Interaction Prediction on BACE-1 Inhibitors Data for Alzheimer Disease using Message Passing Neural Network

Suat Toraman; Bihter Daş

Makale detayları

Interaction Prediction on BACE-1 Inhibitors Data for Alzheimer Disease using Message Passing Neural Network

Yazarlar:

Suat Toraman | Bihter Daş

Yayıncı:

Fırat University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Firat University Journal of Experimental and Computational Engineering Vol.4 Issue 1, pp.72-84

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341164

pISSN:

2822-2881

Anahtar kelimeler:

Özet:

 The medical condition that develops as memory loss, dementia, and a general decrease in cognitive functions due to the death of brain cells over time is called Alzheimers disease. This disease can lead to a gradual decline in cognitive functions and eventually severe memory losses that affect a persons daily life. Although the exact mechanism that causes Alzheimers disease is not fully understood, it has been associated with certain structural changes in the brain, such as plaques and neurofibrillary bundles. This study investigates the use of geometric deep learning methods for the discovery of BACE-1 inhibitors that are promising in addressing Alzheimers disease. Our study builds on these advancements by integrating GDL with pharmacological criteria, such as the QED criterion and Lipinskis rule, to predict BACE-1 inhibitors with enhanced accuracy and drug-like properties. Our model, which combines message-passing neural networks MPNNs and fully connected network FCN architectures, achieved a success rate of 87.7. This performance not only surpasses that of previous studies but also ensures the practical applicability of our findings in drug discovery for Alzheimers disease. The dual focus on prediction accuracy and drug likeness sets our work apart, providing a more comprehensive approach to identifying effective therapeutic agents.

 The medical condition that develops as memory loss, dementia, and a general decrease in cognitive functions due to the death of brain cells over time is called Alzheimers disease. This disease can lead to a gradual decline in cognitive functions and eventually severe memory losses that affect a persons daily life. Although the exact mechanism that causes Alzheimers disease is not fully understood, it has been associated with certain structural changes in the brain, such as plaques and neurofibrillary bundles. This study investigates the use of geometric deep learning methods for the discovery of BACE-1 inhibitors that are promising in addressing Alzheimers disease. Our study builds on these advancements by integrating GDL with pharmacological criteria, such as the QED criterion and Lipinskis rule, to predict BACE-1 inhibitors with enhanced accuracy and drug-like properties. Our model, which combines message-passing neural networks MPNNs and fully connected network FCN architectures, achieved a success rate of 87.7. This performance not only surpasses that of previous studies but also ensures the practical applicability of our findings in drug discovery for Alzheimers disease. The dual focus on prediction accuracy and drug likeness sets our work apart, providing a more comprehensive approach to identifying effective therapeutic agents.

 The medical condition that develops as memory loss, dementia, and a general decrease in cognitive functions due to the death of brain cells over time is called Alzheimers disease. This disease can lead to a gradual decline in cognitive functions and eventually severe memory losses that affect a persons daily life. Although the exact mechanism that causes Alzheimers disease is not fully understood, it has been associated with certain structural changes in the brain, such as plaques and neurofibrillary bundles. This study investigates the use of geometric deep learning methods for the discovery of BACE-1 inhibitors that are promising in addressing Alzheimers disease. Our study builds on these advancements by integrating GDL with pharmacological criteria, such as the QED criterion and Lipinskis rule, to predict BACE-1 inhibitors with enhanced accuracy and drug-like properties. Our model, which combines message-passing neural networks MPNNs and fully connected network FCN architectures, achieved a success rate of 87.7. This performance not only surpasses that of previous studies but also ensures the practical applicability of our findings in drug discovery for Alzheimers disease. The dual focus on prediction accuracy and drug likeness sets our work apart, providing a more comprehensive approach to identifying effective therapeutic agents.

 Beyin hücrelerinin zamanla ölmesine bağlı olarak hafıza kaybı, demans ve bilişsel işlevlerde genel bir azalma şeklinde gelişen tıbbi duruma Alzheimer hastalığı denir. Bu hastalık, bilişsel işlevlerde kademeli bir düşüşe ve sonuçta kişinin günlük yaşamını etkileyen ciddi hafıza kayıplarına yol açabilmektedir. Alzheimer hastalığına neden olan mekanizma tam olarak anlaşılmamasına rağmen beyindeki plaklar ve nörofibriler demetler gibi bazı yapısal değişikliklerle ilişkilendirilmiştir. Bu çalışma, Alzheimer hastalığının tedavisinde ümit verici olan BACE-1 inhibitörlerinin keşfi için geometrik derin öğrenme yönteminin kullanımını araştırmaktadır. Eğitim sürecinde İletişim Geçiş Sinir Ağı ve Tamamen Bağlantılı Ağ kullanılarak özelleştirilmiş bir model geliştirilmiştir. Bu model, moleküler yapıların karmaşık özelliklerini yakalamak için grafik yerleştirmelerin ve tamamen bağlantılı ağların birleşimi yoluyla molekül etkileşimlerini tahmin etmektedir. Sonuçlar, geliştirilen modelin BACE-1 inhibitörlerinin etkileşimlerini başarılı bir şekilde tahmin edebildiğini göstermektedir. Modelin performans oranı 87,7 olarak belirlenmiştir. Bu çalışma, Alzheimer hastalığına yönelik yeni BACE-1 inhibitörlerinin keşfedilmesi ve geliştirilmesi için umut verici bir yol haritası sunmaktadır.

Makale detayları

Interaction Prediction on BACE-1 Inhibitors Data for Alzheimer Disease using Message Passing Neural Network

Yazarlar:

Suat Toraman | Bihter Daş

Yayıncı:

Fırat University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Firat University Journal of Experimental and Computational Engineering Vol.4 Issue 1, pp.72-84

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341164

pISSN:

2822-2881

BACE-1 drug interaction

Alzheimer

Geometric deep learning

Graph network

BACE-1 inhibitors.BACE-1 ilaç etkileşimi

Alzheimer hastalığı

Geometrik derin öğrenme

Grafik ağı

BACE-1 inhibitörleri

Sayı

Makale detayları

Yazarlar: Suat Toraman | Bihter Daş

Yayıncı: Fırat University

Ana Başlıklar: Bilgisayar Yazılımı

Dergi: Firat University Journal of Experimental and Computational Engineering Vol.4 Issue 1, pp.72-84

Belge Tipi: Makale

Yayın Tarihi: 2/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001341164

pISSN: 2822-2881

Sayı

Yazarlar:

Suat Toraman | Bihter Daş

Yayıncı:

Fırat University

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Firat University Journal of Experimental and Computational Engineering Vol.4 Issue 1, pp.72-84

Belge Tipi:

Makale

Yayın Tarihi:

2/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001341164

pISSN:

2822-2881