Algorithm 1 AHN algorithm for saturated and linear hydrocarbon compounds.

Input: a training dataset $\Sigma =(x,y)$, the number of molecules in the compound $n\ge 2$ and a tolerance value $ϵ>0$.

Output: the saturated and linear hydrocarbon compound $AHN$.

Initialize an empty compound $AHN=\left\{\right\}$.

Create a new saturated linear compound C like Equation (2).

Randomly initialize intermolecular distances $r_t$.

while $|y-\psi |>ϵ$ do

Determine all bounds $L_t$ of C using $r_t$.

for each j-th molecule in C do

Determine all parameters of behavior ${\phi }_j$ in Equation (1) using an optimization process.

end-for

Build the compound behavior ψ of C using Equation (3).

Update intermolecular distances using Equations (4) and (5).

end-while

Update $AHN$ with C and ψ.

return $AHN$