IDEA of Development Foundation

Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic potential for complex diseases. However, identifying effective reprogramming strategies through classical wet-lab experiments is hindered by long time commitments and high costs. Although computational methods have been proposed to address this challenge, exact state-of-the-art techniques suffer from limited scalability owing to the notorious state space explosion problem. To overcome this limitation, we explore deep reinforcement learning (DRL) for controlling holistic Boolean network models of complex biological systems, such as gene regulatory and signalling pathway networks. We formulate a novel control problem for Boolean network models operating under the asynchronous update mode, specifically tailored to the context of cellular reprogramming. To solve it, we devise GATTACA - a DRL-based computational framework explicitly designed for scalability, capable of handling large and complex network models where exact methods fail. To facilitate scalability of our framework, we consider our previously introduced concept of a pseudo-attractor and improve the procedure for effective identification of pseudo-attractor states. We incorporate graph neural networks with graph convolution operations into the artificial neural network approximator of the DRL agent's action-value function. The new architecture allows us to leverage the available knowledge on the structure of a biological system and to indirectly, yet effectively, encode the system's dynamics into a latent representation. Experiments on several large-scale, real-world biological networks from the literature demonstrate the scalability and effectiveness of our approach.

Abstract The Belarusian diaspora has undergone a profound transformation since the political crisis of 2020, which featured contested elections, mass protests and severe repressions. This study examines the evolving dynamics between the ‘old’ (pre-2020) and ‘new’ (post-2020) Belarusian diaspora communities in Poland, Lithuania and Germany, focusing on their values, identities and sense of solidarity. Using a mixed-methods approach involving two online surveys and 30 in-depth interviews, this article reveals that the differences between these groups are not just chronological but are also influenced by symbolic, political and emotional factors. The ‘new’ diaspora, driven by political exile, exhibits heightened digital connectivity and emotional mobilisation, whereas the ‘old’ diaspora emphasises cultural practices. Despite symbolic boundaries, solidarity emerges through shared trauma and digital platforms, fostering a hybrid, translocal identity. In the context of Central and Eastern European diaspora studies, this case study highlights the impact of political crises and digital infrastructures on the redefinition of transnational communities.

Abstract Neural signed‐distance fields (SDFs) are a versatile backbone for neural geometry representation, but enforcing CAD‐style developability usually requires Gaussian‐curvature penalties with full Hessian evaluation and second‐order differentiation, which are costly in memory and time. We introduce an off‐diagonal Weingarten loss that regularizes only the mixed shape operator term that represents the gap between principal curvatures and flattens the surface. We present two variants: a finite‐difference version using six SDF evaluations plus one gradient, and an auto‐diff version using a single Hessian‐vector product. Both converge to the exact mixed term and preserve the intended geometric properties without assembling the full Hessian. On the ABC benchmarks the losses match or exceed Hessian‐based baselines while cutting GPU memory and training time by roughly a factor of two. The method is drop‐in and framework‐agnostic, enabling scalable curvature‐aware SDF learning for engineering‐grade shape reconstruction. Our code is available at https://flatcad.github.io/.

Scoring systems are widely adopted in medical applications for their inherent simplicity and transparency, particularly for classification tasks involving tabular data. In this work, we introduce RegScore, a novel, sparse, and interpretable scoring system specifically designed for regression tasks. Unlike conventional scoring systems constrained to integer-valued coefficients, RegScore leverages beam search and k-sparse ridge regression to relax these restrictions, thus enhancing predictive performance. We extend RegScore to bimodal deep learning by integrating tabular data with medical images. We utilize the classification token from the TIP (Tabular Image Pretraining) transformer to generate Personalized Linear Regression parameters and a Personalized RegScore, enabling individualized scoring. We demonstrate the effectiveness of RegScore by estimating mean Pulmonary Artery Pressure using tabular data and further refine these estimates by incorporating cardiac MRI images. Experimental results show that RegScore and its personalized bimodal extensions achieve performance comparable to, or better than, state-of-the-art black-box models. Our method provides a transparent and interpretable approach for regression tasks in clinical settings, promoting more informed and trustworthy decision-making. We provide our code at https://github.com/SanoScience/RegScore .

Based on a qualitative content analysis of 2024 posts from leading pro-government Telegram channels in Belarus, this article examines how these sources spread disinformation about Ukraine. The authors show that such posts were relatively infrequent in 2024, and that their themes shifted in response to developments on the battlefield and changes in the broader international context of the conflict. However, certain false claims and allegations consistently received substantial attention. These include public dissatisfaction with conscription into Ukraine’s armed forces, deceptive and coercive methods of recruitment, declining morale among Ukrainian soldiers, corruption related to the war effort, and allegations of ‘neo-Nazism’ within Ukraine and its military. Although the Belarusian regime is often regarded as a co-aggressor in the Russo–Ukrainian war, little is known about whether and how it actively promotes pro-Kremlin narratives online. This article represents a first attempt to address this gap.

The rights of origin and traditional rights of Indigenous Peoples are aspects mandated by law to be recognized and protected as the basis of recognition. However, these rights are often misunderstood by the state in the formation of customary villages or the management of indigenous communities, resulting in many traditional communities (Indigenous Society) not receiving full recognition. The state often views the issues of indigenous communities administratively, without touching on abstract aspects such as local values, which results in misguided policies. This phenomenon occurs among Indigenous communities in Lebak Regency, where the establishment of customary villages, instead of strengthening customary rights, is caught in the tug-of-war of elite political interests. This discourse shows that asymmetric democracy, which should be an inclusive mechanism, instead creates negative implications such as the politicization of customs, the erosion of local values, the disruption of ecological balance, and the introduction of transactional politics. This article dissects the dynamics of the formation of customary villages through the perspective of asymmetric democracy, highlighting its implications for local values, ecosystem balance, and political practices. Using qualitative methods with a phenomenological approach, this article seeks to explore the meaning of the experiences of Indigenous Communities in Lebak Regency in facing the challenges of democracy and the recognition of customary rights. This study found that the establishment of customary villages in Lebak Regency, which was expected to strengthen the recognition of customary rights, is instead influenced by the tug-of-war of political interests, thereby threatening local values and environmental balance and encouraging the politicization of customary practices within the framework of asymmetric democracy.

Recurrent neural networks are important tools for sequential data processing. However, they are notorious for problems regarding their training. Challenges include capturing complex relations between consecutive states and stability and efficiency of training. In this paper, we introduce a recurrent neural architecture called Deep Memory Update (DMU). It is based on updating the previous memory state with a deep transformation of the lagged state and the network input. The architecture is able to learn to transform its internal state using any nonlinear function. Its training is stable and fast due to relating its learning rate to the size of the module. Even though DMU is based on standard components, experimental results presented here confirm that it can compete with and often outperform state-of-the-art architectures such as Long Short-Term Memory, Gated Recurrent Units, and Recurrent Highway Networks.