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

The Innovation Life, Год журнала: 2024, Номер unknown, С. 100105 - 100105

Опубликована: Янв. 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>

Язык: Английский

---

Phytochemical and biological studies on rare and endangered plants endemic to China. Part XLIV. Integrated NMR/EI-MS/LC-PDA-ESIMS approach for dereplication and targeted isolation of fortunefuroic acids from Keteleeria fortunei across diverse geographical origins

Phytochemistry, Год журнала: 2025, Номер 235, С. 114453 - 114453

Опубликована: Фев. 21, 2025

Язык: Английский

---

Apomixis in Systematics, Evolution and Phylogenetics of Angiosperms: Current Developments and Prospects

Critical Reviews in Plant Sciences, Год журнала: 2024, Номер unknown, С. 1 - 43

Опубликована: Сен. 13, 2024

Язык: Английский

---

Combining new technology with classic taxonomy to overcome hurdles to discovering dark taxa

Systematics and Biodiversity, Год журнала: 2025, Номер 23(1)

Опубликована: Янв. 31, 2025

With numerous perils threatening biodiversity, we must remember that most of the basic units biodiversity—species—remain unknown and therefore difficult to assess. Hordes new species continue be discovered described every year. As each requires extensive work, completing description Earth's biota could require millennia, leaving many wanting automate process via genetic barcoding artificial intelligence. Over time, lesser-known groups species, referred as 'dark taxa', will occupy an increasing proportion awaiting description. dark taxa have few barcodes or images for matching algorithms, however, I propose integrating traditional taxonomy into automated workflows by linking data verified specimens using classic taxonomic keys decision trees identifying images. The roles intelligence would thus limited until can build databases specimens. This strategy vital their scientific names so signify undiscovered which is lacking in current methods.

Язык: Английский

---

Teaching plant identification at a university in the age of artificial intelligence

Plants People Planet, Год журнала: 2025, Номер unknown

Опубликована: Май 15, 2025

Societal Impact Statement Society depends on experts able to correctly identify plants. This skill set is taught at university, classically using tools such as identification keys. The advent of artificial intelligence apps for identification, while benefiting society in many ways, poses a challenge university education: Students may not see the need learning skills beyond an app. lead generation unable verify and maintain plant identification. We suggest teachers carefully adapt their courses so students are equipped with become proficient use all tools. Summary Plant essential humanity. Universities train next who plants develop underlying taxonomic infrastructure. Apps can now high accuracy speed, record data integrate it additional information. These features make them highly attractive general public but also we university. Classically used text‐based keys by comparison appear unnecessarily complex. outline risk this development: emergence provide very infrastructure which depend, output independently. three guiding principles critically engaging university: (1) Treat future experts. They ones will build be test one method another. (2) Design exercises that cover levels. Simple remembering understanding, sufficient casual ID apps, falls short critical mindset strive academia. (3) Emphasise primary data. Understanding botanical information, however much aggregated, derived from physical specimens, essential. Including thoughtfully based these enable assess both strengths weaknesses. help ensure continue

Язык: Английский

---

A Novel Method for Molecular Identification of Genetic Diversity of Plant Resources in <i>Cymbidium</i> Sw. (Orchidaceae) Based on Taxon-Specific Variable Nucleotide Characters from Complete Chloroplast Genome

Hans Journal of Computational Biology, Год журнала: 2024, Номер 14(02), С. 13 - 28

Опубликована: Янв. 1, 2024

Язык: Английский

---

Phylogenetic and taxonomic insights into Betula: low-coverage whole genome sequencing and plastome analysis with focus on the rare Ukrainian endemic species Betula klokovii Zaverucha

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Янв. 15, 2025

Abstract Betula klokovii Zaverucha is a rare endemic species of Ukraine that still not well taxonomically studied. In the current pilot study, we performed low-coverage whole genome sequencing for B. , related ( pendula Roth and pubescens Ehrh.) assumed hybrid × pendula, assessed genomic structure taxa with different mapping settings using UMAP non-linear dimension reduction algorithm, extracted assembled plastomes. Single Nucleotide Polymorphism (SNP) analysis based on (LC-WGS) followed by visualization reveals separation from other analysed taxa. The best taxonomic resolution was achieved reads filtered contamination. contrast, result in obtaining complete plastome assemblies via NOVOPlasty pipeline raw reads. size eight newly plastid genomes ranges between 160,535 160,625bp, GC content 36,1%. We annotated 130 genes (113 unique) all assemblies. addition, investigated klokovii’s relationships 20 birch two intraspecific reconstructing plastome-based Bayesian inference maximum likelihood phylogenies. Overall, phylogeny provides better comparison to phylogenies few or nuclear molecular markers. However, it could be affected chloroplast capture, some factors like quality assembly, suitable detect hybrids when used alone. particular, found likely separate taxon closely but morphologically genetically distinct. study shows genome-wide SNP data have certain potential addressing issues specific within genus L. fully leverage this approach, suggest collecting much larger number sequences sequenced assembled. For understanding there need reference-grade chromosome scale polyploid species.

