New enumeration algorithm for protein structure comparison and classification.

BACKGROUND: Protein structure comparison and classification is an effective method for exploring protein structure-function relations. This problem is computationally challenging. Many different computational approaches for protein structure comparison apply the secondary structure elements (SSEs) representation of protein structures. RESULTS: We study the complexity of the protein structure comparison problem based on a mixed-graph model with respect to different computational frameworks. We develop an effective approach for protein structure comparison based on a novel independent set enumeration algorithm. Our approach (named: ePC, efficient enumeration-based Protein structure Comparison) is tested for general purpose protein structure comparison as well as for specific protein examples. Compared with other graph-based approaches for protein structure comparison, the theoretical running-time O(1.47 rnn2) of our approach ePC is significantly better, where n is the smaller number of SSEs of the two proteins, r is a parameter of small value. CONCLUSION: Through the enumeration algorithm, our approach can identify different substructures from a list of high-scoring solutions of biological interest. Our approach is flexible to conduct protein structure comparison with the SSEs in sequential and non-sequential order as well. Supplementary data of additional testing and the source of ePC will be available at http://bioinformatics.astate.edu/.

An Ensemble of U-Net Models for Kidney Tumor Segmentation With CT Images.

We present here the Arkansas AI-Campus solution method for the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Our Arkansas AI-Campus team participated the KiTS19 Challenge for four months, from March to July of 2019. This paper provides a summary of our methods, training, testing and validation results for this grand challenge in biomedical imaging analysis. Our deep learning model is an ensemble of U-Net models developed after testing many model variations. Our model has consistent performance on the local test dataset and the final competition independent test dataset. The model achieved local test Dice scores of 0.949 for kidney and tumor segmentation, and 0.601 for tumor segmentation, and the final competition test earned Dice scores 0.9470 and 0.6099 respectively. The Arkansas AI-Campus team solution with a composite DICE score of 0.7784 has achieved a final ranking of top fifty worldwide, and top five among the United States teams in the KiTS19 Competition.

COVID19 Diagnosis Using Chest X-rays and Transfer Learning.

A pandemic of respiratory illnesses from a novel coronavirus known as Sars-CoV-2 has swept across the globe since December of 2019. This is calling upon the research community including medical imaging to provide effective tools for use in combating this virus. Research in biomedical imaging of viral patients is already very active with machine learning models being created for diagnosing Sars-CoV-2 infections in patients using CT scans and chest x-rays. We aim to build upon this research. Here we used a transfer-learning approach to develop models capable of diagnosing COVID19 from chest x-ray. For this work we compiled a dataset of 112120 negative images from the Chest X-Ray 14 and 2725 positive images from public repositories. We tested multiple models, including logistic regression and random forest and XGBoost with and without principal components analysis, using five-fold cross-validation to evaluate recall, precision, and f1-score. These models were compared to a pre-trained deep-learning model for evaluating chest x-rays called COVID-Net. Our best model was XGBoost with principal components with a recall, precision, and f1-score of 0.692, 0.960, 0.804 respectively. This model greatly outperformed COVID-Net which scored 0.987, 0.025, 0.048. This model, with its high precision and reasonable sensitivity, would be most useful as "rule-in" test for COVID19. Though it outperforms some chemical assays in sensitivity, this model should be studied in patients who would not ordinarily receive a chest x-ray before being used for screening.

Spatial Pyramid Pooling With 3D Convolution Improves Lung Cancer Detection.

Lung cancer is the leading cause of cancer deaths. Low-dose computed tomography (CT)screening has been shown to significantly reduce lung cancer mortality but suffers from a high false positive rate that leads to unnecessary diagnostic procedures. The development of deep learning techniques has the potential to help improve lung cancer screening technology. Here we present the algorithm, DeepScreener, which can predict a patient's cancer status from a volumetric lung CT scan. DeepScreener is based on our model of Spatial Pyramid Pooling, which ranked 16th of 1972 teams (top 1 percent)in the Data Science Bowl 2017 competition (DSB2017), evaluated with the challenge datasets. Here we test the algorithm with an independent set of 1449 low-dose CT scans of the National Lung Screening Trial (NLST)cohort, and we find that DeepScreener has consistent performance of high accuracy. Furthermore, by combining Spatial Pyramid Pooling and 3D Convolution, it achieves an AUC of 0.892, surpassing the previous state-of-the-art algorithms using only 3D convolution. The advancement of deep learning algorithms can potentially help improve lung cancer detection with low-dose CT scans.

Transfer learning with chest X-rays for ER patient classification.

One of the challenges with urgent evaluation of patients with acute respiratory distress syndrome (ARDS) in the emergency room (ER) is distinguishing between cardiac vs infectious etiologies for their pulmonary findings. We conducted a retrospective study with the collected data of 171 ER patients. ER patient classification for cardiac and infection causes was evaluated with clinical data and chest X-ray image data. We show that a deep-learning model trained with an external image data set can be used to extract image features and improve the classification accuracy of a data set that does not contain enough image data to train a deep-learning model. An analysis of clinical feature importance was performed to identify the most important clinical features for ER patient classification. The current model is publicly available with an interface at the web link: http://nbttranslationalresearch.org/ .

