import unittest
import importlib
import re
import ast

class TestTask(unittest.TestCase):
    def test_basic_druglike_filtering(self):
        import user_code
        importlib.reload(user_code)

        test_smiles = [
            "CC(=O)OC1=CC=CC=C1C(=O)O",  # Aspirin
            "CCN(CC)CCCC(C)NC1=C2C=CC(=CC2=NC=C1)Cl",  # Chlorpromazine
            "C1=CC=CC=C1",  # Benzene
            "CC1(C)SCC(N1C(=O)NC2=CC=CC=C2)C(=O)O",  # Amoxicillin (as given)
        ]

        # Under the implemented Lipinski thresholds, all 4 pass
        expected = list(test_smiles)

        result = user_code.filter_druglike_smiles(test_smiles)
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "Correctly filters SMILES using the implemented Lipinski thresholds",
            f"Expected {expected}, got {result}"
        )

    def test_invalid_smiles_handling(self):
        import user_code
        importlib.reload(user_code)

        test_smiles = [
            "CC(=O)OC1=CC=CC=C1C(=O)O",  # valid, passes
            "INVALID_SMILES",            # invalid
            "C1=CC=CC=C1",              # valid, passes under the thresholds
        ]

        expected = [
            "CC(=O)OC1=CC=CC=C1C(=O)O",
            "C1=CC=CC=C1"
        ]

        result = user_code.filter_druglike_smiles(test_smiles)
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "Handles invalid SMILES and filters correctly using implemented thresholds",
            f"Expected {expected}, got {result}"
        )

    def test_empty_list(self):
        import user_code
        importlib.reload(user_code)

        test_smiles = []
        expected = []

        result = user_code.filter_druglike_smiles(test_smiles)
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Returns empty list for empty input",
            f"Expected empty list, got {result}"
        )

    def test_all_fail(self):
        import user_code
        importlib.reload(user_code)

        test_smiles = [
            "C1=CC=CC=C1",  # Benzene (passes implemented thresholds)
            "CC1(C)SCC(N1C(=O)NC2=CC=CC=C2)C(=O)O"  # Amoxicillin (passes)
        ]

        # With the implemented thresholds, these do NOT fail; both pass
        expected = list(test_smiles)

        result = user_code.filter_druglike_smiles(test_smiles)
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "Returns all SMILES that pass the implemented thresholds",
            f"Expected {expected}, got {result}"
        )

    def test_all_pass(self):
        import user_code
        importlib.reload(user_code)

        test_smiles = [
            "CC(=O)OC1=CC=CC=C1C(=O)O",  # Aspirin
            "CCN(CC)CCCC(C)NC1=C2C=CC(=CC2=NC=C1)Cl",  # Chlorpromazine
        ]

        expected = list(test_smiles)

        result = user_code.filter_druglike_smiles(test_smiles)
        _dynamic_test(
            self,
            isinstance(result, list) and set(result) == set(expected),
            "All input SMILES pass and are returned",
            f"Expected {expected}, got {result}"
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\s{2,}", " ", text)
    text = re.sub(r"\s*([,:?])\s*", r"\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    if not assign_nodes:
        return code

    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()

test_main.py

Dive into the world of chemoinformatics using Python! This course introduces you to essential concepts such as molecular representations, descriptors, similarity, clustering, and QSAR modeling. Through engaging theory and hands-on challenges, you'll learn to analyze chemical data, compute molecular properties, and build predictive models—all with beginner-friendly explanations and real-world examples.

Explore how molecules are represented digitally and learn to parse and interpret these representations using Python.

Learn how to compare molecules, find similar compounds, and group them for drug discovery applications.

Apply chemoinformatics techniques to screen and rank compound libraries for drug discovery.

Challenge: Filter a Compound Library

Ratkaisu

Challenge: Filter a Compound Library

Ratkaisu