ABSTRACT
Reprogramming of cellular metabolism is a driving factor of tumour progression and radiation therapy resistance. Identifying biochemical signatures associated with tumour radioresistance may assist with the development of targeted treatment strategies to improve clinical outcomes. Raman spectroscopy (RS) can monitor post-irradiation biomolecular changes and signatures of radiation response in tumour cells in a label-free manner. Convolutional Neural Networks (CNN) perform feature extraction directly from data in an end-to-end learning manner, with high classification performance. Furthermore, recently developed CNN explainability techniques help visualize the critical discriminative features captured by the model. In this work, a CNN is developed to characterize tumour response to radiotherapy based on its degree of radioresistance. The model was trained to classify Raman spectra of three human tumour cell lines as radiosensitive (LNCaP) or radioresistant (MCF7, H460) over a range of treatment doses and data collection time points. Additionally, a method based on Gradient-Weighted Class Activation Mapping (Grad-CAM) was used to determine response-specific salient Raman peaks influencing the CNN predictions. The CNN effectively classified the cell spectra, with accuracy, sensitivity, specificity, and F1 score exceeding 99.8%. Grad-CAM heatmaps of H460 and MCF7 cell spectra (radioresistant) exhibited high contributions from Raman bands tentatively assigned to glycogen, amino acids, and nucleic acids. Conversely, heatmaps of LNCaP cells (radiosensitive) revealed activations at lipid and phospholipid bands. Finally, Grad-CAM variable importance scores were derived for glycogen, asparagine, and phosphatidylcholine, and we show that their trends over cell line, dose, and acquisition time agreed with previously established models. Thus, the CNN can accurately detect biomolecular differences in the Raman spectra of tumour cells of varying radiosensitivity without requiring manual feature extraction. Finally, Grad-CAM may help identify metabolic signatures associated with the observed categories, offering the potential for automated clinical tumour radiation response characterization.
Subject(s)
Neural Networks, Computer , Spectrum Analysis, Raman , Humans , Spectrum Analysis, Raman/methods , Cell Line, Tumor , MCF-7 Cells , Glycogen/metabolismABSTRACT
Adverse childhood experiences (ACEs) encompass negative, stressful, and potentially traumatic events during childhood, impacting physical and mental health outcomes in adulthood. Limited studies suggest ACEs can have short-term effects on children's gut microbiomes and adult cognitive performance under stress. Nevertheless, the long-term effects of ACEs experienced during adulthood remain unexplored. Thus, this study aimed to assess the long-term effects of ACEs on the gut microbiota of adult nursing students. We employed a multidimensional approach, combining 16S rRNA sequencing, bioinformatics tools, and machine learning to predict functional capabilities. High-ACE individuals had an increased abundance of Butyricimonas spp. and Prevotella spp. and decreased levels of Clostridiales, and Lachnospira spp. Prevotella abundance correlated negatively with L-glutamate and L-glutamine biosynthesis, potentially impacting intestinal tissue integrity. While nursing students with high ACE reported increased depression, evidence for a direct gut microbiota-depression relationship was inconclusive. High-ACE individuals also experienced a higher prevalence of diarrhea. These findings highlight the long-lasting impact of ACEs on the gut microbiota and its functions in adulthood, particularly among nursing students. Further research is warranted to develop targeted interventions and strategies for healthcare professionals, optimizing overall health outcomes.
Subject(s)
Adverse Childhood Experiences , Gastrointestinal Microbiome , Students, Nursing , Adult , Child , Humans , RNA, Ribosomal, 16S/genetics , Computational BiologyABSTRACT
Objective: The microscopic analysis of biopsied lung nodules represents the gold-standard for definitive diagnosis of lung cancer. Deep learning has achieved pathologist-level classification of non-small cell lung cancer histopathology images at high resolutions (0.5-2 µm/px), and recent studies have revealed tomography-histology relationships at lower spatial resolutions. Thus, we tested whether patterns for histological classification of lung cancer could be detected at spatial resolutions such as those offered by ultra-high-resolution CT. Methods: We investigated the performance of a deep convolutional neural network (inception-v3) to classify lung histopathology images at lower spatial resolutions than that of typical pathology. Models were trained on 2167 histopathology slides from The Cancer Genome Atlas to differentiate between lung cancer tissues (adenocarcinoma (LUAD) and squamous-cell carcinoma (LUSC)), and normal dense tissue. Slides were accessed at 2.5 × magnification (4 µm/px) and reduced resolutions of 8, 16, 32, 64, and 128 µm/px were simulated by applying digital low-pass filters. Results: The classifier achieved area under the curve ≥0.95 for all classes at spatial resolutions of 4-16 µm/px, and area under the curve ≥0.95 for differentiating normal tissue from the two cancer types at 128 µm/px. Conclusions: Features for tissue classification by deep learning exist at spatial resolutions below what is typically viewed by pathologists. Advances in knowledge: We demonstrated that a deep convolutional network could differentiate normal and cancerous lung tissue at spatial resolutions as low as 128 µm/px and LUAD, LUSC, and normal tissue as low as 16 µm/px. Our data, and results of tomography-histology studies, indicate that these patterns should also be detectable within tomographic data at these resolutions.
