Bahattin Can Maral, Mehmet Tan · 2022 · IFIP International Conference on Artificial Intelligence Applications and Innovations · Springer International Publishing · pp. 414-425 · Cited by 1
Among the recent developments in bioinformatics and chemogenomics, various deep learning methods have been the most prevalent. This resulted in an over-saturation of powerful models that easily pushed the limits of existing datasets. Subsequently, many novel advancements have been done with improvements to the datasets. Amidst these advancements, researchers of Deep Compound Profiler (DeepCOP) set themselves apart with a novel method of introducing new features whilst keeping the deep learning model relatively basic. In this study, we propose to take this novel method one step further by applying transfer learning between cell lines. In order to better evaluate the benefits of transfer learning, we've introduced 2 drug-based data splits. The transfer learning method, as its core, utilizes the learned knowledge of 'source' cell lines to give a head start to 'target' cell lines.
Bahattin Can Maral · 2022 · arXiv preprint arXiv:2202.11763 · Cited by 18
Super-resolution (SR), the process of obtaining high-resolution images from one or more low-resolution observations of the same scene, has been a very popular topic of research in the last few decades in both signal processing and image processing areas. Due to the recent developments in Convolutional Neural Networks, the popularity of SR algorithms has skyrocketed as the barrier of entry has been lowered significantly. Recently, this popularity has spread into video processing areas to the lengths of developing SR models that work in real-time. In this paper, we compare different SR models that specialize in single image processing and will take a glance at how they evolved to take on many different objectives and shapes over the years.
Rıza Işık, Işıksu Ekşioğlu, Bahattin Can Maral, Benan Bardak, Mehmet Tan · 2020 · 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE) · IEEE · pp. 111-114 · Cited by 1
Understanding the mechanism of action for drugs is vital for drug discovery. Identifying the effect of drugs on gene expression can shed light on the system-side influence of the chemical compounds in biological organisms. In this paper, we propose to use multi-task neural networks to predict chemical induced differential gene expression on cancer cell lines based solely on features of chemicals. Our model predicts differential gene expression identified by a method called Characteristic Direction on a large scale chemical induced gene expression database (LINCS L1000). The results show that the multi-task networks outperform the other single task baselines. We also compare different representations of chemicals and report effect of clustering genes on the prediction performance.
Kimyasalların Gen Düzenleyici Etkilerinin Tahmini için Transfer Öğrenimi
Bahattin Can Maral · 2022 · TOBB ETÜ
Kemogenomik, ilaç tasarımına ve taramaya yardımcı olmak amacıyla biyolojik hedeflerin kimyasal bileşiklere genomik ve/veya proteomik reaksiyonunun incelenmesidir. Kemogenomikteki birçok zorluktan biri, gerçek yaşam deney verilerine bağımlılıktan kaynaklanmaktadır; farklı kimyasal bileşiklerin ve ilaç hedeflerinin kombinasyonu, gerçekçi olmayan sayıda olası deney yaratır ve bu da belirli kimyasallara ve hedeflere yönelik önyargılı veri kümeleriyle sonuçlanmaktadır. Yapay öğrenmedeki son gelişmeler, bu veri kümelerinin sınırlarını kolayca zorlayan güçlü modellerin aşırı doygunluğuyla sonuçlanmıştır. Bu yatkınlıkların etkilerini nötrlemek için, benzer problemlerden bilgi edinme yöntemi olan transfer öğrenmeyi kullanmaktayız. Kemogenomik veri setlerindeki en önemli yanlılık, ilaç hedeflerine yönelik olandır. Bazı hücre dizilerinin erişebilirliği ve önemi, bu deneyler için bir ilaç hedefi olarak kullanılma şansını büyük ölçüde artırırken, diğerlerinin yapay öğrenme modellerini eğitmek için ancak yeterli verisi vardır.