add monomers placeholders

app.py

@@ -1,5 +1,12 @@
+from typing import List
+import numpy as np
 import gradio as gr
 
+from .data_utils import load_monomers
+
+
+monomers_list = load_monomers()
+
 
 def smiles2monomers(smiles: str) -> list[str]:
     """
@@ -8,11 +15,11 @@ def smiles2monomers(smiles: str) -> list[str]:
     return []
 
 
-def generate_monomers(num_monomers: int) -> list[str]:
+def generate_monomers(num_monomers: int, monomers_vocab: List[str]) -> list[str]:
     """
     Produces random list of monomers with num_monomers elements. Not implemented yet.
     """
-    return [f"M{i}" for i in range(num_monomers)]
+    return np.random.choice(monomers_vocab, num_monomers)
 
 
 def monomer2domains(monomer: str) -> list[str]:
@@ -40,7 +47,6 @@ def find_bacteria(monomers: list[str]) -> list[str]:
     return []
 
 
-
 def letter_counter(word, letter):
     """Count the occurrences of a specific letter in a word.
     

data/monomers_list.txt

@@ -0,0 +1,37 @@
+ala
+arg
+asn
+asp
+cys
+gln
+glu
+gly
+his
+ile
+leu
+lys
+phe
+pro
+ser
+thr
+trp
+tyr
+val
+d-ala
+d-arg
+d-asn
+d-asp
+d-cys
+d-gln
+d-glu
+d-gly
+d-his
+d-ile
+d-leu
+d-lys
+d-phe
+d-ser
+d-thr
+d-trp
+d-tyr
+d-val

data_utils.py

@@ -0,0 +1,13 @@
+"""Temporary placeholder to load
+"""
+def load_monomers(filename: str = "./data/monomers_list.txt") -> list[str]:
+    """
+    Loads monomer names from a file.
+    """
+    monomers = []
+    with open(filename, 'r') as file:
+        for line in file:
+            line = line.strip()
+            if len(line) > 0:
+                monomers.append(line)
+    return monomers