Elsevier eBooks, Год журнала: 2024, Номер unknown
Опубликована: Янв. 1, 2024
Язык: Английский
Frontiers in Artificial Intelligence, Год журнала: 2024, Номер 7
Опубликована: Сен. 24, 2024
Cultured meat has the potential to provide a complementary industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research development efforts. Machine learning accelerate cultured technology by streamlining experiments, predicting optimal results, reducing experimentation time resources. use of machine in is its infancy. This review covers work available date on explores future possibilities. We address four areas development: establishing cell lines, culture media design, microscopy image analysis, bioprocessing food processing optimization. In addition, we have included survey datasets relevant CM research. aims foundation necessary for both scientists identify opportunities at intersection between learning.
Язык: Английский
Процитировано
3
The European Physical Journal Plus, Год журнала: 2024, Номер 139(1)
Опубликована: Янв. 22, 2024
Язык: Английский
Процитировано
2
Journal of Hazardous Materials, Год журнала: 2024, Номер 480, С. 136043 - 136043
Опубликована: Окт. 2, 2024
Язык: Английский
Процитировано
2
Trends in Genetics, Год журнала: 2024, Номер 40(7), С. 587 - 600
Опубликована: Апрель 24, 2024
Язык: Английский
Процитировано
1
Heliyon, Год журнала: 2024, Номер 10(23), С. e40696 - e40696
Опубликована: Ноя. 27, 2024
Язык: Английский
Процитировано
1
Advanced Science, Год журнала: 2024, Номер unknown
Опубликована: Ноя. 28, 2024
Abstract Gene regulatory network (GRN) inference, a process of reconstructing gene rules from experimental data, has the potential to discover new rules. However, existing methods often struggle generalize across diverse cell types and account for unseen regulators. Here, this work presents GRNPT, novel Transformer‐based framework that integrates large language model (LLM) embeddings publicly accessible biological data temporal convolutional (TCN) autoencoder capture patterns single‐cell RNA sequencing (scRNA‐seq) trajectories. GRNPT significantly outperforms both supervised unsupervised in inferring GRNs, particularly when training is limited. Notably, exhibits exceptional generalizability, accurately predicting relationships previously even By combining LLMs ability distillate knowledge text deep learning methodologies capturing complex expression overcomes limitations traditional GRN inference enables more accurate comprehensive understanding dynamics.
Язык: Английский
Процитировано
1
Current Plant Biology, Год журнала: 2024, Номер unknown, С. 100432 - 100432
Опубликована: Дек. 1, 2024
Язык: Английский
Процитировано
1
bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown
Опубликована: Фев. 23, 2023
Abstract Alzheimer’s disease and major depressive disorder are prevalent, devastating conditions with limited treatment options. Recent insights suggest that despite distinct phenotypes, these disorders share similar processes such as neuroinflammation. However, the extent of overlapping biological their underlying molecular mechanisms remain to be elucidated. Therefore, we adopted a computational systems biology approach compare regulatory programs in prefrontal cortex both disorders. Leveraging publicly available RNA sequencing data on different human cohorts, at bulk single-cell level, using diverse methodologies, inferred gene networks, which model interactions between transcription factors target genes, characterized cell-type-specific pathways. We identified core circuits shared disorders, including play pivotal role microglial activation IKZF1, IRF8, RUNX1 SPI1. Most had reported Alzheimer’s, but not depression. found several common pathways activation, also more disease-specific Through orthogonal analysis, were able validate predicted disorder. In summary, our work revealed neuroinflammation diseases, under control circuits. The potential relevance genes warrants additional investigation, especially depression, offering possible novel therapeutic opportunities.
Язык: Английский
Процитировано
3
bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown
Опубликована: Июнь 3, 2024
Abstract Computational modelling of cell state transitions has been a great interest many in the field developmental biology, cancer biology and fate engineering because it enables performing perturbation experiments silico more rapidly cheaply than could be achieved wet lab. Recent advancements single-cell RNA sequencing (scRNA-seq) allow capture high- resolution snapshots states as they transition along temporal trajectories. Using these high-throughput datasets, we can train computational models to generate ‘synthetic’ cells that faithfully mimic Here present OneSC, platform simulate synthetic across trajectories using systems stochastic differential equations govern by core transcription factors (TFs) regulatory network. Different from current network inference methods, OneSC prioritizes on generating Boolean produces faithful steady real biological systems. Applying data, inferred TF mouse myeloid progenitor scRNA-seq dataset showed dynamical simulations expression profiles recapitulate four differentiation going into differentiated (erythrocytes, megakaryocytes, granulocytes monocytes). Finally, through in-silico perturbations network, accurately predict decision biases closely match with previous experimental observations.
