1
|
Yang B, Zhou X, Liu S. Tracing the genealogy origin of geographic populations based on genomic variation and deep learning. Mol Phylogenet Evol 2024; 198:108142. [PMID: 38964594 DOI: 10.1016/j.ympev.2024.108142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 05/30/2024] [Accepted: 07/01/2024] [Indexed: 07/06/2024]
Abstract
Assigning a query individual animal or plant to its derived population is a prime task in diverse applications related to organismal genealogy. Such endeavors have conventionally relied on short DNA sequences under a phylogenetic framework. These methods naturally show constraints when the inferred population sources are ambiguously phylogenetically structured, a scenario demanding substantially more informative genetic signals. Recent advances in cost-effective production of whole-genome sequences and artificial intelligence have created an unprecedented opportunity to trace the population origin for essentially any given individual, as long as the genome reference data are comprehensive and standardized. Here, we developed a convolutional neural network method to identify population origins using genomic SNPs. Three empirical datasets (an Asian honeybee, a red fire ant, and a chicken datasets) and two simulated populations are used for the proof of concepts. The performance tests indicate that our method can accurately identify the genealogy origin of query individuals, with success rates ranging from 93 % to 100 %. We further showed that the accuracy of the model can be significantly increased by refining the informative sites through FST filtering. Our method is robust to configurations related to batch sizes and epochs, whereas model learning benefits from the setting of a proper preset learning rate. Moreover, we explained the importance score of key sites for algorithm interpretability and credibility, which has been largely ignored. We anticipate that by coupling genomics and deep learning, our method will see broad potential in conservation and management applications that involve natural resources, invasive pests and weeds, and illegal trades of wildlife products.
Collapse
Affiliation(s)
- Bing Yang
- Department of Entomology, China Agricultural University, Beijing 100193, China
| | - Xin Zhou
- Department of Entomology, China Agricultural University, Beijing 100193, China.
| | - Shanlin Liu
- Department of Entomology, China Agricultural University, Beijing 100193, China; Key Laboratory of Zoological Systematics and Evolution, Institute of Zoology, Chinese Academy of Sciences, Beijing 100101, China.
| |
Collapse
|
2
|
Bifarin O, Fernández FM. Automated Machine Learning and Explainable AI (AutoML-XAI) for Metabolomics: Improving Cancer Diagnostics. JOURNAL OF THE AMERICAN SOCIETY FOR MASS SPECTROMETRY 2024; 35:1089-1100. [PMID: 38690775 PMCID: PMC11157651 DOI: 10.1021/jasms.3c00403] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Revised: 02/08/2024] [Accepted: 04/23/2024] [Indexed: 05/03/2024]
Abstract
Metabolomics generates complex data necessitating advanced computational methods for generating biological insight. While machine learning (ML) is promising, the challenges of selecting the best algorithms and tuning hyperparameters, particularly for nonexperts, remain. Automated machine learning (AutoML) can streamline this process; however, the issue of interpretability could persist. This research introduces a unified pipeline that combines AutoML with explainable AI (XAI) techniques to optimize metabolomics analysis. We tested our approach on two data sets: renal cell carcinoma (RCC) urine metabolomics and ovarian cancer (OC) serum metabolomics. AutoML, using Auto-sklearn, surpassed standalone ML algorithms like SVM and k-Nearest Neighbors in differentiating between RCC and healthy controls, as well as OC patients and those with other gynecological cancers. The effectiveness of Auto-sklearn is highlighted by its AUC scores of 0.97 for RCC and 0.85 for OC, obtained from the unseen test sets. Importantly, on most of the metrics considered, Auto-sklearn demonstrated a better classification performance, leveraging a mix of algorithms and ensemble techniques. Shapley Additive Explanations (SHAP) provided a global ranking of feature importance, identifying dibutylamine and ganglioside GM(d34:1) as the top discriminative metabolites for RCC and OC, respectively. Waterfall plots offered local explanations by illustrating the influence of each metabolite on individual predictions. Dependence plots spotlighted metabolite interactions, such as the connection between hippuric acid and one of its derivatives in RCC, and between GM3(d34:1) and GM3(18:1_16:0) in OC, hinting at potential mechanistic relationships. Through decision plots, a detailed error analysis was conducted, contrasting feature importance for correctly versus incorrectly classified samples. In essence, our pipeline emphasizes the importance of harmonizing AutoML and XAI, facilitating both simplified ML application and improved interpretability in metabolomics data science.
