Learning and evaluating response prediction models using parallel listener consensus

AbstractNutritional management of pigs to optimise growth demands pig-specific, time-specific and place-specific determination and provision of nutritional requirement. These elements need to be incorporated into response prediction models that operate in a real-time (not retrospective) closed-loop control environment. This implies appropriate means for the on-line measurement of response to change in nutrient provision, and the simultaneous means for manipulation of feeding level and feed quality. The paper describes how response prediction modelling and response measurement may now be achieved. Optimisation may be pursued with mixed objectives, including those of production efficiency and environmental protection.

Download Full-text

Ensemble transfer learning for the prediction of anti-cancer drug response

Scientific Reports ◽

10.1038/s41598-020-74921-0 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Yitan Zhu ◽

Thomas Brettin ◽

Yvonne A. Evrard ◽

Alexander Partin ◽

Fangfang Xia ◽

...

Keyword(s):

Tumor Cells ◽

Transfer Learning ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Cancer Drug ◽

Precision Oncology ◽

Learning Framework ◽

Prediction Algorithms ◽

Anti Cancer

Abstract Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the power of transfer learning for three drug response prediction applications including drug repurposing, precision oncology, and new drug development, through different data partition schemes in cross-validation. We extend the classic transfer learning framework through ensemble and demonstrate its general utility with three representative prediction algorithms including a gradient boosting model and two deep neural networks. The ensemble transfer learning framework is tested on benchmark in vitro drug screening datasets. The results demonstrate that our framework broadly improves the prediction performance in all three drug response prediction applications with all three prediction algorithms.

Download Full-text

A Cluster-Based Data Balancing Ensemble Classifier for Response Modeling in Bank Direct Marketing

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026815500224 ◽

2015 ◽

Vol 14 (04) ◽

pp. 1550022 ◽

Cited By ~ 7

Author(s):

Mohammad Amini ◽

Jalal Rezaeenour ◽

Esmaeil Hadavandi

Keyword(s):

Prediction Models ◽

Direct Marketing ◽

Imbalanced Data ◽

Response Prediction ◽

Ensemble Classifier ◽

Ensemble Method ◽

Ensemble Classification ◽

Under Sampling ◽

The Right ◽

Response Modeling

The aim of direct marketing is to find the right customers who are most likely to respond to marketing campaign messages. In order to detect which customers are most valuable, response modeling is used to classify customers as respondent or non-respondent using their purchase history information or other behavioral characteristics. Data mining techniques, including effective classification methods, can be used to predict responsive customers. However, the inherent problem of imbalanced data in response modeling brings some difficulties into response prediction. As a result, the prediction models will be biased towards non-respondent customers. Another problem is that single models cannot provide the desired high accuracy due to their internal limitations. In this paper, we propose an ensemble classification method which removes imbalance in the data, using a combination of clustering and under-sampling. The predictions of multiple classifiers are combined in order to achieve better results. Using data from a bank’s marketing campaigns, this ensemble method is implemented on different classification techniques and the results are evaluated. We also evaluate the performance of this ensemble method against two alternative ensembles. The experimental results demonstrate that our proposed method can improve the performance of the response models for bank direct marketing by raising prediction accuracy and increasing response rate.

Download Full-text

Deep learning for drug response prediction in cancer

Briefings in Bioinformatics ◽

10.1093/bib/bbz171 ◽

2020 ◽

Cited By ~ 9

Author(s):

Delora Baptista ◽

Pedro G Ferreira ◽

Miguel Rocha

Keyword(s):

Deep Learning ◽

Cell Lines ◽

Cancer Cell ◽

High Throughput Screening ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Cancer Cell Lines ◽

Cancer Treatments ◽

Novel Drugs

Abstract Predicting the sensitivity of tumors to specific anti-cancer treatments is a challenge of paramount importance for precision medicine. Machine learning(ML) algorithms can be trained on high-throughput screening data to develop models that are able to predict the response of cancer cell lines and patients to novel drugs or drug combinations. Deep learning (DL) refers to a distinct class of ML algorithms that have achieved top-level performance in a variety of fields, including drug discovery. These types of models have unique characteristics that may make them more suitable for the complex task of modeling drug response based on both biological and chemical data, but the application of DL to drug response prediction has been unexplored until very recently. The few studies that have been published have shown promising results, and the use of DL for drug response prediction is beginning to attract greater interest from researchers in the field. In this article, we critically review recently published studies that have employed DL methods to predict drug response in cancer cell lines. We also provide a brief description of DL and the main types of architectures that have been used in these studies. Additionally, we present a selection of publicly available drug screening data resources that can be used to develop drug response prediction models. Finally, we also address the limitations of these approaches and provide a discussion on possible paths for further improvement. Contact:[email protected]

