Leveraging explainable AI for gut microbiome-based colorectal cancer classification.
Ontology highlight
ABSTRACT:
SUBMITTER: Rynazal R
PROVIDER: S-EPMC9912568 | biostudies-literature | 2023 Feb
REPOSITORIES: biostudies-literature
Publications
Leveraging explainable AI for gut microbiome-based colorectal cancer classification.
Rynazal Ryza R Fujisawa Kota K Shiroma Hirotsugu H Salim Felix F Mizutani Sayaka S Shiba Satoshi S Yachida Shinichi S Yamada Takuji T
Genome biology 20230209 1
Studies have shown a link between colorectal cancer (CRC) and gut microbiome compositions. In these studies, machine learning is used to infer CRC biomarkers using global explanation methods. While these methods allow the identification of bacteria generally correlated with CRC, they fail to recognize species that are only influential for some individuals. In this study, we investigate the potential of Shapley Additive Explanations (SHAP) for a more personalized CRC biomarker identification. Ana ...[more]
Similar Datasets
Project description:Colorectal cancer is a common and deadly disease in the United States accounting for over 50,000 deaths in 2020. This progressive disease is highly preventable with early detection and treatment, but many people do not comply with the recommended screening guidelines. The gut microbiome has emerged as a promising target for noninvasive detection of colorectal cancer. Most microbiome-based classification efforts utilize taxonomic abundance data from operational taxonomic units (OTUs) or amplicon sequence variants (ASVs) with the goal of increasing taxonomic resolution. However, it is unknown which taxonomic resolution is optimal for microbiome-based classification of colorectal cancer. To address this question, we used a reproducible machine learning framework to quantify classification performance of models based on data annotated to phylum, class, order, family, genus, OTU, and ASV levels. We found that model performance increased with increasing taxonomic resolution, up to the family level where performance was equal (P > 0.05) among family (mean area under the receiver operating characteristic curve [AUROC], 0.689), genus (mean AUROC, 0.690), and OTU (mean AUROC, 0.693) levels before decreasing at the ASV level (P < 0.05; mean AUROC, 0.676). These results demonstrate a trade-off between taxonomic resolution and prediction performance, where coarse taxonomic resolution (e.g., phylum) is not distinct enough, but fine resolution (e.g., ASV) is too individualized to accurately classify samples. Similar to the story of Goldilocks and the three bears (L. B. Cauley, Goldilocks and the Three Bears, 1981), mid-range resolution (i.e., family, genus, and OTU) is "just right" for optimal prediction of colorectal cancer from microbiome data. IMPORTANCE Despite being highly preventable, colorectal cancer remains a leading cause of cancer-related death in the United States. Low-cost, noninvasive detection methods could greatly improve our ability to identify and treat early stages of disease. The microbiome has shown promise as a resource for detection of colorectal cancer. Research on the gut microbiome tends to focus on improving our ability to profile species and strain level taxonomic resolution. However, we found that finer resolution impedes the ability to predict colorectal cancer based on the gut microbiome. These results highlight the need for consideration of the appropriate taxonomic resolution for microbiome analyses and that finer resolution is not always more informative.
| S-EPMC8749421 | biostudies-literature
Project description:Microbial Dysbiosis is associated with the etiology and pathogenesis of diseases. The studies on the vaginal microbiome in cervical cancer are essential to discern the cause and effect of the condition. The present study characterizes the microbial pathogenesis involved in developing cervical cancer. Relative species abundance assessment identified Firmicutes, Actinobacteria, and Proteobacteria dominating the phylum level. A significant increase in Lactobacillus iners and Prevotella timonensis at the species level revealed its pathogenic influence on cervical cancer progression. The diversity, richness, and dominance analysis divulges a substantial decline in cervical cancer compared to control samples. The β diversity index proves the homogeneity in the subgroups' microbial composition. The association between enriched Lactobacillus iners at the species level, Lactobacillus, Pseudomonas, and Enterococcus genera with cervical cancer is identified by Linear discriminant analysis Effect Size (LEfSe) prediction. The functional enrichment corroborates the microbial disease association with pathogenic infections such as aerobic vaginitis, bacterial vaginosis, and chlamydia. The dataset is trained and validated with repeated k-fold cross-validation technique using a random forest algorithm to determine the discriminative pattern from the samples. SHapley Additive exPlanations (SHAP), a game theoretic approach, is employed to analyze the results predicted by the model. Interestingly, SHAP identified that the increase in Ralstonia has a higher probability of predicting the sample as cervical cancer. New evidential microbiomes identified in the experiment confirm the presence of pathogenic microbiomes in cervical cancer vaginal samples and their mutuality with microbial imbalance.
