.

0 (hodnocen0 x )

EB

ONLINE

Singapore : World Scientific Publishing Company, 2019

1 online resource (762 pages)

ISBN 9789811215636 (electronic bk.)

ISBN 9789811215629

Print version: Altman, Russ B Biocomputing 2020 - Proceedings Of The Pacific Symposium Singapore : World Scientific Publishing Company,c2019 ISBN 9789811215629

Intro -- Content -- Preface -- ARTIFICIAL INTELLIGENCE FOR ENHANCING CLINICAL MEDICINE -- Session Introduction: Artificial Intelligence for Enhancing Clinical Medicine -- 1. Introduction -- 2. Novel Research Applying Artificial Intelligence to Clinical Medicine -- 2.1. Artificial intelligence for predicting patient outcomes -- 2.2. Artificial intelligence for improved insight into disease pathogenesis and features -- 3. Artificial intelligence for advancing medical workflows -- 4. Artificial intelligence for improving imaging -- 5. Conclusion -- References -- Predicting Longitudinal Outcomes of Alzheimer’s Disease via a Tensor-Based Joint Classification and Regression Model -- 1. Introduction -- 2. Methods -- 2.1. The Longitudinal Joint Learning Model -- 2.2. The Solution Algorithm Using the Multi-Block ADMM -- 3. Experiments -- 3.1. Performance -- 3.2. Empirical Convergence -- 3.3. Biomarker Identification -- 4. Conclusion -- Acknowledgements -- References -- Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph -- 1. Introduction -- 2. Related Work -- 3. Methods -- 3.1. Data collection and preparation -- 3.2. Evaluation with GHKG -- 3.3. Disease predictability analysis -- 3.4. Demographic analysis -- 3.5. Non-linear methods -- 4. Results -- 5. Discussion -- 5.1. Data size does not always matter. -- 5.2. Confounders may explain errors -- 5.3. Increased model complexity does not necessarily help -- 5.4. Limitations remain as an opportunity for future work -- 6. Conclusion -- Acknowledgements -- References -- Increasing Clinical Trial Accrual via Automated Matching of Biomarker Criteria -- 1. INTRODUCTION -- 2. MATERIALS AND METHODS -- 2.1. Specimens and Retrospective Analysis -- 2.2. Real-time Analysis -- 2.3. Source of Biomarker-based Clinical Trial Data -- 3. RESULTS.

1. Introduction -- 2. Background and Related Work -- 3. Data and Preprocessing -- 3.1. Data Source and Cohort Selection -- 3.2. Data Extraction and Preprocessing -- 4. Methodology -- 4.1. Mortality Monitoring Task -- 4.2. Average Pooling and Attention Mechanism -- 4.3. Recurrent Neural Network (RNN) -- 5. Experimental Design -- 5.1. Sampling Strategy -- 5.2. Baseline Model -- 5.3. Experimental Settings -- 6. Results and Analysis -- 6.1. Dimensionality Analysis -- 6.2. Prediction with Different Feature Representations -- 6.3. Interpreting Mortality of Learned Representation -- 7. Discussion and Conclusions -- References -- Multilevel Self-Attention Model and Its Use on Medical Risk Prediction -- 1. Introduction -- 2. Related Work -- 2.1. Future disease prediction -- 3. Methods -- 3.1. Terminology and Notation -- 3.2. Model Architecture -- 3.3. Self-attention Encoder Unit -- 3.4. Loss Function -- 4. Experiments -- 4.1. Source of Data -- 4.2. Dataset preprocessing -- 4.3. Implementation details -- 5. Results -- 5.1. Future disease prediction -- 5.2. Future cost prediction -- 5.3. Case study for the self-attention mechanism -- 6. Conclusion -- 7. Bibliography -- Identifying Transitional High Cost Users from Unstructured Patient Profiles Written by Primary Care Physicians -- 1. Introduction -- 2. Data -- 2.1. EMRPC -- 2.2. Total Healthcare Costs -- 2.3. Encoding of Ordinal Variables -- 2.4. Word Embeddings -- 3. Methods -- 3.1. Bag of Words -- 3.2. EmbEncode -- 3.3. Historical Baseline -- 3.4. Varying the Training Set -- 3.5. Varying the Evaluation Set -- 4. Results -- 5. Discussion -- Acknowledgments -- References -- Obtaining Dual-Energy Computed Tomography (CT) Information from a Single-Energy CT Image for Quantitative Imaging Analysis of Living Subjects by Using Deep Learning -- 1. Introduction -- 2. Methods -- 3. Results.

