hotfix: log full name of directory if not found

main/COMO.ipynb

@@ -53,7 +53,7 @@
     "    3. Compare results between perturbed and unperturbed models (i.e., knocked-out models vs non-knocked-out models)\n",
     "    4. Integrate with disease genes and create a score of drug targets"
    ],
-   "id": "ea1c9614518c30bc"
+   "id": "90fba8b56a999517"
   },
   {
    "metadata": {},
@@ -223,7 +223,7 @@
     "    </tbody>\n",
     "</table>"
    ],
-   "id": "28d59417491e63db"
+   "id": "dcc8d38caab63fab"
   },
   {
    "metadata": {},
@@ -254,7 +254,7 @@
     "scrna_matrix_filepath = {context: Path(f\"data/results/{context}/scrna/scrna_{context}.csv\") for context in context_names}\n",
     "# scrna_matrix_filepath = [Path(f\"data/results/{context}/scrna/scrna_{context}.h5ad\") for context in context_names]\n"
    ],
-   "id": "18061578964ca096"
+   "id": "fd4c387eab48e9ee"
   },
   {
    "metadata": {},
@@ -266,7 +266,7 @@
     "- `taxon_id`: The [NCBI Taxon ID](https://www.ncbi.nlm.nih.gov/taxonomy) to use\n",
     "- `preprocess_mode`: This should be set to `\"create-matrix\"` if you are **not** providing a matrix, otherwise set it to `\"provide-matrix\"`"
    ],
-   "id": "b475e41b000d0cb5"
+   "id": "24a8475316ff6d70"
   },
   {
    "metadata": {},
@@ -291,7 +291,7 @@
     "        log_level=\"INFO\",\n",
     "    )"
    ],
-   "id": "dbfb32f2a0f7b8ef"
+   "id": "cb04960f17cc9b75"
   },
   {
    "metadata": {},
@@ -324,7 +324,7 @@
     "\n",
     "This method is not recommended, as zFPKM is much more robust for a similar level of \"hands-off\" model building\n"
    ],
-   "id": "a820a3985a2601c7"
+   "id": "4bd864328c93b27a"
   },
   {
    "metadata": {},
@@ -345,7 +345,7 @@
     "#### Single Cell RNA Sequencing\n",
     "While the Snakemake pipeline does not yet support single-cell alignment, and COMO does not yet support automated configuration file and counts matrix file creation for single-cell alignment output from STAR, it is possible to use single-cell data to create a model with COMO. Because normalization strategies can be applied to single-cell data in the same way it is applied to bulk RNA sequencing, `como/rnaseq_gen.py` can be used with a provided counts matrix and configuration file, from [Step 1](Step-1:-Initialize-and-Preprocess-RNA-seq-data), above. Just like `\"total\"` and `\"mRNA\"`, `como/rnaseq_gen.py` can be executed with `\"SC\"` as the \"`--library-prep`\" argument to help COMO differentiate it from any bulk RNA sequencing data if multiple strategies are being used."
    ],
-   "id": "a1d6608d045c7399"
+   "id": "e99e612919298aa8"
   },
   {
    "metadata": {},
@@ -364,7 +364,7 @@
     "- `min_zfpkm`: The cutoff for Counts-Per-Million filtering\n",
     "- `prep_method`: The library method used for preparation. Options are: `\"total\"`, `\"mRNA\"`, or `\"SC\"`,\n"
    ],
-   "id": "1fcf38e9cbc3de48"
+   "id": "8e550961a4a443b3"
   },
   {
    "metadata": {},
@@ -400,7 +400,7 @@
     "        cutoff=cutoff\n",
     "    )"
    ],
-   "id": "5a2e17b646d6de36"
+   "id": "d98c023e7738eb64"
   },
   {
    "metadata": {},
@@ -420,7 +420,7 @@
     "- `min_zfpkm`: The cutoff for Counts-Per-Million filtering\n",
     "- `prep_method`: The library method used for preparation. Options are: `\"total\"`, `\"mRNA\"`, or `\"SC\"`,\n"
    ],
-   "id": "87b5397301541650"
+   "id": "28848c3d315fa78c"
   },
   {
    "metadata": {},
@@ -456,7 +456,7 @@
     "        cutoff=cutoff\n",
     "    )"
    ],
-   "id": "3e73c07fa4a9e49a"
+   "id": "3e87f9890bc76e43"
   },
   {
    "metadata": {},
@@ -476,7 +476,7 @@
     "- `min_zfpkm`: The cutoff for Counts-Per-Million filtering\n",
     "- `prep_method`: The library method used for preparation. Options are: `\"total\"`, `\"mRNA\"`, or `\"scrna\"`,\n"
    ],
-   "id": "ae1278480199f415"
+   "id": "bfa9e2cd4152f961"