| S-EPMC10137380 | biostudies-literature
Project description:Alterations in the human microbiome have been observed in a variety of conditions such as asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets can offer an improved understanding of the microbiome's role in human health. To gain actionable insights it is essential to consider both the predictive power and the transparency of the models by providing explanations for the predictions. We combine the collection of leg skin microbiome samples from two healthy cohorts of women with the application of an explainable artificial intelligence (EAI) approach that provides accurate predictions of phenotypes with explanations. The explanations are expressed in terms of variations in the relative abundance of key microbes that drive the predictions. We predict skin hydration, subject's age, pre/post-menopausal status and smoking status from the leg skin microbiome. The changes in microbial composition linked to skin hydration can accelerate the development of personalized treatments for healthy skin, while those associated with age may offer insights into the skin aging process. The leg microbiome signatures associated with smoking and menopausal status are consistent with previous findings from oral/respiratory tract microbiomes and vaginal/gut microbiomes respectively. This suggests that easily accessible microbiome samples could be used to investigate health-related phenotypes, offering potential for non-invasive diagnosis and condition monitoring. Our EAI approach sets the stage for new work focused on understanding the complex relationships between microbial communities and phenotypes. Our approach can be applied to predict any condition from microbiome samples and has the potential to accelerate the development of microbiome-based personalized therapeutics and non-invasive diagnostics.
| S-EPMC7907326 | biostudies-literature
Project description:A large volume of data is being captured through the Phasor Measurement Unit (PMU), which opens new opportunities and challenges to the study of transmission line faults. To be specific, the Phasor Measurement Unit (PMU) data represents many different states of the power networks. The states of the PMU device help to identify different types of transmission line faults. For a precise understanding of transmission line faults, only the parameters that contain voltage and current magnitude estimations are not sufficient. This requirement has been addressed by generating data with more parameters such as frequencies and phase angles utilizing the Phasor Measurement Unit (PMU) for data acquisition. The data has been generated through the simulation of a transmission line model on ePMU DSA tools and Matlab Simulink. Different machine learning models have been trained with the generated synthetic data to classify transmission line fault cases. The individual models including Decision Tree (DT), Random Forest (RF), and K-Nearest Neighbor (K-NN) have outperformed other models in fault classification which have acquired a cross-validation accuracy of 99.84%, 99.83%, and 99.76% respectively across 10 folds. Soft voting has been used to combine the performance of these best-performing models. Accordingly, the constructed ensemble model has acquired a cross-validation accuracy of 99.88% across 10 folds. The performance of the combined models in the ensemble learning process has been analyzed through explainable AI (XAI) which increases the interpretability of the input parameters in terms of making predictions. Consequently, the developed model has been evaluated with several performance matrices, such as precision, recall, and f1 score, and also tested on the IEEE 14 bus system. To sum up, this article has demonstrated the classification of six scenarios including no fault and fault cases from transmission lines with a significant number of training parameters and also interpreted the effect of each parameter to make predictions of different fault cases with great success.