Язык: Английский

---

Commentary on "Preliminary Species Hypotheses" in Entomological Taxonomy: A Global Data and FAIR Infrastructure Perspective

Biodiversity Data Journal, Год журнала: 2025, Номер 13

Опубликована: Фев. 10, 2025

What if early taxonomic findings were treated like preprints, open to iterative improvement or managed with practices from the open-source community, such as Git branching, merging and patch management? Prompted by Buckley's article Charting a Future for Entomological Taxonomy in New Zealand (2024), this commentary explores these possibilities context of biodiversity informatics. In response need rapid, scalable monitoring, Buckley introduces preliminary species hypotheses (PSH) bridge between quick identification tools rigorous Linnaean system, leveraging DNA barcoding AI-assisted image recognition produce provisional classifications that can later be validated. Expanding on Buckley’s framework, emphasises critical role data linking, versioning integration support evolving data. Borrowing software practices, I explore idea managing PSH an infrastructure treats each update versioned "commit", which tracked, refined integrated over time. Drawing insights FAIR (Findable, Accessible, Interoperable, Reusable) principles Digital Extended Specimens, identify requirements PSH, including robust standards, persistent identifiers interoperability global repositories. Additionally, Taxonomic Data Objects offer model dynamically integrating into adaptable taxonomies evolve new tools. By positioning within open, infrastructure-focused advocates scalable, hypothesis-driven meets modern conservation needs, bridging traditional emerging taxonomy.

Язык: Английский

---

Remote sensing and artificial intelligence: revolutionizing pest management in agriculture

Frontiers in Sustainable Food Systems, Год журнала: 2025, Номер 9

Опубликована: Фев. 26, 2025

The agriculture sector is currently facing several challenges, including the growing global human population, depletion of natural resources, reduction arable land, rapidly changing climate, and frequent occurrence diseases such as Ebola, Lassa, Zika, Nipah, most recently, COVID-19 pandemic. These challenges pose a threat to food nutritional security place pressure on scientific community achieve Sustainable Development Goal 2 (SDG2), which aims eradicate hunger malnutrition. Technological advancement plays significant role in enhancing our understanding agricultural system its interactions from cellular level green field for benefit humanity. use remote sensing (RS), artificial intelligence (AI), machine learning (ML) approaches highly advantageous producing precise accurate datasets develop management tools models. technologies are beneficial soil types, efficiently managing water, optimizing nutrient application, designing forecasting early warning models, protecting crops plant insect pests, detecting threats locusts. application RS, AI, ML algorithms promising transformative approach improve resilience against biotic abiotic stresses sustainability meet needs ever-growing population. In this article covered leveraging AI RS data, how these enable real time monitoring, detection, pest outbreaks. Furthermore, discussed allows more precise, targeted control interventions, reducing reliance broad spectrum pesticides minimizing environmental impact. Despite data quality technology accessibility, integration holds potential revolutionizing management.

Язык: Английский

---

FGBNet: A Bio-Subspecies Classification Network with Multi-Level Feature Interaction

Diversity, Год журнала: 2025, Номер 17(4), С. 237 - 237

Опубликована: Март 27, 2025

Biodiversity is a foundation for maintaining ecosystem health and stability, while precise species identification crucial to monitoring protecting ecosystems. Subspecies of organisms, as carriers genetic diversity, play key roles in stability adaptive evolution. Accurate subspecies helps deepen our understanding distribution, ecological relationships, change trends, providing scientific basis effective protection strategies. Therefore, this study proposes FineGrained-BioNet (FGBNet), deep learning network model specifically constructed fine-grained bio-subspecies image classification. The combines detail information supplement module, multi-level feature interaction, coordinate attention (CA) mechanism improve the accuracy efficiency Through experimentation optimization, ConvNeXt selected backbone FGBNet extraction, effectiveness interaction method verified. Additionally, optimal placement CA within also explored. experimental results show that, compared with ConvNeXt-Tiny, achieved an increase 6.204% by increasing parameter quantity only 5.702%, reaching 90.748%. This indicates that significantly improves classification computational efficiency. proposed facilitates more accurate classification, promoting development biodiversity strong technical support conservation.

Язык: Английский

---