Dataset Information

Semi-supervised machine learning for automated species identification by collagen peptide mass fingerprinting.

ABSTRACT: Biomolecular methods for species identification are increasingly being utilised in the study of changing environments, both at the microscopic and macroscopic levels. High-throughput peptide mass fingerprinting has been largely applied to bacterial identification, but increasingly used to identify archaeological and palaeontological skeletal material to yield information on past environments and human-animal interaction. However, as applications move away from predominantly domesticate and the more abundant wild fauna to a much wider range of less common taxa that do not yet have genetically-derived sequence information, robust methods of species identification and biomarker selection need to be determined.Here we developed a supervised machine learning algorithm for classifying the species of ancient remains based on collagen fingerprinting. The aim was to minimise requirements on prior knowledge of known species while yielding satisfactory sensitivity and specificity. The algorithm uses iterations of a modified random forest classifier with a similarity scoring system to expand its identified samples. We tested it on a set of 6805 spectra and found that a high level of accuracy can be achieved with a training set of five identified specimens per taxon.This method consistently achieves higher accuracy than two-dimensional principal component analysis and similar accuracy with hierarchical clustering using optimised parameters, which greatly reduces requirements for human input. Within the vertebrata, we demonstrate that this method was able to achieve the taxonomic resolution of family or sub-family level whereas the genus- or species-level identification may require manual interpretation or further experiments. In addition, it also identifies additional species biomarkers than those previously published.

SUBMITTER: Gu M

PROVIDER: S-EPMC6019507 | biostudies-other | 2018 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Semi-supervised machine learning for automated species identification by collagen peptide mass fingerprinting.

Gu Muxin M Buckley Michael M

BMC bioinformatics 20180626 1

<h4>Background</h4>Biomolecular methods for species identification are increasingly being utilised in the study of changing environments, both at the microscopic and macroscopic levels. High-throughput peptide mass fingerprinting has been largely applied to bacterial identification, but increasingly used to identify archaeological and palaeontological skeletal material to yield information on past environments and human-animal interaction. However, as applications move away from predominantly do ...[more]

PMID: 29940843

Similar Datasets

Project description:Appropriate wound management shortens the healing times and reduces the management costs, benefiting the patient in physical terms and potentially reducing the healthcare system’s economic burden. Among the instrumental measurement methods, the image analysis of a wound area is becoming one of the cornerstones of chronic ulcer management. Our study aim is to develop a solid AI method based on a convolutional neural network to segment the wounds efficiently to make the work of the physician more efficient, and subsequently, to lay the foundations for the further development of more in-depth analyses of ulcer characteristics. In this work, we introduce a fully automated model for identifying and segmenting wound areas which can completely automatize the clinical wound severity assessment starting from images acquired from smartphones. This method is based on an active semi-supervised learning training of a convolutional neural network model. In our work, we tested the robustness of our method against a wide range of natural images acquired in different light conditions and image expositions. We collected the images using an ad hoc developed app and saved them in a database which we then used for AI training. We then tested different CNN architectures to develop a balanced model, which we finally validated with a public dataset. We used a dataset of images acquired during clinical practice and built an annotated wound image dataset consisting of 1564 ulcer images from 474 patients. Only a small part of this large amount of data was manually annotated by experts (ground truth). A multi-step, active, semi-supervised training procedure was applied to improve the segmentation performances of the model. The developed training strategy mimics a continuous learning approach and provides a viable alternative for further medical applications. We tested the efficiency of our model against other public datasets, proving its robustness. The efficiency of the transfer learning showed that after less than 50 epochs, the model achieved a stable DSC that was greater than 0.95. The proposed active semi-supervised learning strategy could allow us to obtain an efficient segmentation method, thereby facilitating the work of the clinician by reducing their working times to achieve the measurements. Finally, the robustness of our pipeline confirms its possible usage in clinical practice as a reliable decision support system for clinicians.

Project description:Collagen is one of the most ubiquitous proteins in the animal kingdom and the dominant protein in extracellular tissues such as bone, skin and other connective tissues in which it acts primarily as a supporting scaffold. It has been widely investigated scientifically, not only as a biomedical material for regenerative medicine, but also for its role as a food source for both humans and livestock. Due to the long-term stability of collagen, as well as its abundance in bone, it has been proposed as a source of biomarkers for species identification not only for heat- and pressure-rendered animal feed but also in ancient archaeological and palaeontological specimens, typically carried out by peptide mass fingerprinting (PMF) as well as in-depth liquid chromatography (LC)-based tandem mass spectrometric methods. Through the analysis of the three most common domesticates species, cow, sheep, and pig, this research investigates the advantages of each approach over the other, investigating sites of sequence variation with known functional properties of the collagen molecule. Results indicate that the previously identified species biomarkers through PMF analysis are not among the most variable type 1 collagen peptides present in these tissues, the latter of which can be detected by LC-based methods. However, it is clear that the highly repetitive sequence motif of collagen throughout the molecule, combined with the variability of the sites and relative abundance levels of hydroxylation, can result in high scoring false positive peptide matches using these LC-based methods. Additionally, the greater alpha 2(I) chain sequence variation, in comparison to the alpha 1(I) chain, did not appear to be specific to any particular functional properties, implying that intra-chain functional constraints on sequence variation are not as great as inter-chain constraints. However, although some of the most variable peptides were only observed in LC-based methods, until the range of publicly available collagen sequences improves, the simplicity of the PMF approach and suitable range of peptide sequence variation observed makes it the ideal method for initial taxonomic identification prior to further analysis by LC-based methods only when required.

Dataset Information

Semi-supervised machine learning for automated species identification by collagen peptide mass fingerprinting.

Publications

Semi-supervised machine learning for automated species identification by collagen peptide mass fingerprinting.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets