RUC. Repositorio da Universidade da Coruña
Publicación
Artículo científico (JournalArticle)
Polymerase Chain Reaction. Perturbation Theory and Machine Learning Artificial Intelligence-Experimental Microbiome Analysis: Applications to Ancient DNA and Tree Soil Metagenomics Cases of Study
[Abstract]: The exponential growth of genomic data has created a pressing need for methods capable of interpreting complex biological information, especially in fields like paleogenomics and environmental metagenomics. Ancient DNA (aDNA) analysis faces challenges such as degradation and contamination, while soil metagenomic DNA (soDNA) analysis is hindered by microbial diversity and incomplete reference databases. To address these limitations, this study proposes the polymerase chain reaction (PCR).Perturbation Theory and Machine Learning (PTML) methodology, which integrates machine learning with Perturbation Theory to analyze genetic sequences without the need for alignment. Two models are developed: the first classifies bacterial aDNA sequences extracted from Miocene amber; the second predicts tree health using microbial gene abundance in forest soils. Both rely on entropy-based descriptors (θk) and structural differences (Δθk) between query and reference sequences, which serve as perturbation operators for supervised learning algorithms. This approach allows the detection of meaningful patterns even without complete genomic references. The aDNA model achieves 99.65% sensitivity and 99.81% specificity, while the soDNA model reaches 98.85% sensitivity and 92.56% specificity. These results confirm the robustness and applicability of PCR.PTML in diverse genomic contexts, presenting it as a valuable tool for ancient DNA classification and environmental metagenomics analysis., These authors, J.L.R. and E.A., contributed equally to this work. This project was funded by grants INCITE07PXI203141ES (Conselleria de Industria, Xunta de Galicia, Spain) and BFU2009-07745 (MINECO, Spain). Likewise, the authors recognize the support of the National Science Foundation under the NSF MRI award OAC-2019077, and support by the State of North Dakota. CCAST HPC System supercomputing support at NDSU is acknowledged. In addition, the work was partly supported by Basque Government/Eusko Jaurlaritza (IT1558-22) and (IT1648-22), SPRI ELKARTEK grants AIMOFGIF (KK-2022/00032), Ministry of Science and Innovation (PID2022-137365NB-I00), and LANBIDE, INVESTIGO, Eusko Jaurlaritza, Grants, IKERDATA 2022/IKER/000040, funded by NextGenerationEU funds of European Commission, and Xunta de Galicia Consolidated group, grant ED431C 2022/46. JCY and RE are members of the Spanish climate-induced forest decline (ReDec) funded by MCIN/AEI (grant RED2024-153822-T), as well as from the projects PID2020-113244GB-C21 and PID2020-113244GA-C22 projects (both funded by MCIN/ AEI /10.13039/501100011033). Also the authors recognize the funding support of the following research groups and centers of The University of A Coruña (UDC): Software Engineering Lab (ISLA), Artificial Neuron Networks and Adaptative Systems – Medical Imaging and Radiological Diagnosis (RNASA- IMEDIR), the Centre for Information and Communications Technology Research (CITIC) and Center for Technological Innovation in Construction and Civil Engineering (CITEEC)., Xunta de Galicia; INCITE07PXI203141ES, Xunta de Galicia; ED431C 2022/46, United States National Science Foundation; OAC-2019077, Gobierno Vasco; IT1558-22, Gobierno Vasco; IT1648-22, Gobierno Vasco; KK-2022/00032
Proyecto:
MICINN / Plan Estatal de Investigación Científica y Técnica y de Innovación 2008-2011 BFU2009-07745
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2022-137365NB-I00
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2024-2027 RED2024-153822-T
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-113244GB-C21
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-113244GA-C22