   },
   {
    "metadata": {},
@@ -512,7 +512,7 @@
     "        cutoff=cutoff\n",
     "    )"
    ],
-   "id": "567734d827571d6f"
+   "id": "c45085c6c12d9a3c"
   },
   {
    "metadata": {},
@@ -529,7 +529,7 @@
     "- `high_batch_ratio`: The ratio required before a gene is considered \"high-confidence\" in the study\n",
     "- `quantile`: The cutoff Transcripts-Per-Million quantile for filtering"
    ],
-   "id": "ea7004d23807dd1"
+   "id": "f01f21670b1e6956"
   },
   {
    "metadata": {},
@@ -556,7 +556,7 @@
     "        quantile=25,\n",
     "    )"
    ],
-   "id": "a7715d2cf9b0191a"
+   "id": "dcbae45189dd2eba"
   },
   {
    "metadata": {},
@@ -582,7 +582,7 @@
     "- `n_neighbors_context`: N nearest neighbors for context clustering. The default is `\"default\"`, which is the total number of contexts\n",
     "- `seed`: The random seed for clustering algorithm initialization. If not specified, `np.random.randint(0, 100000)` is used"
    ],
-   "id": "f4f395e25eeb1185"
+   "id": "354abde9f52ff9cf"
   },
   {
    "metadata": {},
@@ -626,7 +626,7 @@
     "\n",
     "!{cmd}"
    ],
-   "id": "cc61326b8df01fc4"
+   "id": "be527c98a8523323"
   },
   {
    "metadata": {},
@@ -666,7 +666,7 @@
     "\n",
     "Each of the \"weights\" (`total_rna_weight`, `mrna_weight`, etc.) are used to place a significance on each method. Becuase there are many steps in the Dogma from transcription to translation, the gene expression as seen by total RNA or mRNA sequencing may not be representative of the gene's protein expression, and this its metabolic impact. Because of this, you are able to weight each source more (or less) than another."
    ],
-   "id": "236fb36fa41f60b"
+   "id": "db0cfbec103d7d35"
   },
   {
    "metadata": {},
@@ -703,7 +703,7 @@
     "\n",
     "!{cmd}"
    ],
-   "id": "3ce78fc277c55885"
+   "id": "75b84df4d88d7cbe"
   },
   {
    "metadata": {},
@@ -770,7 +770,7 @@
     "- `force_reactions_filename`: The filename of the force reactions to be used. Force reactions will (as the name implies) force the optimizer to use these reactions, **no matter their expression**\n",
     "- `exclude_reactions_filename`: The filename of reactions to exclude from the model, no matter their expression"
    ],
-   "id": "b3a182617ff3eb7a"
+   "id": "30da70d405a80d23"
   },
   {
    "metadata": {},
@@ -839,7 +839,7 @@
     "        # fmt: on\n",
     "        !{cmd}"
    ],
-   "id": "e94c36e65ba46e38"
+   "id": "19918f482629d4fe"
   },
   {
    "metadata": {},
@@ -864,7 +864,7 @@
     "- `exampleTissue`: This is the name of the tissue context\n",
     "- `ALGORITHM`: This is the algorithm (`recon_algorithm`) used in the above model creation step\n"
    ],
-   "id": "47e3e576b43a040d"
+   "id": "38640adc60fe1909"
   },
   {
    "metadata": {},
@@ -941,7 +941,7 @@
     "\n",
     "        !{cmd}"
    ],
-   "id": "4a064f3322a3991e"
+   "id": "ef639305627a4a4"
   },
   {
    "metadata": {},
@@ -960,7 +960,7 @@
     "- `data_source`: The datasource you are using for disease analysis. This should be`\"rnaseq\"`\n",
     "- `taxon_id`: The [NCBI Taxon ID](https://www.ncbi.nlm.nih.gov/taxonomy) to use for disease analysis"
    ],
-   "id": "3aa49b19ab4fc4b9"
+   "id": "ad06b9e81d3d5f39"
   },
   {
    "metadata": {},
@@ -992,7 +992,7 @@
     "\n",
     "    !{cmd}"
    ],
-   "id": "7f946d38cac3a18c"
+   "id": "c9d0e6dfd35adefb"
   },
   {
    "metadata": {},
@@ -1027,7 +1027,7 @@
     "\n",
     "- `solver`: The solver you would like to use. Available options are `\"gurobi\"` or `\"glpk\"`\n"
    ],
-   "id": "feb9da60acb9a3b3"
+   "id": "7093fbd5a6551c18"
   },
   {
    "metadata": {},
@@ -1099,7 +1099,7 @@
     "            cmd = \" \".join(cmd)\n",
     "            !{cmd}"
    ],
-   "id": "c999b3f953381f9f"
+   "id": "281a24eba5e06fc9"
   }
  ],
  "metadata": {},

