object-readme

telatin · May 31, 2024 · 50f3e7d · 50f3e7d
1 parent 7db3184
commit 50f3e7d
Showing 1 changed file with 59 additions and 2 deletions.
diff --git a/first-steps/05-object.ipynb b/first-steps/05-object.ipynb
@@ -38,7 +38,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now let's try to formalise a class for the storing the sequence."
+    "Now let's try to formalise a class for the storing the sequence. **At the end of this notebook an explanation**"
    ]
   },
   {
@@ -164,7 +164,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "we can also control the equality with `__eq__`..."
+    "HINT: we can also control the equality with `__eq__`..."
    ]
   },
   {
@@ -206,6 +206,63 @@
     "\n",
     "Creates and returns a new DNASequence object with the reverse complement sequence."
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class DNASequence:\n",
+    "    # Standard genetic code dictionary\n",
+    "    codon_table = {\n",
+    "        'ATA':'I', 'ATC':'I', 'ATT':'I', 'ATG':'M',\n",
+    "        'ACA':'T', 'ACC':'T', 'ACG':'T', 'ACT':'T',\n",
+    "        'AAC':'N', 'AAT':'N', 'AAA':'K', 'AAG':'K',\n",
+    "        'AGC':'S', 'AGT':'S', 'AGA':'R', 'AGG':'R',\n",
+    "        'CTA':'L', 'CTC':'L', 'CTG':'L', 'CTT':'L',\n",
+    "        'CCA':'P', 'CCC':'P', 'CCG':'P', 'CCT':'P',\n",
+    "        'CAC':'H', 'CAT':'H', 'CAA':'Q', 'CAG':'Q',\n",
+    "        'CGA':'R', 'CGC':'R', 'CGG':'R', 'CGT':'R',\n",
+    "        'GTA':'V', 'GTC':'V', 'GTG':'V', 'GTT':'V',\n",
+    "        'GCA':'A', 'GCC':'A', 'GCG':'A', 'GCT':'A',\n",
+    "        'GAC':'D', 'GAT':'D', 'GAA':'E', 'GAG':'E',\n",
+    "        'GGA':'G', 'GGC':'G', 'GGG':'G', 'GGT':'G',\n",
+    "        'TCA':'S', 'TCC':'S', 'TCG':'S', 'TCT':'S',\n",
+    "        'TTC':'F', 'TTT':'F', 'TTA':'L', 'TTG':'L',\n",
+    "        'TAC':'Y', 'TAT':'Y', 'TAA':'*', 'TAG':'*',\n",
+    "        'TGC':'C', 'TGT':'C', 'TGA':'*', 'TGG':'W',\n",
+    "    }\n",
+    "\n",
+    "    def __init__(self, sequence, name, description=\"\"):\n",
+    "        self.sequence = sequence.upper()\n",
+    "        self.name = name\n",
+    "        self.description = description\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.sequence)\n",
+    "\n",
+    "    def __str__(self):\n",
+    "        desc_str = f\" {self.description}\" if self.description else \"\"\n",
+    "        return f\">{self.name}{desc_str}\\n{self.sequence}\"\n",
+    "\n",
+    "    def __eq__(self, other):\n",
+    "        return self.sequence == other.sequence\n",
+    "    \n",
+    "    def rc(self):\n",
+    "        complement = {'A': 'T', 'T': 'A', 'C': 'G', 'G': 'C'}\n",
+    "        rev_comp = ''.join(complement[base] for base in reversed(self.sequence))\n",
+    "        return DNASequence(rev_comp, self.name + \"_rc\", self.description)\n",
+    "    \n",
+    "    def translate(self):\n",
+    "        protein = []\n",
+    "        # Process the DNA sequence in chunks of three (codons)\n",
+    "        for i in range(0, len(self.sequence), 3):\n",
+    "            codon = self.sequence[i:i+3]\n",
+    "            if len(codon) == 3:\n",
+    "                protein.append(self.codon_table.get(codon, 'X'))  # 'X' for unknown codons\n",
+    "        return ''.join(protein)"
+   ]
   }
  ],
  "metadata": {