Search

Using a machine learning methods, we aim to find biological effect biomarkers of prenatal arsenic exposure in newborn cord blood. From the Gene Expression Omnibus (GEO) database, two datasets (GSE48354 and GSE7967) pertaining to cord blood sequencing while exposed to arsenic were retrieved and merged for additional study. Using the "limma" package in the R, differentially expressed genes (DEGs) were eliminated. Machine learning techniques of the LASSO regression algorithm and SVM-RFE algorithm were used to find potential biological effect biomarkers for cord blood sequencing in pregnant women exposed to arsenic. To evaluate the efficacy of biomarkers, a receiver operating characteristic (ROC) curve was used. Furthermore, we investigated the proportion of invading immune cells in each sample using CIBERSORT, and we investigated the relationship between biomarkers and immune cells using the Spearman approach. Using LASSO regression and the SVM-RFE technique, 28 DEGs were discovered, and the main biomarkers of cord blood exposed to arsenic were discovered to be DENND2D, OLIG1, RGS18, CXCL16, DDIT4, FOS, G0S2, GPR183, JMJD6, and SOCS3. According to an immune infiltration analysis and correlation analysis, key biomarkers were substantially associated with the invading immune cells. Ten genes are important biomarkers of cord blood exposed to arsenic connected with infiltrating immune cells, and infiltrating immune cells may play important roles in cord blood exposed to arsenic, according to the study's findings., (© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

The evolution of pathway enzymes enhances the biosynthesis of high-value chemicals, crucial for pharmaceutical, and agrochemical applications. However, unpredictable evolutionary landscapes of pathway genes often hinder successful evolution. Here, the presence of complex epistasis is identifued within the representative naringenin biosynthetic pathway enzymes, hampering straightforward directed evolution. Subsequently, a biofoundry-assisted strategy is developed for pathway bottlenecking and debottlenecking, enabling the parallel evolution of all pathway enzymes along a predictable evolutionary trajectory in six weeks. This study then utilizes a machine learning model, ProEnsemble, to further balance the pathway by optimizing the transcription of individual genes. The broad applicability of this strategy is demonstrated by constructing an Escherichia coli chassis with evolved and balanced pathway genes, resulting in 3.65 g L-1 naringenin. The optimized naringenin chassis also demonstrates enhanced production of other flavonoids. This approach can be readily adapted for any given number of enzymes in the specific metabolic pathway, paving the way for automated chassis construction in contemporary biofoundries.