Collapse
Affiliation(s)
- Olatomiwa
O. Bifarin
- School
of Chemistry and Biochemistry, Georgia Institute
of Technology, Atlanta, Georgia 30332, United States
| | - Facundo M. Fernández
- School
of Chemistry and Biochemistry, Georgia Institute
of Technology, Atlanta, Georgia 30332, United States
- Petit
Institute of Bioengineering and Bioscience, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
| |
Collapse
|
3
|
Kaptein BL, Pijls B, Koster L, Kärrholm J, Hull M, Niesen A, Heesterbeek P, Callary S, Teeter M, Gascoyne T, Röhrl SM, Flivik G, Bragonzoni L, Laende E, Sandberg O, Solomon LB, Nelissen R, Stilling M. Guideline for RSA and CT-RSA implant migration measurements: an update of standardizations and recommendations. Acta Orthop 2024; 95:256-267. [PMID: 38819193 PMCID: PMC11141406 DOI: 10.2340/17453674.2024.40709] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Accepted: 04/08/2024] [Indexed: 06/01/2024] Open
Abstract
Opening remarks: These guidelines are the result of discussions within a diverse group of RSA researchers. They were approved in December 2023 by the board and selected members of the International Radiostereometry Society to update the guidelines by Valstar et al. [1]. By adhering to these guidelines, RSA studies will become more transparent and consistent in execution, presentation, reporting, and interpretation. Both authors and reviewers of scientific papers using RSA may use these guidelines, summarized in the Checklist, as a reference. Deviations from these guidelines should have the underlying rationale stated.
Collapse
Affiliation(s)
- Bart L Kaptein
- Department of Orthopedics, Leiden University Medical Center, Leiden, The Netherlands.
| | - Bart Pijls
- Department of Orthopedics, Leiden University Medical Center, Leiden, The Netherlands
| | - Lennard Koster
- Department of Orthopedics, Leiden University Medical Center, Leiden, The Netherlands
| | - Johan Kärrholm
- Department of Orthopedics, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Maury Hull
- Orthopedic Surgery Department, University of California, Davis, United States
| | - Abby Niesen
- Orthopedic Surgery Department, University of California, Davis, United States
| | - Petra Heesterbeek
- Orthopedic Research Department, Sint Maartenskliniek, Nijmegen, The Netherlands
| | - Stuart Callary
- Department of Orthopedics and Trauma, Royal Adelaide Hospital, Adelaide, Australia
| | - Matthew Teeter
- Department of Medical Biophysics, Western University, London, Canada
| | | | - Stephan M Röhrl
- Division of Orthopaedic Surgery, Oslo University Hospital, Oslo, Norway
| | - Gunnar Flivik
- Department of Orthopedics, Skane University Hospital, Lund, Sweden
| | | | - Elise Laende
- Department of Surgery, Dalhousie University, Halifax, Canada
| | | | - L Bogdan Solomon
- Department of Orthopedics and Trauma, Royal Adelaide Hospital, Adelaide, Australia
| | - Rob Nelissen
- Department of Orthopedics, Leiden University Medical Center, Leiden, The Netherlands
| | - Maiken Stilling
- Department of Orthopedics, Aarhus University Hospital, Aarhus, Denmark
| |
Collapse
|
4
|
Budhkar A, Tang Z, Liu X, Zhang X, Su J, Song Q. xSiGra: Explainable model for single-cell spatial data elucidation. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.04.27.591458. [PMID: 38746321 PMCID: PMC11092461 DOI: 10.1101/2024.04.27.591458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/16/2024]
Abstract
Recent advancements in spatial imaging technologies have revolutionized the acquisition of high-resolution multi-channel images, gene expressions, and spatial locations at the single-cell level. Our study introduces xSiGra, an interpretable graph-based AI model, designed to elucidate interpretable features of identified spatial cell types, by harnessing multi-modal features from spatial imaging technologies. By constructing a spatial cellular graph with immunohistology images and gene expression as node attributes, xSiGra employs hybrid graph transformer models to delineate spatial cell types. Additionally, xSiGra integrates a novel variant of Grad-CAM component to uncover interpretable features, including pivotal genes and cells for various cell types, thereby facilitating deeper biological insights from spatial data. Through rigorous benchmarking against existing methods, xSiGra demonstrates superior performance across diverse spatial imaging datasets. Application of xSiGra on a lung tumor slice unveils the importance score of cells, illustrating that cellular activity is not solely determined by itself but also impacted by neighboring cells. Moreover, leveraging the identified interpretable genes, xSiGra reveals endothelial cell subset interacting with tumor cells, indicating its heterogeneous underlying mechanisms within the complex cellular communications.
