Update cd-hit and mmseq installation8

.github/workflows/main.yml

@@ -50,7 +50,7 @@ jobs:
         sudo apt-get update
         sudo apt-get install -y mmseqs2
 
-    - name: Install cd-hit (Windows)
+ - name: Install cd-hit (Windows)
       if: runner.os == 'Windows'
       run: |
         curl -L -o cd-hit.tar.gz https://github.com/weizhongli/cdhit/releases/download/V4.8.1/cd-hit-v4.8.1-2019-0228.tar.gz
@@ -70,10 +70,10 @@ jobs:
       run: echo $PATH
 
     - name: Check cd-hit Installation
-      run: cd-hit -h
+      run: which cd-hit || true
 
     - name: Check mmseqs2 Installation
-      run: mmseqs -h
+      run: which mmseqs || true
 
     - name: Run Tests
       run: pytest tests

aaanalysis/data_handling/_seq_preproc.py

@@ -29,9 +29,10 @@ def check_match_list_seq_alphabet(list_seq=None, alphabet=None):
         raise ValueError(f"Following amino acid(s) from 'list_seq' are not in 'alphabet': {invalid_chars}")
 
 
-def check_match_gap_alphabet():
-    """"""
-
+def check_match_gap_alphabet(gap="_", alphabet=None):
+    """Check that gap is not in alphabet"""
+    if gap in alphabet:
+        raise ValueError(f"'gap' ('{gap}') should not be contained in the 'alphabet' ('{alphabet}')")
 
 
 # II Main Functions
@@ -77,8 +78,9 @@ def encode_one_hot(list_seq: Union[List[str], str] = None,
                                       check_all_str_or_convertible=True,
                                       accept_none=False, accept_str=True)
         ut.check_str(name="alphabet", val=alphabet, accept_none=False)
-        ut.check_str(name="gap", val=gap, accept_none=False)
+        check_gap(gap=gap)
         ut.check_str_options(name="pad_at", val=pad_at, list_str_options=["N", "C"])
+        check_match_gap_alphabet(gap=gap, alphabet=alphabet)
         check_match_list_seq_alphabet(list_seq=list_seq, alphabet=alphabet)
         # Create encoding
         feature_matrix = encode_one_hot(list_seq=list_seq, alphabet=alphabet, gap=gap, pad_at=pad_at)