| S-EPMC10861062 | biostudies-literature
Project description:BackgroundColorectal cancer (CRC) is a type of tumor caused by the uncontrolled growth of cells in the mucosa lining the last part of the intestine. Emerging evidence underscores an association between CRC and gut microbiome dysbiosis. The high mortality rate of this cancer has made it necessary to develop new early diagnostic methods. Machine learning (ML) techniques can represent a solution to evaluate the interaction between intestinal microbiota and host physiology. Through explained artificial intelligence (XAI) it is possible to evaluate the individual contributions of microbial taxonomic markers for each subject. Our work also implements the Shapley Method Additive Explanations (SHAP) algorithm to identify for each subject which parameters are important in the context of CRC.ResultsThe proposed study aimed to implement an explainable artificial intelligence framework using both gut microbiota data and demographic information from subjects to classify a cohort of control subjects from those with CRC. Our analysis revealed an association between gut microbiota and this disease. We compared three machine learning algorithms, and the Random Forest (RF) algorithm emerged as the best classifier, with a precision of 0.729 ± 0.038 and an area under the Precision-Recall curve of 0.668 ± 0.016. Additionally, SHAP analysis highlighted the most crucial variables in the model's decision-making, facilitating the identification of specific bacteria linked to CRC. Our results confirmed the role of certain bacteria, such as Fusobacterium, Peptostreptococcus, and Parvimonas, whose abundance appears notably associated with the disease, as well as bacteria whose presence is linked to a non-diseased state.DiscussionThese findings emphasizes the potential of leveraging gut microbiota data within an explainable AI framework for CRC classification. The significant association observed aligns with existing knowledge. The precision exhibited by the RF algorithm reinforces its suitability for such classification tasks. The SHAP analysis not only enhanced interpretability but identified specific bacteria crucial in CRC determination. This approach opens avenues for targeted interventions based on microbial signatures. Further exploration is warranted to deepen our understanding of the intricate interplay between microbiota and health, providing insights for refined diagnostic and therapeutic strategies.
| S-EPMC10901987 | biostudies-literature
Project description:Although colorectal cancer is the third leading cause of death in Morocco, there are no studies of the microbiome changes associated with the disease in the Moroccan population. The aim of our study was to compare the stool microbiome of Moroccan cancer patients with healthy individuals. We analyzed the microbiome composition of samples from 11 CRC patients and 12 healthy individuals by 16S rRNA amplicon sequencing. Principal coordinate analysis of samples revealed defined cancer versus healthy clusters. Our findings showed that cancer samples had higher proportions of Firmicutes (T?=?50.5%; N?=?28.4%; p?=?0.04), specifically of Clostridia (T?=?48.3%; N?=?19.0%; p?=?0.002), and Fusobacteria (T?=?0.1%; N?=?0.0%; p?=?0.02), especially of Fusobacteriia (T?=?0.1%; N?=?0.0%; p?=?0.02), while Bacteroidetes were enriched in healthy samples (T?=?35.1%; N?=?62.8%; p?=?0.06), particularly the class Bacteroidia (T?=?35.1%; N?=?62.6%; p?=?0.06). Porphyromonas, Clostridium, Ruminococcus, Selenomonas, and Fusobacterium were significantly overrepresented in diseased patients, similarly to other studies. Predicted functional information showed that bacterial motility proteins, flagellar assembly, and fatty acid biosynthesis metabolism were significantly overrepresented in cancer patients, while amino acid metabolism and glycan biosynthesis were overrepresented in controls. This suggests that involvement of these functional metagenomes is similar and relevant in the carcinogenesis process, independent of the origin of the samples. Results from this study allowed identification of bacterial taxa relevant to the Moroccan population and encourages larger studies to facilitate population-directed therapeutic approaches.
| S-EPMC6096775 | biostudies-literature
Project description:Background and Motivation: COVID-19 has resulted in a massive loss of life during the last two years. The current imaging-based diagnostic methods for COVID-19 detection in multiclass pneumonia-type chest X-rays are not so successful in clinical practice due to high error rates. Our hypothesis states that if we can have a segmentation-based classification error rate <5%, typically adopted for 510 (K) regulatory purposes, the diagnostic system can be adapted in clinical settings. Method: This study proposes 16 types of segmentation-based classification deep learning-based systems for automatic, rapid, and precise detection of COVID-19. The two deep learning-based segmentation networks, namely UNet and UNet+, along with eight classification models, namely VGG16, VGG19, Xception, InceptionV3, Densenet201, NASNetMobile, Resnet50, and MobileNet, were applied to select the best-suited combination of networks. Using the cross-entropy loss function, the system performance was evaluated by Dice, Jaccard, area-under-the-curve (AUC), and receiver operating characteristics (ROC) and validated using Grad-CAM in explainable AI framework. Results: The best performing segmentation model was UNet, which exhibited the accuracy, loss, Dice, Jaccard, and AUC of 96.35%, 0.15%, 94.88%, 90.38%, and 0.99 (p-value <0.0001), respectively. The best performing segmentation-based classification model was UNet+Xception, which exhibited the accuracy, precision, recall, F1-score, and AUC of 97.45%, 97.46%, 97.45%, 97.43%, and 0.998 (p-value <0.0001), respectively. Our system outperformed existing methods for segmentation-based classification models. The mean improvement of the UNet+Xception system over all the remaining studies was 8.27%. Conclusion: The segmentation-based classification is a viable option as the hypothesis (error rate <5%) holds true and is thus adaptable in clinical practice.