main/como/cluster_rnaseq.py

@@ -57,19 +57,13 @@ def __post_init__(self):  # noqa: C901, ignore too complex
         if 0 > self.min_distance > 1.0:
             raise ValueError("--min_dist must be a float between 0 and 1")
 
-        if (
-            isdigit(self.num_replicate_neighbors) and self.num_replicate_neighbors < 1
-        ) or self.num_replicate_neighbors != "default":
+        if (isdigit(self.num_replicate_neighbors) and self.num_replicate_neighbors < 1) or self.num_replicate_neighbors != "default":
             raise ValueError("--n-neighbors-rep must be either 'default' or an integer > 1")
 
-        if (
-            isdigit(self.num_batch_neighbors) and self.num_batch_neighbors < 1
-        ) or self.num_batch_neighbors != "default":
+        if (isdigit(self.num_batch_neighbors) and self.num_batch_neighbors < 1) or self.num_batch_neighbors != "default":
             raise ValueError("--n-neighbors-batch must be either 'default' or an integer > 1")
 
-        if (
-            isdigit(self.num_context_neighbors) and self.num_context_neighbors < 1
-        ) or self.num_context_neighbors != "default":
+        if (isdigit(self.num_context_neighbors) and self.num_context_neighbors < 1) or self.num_context_neighbors != "default":
             raise ValueError("--n-neighbors-context must be either 'default' or an integer > 1")
 
 

main/como/combine_distributions.py

@@ -59,12 +59,7 @@ def _merge_batch(wd, context, batch):
         zmat.columns = rep_names
 
         stack_df = pd.concat(
-            [
-                pd.DataFrame(
-                    {"entrez_gene_id": zmat["entrez_gene_id"], "zscore": zmat[col].astype(float), "source": col}
-                )
-                for col in zmat.columns[1:]
-            ]
+            [pd.DataFrame({"entrez_gene_id": zmat["entrez_gene_id"], "zscore": zmat[col].astype(float), "source": col}) for col in zmat.columns[1:]]
         )
 
         plot_name_png = wd / "figures" / f"plot_{context}_{Path(f).stem}.png"
@@ -108,9 +103,7 @@ def weighted_z(x):
 
         stack_df = pd.concat(
             [
-                pd.DataFrame(
-                    {"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col}
-                )
+                pd.DataFrame({"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col})
                 for col in merge_df.columns[1:]
             ]
         )
@@ -157,9 +150,7 @@ def weighted_z(x, n_reps):
 
         stack_df = pd.concat(
             [
-                pd.DataFrame(
-                    {"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col}
-                )
+                pd.DataFrame({"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col})
                 for col in merge_df.columns[1:]
             ]
         )
@@ -259,9 +250,7 @@ def weighted_z(x, weights):
 
