Advancing microbial production through artificial intelligence-aided biology.

Microbial cell factories (MCFs) have been leveraged to construct sustainable platforms for value-added compound production. To optimize metabolism and reach optimal productivity, synthetic biology has developed various genetic devices to engineer microbial systems by gene editing, high-throughput protein engineering, and dynamic regulation. However, current synthetic biology methodologies still rely heavily on manual design, laborious testing, and exhaustive analysis. The emerging interdisciplinary field of artificial intelligence (AI) and biology has become pivotal in addressing the remaining challenges. AI-aided microbial production harnesses the power of processing, learning, and predicting vast amounts of biological data within seconds, providing outputs with high probability. With well-trained AI models, the conventional Design-Build-Test (DBT) cycle has been transformed into a multidimensional Design-Build-Test-Learn-Predict (DBTLP) workflow, leading to significantly improved operational efficiency and reduced labor consumption. Here, we comprehensively review the main components and recent advances in AI-aided microbial production, focusing on genome annotation, AI-aided protein engineering, artificial functional protein design, and AI-enabled pathway prediction. Finally, we discuss the challenges of integrating novel AI techniques into biology and propose the potential of large language models (LLMs) in advancing microbial production.

Socioeconomic Status and Tooth Loss Impact on Oral Health-Related Quality of Life in Chinese Elderly.

OBJECTIVE: We studied the association between the socioeconomic status (SES), tooth loss, and oral health-related quality of life (OHRQoL) in an adult cohort in western China. As socioeconomic inequalities in oral health are often neglected in oral health promotion. we aimed to verify the impact of SES on tooth loss and OHRQoL. METHODS: In all, 348 participants aged 60 years and older were selected for this study. Relationships amongst SES, tooth loss, and OHRQoL were identified by using a structural equation model (SEM). RESULTS: In the final sample, 312 people were included, and the response rate was 89.7%. The bias-corrected 95% confidence intervals of the total, direct, and indirect effects were (-0.267 to 0.475), (-0.489 to 0.185), and (0.088 to 0.450), respectively. The comparative fit index of SEM was 0.943. The model showed that their SES directly affected tooth loss in the elderly population. This indirectly affects their oral health-related quality of life. The numbers of natural teeth and occlusal units (with standardised path coefficients of 0.79 and 0.74, respectively) were found to be the most significant factors relating to tooth loss. CONCLUSION: SES affected the oral health-related quality of life in elderly people through tooth loss in a Chinese study population. Our data suggest that improvements in the social and economic environments are a primary measure that should be implmented to prevent tooth loss and improve the OHRQoL.

Chemical evolution in nitrogen shocked beyond the molecular stability limit.

Evolution of nitrogen under shock compression up to 100 GPa is revisited via molecular dynamics simulations using a machine-learned interatomic potential. The model is shown to be capable of recovering the structure, dynamics, speciation, and kinetics in hot compressed liquid nitrogen predicted by first-principles molecular dynamics, as well as the measured principal shock Hugoniot and double shock experimental data, albeit without shock cooling. Our results indicate that a purely molecular dissociation description of nitrogen chemistry under shock compression provides an incomplete picture and that short oligomers form in non-negligible quantities. This suggests that classical models representing the shock dissociation of nitrogen as a transition to an atomic fluid need to be revised to include reversible polymerization effects.

Core-Periphery Principle Guided Redesign of Self-Attention in Transformers.

Designing more efficient, reliable, and explainable neural network architectures is critical to studies that are based on artificial intelligence (AI) techniques. Previous studies, by post-hoc analysis, have found that the best-performing ANNs surprisingly resemble biological neural networks (BNN), which indicates that ANNs and BNNs may share some common principles to achieve optimal performance in either machine learning or cognitive/behavior tasks. Inspired by this phenomenon, we proactively instill organizational principles of BNNs to guide the redesign of ANNs. We leverage the Core-Periphery (CP) organization, which is widely found in human brain networks, to guide the information communication mechanism in the self-attention of vision transformer (ViT) and name this novel framework as CP-ViT. In CP-ViT, the attention operation between nodes is defined by a sparse graph with a Core-Periphery structure (CP graph), where the core nodes are redesigned and reorganized to play an integrative role and serve as a center for other periphery nodes to exchange information. We evaluated the proposed CP-ViT on multiple public datasets, including medical image datasets (INbreast) and natural image datasets. Interestingly, by incorporating the BNN-derived principle (CP structure) into the redesign of ViT, our CP-ViT outperforms other state-of-the-art ANNs. In general, our work advances the state of the art in three aspects: 1) This work provides novel insights for brain-inspired AI: we can utilize the principles found in BNNs to guide and improve our ANN architecture design; 2) We show that there exist sweet spots of CP graphs that lead to CP-ViTs with significantly improved performance; and 3) The core nodes in CP-ViT correspond to task-related meaningful and important image patches, which can significantly enhance the interpretability of the trained deep model.

REPRESENTATIVE FUNCTIONAL CONNECTIVITY LEARNING FOR MULTIPLE CLINICAL GROUPS IN ALZHEIMER'S DISEASE.

Mild cognitive impairment (MCI) is a high-risk dementia condition which progresses to probable Alzheimer's disease (AD) at approximately 10% to 15% per year. Characterization of group-level differences between two subtypes of MCI - stable MCI (sMCI) and progressive MCI (pMCI) is the key step to understand the mechanisms of MCI progression and enable possible delay of transition from MCI to AD. Functional connectivity (FC) is considered as a promising way to study MCI progression since which may show alterations even in preclinical stages and provide substrates for AD progression. However, the representative FC patterns during AD development for different clinical groups, especially for sMCI and pMCI, have been understudied. In this work, we integrated autoencoder and multi-class classification into a single deep model and successfully learned a set of clinical group related feature vectors. Specifically, we trained two non-linear mappings which realized the mutual transformations between the original FC space and the feature space. By mapping the learned clinical group related feature vectors to the original FC space, representative FCs were constructed for each group. Moreover, based on these feature vectors, our model achieves a high classification accuracy - 68% for multi-class classification (NC vs SMC vs sMCI vs pMCI vs AD). Code has been released.

SUPERVISED DEEP TREE IN ALZHEIMER'S DISEASE.

As a progressive neurodegenerative disorder, the pathological changes of Alzheimer's disease (AD) might begin as much as two decades before the manifestation of clinical symptoms. Since the nature of the irreversible pathology of AD, early diagnosis provides a more tractable way for disease intervention and treatment. Therefore, numerous approaches have been developed for early diagnostic purposes. Although several important biomarkers have been established, most of the existing methods show limitations in describing the continuum of AD progression. However, understanding this continuous development is essential to understand the intrinsic progression mechanism of AD. In this work, we proposed a supervised deep tree model (SDTree) to integrate AD progression and individual prediction. The proposed SDTree method models the progression of AD as a tree embedded in a latent space using nonlinear reversed graph embedding. In this way, the continuum of AD progression is encoded into the locations on the tree structure. The learned tree structure can not only represent the continuum of AD but make predictions for new subjects. We evaluated our method on the classification task and achieved promising results on Alzheimer's Disease Neuroimaging Initiative dataset.