Dataset Information

ImPlatelet classifier: image-converted RNA biomarker profiles enable blood-based cancer diagnostics.

ABSTRACT: Liquid biopsies offer a minimally invasive sample collection, outperforming traditional biopsies employed for cancer evaluation. The widely used material is blood, which is the source of tumor-educated platelets. Here, we developed the imPlatelet classifier, which converts RNA-sequenced platelet data into images in which each pixel corresponds to the expression level of a certain gene. Biological knowledge from the Kyoto Encyclopedia of Genes and Genomes was also implemented to improve accuracy. Images obtained from samples can then be compared against standard images for specific cancers to determine a diagnosis. We tested imPlatelet on a cohort of 401 non-small cell lung cancer patients, 62 sarcoma patients, and 28 ovarian cancer patients. imPlatelet provided excellent discrimination between lung cancer cases and healthy controls, with accuracy equal to 1 in the independent dataset. When discriminating between noncancer cases and sarcoma or ovarian cancer patients, accuracy equaled 0.91 or 0.95, respectively, in the independent datasets. According to our knowledge, this is the first study implementing an image-based deep-learning approach combined with biological knowledge to classify human samples. The performance of imPlatelet considerably exceeds previously published methods and our own alternative attempts of sample discrimination. We show that the deep-learning image-based classifier accurately identifies cancer, even when a limited number of samples are available.

SUBMITTER: Pastuszak K

PROVIDER: S-EPMC8486571 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The human microbiota is associated with various disease states and holds a great promise for non-invasive diagnostics. However, microbiota data is challenging for traditional diagnostic approaches: It is high-dimensional, sparse and comprises of high inter-personal variation. State of the art machine learning tools are therefore needed to achieve this goal. While these tools have the ability to learn from complex data and interpret patterns therein that cannot be identified by humans, they often operate as black boxes, offering no insight into their decision-making process. In most cases, it is difficult to represent the learning of a classifier in a comprehensible way, which makes them prone to be mistrusted, or even misused, in a clinical environment. In this study, we aim to elucidate microbiota-based classifier decisions in a biologically meaningful context to allow their interpretation.We applied a method for explanation of classifier decisions on two microbiota datasets of increasing complexity: gut versus skin microbiota samples, and inflammatory bowel disease versus healthy gut microbiota samples. The algorithm simulates bacterial species as being unknown to a pre-trained classifier, and measures its effect on the outcome. Consequently, each patient is assigned a unique quantitative estimation of which species in their microbiota defined the classification of their sample. The algorithm was able to explain the classifier decisions well, demonstrated by our validation method, and the explanations were biologically consistent with recent microbiota findings.Application of a method for explaining individual classifier decisions for complex microbiota analysis proved feasible and opens perspectives on personalized therapy. Providing an explanation to support a microbiota-based diagnosis could guide decisions of clinical microbiologists, and has the potential to increase their confidence in the outcome of such decision support systems. This may facilitate the development of new diagnostic applications.

Project description:BackgroundThere is a need to identify scalable tuberculosis screening strategies among high burden populations. The WHO has identified a non-sputum-based triage test as a development priority.MethodsWe performed a diagnostic case-control study of point-of-care C-reactive protein (CRP) and Prototype-Xpert-MTB-Host-Response (Xpert-MTB-HR) assays in the context of a mass screening program for tuberculosis in two prisons in Brazil. All incarcerated individuals irrespective of symptoms were screened by sputum Xpert MTB/RIF and sputum culture. Among consecutive, Xpert MTB/RIF or culture-confirmed cases and Xpert MTB/RIF and culture-negative controls, CRP was quantified in serum by a point-of-care assay (iChroma-II) and a 3-gene expression score was quantified from whole blood using the Xpert-MTB-HR cartridge. We evaluated receiver operating characteristic area under the curve (AUC) and assessed specificity at 90% sensitivity and sensitivity at 70% specificity, consistent with WHO target product profile (TPP) benchmarks.FindingsTwo hundred controls (no TB) and 100 culture- or Xpert MTB/RIF-positive tuberculosis cases were included. Half of tuberculosis cases and 11% of controls reported any tuberculosis symptoms. AUC for CRP was 0·79 (95% CI: 0·73-0·84) and for Xpert-MTB-HR was 0·84 (95% CI: 0·79-0·89). At 90% sensitivity, Xpert-MTB-HR had significantly higher specificity (53·0%, 95% CI: 45·0-69·0%) than CRP (28·1%, 95% CI: 20·2-41·8%) (p = 0·003), both well below the TPP benchmark of 70%. Among individuals with medium or high sputum Xpert MTB/RIF semi-quantitative load, sensitivity (at 70% specificity) of CRP (90·3%, 95% CI: 74·2-98·0) and Xpert-MTB-HR (96·8%, 95% CI: 83·3-99·9%) was higher.InterpretationFor active case finding in this high tuberculosis-burden setting, CRP and Xpert-MTB-HR did not meet TPP benchmarks for a triage test. However, Xpert-MTB-HR was highly sensitive in detecting individuals with medium or high sputum bacillary burden.FundingNational Institutes of Health (R01 AI130058 and R01 AI149620) and Brazilian National Council for Scientific and Technological Development (CNPq-404182/2019-4).

Dataset Information

ImPlatelet classifier: image-converted RNA biomarker profiles enable blood-based cancer diagnostics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets