Release 0.7.2

assembly_finder/assembly_finder.VERSION

@@ -1 +1 @@
-0.7.1
+0.7.2

assembly_finder/workflow/envs/taxonkit.yml

@@ -1,4 +1,4 @@
-name: ncbi-datasets-cli
+name: taxonkit
 channels:
   - conda-forge
   - bioconda

assembly_finder/workflow/rules/download.smk

@@ -1,6 +1,6 @@
 rule download_taxdump:
     output:
-        temp(os.path.join(TAXONKIT, "taxdump.tar.gz")),
+        os.path.join(TAXONKIT, "taxdump.tar.gz"),
     log:
         os.path.join(dir.out.logs, "curl.log"),
     conda:
@@ -200,7 +200,7 @@ rule unzip_archive:
     input:
         os.path.join(dir.out.base, "archive.zip"),
     output:
-        temp(directory(os.path.join(dir.out.base, "archive"))),
+        directory(os.path.join(dir.out.base, "archive")),
     log:
         os.path.join(dir.out.logs, "unzip.log"),
     conda:
@@ -283,8 +283,9 @@ rule add_genome_paths:
         df.to_csv(output[0], sep="\t", index=None)
 
 
-rule cleanup_reports:
+rule cleanup_files:
     input:
+        os.path.join(dir.out.base, "archive"),
         os.path.join(dir.out.base, "assembly_summary.tsv"),
         os.path.join(dir.out.base, "sequence_report.tsv"),
         os.path.join(dir.out.base, "taxonomy.tsv"),
@@ -296,6 +297,7 @@ rule cleanup_reports:
         os.path.join(dir.env, "utils.yml")
     shell:
         """
+        rm -rf {input[0]}
         find {params[0]} -name "*.json*" -print0 | xargs -0 rm
         touch {output}
         """

docs/examples.md

@@ -1,20 +1,43 @@
+## Small datasets
+
+### Staphylococcus aureus reference genome
+
+```sh
+assembly_finder -i staphylococcus_aureus --source refseq -nb 1
+```
+
+### Download from a list of taxons
+
+```sh
+assembly_finder -i 1290,1813735,114185 -o test -nb 1
+```
+
+## Big datasets
+
 !!! warning
+
     These examples are for big datasets downloads, so using an NCBI api-key is highly recommended
 
-## Best ranking genome for each bacteria species
+### Download all chlamydia genomes
+
+```sh
+assembly_finder -i chlamydia --api-key <api-key>
+```
+
+### Best ranking genome for each bacteria species
 
 ```sh
 assembly_finder -i bacteria --api-key <api-key> --rank species --nrank 1
 ```
 
-## Complete RefSeq bacteria viruses and archaea (excluding metagenomes and atypical genomes)
+### Complete RefSeq bacteria viruses and archaea <small>(excluding MAGs and atypical)</small>
 
 ```sh
 assembly_finder -i bacteria,viruses,archaea -o outdir --api-key <api-key> --source refseq --assembly-level complete --mag exclude --atypical
 ```
 
-## Download sequences from a specific bioproject 
+### Specific bioproject
 
 ```sh
-assembly_finder -i PRJNA289059 --accession
+assembly_finder -i PRJNA289059 --api-key <api-key> --accession
 ```

docs/inputs.md

@@ -1,31 +1,45 @@
 # Inputs
+
 Input can be either a string or a table, and queries can be either taxa or accession as shown in [NCBI datasets docs](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/download-and-install).
+
 ## Strings
+
 === "Taxons"
+
     !!! note
+
         Taxons can be either taxids or taxon names
 
-    ``` sh
+    ```sh
     assembly_finder -i 1290,staphylococcus_aureus,562 -nb 1 -o taxons
     ```
+
 === "Accessions"
-    ``` sh
+
+    ```sh
     assembly_finder --accession -i GCF_003812505.1,GCF_000418345.1,GCF_000157115.2 -o accessions
     ```
 
 ## Tables
+
 === "Taxons"
-    | taxon                 | nb  |
+
+    !!! note
+        You can set the number of genomes per taxon in the table
+
+    | taxon | nb |
     | :-------------------- | :-- |
-    | 1290                  | 1   |
-    | staphylococcus_aureus | 1   |
-    | 562                   | 1   |
+    | 1290 | 1 |
+    | staphylococcus_aureus | 1 |
+    | 562 | 1 |
 
 === "Accessions"
+
     !!! note
+
         The accession table does not have a header
+
     | GCF_003812505.1 |
     | :-------------- |
     | GCF_000418345.1 |
     | GCF_000157115.2 |
-