Gut Microbiota Analysis and In Silico Biomarker Detection of Children with Autism Spectrum Disorder across Cohorts.

The study of human gut microbiota has attracted increasing interest in the fields of life science and healthcare. However, the complicated and interconnected associations between gut microbiota and human diseases are still difficult to determine in a predictive fashion. Artificial intelligence such as machine learning (ML) and deep learning can assist in processing and interpreting biological datasets. In this study, we aggregated data from different studies based on the species composition and relative abundance of gut microbiota in children with autism spectrum disorder (ASD) and typically developed (TD) individuals and analyzed the commonalities and differences of ASD-associated microbiota across cohorts. We established a predictive model using an ML algorithm to explore the diagnostic value of the gut microbiome for the children with ASD and identify potential biomarkers for ASD diagnosis. The results indicated that the Shenzhen cohort achieved a higher area under the receiver operating characteristic curve (AUROC) value of 0.984 with 97% accuracy, while the Moscow cohort achieved an AUROC value of 0.81 with 67% accuracy. For the combination of the two cohorts, the average prediction results had an AUROC of 0.86 and 80% accuracy. The results of our cross-cohort analysis suggested that a variety of influencing factors, such as population characteristics, geographical region, and dietary habits, should be taken into consideration in microbial transplantation or dietary therapy. Collectively, our prediction strategy based on gut microbiota can serve as an enhanced strategy for the clinical diagnosis of ASD and assist in providing a more complete method to assess the risk of the disorder.

Rapid and non-invasive discrimination of acute leukemia bone marrow supernatants by Raman spectroscopy and multivariate statistical analysis.

A simple and non-invasive detection method for acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) was established by systematically investigating the characteristics of bone marrow supernatants from 61 AML patients, 22 ALL patients, and 5 volunteers without hematological tumors by Raman spectroscopy and orthogonal partial least squares discriminant analysis (OPLS-DA). The control group could be well distinguished from the AML and ALL groups by Raman peaks of 859, 1031, 1437, 1443, 1446, 1579, and 1603 cm-1 and from the AML subtypes groups (AML-M2, AML-M3, AML-M4, and AML-M5) by the Raman peaks of 859, 1221, 1230, 1437, 1443, and 1603 cm-1, indicating high sensitivity and specificity of the method. Potentially important variables of acute leukemia (AL) prognosis, such as cholesterol, high-density lipoprotein, low-density lipoprotein, adenosine deaminase, and hemoglobin, could be effectively identified by Raman peaks of 1437, 1443, and 1579 cm-1. Therefore, Raman spectroscopy can be considered as a new non-invasive clinical tool for the detection of different types of AL and can be used to correlate biochemical parameters of AL patients with the classification and prognosis of AL.

Raman spectroscopy-based biomarker screening by studying the fingerprint characteristics of chronic lymphocytic leukemia and diffuse large B-cell lymphoma.

Raman spectroscopy (RS) can provide fingerprint-type information on biochemical molecules. RS-based blood plasma analysis of solid tumors has been reported in recent years; however, there are no studies on the use of this analysis for detecting blood diseases. We studied the features of blood plasma in patients with diffuse large B-cell lymphoma (DLBCL) and chronic lymphocytic leukemia (CLL) by RS with the aim of developing a simple blood test for noninvasive DLBCL and CLL detection. We analyzed blood plasma from 33 DLBCL patients, 39 CLL patients and 30 healthy volunteers. Orthogonal partial least squares discriminant analysis (OPLS-DA) could build two clusters with almost no overlap between DLBCL/CLL and the controls. We used the prediction set to test the model built by OPLS-DA. For the CLL model, the sensitivity was 92.86%, and the specificity was 100%, whereas for the DLBCL model, the sensitivity was 80% and the specificity was 92.31%. We found Raman bands specific to both DLBCL and CLL patients in comparison with the healthy volunteers. Most importantly, we found that the combination of the 1445 cm-1 and 1655 cm-1 Raman shifts could discriminate DLBCL from CLL and even the other solid tumors reported to date. Further analysis of the assignments of 1655 cm-1 also gave us a clue to find potential important variables hemoglobin and serum albumin related with the CLL prognosis. Our exploratory study primarily demonstrated the great potential of developing RS blood plasma analysis as a novel clinical tool for the noninvasive detection of DLBCL and CLL.