DNAp: A Pipeline for DNA-seq Data Analysis.

Next-generation sequencing is empowering genetic disease research. However, it also brings significant challenges for efficient and effective sequencing data analysis. We built a pipeline, called DNAp, for analyzing whole exome sequencing (WES) and whole genome sequencing (WGS) data, to detect mutations from disease samples. The pipeline is containerized, convenient to use and can run under any system, since it is a fully automatic process in Docker container form. It is also open, and can be easily customized with user intervention points, such as for updating reference files and different software or versions. The pipeline has been tested with both human and mouse sequencing datasets, and it has generated mutations results, comparable to published results from these datasets, and reproducible across heterogeneous hardware platforms. The pipeline DNAp, funded by the US Food and Drug Administration (FDA), was developed for analyzing DNA sequencing data of FDA. Here we make DNAp an open source, with the software and documentation available to the public at http://bioinformatics.astate.edu/dna-pipeline/ .

Liquid biopsy and its role in an advanced clinical trial for lung cancer.

Liquid biopsy methodologies, for the purpose of plasma genotyping of cell-free DNA (cfDNA) of solid tumors, are a new class of novel molecular assays. Such assays are rapidly entering the clinical sphere of research-based monitoring in translational oncology, especially for thoracic malignancies. Potential applications for these blood-based cfDNA assays include: (i) initial diagnosis, (ii) response to therapy and follow-up, (iii) tumor evolution, and (iv) minimal residual disease evaluation. Precision medicine will benefit from cutting-edge molecular diagnostics, especially regarding treatment decisions in the adjuvant setting, where avoiding over-treatment and unnecessary toxicity are paramount. The use of innovative genetic analysis techniques on individual patient tumor samples is being pursued in several advanced clinical trials. Rather than using a categorical treatment plan, the next critical step of therapeutic decision making is providing the "right" cancer therapy for an individual patient, including correct dose and timeframe based on the molecular analysis of the tumor in question. Per the 21st Century Cures Act, innovative clinical trials are integral for biomarker and drug development. This will include advanced clinical trials utilizing: (i) innovative assays, (ii) molecular profiling with cutting-edge bioinformatics, and (iii) clinically relevant animal or tissue models. In this paper, a mini-review addresses state-of-the-art liquid biopsy approaches. Additionally, an on-going advanced clinical trial for lung cancer with novelty through synergizing liquid biopsies, co-clinical trials, and advanced bioinformatics is also presented. Impact statement Liquid biopsy technology is providing a new source for cancer biomarkers, and adds new dimensions in advanced clinical trials. Utilizing a non-invasive routine blood draw, the liquid biopsy provides abilities to address perplexing issues of tumor tissue heterogeneity by identifying mutations in both primary and metastatic lesions. Regarding the assessment of response to cancer therapy, the liquid biopsy is not ready to replace medical imaging, but adds critical new information; for instance, through a temporal assessment of quantitative circulating tumor DNA (ctDNA) assay results, and importantly, the ability to monitor for signs of resistance, via emerging clones. Adjuvant therapy may soon be considered based on a quantitative cfDNA assay. As sensitivity and specificity of the technology continue to progress, cancer screening and prevention will improve and save countless lives by finding the cancer early, so that a routine surgery may be all that is required for a definitive cure.

Big data - a 21st century science Maginot Line? No-boundary thinking: shifting from the big data paradigm.

Whether your interests lie in scientific arenas, the corporate world, or in government, you have certainly heard the praises of big data: Big data will give you new insights, allow you to become more efficient, and/or will solve your problems. While big data has had some outstanding successes, many are now beginning to see that it is not the Silver Bullet that it has been touted to be. Here our main concern is the overall impact of big data; the current manifestation of big data is constructing a Maginot Line in science in the 21st century. Big data is not "lots of data" as a phenomena anymore; The big data paradigm is putting the spirit of the Maginot Line into lots of data. Big data overall is disconnecting researchers and science challenges. We propose No-Boundary Thinking (NBT), applying no-boundary thinking in problem defining to address science challenges.

TERPRED: A Dynamic Structural Data Analysis Tool.

Computational protein structure prediction mainly involves the main-chain prediction and the side-chain confirmation determination. In this research, we developed a new structural bioinformatics tool, TERPRED for generating dynamic protein side-chain rotamer libraries. Compared with current various rotamer sampling methods, our work is unique in that it provides a method to generate a rotamer library dynamically based on small sequence fragments of a target protein. The Rotamer Generator provides a means for existing side-chain sampling methods using static pre-existing rotamer libraries, to sample from dynamic target-dependent libraries. Also, existing side-chain packing algorithms that require large rotamer libraries for optimal performance, could possibly utilize smaller, target-relevant libraries for improved speed.