No description available.

No description available.

No description available.

No description available.

There exist many real-world applications such as recommendation systems, document retrieval, and computational biology where the correct ordering of instances is of equal or greater importance than predicting the exact value of some discrete or continuous outcome. Learning-to-Rank (LTR) refers to a group of algorithms that apply machine learning techniques to tackle these ranking problems. Despite their empirical success, most existing LTR models are not built to be robust to errors in labeling or annotation, distributional data shift, or adversarial data perturbations. To fill this gap, we develop four LTR frameworks that are robust to various types of perturbations. First, Pairwise Elastic Net Regression Ranking (PENRR) is an elastic-net-based regression method for drug sensitivity prediction. PENRR infers robust predictors of drug responses from patient genomic information. The special design of this model (comparing each drug with other drugs in the same cell line and comparing that drug with itself in other cell lines) significantly enhances the accuracy of the drug prediction model under limited data. This approach is also able to solve the problem of fitting on the insensitive drugs that is commonly encountered in regression-based models. Second, Regression-based Ranking by Pairwise Cluster Comparisons (RRPCC) is a ridge-regression-based method for ranking clusters of similar protein complex conformations generated by an underlying docking program (i.e., ClusPro). Rather than using regression to predict scores, which would equally penalize deviations for either low-quality and high-quality clusters, we seek to predict the difference of scores for any pair of clusters corresponding to the same complex. RRPCC combines these pairwise assessments to form a ranked list of clusters, from higher to lower quality. We apply RRPCC to clusters produced by the automated docking server ClusPro and, depending on the training/validation strategy, we show. improvement by 24%–100% in ranking acceptable or better quality clusters first, and by 15%–100% in ranking medium or better quality clusters first. Third, Distributionally Robust Multi-Output Regression Ranking (DRMRR) is a listwise LTR model that induces robustness into LTR problems using the Distributionally Robust Optimization framework. Contrasting to existing methods, the scoring function of DRMRR was designed as a multivariate mapping from a feature vector to a vector of deviation scores, which captures local context information and cross-document interactions. DRMRR employs ranking metrics (i.e., NDCG) in its output. Particularly, we used the notion of position deviation to define a vector of relevance score instead of a scalar one. We then adopted the DRO framework to minimize a worst-case expected multi-output loss function over a probabilistic ambiguity set that is defined by the Wasserstein metric. We also presented an equivalent convex reformulation of the DRO problem, which is shown to be tighter than the ones proposed by the previous studies. Fourth, Inversion Transformer-based Neural Ranking (ITNR) is a Transformer-based model to predict drug responses using RNAseq gene expression profiles, drug descriptors, and drug fingerprints. It utilizes a Context-Aware-Transformer architecture as its scoring function that ensures the modeling of inter-item dependencies. We also introduced a new loss function using the concept of Inversion and approximate permutation matrices. The accuracy and robustness of these LTR models are verified through three medical applications, namely cluster ranking in protein-protein docking, medical document retrieval, and drug response prediction.

Investigating interactions between proteins and small molecules at an atomic scale is fundamental towards understanding biological processes and designing novel candidates during the pre-clinical stages of drug discovery. By optimizing the methods used to study these interactions in terms of accuracy and computational cost, we can accelerate this aspect of biological research and contribute more readily to therapeutic design. While biological assays and other experimental techniques are invaluable in quantitatively determining in vitro and in vivo inhibition activity, as well as validating computational predictions, there is an inherent benefit in the possible throughput provided by molecular dynamics (MD) simulations and related computational methods. These calculations provide researchers with unparalleled access to large amounts of all-atom sampling of biological systems, including non-physical pathways and other enhanced sampling methods. This dissertation presents research into advancing the application of expanded ensemble and other simulation-based methods of ligand design towards reliable and efficient absolute free energy of binding calculations on the scale of hundreds to thousands of small molecule ligands. This culminates in a combined workflow that allows for an automated approach to the force-field parameterization of custom systems, simulation preparation, optimization of the restraint and sampling protocols, production free energy simulations, and analysis that has facilitated the computation of absolute binding free energy predictions. Specifically highlighted is our ongoing effort to discover novel inhibitors of the main protease (Mpro) of SARS-CoV-2 as well as participation in the SAMPL9 Host-Guest Challenge. / Chemistry

A data analytic materials informatics methodology is proposed after applying different data mining techniques on some datasets of particular domain in order to discover and model certain patterns, trends and behavior related to that domain. In essence, it is proposed to develop an information mining tool for vapor-grown carbon nanofiber (VGCNF)/vinyl ester (VE) nanocomposites as a case study. Formulation and processing factors (VGCNF type, use of a dispersing agent, mixing method, and VGCNF weight fraction) and testing temperature were utilized as inputs and the storage modulus, loss modulus, and tan delta were selected as outputs or responses. The data mining and knowledge discovery algorithms and techniques included self-organizing maps (SOMs) and clustering techniques. SOMs demonstrated that temperature had the most significant effect on the output responses followed by VGCNF weight fraction. A clustering technique, i.e., fuzzy C-means (FCM) algorithm, was also applied to discover certain patterns in nanocomposite behavior after using principal component analysis (PCA) as a dimensionality reduction technique. Particularly, these techniques were able to separate the nanocomposite specimens into different clusters based on temperature and tan delta features as well as to place the neat VE specimens in separate clusters. In addition, an artificial neural network (ANN) model was used to explore the VGCNF/VE dataset. The ANN was able to predict/model the VGCNF/VE responses with minimal mean square error (MSE) using the resubstitution and 3olds cross validation (CV) techniques. Furthermore, the proposed methodology was employed to acquire new information and mechanical and physical patterns and trends about not only viscoelastic VGCNF/VE nanocomposites, but also about flexural and impact strengths properties for VGCNF/ VE nanocomposites. Formulation and processing factors (curing environment, use or absence of dispersing agent, mixing method, VGCNF fiber loading, VGCNF type, high shear mixing time, sonication time) and testing temperature were utilized as inputs and the true ultimate strength, true yield strength, engineering elastic modulus, engineering ultimate strength, flexural modulus, flexural strength, storage modulus, loss modulus, and tan delta were selected as outputs. This work highlights the significance and utility of data mining and knowledge discovery techniques in the context of materials informatics.

No description available.

No description available.

With the increasing use of electronic devices, the need for affordable wireless services specifically context-aware services, in a so-called Personal Area Network (PAN) is becoming an area with significant potential. Service discovery is a basic function. Even though a number of service discovery protocols have been implemented, a specific protocol for a PAN environment may need to be developed, as the characteristics of a PANs differ from other networking environments. Thus, the specific requirements for service discovery from a PAN perspective were studied. Methods for service discovery will be described that take into account both local and remote services. These methods will then be evaluated in a SIP telephony infrastructure to decide where a call should be delivered. The location of a person is done by using the implemented service discovery. / Med en ökad användning av elektroniska enheter blir behovet av trådlösa tjänster, speciellt context-medvetna tjänster i så kallade Personal Area Network (PAN), ett område med betydlig potential. Service Discovery är en grundläggande funktion. Även om flera service discovery protocols har implementerats finns det behov av ett specifikt protokoll för PAN-miljöer då egenskaperna hos ett PAN skiljer sig från andra nätverksmiljöer. Således studerades de specifika krav för service discovery från ett PAN perspektiv. Metoder för service discovery kommer att ta med i beräkningen båda lokala och avlägna tjänster. Dessa metoder utvärderas i en SIP telephony infrastructure för att avgöra var en påringning ska levereras. Lokalisering av en användare sker genom det implementerade service discovery-protokollet.