Origin Sample Prediction and Spatial Modeling of Antimicrobial Resistance in Metagenomic Sequencing Data

The steady elaboration of the Metagenomic and Metadesign of Subways and Urban Biomes (MetaSUB) international consortium project raises important new questions about the origin, variation, and antimicrobial resistance of the collected samples. CAMDA (Critical Assessment of Massive Data Analysis, http://camda.info/) forum organizes annual challenges where different bioinformatics and statistical approaches are tested on samples collected around the world for bacterial classification and prediction of geographical origin. This work proposes a method which not only predicts the locations of unknown samples, but also estimates the relative risk of antimicrobial resistance through spatial modeling. We introduce a new component in the standard analysis as we apply a Bayesian spatial convolution model which accounts for spatial structure of the data as defined by the longitude and latitude of the samples and assess the relative risk of antimicrobial resistance taxa across regions which is relevant to public health. We can then use the estimated relative risk as a new measure for antimicrobial resistance. We also compare the performance of several machine learning methods, such as Gradient Boosting Machine, Random Forest, and Neural Network to predict the geographical origin of the mystery samples. All three methods show consistent results with some superiority of Random Forest classifier. In our future work we can consider a broader class of spatial models and incorporate covariates related to the environment and climate profiles of the samples to achieve more reliable estimation of the relative risk related to antimicrobial resistance.

Using Machine Learning in Accuracy Assessment of Knowledge-Based Energy and Frequency Base Likelihood in Protein Structures

Many aspects of the study of protein folding and dynamics have been affected by the accumulation of data about native protein structures and recent advances in machine learning. Computational methods for predicting protein structures from their sequences are now heavily based on machine learning tools and on approaches that extract knowledge and rules from data using probabilistic models. Many of these methods use scoring functions to determine which structure best fits a native protein sequence. Using computational approaches, we obtained two scoring functions: knowledge-based energy and likelihood of base frequency, and we compared their accuracy in measuring the sequence structure fit. We compared the machine learning models’ accuracy of predictions for knowledge-based energy and likelihood values to validate our results, showing that likelihood is a more accurate scoring function than knowledge-based energy.

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models

Background

Recently high-throughput technologies have been massively used alongside clinical tests to study various types of cancer. Data generated in such large-scale studies are heterogeneous, of different types and formats. With lack of effective integration strategies novel models are necessary for efficient and operative data integration, where both clinical and molecular information can be effectively joined for storage, access and ease of use. Such models, combined with machine learning methods for accurate prediction of survival time in cancer studies, can yield novel insights into disease development and lead to precise personalized therapies.

Results

We developed an approach for intelligent data integration of two cancer datasets (breast cancer and neuroblastoma) − provided in the CAMDA 2018 ‘Cancer Data Integration Challenge’, and compared models for prediction of survival time. We developed a novel semantic network-based data integration framework that utilizes NoSQL databases, where we combined clinical and expression profile data, using both raw data records and external knowledge sources. Utilizing the integrated data we introduced Tumor Integrated Clinical Feature (TICF) − a new feature for accurate prediction of patient survival time. Finally, we applied and validated several machine learning models for survival time prediction.

Conclusion

We developed a framework for semantic integration of clinical and omics data that can borrow information across multiple cancer studies. By linking data with external domain knowledge sources our approach facilitates enrichment of the studied data by discovery of internal relations. The proposed and validated machine learning models for survival time prediction yielded accurate results.

Reviewers

This article was reviewed by Eran Elhaik, Wenzhong Xiao and Carlos Loucera.

SU-E-T-553: Dose-Mass Vs. Dose-Volume Optimization: A Phantom Study

PURPOSE

To demonstrate the merits of mass-based optimization in comparison with volume-based optimization using a simple test phantom.

METHODS

Dose-volume-histogram-based (DVH-based) quadratic objective functions are converted into dose-mass-histogram-based (DMH-based) objective functions by multiplying per-voxel volumes by per-voxel densities within the objective. A digital phantom with a 1.0 g/cm³ target is constructed for irradiation with two beams: one beam path contains a 0.2 g/cm³ volume-of-interest (VOI0.2) while the orthogonal beam-path contains an equal-volume 0.8 g/cm³ VOI (VOI0.8). Monitor-units are computed to achieve a 100 cGy average target dose for each individual beam, and for two-beam DVH-based and DMH-based optimizations.

RESULTS

For single-beam irradiation through VOI0.2, the average dose to VOI0.2 is 20.5 cGy. For single-beam irradiation through VOI0.8, the average dose to VOI0.8 is 25.2 cGy. Traversing the low density volume results in ∼23% lower dose. When DVH- and DMH-based optimizations are performed such that target dose-volume-histograms of the optimizations match, for the DVH optimization 60% vs. 40% of the dose is delivered through VOI0.2 vs. VOI0.8. For DMH-optimization, the split between dose delivered through VOI0.2 vs. VOI0.8 is 70% vs. 30%.

CONCLUSIONS

When density is constant, there is no difference between DVH- and DMH-based optimizations. However, in heterogeneous media, DMH and DVH solutions differ when low and high density materials have the same dose objectives. Delivering target dose through lower density VOIs facilitates target dose deposition due to a decrease in attenuating material, and the decreased attenuation lowers dose to the low density VOI. From mathematical and physical points of view dose-mass optimization is more general than dose-volume optimization.