     stack_df = pd.concat(
         [
-            pd.DataFrame(
-                {"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col}
-            )
+            pd.DataFrame({"entrez_gene_id": merge_df["entrez_gene_id"], "zscore": merge_df[col].astype(float), "source": col})
             for col in merge_df.columns[1:]
         ]
     )
@@ -343,11 +332,7 @@ def _combine_zscores(  # noqa: C901
                 num_reps.extend(res[1])
                 combine_z_matrix = _combine_batch_zdistro(trna_workdir, context, batch, z_matrix)
                 combine_z_matrix.columns = ["entrez_gene_id", batch]
-                merge_z_data = (
-                    combine_z_matrix
-                    if merge_z_data.empty
-                    else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
-                )
+                merge_z_data = combine_z_matrix if merge_z_data.empty else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
 
             comb_batches_z_trna = _combine_context_zdistro(trna_workdir, context, num_reps, merge_z_data)
             filename = trna_workdir / f"combined_zFPKM_{context}.csv"
@@ -369,11 +354,7 @@ def _combine_zscores(  # noqa: C901
                 num_reps.extend(res[1])
                 combine_z_matrix = _combine_batch_zdistro(mrna_workdir, context, batch, z_matrix)
                 combine_z_matrix.columns = ["entrez_gene_id", batch]
-                merge_z_data = (
-                    combine_z_matrix
-                    if merge_z_data.empty
-                    else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
-                )
+                merge_z_data = combine_z_matrix if merge_z_data.empty else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
 
             comb_batches_z_mrna = _combine_context_zdistro(mrna_workdir, context, num_reps, merge_z_data)
             filename = mrna_workdir / f"combined_zFPKM_{context}.csv"
@@ -395,11 +376,7 @@ def _combine_zscores(  # noqa: C901
                 num_reps.extend(res[1])
                 combine_z_matrix = _combine_batch_zdistro(scrna_workdir, context, batch, z_matrix)
                 combine_z_matrix.columns = ["entrez_gene_id", batch]
-                merge_z_data = (
-                    combine_z_matrix
-                    if merge_z_data.empty
-                    else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
-                )
+                merge_z_data = combine_z_matrix if merge_z_data.empty else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
 
             comb_batches_z_scrna = _combine_context_zdistro(scrna_workdir, context, num_reps, merge_z_data)
             filename = scrna_workdir / f"combined_zFPKM_{context}.csv"
@@ -421,11 +398,7 @@ def _combine_zscores(  # noqa: C901
                 num_reps.extend(res[1])
                 combine_z_matrix = _combine_batch_zdistro(protein_workdir, context, batch, z_matrix)
                 combine_z_matrix.columns = ["entrez_gene_id", batch]
-                merge_z_data = (
-                    combine_z_matrix
-                    if merge_z_data.empty
-                    else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
-                )
+                merge_z_data = combine_z_matrix if merge_z_data.empty else pd.merge(merge_z_data, combine_z_matrix, on="entrez_gene_id", how="outer")
 
             comb_batches_z_prot = _combine_context_zdistro(protein_workdir, context, num_reps, merge_z_data)
             filename = protein_workdir / f"combined_zscore_proteinAbundance_{context}.csv"
@@ -435,15 +408,8 @@ def _combine_zscores(  # noqa: C901
                 filename = protein_workdir / f"model_scores_{context}.csv"
                 comb_batches_z_prot.to_csv(filename, index=False)
 
-        if (
-            comb_batches_z_mrna is None
-            and comb_batches_z_trna is None
-            and comb_batches_z_scrna is None
-            and comb_batches_z_prot is None
-        ):
-            logger.critical(
-                f"The context '{context}' was found in the configuration file but no data was found on disk!"
-            )
+        if comb_batches_z_mrna is None and comb_batches_z_trna is None and comb_batches_z_scrna is None and comb_batches_z_prot is None:
+            logger.critical(f"The context '{context}' was found in the configuration file but no data was found on disk!")
             continue
 
         comb_omics_z = _combine_omics_zdistros(