| S-EPMC9497601 | biostudies-literature
Project description:Pollen monitoring have become data-intensive in recent years as real-time detectors are deployed to classify airborne pollen grains. Machine learning models with a focus on deep learning, have an essential role in the pollen classification task. Within this study we developed an explainable framework to unveil a deep learning model for pollen classification. Model works on data coming from single particle detector (Rapid-E) that records for each particle optical fingerprint with scattered light and laser induced fluorescence. Morphological properties of a particle are sensed with the light scattering process, while chemical properties are encoded with fluorescence spectrum and fluorescence lifetime induced by high-resolution laser. By utilizing these three data modalities, scattering, spectrum, and lifetime, deep learning-based models with millions of parameters are learned to distinguish different pollen classes, but a proper understanding of such a black-box model decisions demands additional methods to employ. Our study provides the first results of applied explainable artificial intelligence (xAI) methodology on the pollen classification model. Extracted knowledge on the important features that attribute to the predicting particular pollen classes is further examined from the perspective of domain knowledge and compared to available reference data on pollen sizes, shape, and laboratory spectrofluorometer measurements.
| S-EPMC9958198 | biostudies-literature
Project description:We tested the hypothesis that an altered community of gut microbes is associated with risk of colorectal cancer (CRC) in a study of 47 CRC case subjects and 94 control subjects. 16S rRNA genes in fecal bacterial DNA were amplified by universal primers, sequenced by 454 FLX technology, and aligned for taxonomic classification to microbial genomes using the QIIME pipeline. Taxonomic differences were confirmed with quantitative polymerase chain reaction and adjusted for false discovery rate. All statistical tests were two-sided. From 794217 16S rRNA gene sequences, we found that CRC case subjects had decreased overall microbial community diversity (P = .02). In taxonomy-based analyses, lower relative abundance of Clostridia (68.6% vs 77.8%) and increased carriage of Fusobacterium (multivariable odds ratio [OR] = 4.11; 95% confidence interval [CI] = 1.62 to 10.47) and Porphyromonas (OR = 5.17; 95% CI = 1.75 to 15.25) were found in case subjects compared with control subjects. Because of the potentially modifiable nature of the gut bacteria, our findings may have implications for CRC prevention.
| S-EPMC3866154 | biostudies-literature
Project description:IntroductionGraph-based representations are becoming more common in the medical domain, where each node defines a patient, and the edges signify associations between patients, relating individuals with disease and symptoms in a node classification task. In this study, a Graph Convolutional Networks (GCN) model was utilized to capture differences in neurocognitive, genetic, and brain atrophy patterns that can predict cognitive status, ranging from Normal Cognition (NC) to Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Elucidating model predictions is vital in medical applications to promote clinical adoption and establish physician trust. Therefore, we introduce a decomposition-based explanation method for individual patient classification.MethodsOur method involves analyzing the output variations resulting from decomposing input values, which allows us to determine the degree of impact on the prediction. Through this process, we gain insight into how each feature from various modalities, both at the individual and group levels, contributes to the diagnostic result. Given that graph data contains critical information in edges, we studied relational data by silencing all the edges of a particular class, thereby obtaining explanations at the neighborhood level.ResultsOur functional evaluation showed that the explanations remain stable with minor changes in input values, specifically for edge weights exceeding 0.80. Additionally, our comparative analysis against SHAP values yielded comparable results with significantly reduced computational time. To further validate the model's explanations, we conducted a survey study with 11 domain experts. The majority (71%) of the responses confirmed the correctness of the explanations, with a rating of above six on a 10-point scale for the understandability of the explanations.DiscussionStrategies to overcome perceived limitations, such as the GCN's overreliance on demographic information, were discussed to facilitate future adoption into clinical practice and gain clinicians' trust as a diagnostic decision support system.
| S-EPMC10801225 | biostudies-literature