Download Full-text

Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer

BMC Genomics ◽

10.1186/s12864-021-07524-2 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Vidhi Malik ◽

Yogesh Kalakoti ◽

Durai Sundar

Keyword(s):

Breast Cancer ◽

Cancer Patients ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Precision Oncology ◽

Z Score ◽

Breast Cancer Patients ◽

Omics Integration ◽

Ic50 Values

Abstract Background Survival and drug response are two highly emphasized clinical outcomes in cancer research that directs the prognosis of a cancer patient. Here, we have proposed a late multi omics integrative framework that robustly quantifies survival and drug response for breast cancer patients with a focus on the relative predictive ability of available omics datatypes. Neighborhood component analysis (NCA), a supervised feature selection algorithm selected relevant features from multi-omics datasets retrieved from The Cancer Genome Atlas (TCGA) and Genomics of Drug Sensitivity in Cancer (GDSC) databases. A Neural network framework, fed with NCA selected features, was used to develop survival and drug response prediction models for breast cancer patients. The drug response framework used regression and unsupervised clustering (K-means) to segregate samples into responders and non-responders based on their predicted IC50 values (Z-score). Results The survival prediction framework was highly effective in categorizing patients into risk subtypes with an accuracy of 94%. Compared to single-omics and early integration approaches, our drug response prediction models performed significantly better and were able to predict IC50 values (Z-score) with a mean square error (MSE) of 1.154 and an overall regression value of 0.92, showing a linear relationship between predicted and actual IC50 values. Conclusion The proposed omics integration strategy provides an effective way of extracting critical information from diverse omics data types enabling estimation of prognostic indicators. Such integrative models with high predictive power would have a significant impact and utility in precision oncology.

Download Full-text

Efficient Implementation of Step Response Prediction Models for Embedded Model Predictive Control**This work is funded by the Research Council of Norway (NFR) and Statoil through the PETROMAKS project 215684, and also by NFR, Statoil, and DNV through the AMOS project 223254.

IFAC-PapersOnLine ◽

10.1016/j.ifacol.2015.11.283 ◽

2015 ◽

Vol 48 (23) ◽

pp. 197-204

Author(s):

D.K.M. Kufoalor ◽

L. Imsland ◽

T.A. Johansen

Keyword(s):

Model Predictive Control ◽

Predictive Control ◽

Research Council ◽

Prediction Models ◽

Response Prediction ◽

Efficient Implementation ◽

Step Response ◽

Embedded Model

Download Full-text

Cross Flow and In-Line Damping Measurements From Forced Excitations of a Flexible Cylinder in a Uniform Flow

23rd International Conference on Offshore Mechanics and Arctic Engineering, Volume 3 ◽

10.1115/omae2004-51397 ◽

2004 ◽

Author(s):

Madan Venugopal ◽

J. Kim Vandiver

Keyword(s):

Prediction Models ◽

Steel Wire ◽

Three Dimensional ◽

Cross Flow ◽

Response Prediction ◽

Uniform Flow ◽

Experimental Methodology ◽

Ocean Engineering ◽

Flexible Cylinder ◽

Fluid Damping

Tensioned flexible cylindrical structures are important in many ocean engineering applications such as moorings for buoys and platforms, marine risers and towing cables. Modeling the vibration of these structures is complicated because these are complex three-dimensional, unsymmetrical, fluid structure interaction problems. Damping is an important, but poorly understood, component of the response prediction models developed for modeling such systems. In particular, there is a scarcity of good data on damping of flexible cylinders vibrating in uniform and non-uniform external flow. This is, in part, due to the difficulty of measuring fluid damping on a vibrating cylinder in a flow. Results are presented here which address some of these limitations. Forced vibration tests were performed on two 13 ft long tensioned flexible cylinders (an ABS tube and a steel wire) in a current tank to determine in air and still water damping as well as cross flow and in-line damping in a uniform flow. The experimental methodology is described and results are presented for a range of reduced velocities. The results show an increase in fluid damping with increased reduced velocities for small amplitudes of vibration.