3.1. STAMP assay identifies somatic mutations -- 3.2. Algorithmic pipeline flags eligible patients for precision medicine clinical trials -- 3.2.1. Automation of Feature Matching -- 3.2.2. Manual Review of Matching Output -- 3.3. Validation of algorithmic pipeline -- 3.4. Match rate analysis of STAMP-identified mutations -- 4. DISCUSSION -- 4.1. Incorporation of informatics into clinical workflows -- 4.2. Limitations of algorithmic pipelines -- 5. CONCLUSION -- 6. AUTHOR CONTRIBUTIONS -- 7. ACKNOWLEDGEMENTS -- 8. REFERENCES -- 9. FIGURES -- 10. SUPPLEMENTARY TABLES AND FIGURES -- Addressing the Credit Assignment Problem in Treatment Outcome Prediction Using Temporal Difference Learning -- 1. Introduction -- 2. Dataset -- 3. Methods -- 3.1. Feature Extraction -- 3.2. Temporal Difference Learning -- 3.2.1. State-Estimation -- 3.2.2. Value Iteration -- 3.2.3. Optimization -- 3.3. Baselines and Performance Measure -- 4. Results -- 5. Discussion and Conclusion -- References -- Multiclass Disease Classification from Microbial Whole-Community Metagenomes -- 1. Introduction -- 2. Previous Work -- 3. Problem Setup -- 3.1. Dataset Construction -- 3.2. Graph Convolutional Neural Networks -- 3.3. Models -- 3.4. Training -- 4. Results -- 5. Conclusion -- 6. Acknowledgments -- 7. External Links -- References -- LitGen: Genetic Literature Recommendation Guided by Human Explanations -- 1. Introduction -- 2. Clinical Variant Curation Data -- 2.1. ClinGen’s Variant Curation Interface (VCI) -- 2.2. Labeled papers -- 2.3. Unlabeled papers -- 3. Method -- 3.1. BiLSTM baseline -- 3.2. Leveraging unlabeled data -- 3.3. Explanations in multitask learning -- 3.4. Explanations as feature selection for proxy labeling -- 4. Experimental results -- 4.1. Evaluation metrics -- 4.2. Performance comparison -- 4.3. Performance of Proxy Labeling Model.

4.4. Performance by Evidence Types -- 5. Discussion -- References -- From Genome to Phenome: Predicting Multiple Cancer Phenotypes Based on Somatic Genomic Alterations via the Genomic Impact Transformer -- 1. Introduction -- 2. Materials and methods -- 2.1. SGAs and DEGs pre-processing -- 2.2. The GIT neural network -- 2.2.1. GIT network structure: encoder-decoder architecture -- 2.2.2. Pre-training gene embeddings using Gene2Vec algorithm -- 2.2.3. Encoder: multi-head self-attention mechanism -- 2.2.4. Decoder: multi-layer perceptron (MLP) -- 2.3. Training and evaluation -- 3. Results -- 3.1. GIT statistically detects real biological signals -- 3.2. Gene embeddings compactly represent the functional impact of SGAs -- 3.4. Personalized tumor embeddings reveal distinct survival profiles -- 3.5. Tumor embeddings are predictive of drug responses of cancer cell lines -- 4. Conclusion and Future Work -- Acknowledgments -- Funding -- References -- Automated Phenotyping of Patients with Non-Alcoholic Fatty Liver Disease Reveals Clinically Relevant Disease Subtypes -- 1. Introduction -- 2. Methods -- 2.1. NAFLD definition -- 2.2. Natural language processing -- 2.3. Data collection -- 2.4. Clinical feature standardization and quality control -- 2.4.1. Demographic data -- 2.4.2. Diagnoses, procedures, medications -- 2.4.3. Laboratory tests -- 2.4.4. Vital signs -- 2.5. Patient pairwise distance and clustering -- 2.6. Statistical analysis -- 2.6.1. Descriptive statistics -- 2.6.2. Survival analysis -- 3. Results -- 3.1. Descriptive statistics for the cohort -- 3.2. Identification of NAFLD subtypes -- 3.3. Identification of distinct outcomes by NAFLD subtype -- 3.4. Internal cross-validation of the subtypes discovered -- 4. Conclusion -- 5. References -- References -- Monitoring ICU Mortality Risk with a Long Short-Term Memory Recurrent Neural Network.

2.3. Docking AP2a to the IDRs by superposition.

4. Discussion and Conclusion -- 5. Acknowledge -- References -- INTRINSICALLY DISORDERED PROTEINS (IDPS) AND THEIR FUNCTIONS -- Session Introduction: On the Importance of Computational Biology and Bioinformatics to the Origins and Rapid Progression of the Intrinsically Disordered Proteins Field -- 1. Introduction -- 2. Computational prediction of IDPs and IDRs and their functions -- 3. Popularization of research on IDPs and IDRs -- 4. A Collection of Recent Papers on IDPs and IDRs -- References -- Many-to-One Binding by Intrinsically Disordered Protein Regions -- 1. Introduction -- 2. Results -- 2.1. Many-to-one binding datasets -- 2.2. Many-to-one binding profiles: independent and overlapping -- 2.3 Comparing VOR (with backbone only) and RMSEASA Values -- 2.4. Selected many-to-one case studies -- 3. Discussion -- 4. Materials and Methods -- 4.1. Dataset preparation -- 4.2. MoRF sequence similarity -- 4.3. MoRF interface similarity -- References -- Disordered Function Conjunction: On the In-Silico Function Annotation of Intrinsically Disordered Regions -- 1. Introduction -- 2. Materials and Methods -- 2.1. Data collection -- 2.2. Computational workflow -- 2.2.1. Feature-based representation of protein regions -- 2.2.2. Prediction of protein region functions -- 2.2.3. Assessment of the function prediction and clustering -- 3. Results and Discussion -- 3.1. Prediction of individual functions of IDRs -- 3.2. IDRs described in multidimensional space form function-related clusters -- 3.3. Case studies -- 4. Conclusions -- Acknowledgments -- References -- De novo Ensemble Modeling Suggests that AP2-Binding to Disordered Regions Can Increase Steric Volume of Epsin but Not Eps15 -- 1. Introduction -- 2. Methods -- 2.1. Generation of structural ensembles -- 2.2. Filtering Epsin conformers to mimic the effect of Plasma membrane.

001894865

express

(Au-PeEL)EBL6383176

(MiAaPQ)EBC6383176

(OCoLC)1231606405