better error messages when problems with barcode_runs (#101)

* better error messages when problems with `barcode_runs`

* `black` formatting w newer version of `black`

CHANGELOG.md

@@ -1,5 +1,8 @@
 # CHANGELOG
 
+#### version 3.6.1
+- Better error messages with problems with `barcode_runs`
+
 ### version 3.6.0
 - Add `func_effect_diffs` option to compare differences among functional effects.
 - Update environment:

Snakefile

@@ -1,6 +1,5 @@
 """Top-level ``snakemake`` file that runs analysis."""
 
-
 import collections
 import itertools
 import os
@@ -27,8 +26,13 @@ else:
     )
     if not set(barcode_run_req_cols).issubset(barcode_runs.columns):
         raise ValueError(f"{barcode_runs.columns=} missing {barcode_run_req_cols=}")
-assert len(barcode_runs) == barcode_runs["sample"].nunique()
-assert barcode_runs[barcode_run_req_cols].notnull().all().all()
+if len(barcode_runs) != barcode_runs["sample"].nunique():
+    raise ValueError(
+        "`barcode_runs` contains duplicated (non-unique) samples:\n"
+        + str(barcode_runs.groupby("sample").size().sort_values(ascending=False))
+    )
+if not barcode_runs[barcode_run_req_cols].notnull().all().all():
+    raise ValueError(f"{barcode_run_req_cols=} not all non-null")
 
 # check no FASTQ assigned to multiple samples
 dup_fastq_R1 = (

antibody_escape.smk

@@ -5,7 +5,6 @@ Note that these rules can analyze arbitrary assays. Throughout the workflow, the
 
 """
 
-
 # read the config for antibody escape
 with open(config["antibody_escape_config"]) as f:
     antibody_escape_config = yaml.safe_load(f)

build_variants.smk

@@ -1,6 +1,5 @@
 """``snakemake`` files with rules for building variants."""
 
-
 build_variants_docs = {}
 
 

count_variants.smk

@@ -1,6 +1,5 @@
 """``snakemake`` files with rules for counting variants from barcode sequencing."""
 
-
 # Names and values of files to add to docs
 count_variants_docs = {
     "Analysis notebooks": collections.defaultdict(dict),

func_effects.smk

@@ -1,6 +1,5 @@
 """``snakemake`` files with rules for calculating functional effects."""
 
-
 # read the config for func effects
 with open(config["func_effects_config"]) as f:
     func_effects_config = yaml.safe_load(f)

notebooks/build_codon_variants.ipynb

@@ -574,9 +574,11 @@
     "        ),\n",
     "        y=alt.Y(\"percent\", title=\"% variants with mutation\"),\n",
     "        tooltip=[\n",
-    "            alt.Tooltip(c, format=\".3g\")\n",
-    "            if c in {\"percent\", \"count\", \"n_variants\"}\n",
-    "            else c\n",
+    "            (\n",
+    "                alt.Tooltip(c, format=\".3g\")\n",
+    "                if c in {\"percent\", \"count\", \"n_variants\"}\n",
+    "                else c\n",
+    "            )\n",
     "            for c in site_freqs.columns\n",
     "        ],\n",
     "    )\n",

notebooks/summary.ipynb

@@ -902,9 +902,11 @@
     "        ),\n",
     "        color=alt.Color(\n",
     "            f\"{antibody_set} escape_floored:Q\",\n",
-    "            title=f\"{antibody_set} escape\"\n",
-    "            if len(antibody_set) < 14\n",
-    "            else [antibody_set, \"escape\"],\n",
+    "            title=(\n",
+    "                f\"{antibody_set} escape\"\n",
+    "                if len(antibody_set) < 14\n",
+    "                else [antibody_set, \"escape\"]\n",
+    "            ),\n",
     "            legend=legend,\n",
     "            scale=alt.Scale(\n",
     "                zero=True,\n",

scripts/build_docs.py

@@ -1,6 +1,5 @@
 """Implements ``snakemake`` rule to translate gene sequence."""
 
-
 import os
 import sys
 

scripts/count_barcodes.py

@@ -1,6 +1,5 @@
 """Count variants from Illumina barcodes."""
 
-
 import os
 import sys
 

scripts/format_altair_html.py

@@ -4,7 +4,6 @@
 
 """
 
-
 import argparse
 
 from bs4 import BeautifulSoup as bs

scripts/func_scores.py

@@ -1,6 +1,5 @@
 """Get functional scores from barcode counts."""
 
-
 import sys
 
 import alignparse.utils

scripts/gene_sequence.py

@@ -1,6 +1,5 @@
 """Implements ``snakemake`` rule to get gene sequence."""
 
-
 import sys
 
 import Bio.SeqIO

scripts/prob_escape.py

@@ -1,6 +1,5 @@
 """Get probabilities (fraction) of antibody escape from variant counts."""
 
-
 import sys
 
 import Bio.SeqIO

scripts/translate_geneseq.py

@@ -1,6 +1,5 @@
 """Implements ``snakemake`` rule to translate gene sequence."""
 
-
 import sys
 
 import Bio.SeqIO

test_example/scripts/spatial_distances.py

@@ -1,6 +1,5 @@
 """Implements ``snakemake`` rule `spatial_distances`"""
 
-
 import sys
 import urllib