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

Abstract

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.

Artificial intelligence for early detection of pancreatic adenocarcinoma: The future is promising

“…Recent data showed that early diagnosis could be possible through AI analysis of the transcription products of certain PDAC genes. These studies have reported sensitivity and specificity ranging from 88%-95% and 83%-95% respectively[ 58 , 59 ]. AI has also been utilized to match PDAC biological information with chemical properties of specific drugs in order to develop models capable of predicting response to these specific agents[ 60 , 61 ].…”

Predicting the Use Labor Induction Intervention: A Machine Learning Approach for the Birth-Cohort Registry at A Tertiary Hospital in North Tanzania.

“…This algorithm can learn by themselves and produce the output that is not limited to the input provided to them. Another fascinating feature is that, even if a neuron is not responding or a piece of information is missing, the network can detect the fault and still produce the output [36,37]. In addition, ANN can perform multiple tasks in parallel without affecting the system performance.…”

Identifying Drug Targets in Pancreatic Ductal Adenocarcinoma Through Machine Learning, Analyzing Biomolecular Networks, and Structural Modeling

“…Additionally, we evaluated gene expression as an input feature for ML and selected the most relevant genes for PDAC using SVM-RFE (Almeida et al, 2020), which provided a ranking for the genes. Then, each DEG was assigned an R s value (see Materials and Methods), which was used to further rank all genes.…”

“…By applying ML algorithms to proteomics and other molecular data from The Cancer Genome Atlas (TCGA), two subtypes of pancreatic cancer can be classified (Sinkala et al, 2020). A meta-analysis of PDAC microarray data could help predict biomarkers that can be used to build AI-based computational predictors for classifying PDAC and normal samples (Bhasin et al, 2016), as well as predicting sample status (Almeida et al, 2020). To predict and validate novel drug targets for cancer, including PDAC, a ML-based classifier that integrates a variety of genomic and systems datasets was built to prioritize drug targets (Jeon et al, 2014).…”