Artificial intelligence for life sciences: A comprehensive guide and future trends

The Innovation Life, Journal Year: 2024, Volume and Issue: unknown, P. 100105 - 100105

Published: Jan. 1, 2024

<p>Artificial intelligence has had a profound impact on life sciences. This review discusses the application, challenges, and future development directions of artificial in various branches sciences, including zoology, plant science, microbiology, biochemistry, molecular biology, cell developmental genetics, neuroscience, psychology, pharmacology, clinical medicine, biomaterials, ecology, environmental science. It elaborates important roles aspects such as behavior monitoring, population dynamic prediction, microorganism identification, disease detection. At same time, it points out challenges faced by application data quality, black-box problems, ethical concerns. The are prospected from technological innovation interdisciplinary cooperation. integration Bio-Technologies (BT) Information-Technologies (IT) will transform biomedical research into AI for Science paradigm.</p>

Language: Английский

---

Three-dimensional surface motion capture of multiple freely moving pigs using MAMMAL

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: Nov. 25, 2023

Understandings of the three-dimensional social behaviors freely moving large-size mammals are valuable for both agriculture and life science, yet challenging due to occlusions in close interactions. Although existing animal pose estimation methods captured keypoint trajectories, they ignored deformable surfaces which contained geometric information essential interaction prediction dealing with occlusions. In this study, we develop a Multi-Animal Mesh Model Alignment (MAMMAL) system based on an articulated surface mesh model. Our self-designed MAMMAL algorithms automatically enable us align multi-view images into our model capture 3D motions multiple animals, display better performance upon severe compared traditional triangulation allow complex analysis. By utilizing MAMMAL, able quantitatively analyze locomotion, postures, animal-scene interactions, as well detailed tail pigs. Furthermore, experiments mouse Beagle dogs demonstrate generalizability across different environments mammal species.

Language: Английский

---

Ethological computational psychiatry: Challenges and opportunities

Current Opinion in Neurobiology, Journal Year: 2024, Volume and Issue: 86, P. 102881 - 102881

Published: May 1, 2024

Studying the intricacies of individual subjects' moods and cognitive processing over extended periods time presents a formidable challenge in medicine. While much systems neuroscience appropriately focuses on link between neural circuit functions well-constrained behaviors short timescales (e.g., trials, hours), many mental health conditions involve complex interactions mood cognition that are non-stationary across behavioral contexts evolve timescales. Here, we discuss opportunities, challenges, possible future directions computational psychiatry to quantify continuously monitored behaviors. We suggest this exploratory effort may contribute more precision-based approach treating disorders facilitate robust reverse translation animal species. conclude with ethical considerations for any field aims bridge artificial intelligence patient monitoring.

Language: Английский

---

Quantifying social roles in multi-animal videos using subject-aware deep-learning

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 10, 2024

ABSTRACT Analyzing social behaviors is critical for many fields, including neuroscience, psychology, and ecology. While computational tools have been developed to analyze videos containing animals engaging in limited interactions under specific experimental conditions, automated identification of the roles freely moving individuals a multi-animal group remains unresolved. Here we describe deep-learning-based system – named LabGym2 identifying quantifying groups. This uses subject-aware approach: it evaluates behavioral state every individual two or more while factoring its environmental surroundings. We demonstrate performance deep-learning different species assays, from partner preference freely-moving insects primate field. Our deep learning approach provides controllable, interpretable, efficient framework enable new paradigms systematic evaluation interactive behavior identified within group.

Language: Английский

---

Automated pose estimation in primates

American Journal of Primatology, Journal Year: 2021, Volume and Issue: 84(10)

Published: Dec. 2, 2021

Understanding the behavior of primates is important for primatology, psychology, and biology more broadly. It also biomedicine, where are an model organism, whose often variable interest. Our ability to rigorously quantify has, however, long been limited. On one hand, we can low-information measures like preference, looking time, reaction time; on other, use gestalt behavioral categories tracked via ethogram, but at high cost with variability. Recent technological advances have led a major revolution in measurement that offers affordable scalable rigor. Specifically, digital video cameras automated pose tracking software provide full-body position (i.e., pose) over time behavior) spatial temporal resolution. Pose-tracking technology turn be used infer states, such as eating, sleeping, mating. We call this approach imaging. In review, situate imaging history study behavior, argue investment development analytical research techniques profit from advent era big propose primate centers zoos will take central role relevant fields than they past.