Collapse
|
5
|
Zhang X, Ma L, Sun D, Yi M, Wang Z. Artificial Intelligence in Telemedicine: A Global Perspective Visualization Analysis. Telemed J E Health 2024. [PMID: 38436235 DOI: 10.1089/tmj.2023.0704] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/05/2024] Open
Abstract
Background: The use of artificial intelligence (AI) in telemedicine has been a popular topic in academic research in recent years, resulting in a surge of literature publications. This study provides a scientific overview of AI in telemedicine through bibliometric and visualization analysis. Methods: The Web of Science Core Collection was used as the data source, and the search was conducted on June 1, 2023. A total of 2,860 articles and review studies published in English between 2010 and 2023 were included. This study analyzed general information on the field, trends in publication output, countries/regions, authors, journals, influential articles, keyword usage, and knowledge flows between disciplines. The Bibliometrix R package, VOSviewer, and CiteSpace were used for the analysis. Results: The rate of articles published on AI in telemedicine is increasing by ∼42.1% annually. The United States and China are the top two countries in terms of the number of articles published, accounting for 37.1% of the overall publication volume. In addition to AI and telemedicine, machine learning, digital health, and deep learning are the top three keywords in terms of frequency of occurrence. The keyword time trend graph shows that ChatGPT became one of the important keywords in 2023. The analysis of burst detection suggests that mobile health, based on mobile phones, may be a promising area for future research. Conclusions: This study systematically reviewed the development of AI in telemedicine and identified current research hotspots and future research directions. The results will provide impetus for the innovative development of this field.
Collapse
Affiliation(s)
- Xu Zhang
- School of Nursing, Peking University, Beijing, China
| | - Li Ma
- Department of Emergency Medicine, Peking University Third Hospital, Beijing, China
| | - Di Sun
- School of Nursing, Liaoning University of Traditional Chinese Medicine, Shenyang, Liaoning, China
| | - Mo Yi
- School of Nursing, Peking University, Beijing, China
| | - Zhiwen Wang
- School of Nursing, Peking University, Beijing, China
| |
Collapse
|
6
|
Gogoberidze N, Cimini BA. Defining the boundaries: challenges and advances in identifying cells in microscopy images. Curr Opin Biotechnol 2024; 85:103055. [PMID: 38142646 PMCID: PMC11170924 DOI: 10.1016/j.copbio.2023.103055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Revised: 11/28/2023] [Accepted: 11/28/2023] [Indexed: 12/26/2023]
Abstract
Segmentation, or the outlining of objects within images, is a critical step in the measurement and analysis of cells within microscopy images. While improvements continue to be made in tools that rely on classical methods for segmentation, deep learning-based tools increasingly dominate advances in the technology. Specialist models such as Cellpose continue to improve in accuracy and user-friendliness, and segmentation challenges such as the Multi-Modality Cell Segmentation Challenge continue to push innovation in accuracy across widely varying test data as well as efficiency and usability. Increased attention on documentation, sharing, and evaluation standards is leading to increased user-friendliness and acceleration toward the goal of a truly universal method.
Collapse
Affiliation(s)
| | - Beth A Cimini
- Imaging Platform, Broad Institute, Cambridge, MA 02142, USA.
| |
Collapse
|
7
|
Pandiri AR, Auerbach SS, Stevens JL, Blomme EAG. Toxicogenomics Approaches to Address Toxicity and Carcinogenicity in the Liver. Toxicol Pathol 2023; 51:470-481. [PMID: 38288963 PMCID: PMC11014763 DOI: 10.1177/01926233241227942] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/13/2024]
Abstract
Toxicogenomic technologies query the genome, transcriptome, proteome, and the epigenome in a variety of toxicological conditions. Due to practical considerations related to the dynamic range of the assays, sensitivity, cost, and technological limitations, transcriptomic approaches are predominantly used in toxicogenomics. Toxicogenomics is being used to understand the mechanisms of toxicity and carcinogenicity, evaluate the translational relevance of toxicological responses from in vivo and in vitro models, and identify predictive biomarkers of disease and exposure. In this session, a brief overview of various transcriptomic technologies and practical considerations related to experimental design was provided. The advantages of gene network analyses to define mechanisms were also discussed. An assessment of the utility of toxicogenomic technologies in the environmental and pharmaceutical space showed that these technologies are being increasingly used to gain mechanistic insights and determining the translational relevance of adverse findings. Within the environmental toxicology area, there is a broader regulatory consideration of benchmark doses derived from toxicogenomics data. In contrast, these approaches are mainly used for internal decision-making in pharmaceutical development. Finally, the development and application of toxicogenomic signatures for prediction of apical endpoints of regulatory concern continues to be area of intense research.
Collapse
Affiliation(s)
- Arun R Pandiri
- National Institute of Environmental Health Sciences, Durham, North Carolina, USA
| | - Scott S Auerbach
- National Institute of Environmental Health Sciences, Durham, North Carolina, USA
| | | | | |
Collapse
|