Multi-Objective Drug Molecule Optimization Based on Tanimoto Crowding Distance and Acceptance Probability

. 2025 Aug 20;18(8):1227. doi: 10.3390/ph18081227

Algorithm 2 The framework of the algorithm for MoGA-TA

Require:
P (initial population), N (number of generations)
Ensure:
Optimized molecules
1:
for $i = 0$ to N do
2:
$P_{i}^{'} \Leftarrow m u t a t i o n (P_{i}) + c r o s s o v e r (P_{i})$
3:
$f r o n t s \Leftarrow f r o n t s s o r t i n g (P_{i}^{'} + P_{i})$
4:
$c r o w d i n g_d i s \Leftarrow c r o w d i n g_d i s t a n c e (f r o n t s)$
5:
$a c c e p t_p r o b \Leftarrow a c c e p t a n c e_p r o b a b i l i t y (i)$
6:
$P_{i + 1} \Leftarrow []$
7:
for each front in $f r o n t s$ do
8:
if satisfy_splitting_condition(front) then
9:
$P_{i + 1} \Leftarrow s o r t_s e l e c t i o n (f r o n t, a c c e p t_p r o b)$
10:
else
11:
$P_{i + 1} \Leftarrow P_{i + 1} + f r o n t$
12:
end if
13:
end for
14:
end for