Language: Английский

---

Translational models of stress and resilience: An applied neuroscience methodology review

Neuroscience Applied, Journal Year: 2024, Volume and Issue: 3, P. 104064 - 104064

Published: Jan. 1, 2024

Stress, encompassing psychological, physical, and physiological challenges, is an important factor affecting individual's well-being potentially leading to psychiatric, neurodegenerative, immune, metabolic disorders. However, not everyone exposed stress develops these conditions, highlighting the concept of resilience. Resilience a dynamic process categorized into four dimensions: pre-existing resilience capacity, ongoing processes, post-stress outcomes, recovery from psychopathologies. These dimensions involve genomic, cellular, systemic interactions influenced by genetic factors, early life experiences, adult experiences in addition community/environmental health behaviors. The biological response encompasses endocrine, autonomic, immunological, behavioral components, modulated stressor characteristics individual traits. Due limitations studying humans, translational models using rodents cell cultures are essential. Rodent include acute, chronic, traumatic paradigms, aiding study stress-related molecular outcomes. Additionally, models, such as prenatal maternal separation, provide insights developmental impacts. In this review, first, rodent for lifelong exposure will be summarized considering their validity, advantages, limitations. Subsequently, overview designed enhance capacity rodents, later employed outcomes given. Lastly, focus shifted culture iPSCs models. Finally, future considerations focused on improving used discussed. It aimed designs access more effective biomarkers associated with Stress complex phenomena various spanning levels. Integrating data across remains crucial unraveling complexities disorders

Language: Английский

---

Study of tree shrew biology and models: A booming and prosperous field for biomedical research

动物学研究, Journal Year: 2024, Volume and Issue: 45(4), P. 877 - 909

Published: Jan. 1, 2024

The tree shrew (Tupaia belangeri) has long been proposed as a suitable alternative to non-human primates (NHPs) in biomedical and laboratory research due its close evolutionary relationship with primates. In recent years, significant advances have facilitated studies, including the determination of genome, genetic manipulation using spermatogonial stem cells, viral vector-mediated gene delivery, mapping brain atlas. However, limited availability shrews globally remains substantial challenge field. Additionally, determining key questions best answered constitutes another difficulty. Tree models historically used study hepatitis B virus (HBV) C (HCV) infection, myopia, psychosocial stress-induced depression, more studies focusing on developing animal for infectious neurodegenerative diseases. Despite these efforts, impact not yet matched that rodent or NHP research. This review summarizes prominent advancements reflects biological addressed this model. We emphasize intensive dedication robust international collaboration are essential achieving breakthroughs studies. use unique resource is expected gain considerable attention application advanced techniques development viable models, meeting increasing demands life science

Language: Английский

---

Chimpanzee Activity and Behavioral Diversity Extends Across 24 Hours in Both Captive and Wild Settings

American Journal of Primatology, Journal Year: 2025, Volume and Issue: 87(1)

Published: Jan. 1, 2025

ABSTRACT Studying nocturnal behavior is crucial for understanding the full scope of a species' behavioral flexibility so as to inform conservation wild populations and care captive individuals. However, this aspect primate understudied, especially in great apes, which exhibit some widest documented diversity flexibility. Our investigation among first systematically compare 24 h activity patterns activities chimpanzees (Saint Louis Zoo, USA) with those (three sites across Nouabalé‐Ndoki National Park Republic Congo) published data set all chimpanzee subspecies. Furthermore, we examined influence human changes group's composition on behaviors zoo‐living chimpanzees. results reveal that significantly different compared their counterparts, increased (particularly early morning) more observations feeding social at night. Additionally, absence visitors change were found these patterns. These findings underscore importance integrating holistic approaches conservation. This study also highlights immense potential implementing remote monitoring technology, such video camera traps, contexts. Such extend contexts benefit not only apes but provide opportunities caregivers, managers, students who are involved collaborative initiatives.

Language: Английский

---

Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour

IEEE Transactions on Image Processing, Journal Year: 2025, Volume and Issue: 34, P. 623 - 638

Published: Jan. 1, 2025

Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations keypoints or skeleton) been used to interpret behaviours mice. Nevertheless, effective encoding and decoding interaction underlying the rarely investigated existing methods. In particular, it is challenging model complex interactions between due highly deformable body shapes ambiguous movement patterns. To deal with modelling problem, we here propose a Cross-Skeleton Interaction Graph Aggregation Network (CS-IGANet) learn abundant dynamics freely interacting mice, where Node-level module (CS-NLI) multi-level intra-, inter- cross-skeleton interactions). Furthermore, design novel Interaction-Aware Transformer (IAT) dynamically graph-level representation update node-level representation, guided by our proposed interaction-aware self-attention mechanism. Finally, enhance ability model, auxiliary self-supervised learning task for measuring similarity nodes. Experimental results on standard CRMI13-Skeleton PDMB-Skeleton datasets show that outperforms several other state-of-the-art approaches.

Language: Английский

---

An intelligent humidity sensing system for human behavior recognition

Microsystems & Nanoengineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 22, 2025

Abstract An intelligent humidity sensing system has been developed for real-time monitoring of human behaviors through respiration detection. The key component this is a sensor that integrates thermistor and micro-heater. This employs porous nanoforests as its material, achieving sensitivity 0.56 pF/%RH within range 60–90% RH, along with excellent long-term stability superior gas selectivity. micro-heater in the device provides high operating temperature, enhancing by 5.8 times. significant improvement enables capture weak variations exhaled gases, while continuously monitors sensor’s temperature during use crucial information related to respiration. With assistance machine learning algorithm, behavior recognition based on constructed, enabling states be classified identified an accuracy up 96.2%. simple yet method holds great potential widespread applications medical analysis daily health monitoring.

Language: Английский

---