PDAC-ANN: an artificial neural network to predict pancreatic ductal adenocarcinoma based on gene expression

BACKGROUND

Although the pancreatic ductal adenocarcinoma (PDAC) presents high mortality and metastatic potential, there is a lack of effective therapies and a low survival rate for this disease. This PDAC scenario urges new strategies for diagnosis, drug targets, and treatment.

METHODS

We performed a gene expression microarray meta-analysis of the tumor against normal tissues in order to identify differentially expressed genes (DEG) shared among all datasets, named core-genes (CG). We confirmed the CG protein expression in pancreatic tissue through The Human Protein Atlas. It was selected five genes with the highest area under the curve (AUC) among these proteins with expression confirmed in the tumor group to train an artificial neural network (ANN) to classify samples.

RESULTS

This microarray included 461 tumor and 187 normal samples. We identified a CG composed of 40 genes, 39 upregulated, and one downregulated. The upregulated CG included proteins and extracellular matrix receptors linked to actin cytoskeleton reorganization. With the Human Protein Atlas, we verified that fourteen genes of the CG are translated, with high or medium expression in most of the pancreatic tumor samples. To train our ANN, we selected the best genes (AHNAK2, KRT19, LAMB3, LAMC2, and S100P) to classify the samples based on AUC using mRNA expression. The network classified tumor samples with an f1-score of 0.83 for the normal samples and 0.88 for the PDAC samples, with an average of 0.86. The PDAC-ANN could classify the test samples with a sensitivity of 87.6 and specificity of 83.1.

CONCLUSION

The gene expression meta-analysis and confirmation of the protein expression allow us to select five genes highly expressed PDAC samples. We could build a python script to classify the samples based on RNA expression. This software can be useful in the PDAC diagnosis.

Parasitism-Mediated Interactions Between the Ring-Legged Earwig and Sugarcane Borer Larvae

Sugarcane is one of the most economically important crops in Brazil. The damage caused by Diatraea saccharalis (F.) (Lepidoptera: Crambidae) results in high costs for its production. Cotesia flavipes Cameron (Hymenoptera: Braconidae) is the most efficient means of controlling this pest. The prohibition of burning and the preservation of soil cover through non-tillage practices increased many population densities of natural enemies of the sugarcane borer (SCB) in sugarcane fields. Euborellia annulipes (Lucas) (Dermaptera: Anisolabididae) is a predator found in sugarcane fields and is associated with predation of SCB. This study aimed to evaluate the influence of parasitism of D. saccharalis by C. flavipes on predation by E. annulipes adult females. For this purpose, fourth instar sugarcane borer larvae were exposed to parasitism over a 5-day period or were not parasitized. Subsequently, the prey was supplied to the predator in arenas under choice and no-choice conditions and under different densities to evaluate the feeding preference over a 12-h period and functional response of the predator over a 24-h period. E. annulipes killed 2-3 fourth instar larvae of the sugarcane borer over a 12-h period. SCB parasitism did not affect the feeding preference of the predator and did not alter the type II functional response. However, the handling time of the predator was lower (1.943 h) and there was a higher T/T_h ratio on the non-parasitized larvae (12.352). Our findings indicate E. annulipes as a promising biological control agent of D. saccharalis, with a potential to assist in the sugarcane borer management approaches and could to reduce the costs of parasitoid release in the field.

Interleukin-10 rs2227307 and CXCR2 rs1126579 polymorphisms modulate the predisposition to septic shock

Despite major improvements in its treatment and diagnosis, sepsis is still a leading cause of death and admittance to the intensive care unit (ICU). Failure to identify patients at high risk of developing septic shock contributes to an increase in the sepsis burden and rapid molecular tests are currently the most promising avenue to aid in patient risk determination and therapeutic anticipation. The primary goal of this study was to evaluate the genetic susceptibility that affects sepsis outcome in 72 sepsis patients admitted to the ICU. Seven polymorphisms were genotyped in key inflammatory response genes in sepsis, including tumour necrosis factor-α, interlelukin (IL)-1β, IL-10, IL-8, Toll-like receptor 4, CXCR1 and CXCR2. The primary finding showed that patients who were homozygous for the major A allele in IL-10 rs1800896 had almost five times higher chance to develop septic shock compared to heterozygotes. Similarly, selected clinical features and CXCR2 rs1126579 single nucleotide polymorphisms modulated septic shock susceptibility without affecting survival. These data support the hypothesis that molecular testing has clinical usefulness to improve sepsis prognostic models. Therefore, enrichment of the ICU portfolio by including these biomarkers will aid in the early identification of sepsis patients who may develop septic shock.