )
-
-    config_str = f"qc: {{host_fp: {hosts_fp}}}"
+    config_str = f"sbx_vsearch: {{db_fp: {db_fp}}}"
     sp.check_output(
         [
             "sunbeam",
@@ -63,7 +49,7 @@ def run_sunbeam(setup):
                 "conda",
                 "--profile",
                 project_dir,
-                "all_classify",
+                "all_vsearch",
                 "--directory",
                 tmpdir,
             ]
@@ -84,24 +70,9 @@ def run_sunbeam(setup):
 def test_full_run(run_sunbeam):
     output_fp, benchmarks_fp = run_sunbeam
 
-    all_samples_fp = output_fp / "classify" / "kraken" / "all_samples.tsv"
+    long_report_fp = output_fp / "mapping" / "vsearch" / "LONG_report.tsv"
+    long_fasta_fp = output_fp / "mapping" / "vsearch" / "LONG.fasta"
 
     # Check output
-    assert all_samples_fp.exists()
-
-    with open(all_samples_fp) as f:
-        header_line = f.readline()
-        print(f"Header line: {header_line}")
-        assert "TEST-taxa" in header_line
-        assert "EMPTY-taxa" in header_line
-        assert "Consensus Lineage" in header_line
-        test_index = header_line.split("\t").index("TEST-taxa")
-        empty_index = header_line.split("\t").index("EMPTY-taxa")
-
-        lines = f.readlines()
-        print(lines)
-        for line in lines:
-            if line[0] == "2":
-                fields = line.split("\t")
-                assert int(fields[empty_index]) == 0
-                assert int(fields[test_index]) > 0
+    assert long_report_fp.exists()
+    assert long_fasta_fp.exists()
diff --git a/README.md b/README.md
index 65a698d..7aa5ca3 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,9 @@
 # sbx_vsearch
 
 <!-- badges: start -->
-
+[![Tests](https://github.com/sunbeam-labs/sbx_vsearch/actions/workflows/pr.yml/badge.svg)](https://github.com/sunbeam-labs/sbx_vsearch/actions/workflows/pr.yml)
+[![Release](https://img.shields.io/github/release/sunbeam-labs/sbx_vsearch.svg?style=flat)](https://github.com/sunbeam-labs/sbx_vsearch/releases/latest)
+[![DockerHub](https://img.shields.io/docker/pulls/sunbeamlabs/sbx_vsearch)](https://hub.docker.com/repository/docker/sunbeamlabs/sbx_vsearch/)
 <!-- badges: end -->
 
 A [Sunbeam](https://github.com/sunbeam-labs/sunbeam) extension for using [Vsearch](https://github.com/torognes/vsearch) with the `--usearch-global` option to do alignment of reads to any fasta file. 
@@ -27,7 +29,7 @@ N.B. For sunbeam versions <4 the last command will be something like `sunbeam ru
 
 ## Configuration
 
-  - db: Is the filepath to a directory containing reference fasta files
+  - db_fp: Is the filepath to a directory containing reference fasta files
   - threads: Is the number of threads to use while running vsearch
   - min_id: Is the minimum identity for query-target match
   - weak_id: Is the set lower than min-id and you will get some weaker matches too
diff --git a/config.yml b/config.yml
index 3a2356c..3e342fb 100644
--- a/config.yml
+++ b/config.yml
@@ -1,5 +1,5 @@
 sbx_vsearch:
-  db: ""
+  db_fp: ""
   threads: 4
   min_id: 0.85 #minimum identity for query-target match
   weak_id: 0.85 #set lower than min-id and you will get some weaker matches too
diff --git a/sbx_vsearch.smk b/sbx_vsearch.smk
index 195dd5f..3bc41f1 100644
--- a/sbx_vsearch.smk
+++ b/sbx_vsearch.smk
@@ -46,7 +46,7 @@ rule fq_2_fa:
 rule run_vsearch:
     input:
         query=str(MAPPING_FP / "R1" / "{sample}_1.fasta"),
-        db=str(Cfg["sbx_vsearch"]["db"]),
+        db=str(Cfg["sbx_vsearch"]["db_fp"]),
     output:
         reports=str(MAPPING_FP / "vsearch" / "{sample}_report.tsv"),
         alignments=str(MAPPING_FP / "vsearch" / "{sample}.fasta"),