VAWKUM Transactions on Computer Sciences DeepImmuno-PSSM: Identification of Immunoglobulin based on Deep learning and PSSM-Profiles Ali Ghulam 1* , Zar Nawab Khan Swati 2 , Farman Ali 3 , Saima Tunio 4 , Nida Jabeen 5 , Natasha Iqbal 6 1 Information Technology Centre, Sindh Agriculture University, Sindh, Pakistan; 2 Department of computer science, Karakoram international university Gilgit, Pakistan; 3 Department of Elementary and Secondary Education, Peshawar, Khyber Pakhtunkhwa, Pakistan; 4 Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; 5 College of information and compute, Taiyuan university of Technology, 030024, Shanxi Taiyuan, China; 6 Department of Botany, Government College University of Faisalabad, 37000, Faisalabad, Pakistan. Keywords: Immunoglobulin proteins, dipeptide acid composition (DPC), convolutional neural network (CNN) Journal Info: Submitted: January 08, 2023 Accepted: March 12, 2023 Published: March 17, 2023 Abstract Immunoglobulin has a close connection to a number of disorders and is important in both biological and medicinal contexts. Therefore, it is cru- cial for illness research to employ efficient techniques to increase the catego- rization accuracy of immunoglobulins. Computational models have been used in a small number of research to address this important issue, but the accuracy of the predictions is not good enough. As a result, we use a cutting-edge deep learning technique with convolutional neural networks to enhance the perfor- mance results. In this study, the immunoglobulin features were extracted us- ing the dipeptide acid composition (DPC) with the position-specific scoring matrix (DPC-PSSM) and position-specific scoring matrix-transition probability composi- tion (PSSM-TPC) methods. we apply extracted features information from the DPC- PSSM profiles and PSSM-TPC profile by using a 1D-convolutional neural network (CNN) over an input shape. The outcomes demonstrated that the DeepImmuno- PSSM method based on sequential minimal optimization was able to properly predict DPC-PSSM accuracy score 93.44 percent obtained and of the immunoglob- ulins using the greatest feature subcategory produced by the PSSM-TPC feature mining approach accuracy score of 89.92 percent obtained. Our findings indi- cate that we are able to provide a useful model for enhancing immunoglobulin proteins’ capacity for prediction. Additionally, it implies that employing sequence data in deep learning and PSSM-based features may open up new path for bio- chemical modelling. *Correspondence Author Email Address: VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VFAST Transactions on Mathematics VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences VAWKUM Transactions on Computer Sciences http://vfast.org/journals/index.php/VTCS@ 2023 ISSN(e): 2308-8168, ISSN(p): 2411-6335 54 garahu@sau.edu.pk Volume 11, Number 1, January-June 2023 pp:54-66