Akademik Veri Yönetim Sistemi
15.TIP BİLİŞİMİ KONGRESİ, Trabzon, Türkiye, 30 - 31 Mayıs 2024, ss.223-224
Products with different ingredients are needed for the
treatment of various diseases. One of the most commonly used methods to obtain
these products is organic synthesis. Although organic synthesis has a history of
190 years, it is not fast enough to discover new drugs and materials. Expert
knowledge is relied upon in the process of determining synthetic routes that will
result in the target product. This situation causes to prolong the discovery process
and increase the incurred expenses in this direction. To overcome this problem,
the discovery of synthetic routes has become different with the developing machine learning technologies. One of the important points in the discovery of new
molecules lies in well-designed and applicable retrosynthetic routes. The aim of
retrosynthesis work is to design synthetic routes from the target molecule to the
starting materials. When the literature was examined within the scope of the research, it was seen that machine learning-supported retrosynthesis studies were
still in their early stages. It is thought that the study conducted in this direction
will help chemists find better synthesis routes that will reach the target product
more quickly.