Plastic scintillation detectors are widely utilized in radiation measurement because of their unique characteristics. However, they are generally used for counting applications because of the energy broadening effect and the absence of a photo peak in their spectra. To overcome their weaknesses, many studies on pseudo spectroscopy have been reported, but most of them have not been able to directly identify the energy of incident gamma rays. In this paper, we propose a method to reconstruct Compton edges in plastic gamma spectra using an artificial neural network for direct pseudo gamma spectroscopy. Spectra simulated using MCNP 6.2 software were used to generate training and validation sets. Our model was trained to reconstruct Compton edges in plastic gamma spectra. In addition, we aimed for our model to be capable of reconstructing Compton edges even for spectra having poor counting statistics by designing a dataset generation procedure. Minimum reconstructible counts for single isotopes were evaluated with metric of mean averaged percentage error as 650 for ⁶⁰Co, 2000 for ¹³⁷Cs, 3050 for ²²Na, and 3750 for ¹³³Ba. The performance of our model was verified using the simulated spectra measured by a PVT detector. Although our model was trained using simulation data only, it successfully reconstructed Compton edges even in measured gamma spectra with poor counting statistics.

Automatically predicting RNA 3D structure from sequence remains an unsolved challenge in biology and biotechnology. Here, we describe a Kaggle code competition engaging over 1700 teams and 43 previously unreleased structures to tackle this challenge. The top three submitted algorithms achieved scores within statistical error of the winners of the recent CASP16 competition. Unexpectedly, the top Kaggle strategy involved a pipeline for discovering 3D templates, without the use of deep learning. We integrated this template-modeling pipeline and other Kaggle strategies to develop a single model RNAPro that retrospectively outperformed individual Kaggle models on the same test set. These results suggest a growing importance of template-based modeling in RNA structure prediction.

With the fact that protein functionality is tied to its structure and shape, a protein design paradigm of generating proteins tailored to specific shape contexts has been utilized for various biological applications. Recently, researchers have shown that top-down strategies are possible with the aid of deep learning for the shape-conditioned design. However, state-of-the-art models have limitations because they do not fully consider the geometric and chemical constraints of the entire shape. In response, we propose ShapeProt, a pioneering end-to-end protein design framework that directly generates protein surfaces and generate sequences with considering the entire nature of the generated shapes. ShapeProt distinguishes itself from current protein deep learning models that primarily handle sequence or structure data because ShapeProt directly handles surfaces. ShapeProt framework employs mask-based inpainting and conditioning to generate diverse shapes at the desired location, and these shapes are then translated into sequences using a shape-conditioned language model. Drawing upon various experimental results, we first prove the feasibility of generative design directly on the three-dimensional molecular surfaces beyond sequences and structures.

Based on the central dogma that protein structure determines its functionality, an important approach for protein sequence design is to identify promising sequences that fold into pre-designed structures based on domain knowledge. Numerous studies have introduced deep generative model-based inverse-folding, which utilizes various generative models to translate fixed backbones to corresponding sequences. In this work, we reveal that denoising training enables models to deeply capture the protein energy landscape, which previous models do not fully leverage. Based on this, we propose a novel Denoising-enhanced protein fixed backbone design (DNDesign), which combines conventional inverse-folding networks with a novel plug-in module, which learns the physical understanding via denoising training and transfers the knowledge to the entire network. Through extensive experiments, we demonstrate that DNDesign can easily be integrated into state-of-the-art models and improve performance in multiple modes, including auto-regressive, non-auto-regressive, and scaled-up scenarios. Furthermore, we introduce a fixed backbone conservation analysis based on potential energy changes, which confirms that DNDesign ensures more energetically favorable inverse-folding.