add hmm-file and pfam-accession artifacts

rel #2244

anvio/docs/__init__.py

@@ -377,11 +377,23 @@
         "provided_by_anvio": True,
         "provided_by_user":True
     },
+    "pfam-accession": {
+        "name": "PFAM ACCESSION",
+        "type": "TXT",
+        "provided_by_anvio": False,
+        "provided_by_user": True
+    },
+    "hmm-file": {
+        "name": "HMM MODEL FILE",
+        "type": "TXT",
+        "provided_by_anvio": False,
+        "provided_by_user": True
+    },
     "hmm-source": {
         "name": "HMM SOURCE",
         "type": "HMM",
         "provided_by_anvio": False,
-        "provided_by_user":True
+        "provided_by_user": True
     },
     "hmm-hits": {
         "name": "HMM PROFILE",

anvio/docs/artifacts/hmm-file.md

@@ -0,0 +1,3 @@
+A flat text HMM that literally desribes the properties of the model and lists transition probabilities.
+
+Such files are typically generated by the program `hmmbuild` (which is a part of the [HMMER](http://hmmer.org/) package and installed in every anvi'o environment) from FASTA files of aligned sequnces.

anvio/docs/artifacts/pfam-accession.md

@@ -0,0 +1,3 @@
+One or more accession numbers that match to valid entries in the [Pfam database](https://www.ebi.ac.uk/interpro/entry/pfam/).
+
+Such as [PF00001](https://www.ebi.ac.uk/interpro/entry/pfam/PF00001/) or [PF14437](https://www.ebi.ac.uk/interpro/entry/pfam/PF14437/).

sandbox/anvi-script-gen-defense-finder-models-to-hmm-directory

@@ -21,7 +21,7 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __authors__ = ['ge0rges']
 __provides__ = ["hmm-source"]
-__requires__ = ["hmm"]
+__requires__ = []
 __description__ = ("This program generates an anvi'o compatible HMM directory to be used with `anvi-run-hmms` "
                    "from the MDMParis Defense Finder Models.")
 

sandbox/anvi-script-hmm-to-hmm-directory

@@ -18,8 +18,8 @@ __credits__ = []
 __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __authors__ = ['ge0rges']
+__requires__ = ["hmm-file"]
 __provides__ = ["hmm-source"]
-__requires__ = ["hmm"]
 __description__ = ("You give this program one or more HMM files from `hmmbuild`, and it generates "
                    "an anvi'o compatible HMM directory to be used with `anvi-run-hmms`")
 

sandbox/anvi-script-pfam-accessions-to-hmms-directory

@@ -17,8 +17,8 @@ __credits__ = []
 __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __authors__ = ['meren']
+__requires__ = ["pfam-accession"]
 __provides__ = ["hmm-source"]
-__requires__ = []
 __description__ = ("You give this program one or more PFAM accession ids, and it generates "
                    "an anvi'o compatible HMM directory to be used with `anvi-run-hmms`")
 
@@ -76,7 +76,7 @@ def main(args):
         except:
             failed_accession_ids.add(pfam_accession)
             continue
-        
+
         try:
             data_dict[pfam_accession] = {}
             data_dict[pfam_accession]['ga'] = utils.get_attribute_from_hmm_file(fp, 'GA ')
@@ -87,7 +87,7 @@ def main(args):
         except ValueError:
             run.warning(f"The PFAM accession {pfam_accession} could not be included due to a missing attribute. "
                         f"Anvi'o will continue without it")
-        
+
     progress.end()
 
     if len(failed_accession_ids):
@@ -154,11 +154,11 @@ if __name__ == '__main__':
     parser = ArgumentParser(description=__description__)
 
     parser.add_argument('--pfam-accessions-list', nargs='+', help="One or more PFAM accession IDs "
-                "(such as PF14437.6). If you have multiple accessions, you can separate them from "
+                "(such as PF14437). If you have multiple accessions, you can separate them from "
                 "each other with a space. If you have too many, consider using the "
                 "`--pfam-accessions-file` parameter instead.", metavar='PFAM_ACCESSION')
     parser.add_argument('--pfam-accessions-file', help="A single column text file where each column "
-                "is a single PFAM accession ID (such as PF14437.6). You may have as many accession "
+                "is a single PFAM accession ID (such as PF14437). You may have as many accession "
                 "ids as you like in this file.", metavar='FILE')
     parser.add_argument('-O', '--output-directory', metavar='PATH', help="Output directory for the "
                 "anvi'o-formatted HMMs. Choose the name wisely as this will be the name that will "