Download Full-text

Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models

Genes ◽

10.3390/genes11091070 ◽

2020 ◽

Vol 11 (9) ◽

pp. 1070 ◽

Cited By ~ 1

Author(s):

Yitan Zhu ◽

Thomas Brettin ◽

Yvonne A. Evrard ◽

Fangfang Xia ◽

Alexander Partin ◽

...

Keyword(s):

Drug Response ◽

Prediction Models ◽

Gene Selection ◽

Expression Patterns ◽

Response Prediction ◽

Cancer Drug ◽

P Value ◽

In Vitro Drug Screening ◽

Multiple Drugs

The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted p-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.

Download Full-text

Application of network diffusion approaches to drug screenings: A perspective on multilayered networks derived from cell lines and drugs

10.7287/peerj.preprints.3339 ◽

2017 ◽

Author(s):

Vigneshwari Subramanian ◽

Bence Szalai ◽

Luis Tobalina ◽

Julio Saez-Rodriguez

Keyword(s):

Cell Line ◽

Cell Lines ◽

Protein Interactions ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Single Type ◽

Disease Genes ◽

Cell Line Cell ◽

Network Diffusion

Network diffusion approaches are frequently used for identifying the relevant disease genes and for prioritizing the genes for drug sensitivity predictions. Majority of these studies rely on networks representing a single type of information. However, using multiplex heterogeneous networks (networks with multiple interconnected layers) is much more informative and helps to understand the global topology. We built a multi-layered network that incorporates information on protein-protein interactions, drug-drug similarities, cell line-cell line similarities and co-expressed genes. We applied Random Walk with Restart algorithm to investigate the interactions between drugs, targets and cancer cell lines. Results of ANOVA models show that these prioritized genes are among the most significant ones that relate to drug response. Moreover, the predictive power of the drug response prediction models built using the gene expression data of only the top ranked genes is similar to the models built using all the available genes. Taken together, the results confirm that the multiplex heterogeneous network-based approach is efficient in identifying the most significant genes associated with drug response.

Download Full-text

PREDICTORS OF THERAPEUTIC RESPONSE AND LENGTH OF HOSPITALIZATION IN PATIENTS WITH SCHIZOPHRENIA DURING PHARMACOTHERAPY

Journal of the Grodno State Medical University ◽

10.25298/2221-8785-2021-19-5-532-540 ◽

2021 ◽

Vol 19 (5) ◽

pp. 532-540

Author(s):

M. V. Assanovich ◽

Keyword(s):

Negative Symptoms ◽

Therapeutic Response ◽

Prediction Models ◽

Response Prediction ◽

Diagnostic Value ◽

Positive Symptoms ◽

Duration Of Hospitalization ◽

Symptomatic Remission ◽

Length Of Hospitalization ◽

Positive And Negative Symptoms

Topicality. Search for scientifically based criteria for symptomatic remission and outcomes in schizophrenia is an urgent problem in modern psychiatry. Aim. To determine predictors of therapeutic response and duration of hospitalization during the course of psychopharmacotherapy in patients with schizophrenia. Material and methods. Clinical and metric examination using scales for assessing severity of positive (SAPS, PSYRATS, BABS) and negative (SANS, NSA-5) symptoms was performed in 157 patients with a diagnosis of schizophrenia twice: on admission to hospital and after the course of psychopharmacotherapy. The model for predicting therapeutic response was built using logistic regression, the model for predicting duration of hospitalization was built using linear regression using metrically justified criteria for achieving a significantly low level of severity of positive and negative symptoms as criteria for a significant therapeutic response. Results. The predictors were determined that increase and decrease likelihood of therapeutic response for scales for assessing positive and negative symptoms in patients with schizophrenia during the course of psychopharmacotherapy. Conclusions. Therapeutic response prediction models for scales for assessing the severity of positive symptoms and scales for the severity of negative symptoms are of good quality and high diagnostic value.

Download Full-text