ABSTRACT
Computer-aided prediction of aptamer sequences has been focused on primary sequence alignment and motif comparison. We observed that many aptamers have a conserved hairpin, yet the sequence of the hairpin can be highly variable. Taking such secondary structure information into consideration, a new algorithm combining conserved primary sequences and secondary structures is developed, which combines three scores based on sequence abundance, stability, and structure, respectively. This algorithm was used in the prediction of aptamers from the caffeine and theophylline selections. In the late rounds of the selections, when the libraries were converged, the predicted sequences matched well with the most abundant sequences. When the libraries were far from convergence and the sequences were deemed challenging for traditional analysis methods, this algorithm still predicted aptamer sequences that were experimentally verified by isothermal titration calorimetry. This algorithm paves a new way to look for patterns in aptamer selection libraries and mimics the sequence evolution process. It will help shorten the aptamer selection time and promote the biosensor and chemical biology applications of aptamers.
Subject(s)
Aptamers, Nucleotide , Biosensing Techniques , Aptamers, Nucleotide/genetics , Aptamers, Nucleotide/chemistry , SELEX Aptamer Technique/methods , Sequence Alignment , TheophyllineABSTRACT
Tumour cells exhibit altered metabolic pathways that lead to radiation resistance and disease progression. Raman spectroscopy (RS) is a label-free optical modality that can monitor post-irradiation biomolecular signatures in tumour cells and tissues. Convolutional Neural Networks (CNN) perform automated feature extraction directly from data, with classification accuracy exceeding that of traditional machine learning, in cases where data is abundant and feature extraction is challenging. We are interested in developing a CNN-based predictive model to characterize clinical tumour response to radiation therapy based on their degree of radiosensitivity or radioresistance. In this work, a CNN architecture is built for identifying post-irradiation spectral changes in Raman spectra of tumour tissue. The model was trained to classify irradiated versus non-irradiated tissue using Raman spectra of breast tumour xenografts. The CNN effectively classified the tissue spectra, with accuracies exceeding 92.1% for data collected 3 days post-irradiation, and 85.0% at day 1 post-irradiation. Furthermore, the CNN was evaluated using a leave-one-out- (mouse, section or Raman map) validation approach to investigate its generalization to new test subjects. The CNN retained good predictive accuracy (average accuracies 83.7%, 91.4%, and 92.7%, respectively) when little to no information for a specific subject was given during training. Finally, the classification performance of the CNN was compared to that of a previously developed model based on group and basis restricted non-negative matrix factorization and random forest (GBR-NMF-RF) classification. We found that CNN yielded higher classification accuracy, sensitivity, and specificity in mice assessed 3 days post-irradiation, as compared with the GBR-NMF-RF approach. Overall, the CNN can detect biochemical spectral changes in tumour tissue at an early time point following irradiation, without the need for previous manual feature extraction. This study lays the foundation for developing a predictive framework for patient radiation response monitoring.
Subject(s)
Breast Neoplasms , Spectrum Analysis, Raman , Humans , Animals , Mice , Female , Heterografts , Neural Networks, Computer , Algorithms , Breast Neoplasms/radiotherapyABSTRACT
Fundamental restoration ecology and community ecology theories can help us better understand the underlying mechanisms of fecal microbiota transplantation (FMT) and to better design future microbial therapeutics for recurrent Clostridioides difficile infections (rCDI) and other dysbiosis-related conditions. In this study, stool samples were collected from donors and rCDI patients one week prior to FMT (pre-FMT), as well as from patients one week following FMT (post-FMT). Using metagenomic sequencing and machine learning, our results suggested that FMT outcome is not only dependent on the ecological structure of the recipients, but also the interactions between the donor and recipient microbiomes at the taxonomical and functional levels. We observed that the presence of specific bacteria in donors (Clostridioides spp., Desulfovibrio spp., Odoribacter spp. and Oscillibacter spp.) and the absence of fungi (Yarrowia spp.) and bacteria (Wigglesworthia spp.) in recipients prior to FMT could predict FMT success. Our results also suggested a series of interlocked mechanisms for FMT success, including the repair of the disturbed gut ecosystem by transient colonization of nexus species followed by secondary succession of bile acid metabolizers, sporulators, and short chain fatty acid producers.
Subject(s)
Fecal Microbiota Transplantation , Feces/microbiology , Gastrointestinal Microbiome , Adult , Bacteroidetes/metabolism , Clostridiales/metabolism , Clostridioides/metabolism , Clostridium Infections/microbiology , Clostridium Infections/therapy , Desulfovibrio/metabolism , Female , Gastrointestinal Microbiome/genetics , Humans , Machine Learning , Male , Metagenomics , Tissue Donors , Treatment OutcomeABSTRACT
In most areas of machine learning, it is assumed that data quality is fairly consistent between training and inference. Unfortunately, in real systems, data are plagued by noise, loss, and various other quality reducing factors. While a number of deep learning algorithms solve end-stage problems of prediction and classification, very few aim to solve the intermediate problems of data pre-processing, cleaning, and restoration. Long Short-Term Memory (LSTM) networks have previously been proposed as a solution for data restoration, but they suffer from a major bottleneck: a large number of sequential operations. We propose using attention mechanisms to entirely replace the recurrent components of these data-restoration networks. We demonstrate that such an approach leads to reduced model sizes by as many as two orders of magnitude, a 2-fold to 4-fold reduction in training times, and 95% accuracy for automotive data restoration. We also show in a case study that this approach improves the performance of downstream algorithms reliant on clean data.