Undersampling: case studies of flaviviral inhibitory activities

Preoperative contrast-enhanced CT-based radiomics nomogram for differentiating benign and malignant primary retroperitoneal tumors

OBJECTIVES

This study evaluated the ability of a preoperative contrast-enhanced CT (CECT)-based radiomics nomogram to differentiate benign and malignant primary retroperitoneal tumors (PRT).

METHODS

Images and data from 340 patients with pathologically confirmed PRT were randomly placed into training (n = 239) and validation sets (n = 101). Two radiologists independently analyzed all CT images and made measurements. Key characteristics were identified through least absolute shrinkage selection combined with four machine-learning classifiers (support vector machine, generalized linear model, random forest, and artificial neural network back propagation) to create a radiomics signature. Demographic data and CECT characteristics were analyzed to formulate a clinico-radiological model. Independent clinical variables were merged with the best-performing radiomics signature to develop a radiomics nomogram. The discrimination capacity and clinical value of three models were quantified by the area under the receiver operating characteristics (AUC), accuracy, and decision curve analysis.

RESULTS

The radiomics nomogram was able to consistently differentiate between benign and malignant PRT in the training and validation datasets, with AUCs of 0.923 and 0.907, respectively. Decision curve analysis manifested that the nomogram achieved higher clinical net benefits than did separate use of the radiomics signature and clinico-radiological model.

CONCLUSIONS

The preoperative nomogram is valuable for differentiating between benign and malignant PRT; it can also aid in treatment planning.

KEY POINTS

• A noninvasive and accurate preoperative determination of benign and malignant PRT is crucial to identifying suitable treatments and predicting disease prognosis. • Associating the radiomics signature with clinical factors facilitates differentiation of malignant from benign PRT with improved diagnostic efficacy (AUC) and accuracy from 0.772 to 0.907 and from 0.723 to 0.842, respectively, compared with the clinico-radiological model alone. • For some PRT with anatomically special locations and when biopsy is extremely difficult and risky, a radiomics nomogram may provide a promising preoperative alternative for distinguishing benignity and malignancy.

A CT-based radiomics nomogram for differentiation of squamous cell carcinoma and non-Hodgkin's lymphoma of the palatine tonsil

OBJECTIVES

Accurate preoperative differentiation between squamous cell carcinoma (SCC) and non-Hodgkin's lymphoma (NHL) in the palatine tonsil is crucial because of their different treatment. This study aimed to construct and validate a contrast-enhanced CT (CECT)-based radiomics nomogram for preoperative differentiation of SCC and NHL in the palatine tonsil.

METHODS

This study enrolled 135 patients with a pathological diagnosis of SCC or NHL from two clinical centers, who were divided into training (n = 94; SCC = 50, NHL = 44) and external validation sets (n = 41; SCC = 22, NHL = 19). A radiomics signature was constructed from radiomics features extracted from routine CECT images and a radiomics score (Rad-score) was calculated. A clinical model was established using demographic features and CT findings. The independent clinical factors and Rad-score were combined to construct a radiomics nomogram. Performance of the clinical model, radiomics signature, and nomogram was assessed using receiver operating characteristics analysis and decision curve analysis.

RESULTS

Eleven features were finally selected to construct the radiomics signature. The radiomics nomogram incorporating gender, mean CECT value, and radiomics signature showed better predictive value for differentiating SCC from NHL than the clinical model for training (AUC, 0.919 vs. 0.801, p = 0.004) and validation (AUC, 0.876 vs. 0.703, p = 0.029) sets. Decision curve analysis demonstrated that the radiomics nomogram was more clinically useful than the clinical model.

CONCLUSIONS

A CECT-based radiomics nomogram was constructed incorporating gender, mean CECT value, and radiomics signature. This nomogram showed favorable predictive efficacy for differentiating SCC from NHL in the palatine tonsil, and might be useful for clinical decision-making.

KEY POINTS

• Differential diagnosis between SCC and NHL in the palatine tonsil is difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, gender, and mean contrast-enhanced CT value facilitates differentiation of SCC from NHL with improved diagnostic efficacy.

Evolving scenario of big data and Artificial Intelligence (AI) in drug discovery

The accumulation of massive data in the plethora of Cheminformatics databases has made the role of big data and artificial intelligence (AI) indispensable in drug design. This has necessitated the development of newer algorithms and architectures to mine these databases and fulfil the specific needs of various drug discovery processes such as virtual drug screening, de novo molecule design and discovery in this big data era. The development of deep learning neural networks and their variants with the corresponding increase in chemical data has resulted in a paradigm shift in information mining pertaining to the chemical space. The present review summarizes the role of big data and AI techniques currently being implemented to satisfy the ever-increasing research demands in drug discovery pipelines.

Evolutionary algorithm-based generation of optimum peptide sequences with dengue virus inhibitory activity

Background: There is currently no effective dengue virus (DENV) therapeutic. We aim to develop a genetic algorithm-based framework for the design of peptides with possible DENV inhibitory activity. Methods & results: A Python-based tool (denominated AutoPepGEN) based on a DENV support vector machine classifier as the objective function was implemented. AutoPepGEN was applied to the design of three- to seven-amino acid sequences and ten peptides were selected. Peptide-protease (DENV) docking and Molecular Mechanics-Generalized Born Surface Area calculations were performed for the selected sequences and favorable binding energies were observed. Conclusion: It is hoped that AutoPepGEN will serve as an in silico alternative to the experimental design of positional scanning combinatorial libraries, known to be prone to a combinatorial explosion. AutoPepGEN is available at: https://github.com/sjbarigye/AutoPepGEN.

Generative Adversarial Networks (GANs) Based Synthetic Sampling for Predictive Modeling

In the present report we evaluate the possible utility of the Generative Adversarial Networks (GANs) in mapping the chemical structural space for molecular property profiles, with the goal of subsequently yielding synthetic (artificial) samples for ligand-based molecular modeling. Two case studies are considered: BACE-1 (β-Secretase 1) and DENV (Dengue Virus) inhibitory activities, with the former focused on data populating and the latter on data balancing tasks. We train GANs using subsamples extracted from datasets for each bioactivity endpoint, and apply the trained networks in generating synthetic examples from the respective bioactivity chemical spaces. Original and synthetic samples are pooled together and employed to build BACE-1 and DENV inhibitory activity classifiers and their performance evaluated over tenfold external validation sets. In both case studies, the obtained classifiers demonstrate satisfactory predictivity with the former yielding accuracy (ACC) and Mathew's correlation coefficient (MCC) values of 0.80 and 0.59, while the latter produces balanced accuracy(BACC) and MCC values of 0.81 and 0.70, respectively. Moreover, the statistics of these classifiers are compared with those of other models in the literature demonstrating comparable to better performance. These results suggest that GANs may be useful in mapping the chemical space for molecular property profiles of interest, and thus allow for the extraction of synthetic examples for computational modeling.