مطالعه ارتباط كمي ساختار – فعاليت جهت پيش بيني فعاليت دارويي برخي از تركيبات پيريدين در درمان سرطان پوست با استفاده از الگوريتم كرم شب تاب

Quantitative structure–activity relationship study for predicting activity of some medicine compounds by firefly algorithm

ﻣﻄﺎﻟﻌﻪ ارﺗﺒﺎط ﮐﻤﯽ-ﺳﺎﺧﺘﺎر ﻓﻌﺎﻟﯿﺖ)QSAR( ﺟﻬﺖ ﭘﯿﺶ ﺑﯿﻨﯽ ﻓﻌﺎﻟﯿﺖ داروﯾﯽ ﺑﺮﺧﯽ از ﺗﺮﮐﯿﺒﺎت ﭘﯿﺮﯾﺪﯾﻦ و ﻣﺸﺘﻘﺎت آن در درﻣﺎن ﺳﺮﻃﺎن ﭘﻮﺳﺖ اﻧﺠﺎم ﺷﺪ. در اﺑﺘﺪا ﺳﺎﺧﺘﺎر ﺗﺮﮐﯿﺒﺎت ﻣﻮرد ﻧﻈﺮ ﺗﻮﺳﻂ ﻧﺮم اﻓﺰار ﻫﺎﯾﭙﺮﮐﻢ رﺳﻢ و ﺑﻬﯿﻨﻪ ﮔﺮدﯾﺪ. ﺳﭙﺲ ﺗﻌﺪاد 1481 ﺗﻮﺻﯿﻒ ﮐﻨﻨﺪه ﺗﻮﺳﻂ ﻧﺮم اﻓﺰار دراﮔﻮن ﻣﺤﺎﺳﺒﻪ ﺷﺪ. ﺑﺮاي اﻧﺘﺨﺎب ﻣﻨﺎﺳﺐ ﺗﺮﯾﻦ ﺗﻮﺻﯿﻒ ﮐﻨﻨﺪه ﻫﺎ از روش رﮔﺮﺳﯿﻮن ﻣﺮﺣﻠﻪ اﯾﯽ و اﻟﮕﻮرﯾﺘﻢ ﮐﺮم ﺷﺐ ﺗﺎب اﺳﺘﻔﺎده ﺷﺪ. عملكرد هر مدل توسط سري تست مورد بررسي قرار گرفت. ريشه ميانگين مربعات خطا سري پيش بيني(RMSEP)، خطاي نسبي پيش بيني (REP) و ضريب تعيين (R2) و خطاي استاندارد پيش بيني (SEP) در روشهاي SW-MLR و FF-MLR بدست آمد

Quantitative structure–activity relationship models were developed for predicting activity of a series of medicine compounds such as pyridine derivatives. The suitable set of the molecular descriptors was calculated and the important descriptors using the variable selections of the stepwise (SW) and the firefly algorithm (FFA) were selected. The predictive quality of the QSAR models was tested for an external set of compounds by multiple linear regression (MLR). Statistical parameters for SW-MLR and FF-MLR were R2 train = 0.835, 0.859, RMSEP = 0.620, 0.786, REP= 10.72, 10.52 respectively. A comparison between the attained results indicated the superiority of the firefly algorithm over the stepwise method in the feature selection. The predicted results of this study can be used to design new inhibitors of melanoma anti-cancer.