A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

The necessity for reliable ab initio protein secondary structure prediction is growing along with the demand for accurate tertiary structure prediction. Although recent developments have slightly exceeded previous methods of secondary structure prediction, these methods rarely surpass 80% accuracy. Developing new tools and methods to improve secondary structure prediction is essential to the improvement of tertiary structure prediction in proteins. Here we present DNSS, a secondary structure predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures. Graphical processing units and CUDA software are used to optimize the deep network architecture and efficiently…

Automated Large-Scale File Preparation and Docking: Evaluation of ITScore and STScore Using the 2012 Community Structure−Activity Resource Benchmark

We present the first study utilizing the full set of compounds from the recently released 2012 Community Structure−Activity Resource (CSAR) data set. The CSAR data set is a realistic benchmark for protein-ligand docking scoring functions, containing 57 crystal structures and 757 compounds, most with known affinities from pharmaceutical companies. We used the CSAR data set to evaluate two knowledge-based scoring functions, ITScore and STScore, and a simple force-field-based potential, FFPScore. To conduct this large-scale docking evaluation, we scripted our docking software and associated tools for automated preparation, docking, and evaluation, enabling others to reproduce our results. We also developed a…

Simulation based Training for Medical Skills: Comparative Effectiveness of Training Methods and Evaluating the Translational Impact

Simulation based medical education is gaining wide spread appeal as a means to increase medical skill training opportunities and enhance patient safety in a changing medical environment. Two factors have accelerated the adoption of patient simulation in health care including; 1) the successful use of simulation in other high risk endeavors such as airline pilot training, and, 2) the high face validity of patient simulation. It is expected that the use of computerized manikins and patient simulation will continue to grow. Much research demonstrates the use and apparent effectiveness of simulation-based training. However, comparative evaluation of simulation-based training methods is…

Large-Scale Pairwise Alignments on GPU Clusters: Exploring the Implementation Space

Several problems in computational biology require the all-against-all pairwise comparisons of tens of thousands of individual biological sequences. Each such comparison can be performed with the well-known Needleman-Wunsch alignment algorithm. However, with the rapid growth of biological databases, performing all possible comparisons with this algorithm in serial becomes extremely time-consuming. The massive computational power of graphics processing units (GPUs) makes them an appealing choice for accelerating these computations. As such, CPU-GPU clusters can enable all-against-all comparisons on large datasets. In this work, we present four GPU implementations for large-scale pairwise sequence alignment: TiledDScan-mNW, DScan-mNW, RScan-mNW and LazyRScan-mNW. The proposed GPU…

TeleMDID: Mobile Technology Applications for Interactive Diagnoses in Teledermatology

A web-based dermatology image management application, Missouri Dermatology Image Database (MDID), has been developed to facilitate dermatology practices. The digital images captured offsite are transferred to MDID’s secure server via encrypted connection and user authentication. Uploaded images can be organized by multiple criteria, and patients and images can be easily searched. Originally, the MDID database only applied to in-person patients.  Prior to designing the mobile application, we conducted informal observations of telehealth workflow. A typical Missouri Telehealth Network (MTN) dermatology session lasts 15-25 minutes, and is similar to a clinic visit. Images from offsite are transmitted by attaching a digital…

A Study of User Behaviors in Web-based Medical Image Management and Search

Medical professionals in various specialties work closely with digital images for diagnosis, research and education. Electronic applications of image management are emerging in virtually every medical specialty, including cardiology, radiology, pathology, dermatology, orthopedics, OB/GYN etc.  Compared to radiology, there is a less well-established adoption of such applications as PACS in dermatology in daily practices. Mizzou Dermatology Image Database (MDID) is a web-based medical image management system dedicated to the daily practice at Department of Dermatology, University of Missouri. A longitudinal system user behavior and acceptance study has been conducted using mixed methodologies including periodic surveys, field observations, interviews and application…

Decision Tree Induction for the Screening of Patients at Risk of Moderately Emetogenic Chemotherapy-Induced Nausea and Vomiting During Delayed Phase

Chemotherapy-Induced Nausea and Vomiting (CINV) are the most feared and common side-effects of chemotherapy for cancer patients. The main care plan for CINV consists of preventative care using antiemetics before chemotherapy. CINV considerably impairs the life quality of cancer patients and increases the healthcare cost due to extended hospitalization or re-hospitalization. Thus, it is imperative to identify the patients at high-risk of CINV and provide sufficient antiemetic prophylaxis before chemotherapy. Several recent studies demonstrated that patient-related factors also significantly affect the risk of CINV but how those factors altogether affect the risk of CINV is an unknown fact. This is…

The MDID project: A study of dermatological image archive, search and use behaviors

A novel, web-based dermatology image management application (MDID) has been developed to facilitate the practices in the Department of Dermatology at the University of Missouri School of Medicine. Since its launch in early January, there are over 1700 images of over 500 patients have been uploaded to the MDID.  What are the conventional practices? Are there any differences of preference and activities among professional groups? Are there any changes in image use after adoption of MDID? To answer these questions, we are conducting a mix-method research including surveys, field observations, interviews, and user activity log analysis. A pre-launch survey has…