Язык: Английский
Процитировано
0
Neural Regeneration Research, Год журнала: 2024, Номер 20(6), С. 1703 - 1704
Опубликована: Июнь 26, 2024
The brain, with its trillions of neural connections, different cellular types, and molecular complexities, presents a formidable challenge for researchers aiming to comprehend the multifaceted nature health. As traditional methods have provided valuable insights, emerging technologies offer unprecedented opportunities delve deeper into underpinnings brain function. In ever-evolving landscape neuroscience, quest unravel mysteries human is bound take leap forward thanks new technological improvements bold interpretative frameworks. Indeed, as our understanding intricacies advances, so does need comprehensive integrative approaches studying health in synergistic manner, bridging gap between biology (e.g., pathways), interactions environmental influences), advanced computational analyses explainable artificial intelligence). Brain health, therefore, not just about function itself; it comprehending complex relational networks surrounding environment (represented by physiological, psychological, or external stimuli) putting this information at service personalized well-being through precision medicine. Advancements whole genome sequencing single-cell revolutionized ability scrutinize individual cells within (Bagger et al., 2024). Techniques such RNA sequencing, epigenomics, proteomics enable capture heterogeneity that exists among drastically levels detail (Zhang By examining gene expression, epigenetic modifications, protein profiles resolution, scientists can diversity (Rizzuti 2023). application omics research offers insights cell states, interactions, providing nuanced development, neurodegenerative disorders, dynamics underlying cognitive functions. Additionally, approach facilitates identification rare populations transitional states may play crucial roles (Kwok lens which was studied could often detect general outlines pathological mechanisms but lacked resolution discern finer features. With omics, we become able detail. So, decipher unique signatures diverse shedding light on also unraveling intricate relationship genes, proteins, modifications influence landscape. scenario, pan-omic applied level (i.e. study totality specific biological molecules collection cells) seem be definitive tool specificities disease, establishing paramount contribution each cell, type alterations, physiological even allowing delineation neuropsychological correlates physical structures activity changes significantly relation psychological change) (Abondio 2024; Groza exist isolation: constantly influenced surroundings operates. Polymorphic factors, ranging from pollutants toxins lifestyle socioeconomic status, contribute interplay shapes Environmental neurology recognizes brains intricately connected what happens around us, both short long term, seeks elucidate how these factors impact molecular, cellular, systemic (Reis Studying determinants requires interdisciplinary collaboration, incorporating expertise science, epidemiology, neuroscience. identifying develop targeted interventions preventive strategies. Integration pan-omics provides further dimension holistic perspective, connecting alterations exposures, paving way conservation. Given all live hyper-accelerated modernity defined rapidly changing natural, socioeconomic, industrial, digital, technological, interpersonal variables, immediate socio-environmental paramount. From air pollution choices, everything leaves an imprint brain: delving exposures neurological extreme only would frame effectors inform willful construction stable environments restorative nurture rather than causing harm (Hachinski sheer volume complexity data generated multidisciplinary necessitate analytical tools. Artificial intelligence (AI), capacity pattern recognition, machine learning, predictive modeling, emerges component analysis high-dimensional datasets (Kim Machine learning algorithms subtle patterns data, associated disease conditions. Integrating AI models enables relationships brain. AI-driven modeling holds potential anticipate individualized risk decline disorders based person's characteristics (Vodovotz Advanced architectures particular interest include deep-learning transformers, been developed primarily natural language processing computer vision context, they used integrated decision-making processes supported neuroimaging (Wang A characteristic feature implies attention mechanism, allows simultaneous input contextualizing analyzed object rest differentially weighting them, most relevant pieces will supply amplified signal throughout model. explosion studies number biopsychosocial considered variables (and merely corrective values simplified equation), responds digital structure helps making sense landscapes. spot eyes might miss; predict certain responses, offering glimpse future (Kalyakulina This, course, demote experience, expertise, clinician, support expert opinion borderline cases. integration pan-omics, neurology, (Figure 1) promise create powerful synergy transcends limitations approaches. This framework examine types response stimuli, uncovering critical underlie variations For example, neuronal subpopulations delineated level, elucidating differential vulnerability stressors. recently paradigm direction exposomics, systematically investigates cell-environment transient life-long significant (Tamiz 2022). behavioral monitoring enacted assess collect discrete continuous while -omic biomarker relay internal exposome response, favoring interpretation mitigation public wider repercussions policy One Health approach, elevating standards healthy ecosystem turn favor healthier living conditions urban rural areas and, extension, individuals (Wood then long-term consequences strategies mitigate adverse effects. Ideally, following delineated: reveal nuances identifies players influencing determines refer community. (precision) medicine stressors affect neurons, predicting risks combination genetic predispositions devising are group people shared characteristics.Figure 1: Integrative research.Schematic representation synergystically Created Adobe Illustrator 2020.While proposed great promise, several challenges must addressed fully realize potential. Technical drawbacks noise limitations, require ongoing refinement, well standardization experimental protocols pipelines, ensuring comparability across studies, repeatability. Moreover, size should analyzed, integrated, stored, managed infrastructures magnitude power. While some material obstacles easier bypass achieve goal integrating omic AI, there algorithmic computation considered. especially new, field crossroads ecology, sciences, biology, faces accurately quantifying characterizing other parameters correctors, predictive, generative models. Developing databases catalog their essential advancing field. reference intelligence, ethical concerns, interpretability models, robust validation present challenges; particular, responsible transparent use imperative foster trust results applications. conclusion, heralds promising era research. connections determinants, influences, outcomes. technology continues advance, deepen pave embracing environment, move closer ultimately contributing development therapies range It recognize potentials limitations) reshaping perceive prioritize experience benefit individual, Open peer reviewer:Shouneng Peng, Icahn School Medicine Mount Sinai, USA. Additional file:Open review report 1.P-Reviewer: Peng S; C-Editors: Zhao M, Liu WJ, Qiu Y; T-Editor: Jia Y
Язык: Английский
Процитировано
0