Scalable Optimal Bayesian Classification of Single-Cell Trajectories under Regulatory Model Uncertainty

Hajiramezanali, Ehsan; Imani, Mahdi; Braga-Neto, Ulisses; Qian, Xiaoning; Dougherty, Edward R.

doi:10.1145/3233547.3233689

Cited by 7 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, if five amino acid indices are used and N e = 2, then there will be 10 base learners in total. The proposed framework may be improved by some new techniques such as Optimal Bayesian Classification [44] and Bayesian Inverse Reinforcement Learning [45].…”

Section: Representation Of Gpcr-drug Pairsmentioning

confidence: 99%

Identifying GPCR-drug interaction based on wordbook learning from sequences

et al. 2020

View full text Add to dashboard Cite

Background: G protein-coupled receptors (GPCRs) mediate a variety of important physiological functions, are closely related to many diseases, and constitute the most important target family of modern drugs. Therefore, the research of GPCR analysis and GPCR ligand screening is the hotspot of new drug development. Accurately identifying the GPCR-drug interaction is one of the key steps for designing GPCRtargeted drugs. However, it is prohibitively expensive to experimentally ascertain the interaction of GPCR-drug pairs on a large scale. Therefore, it is of great significance to predict the interaction of GPCR-drug pairs directly from the molecular sequences. With the accumulation of known GPCR-drug interaction data, it is feasible to develop sequence-based machine learning models for query GPCR-drug pairs. Results: In this paper, a new sequence-based method is proposed to identify GPCRdrug interactions. For GPCRs, we use a novel bag-of-words (BoW) model to extract sequence features, which can extract more pattern information from low-order to high-order and limit the feature space dimension. For drug molecules, we use discrete Fourier transform (DFT) to extract higher-order pattern information from the original molecular fingerprints. The feature vectors of two kinds of molecules are concatenated and input into a simple prediction engine distance-weighted Knearest-neighbor (DWKNN). This basic method is easy to be enhanced through ensemble learning. Through testing on recently constructed GPCR-drug interaction datasets, it is found that the proposed methods are better than the existing sequence-based machine learning methods in generalization ability, even an unconventional method in which the prediction performance was further improved by post-processing procedure (PPP). Conclusions: The proposed methods are effective for GPCR-drug interaction prediction, and may also be potential methods for other target-drug interaction prediction, or protein-protein interaction prediction. In addition, the new proposed feature extraction method for GPCR sequences is the modified version of the traditional BoW model and may be useful to solve problems of protein classification or attribute prediction. The source code of the proposed methods is freely available for academic research at https://github.com/wp3751/GPCR-Drug-Interaction.

show abstract

Section: Representation Of Gpcr-drug Pairsmentioning

confidence: 99%

Identifying GPCR-drug interaction based on wordbook learning from sequences

et al. 2020

View full text Add to dashboard Cite

show abstract

“…1 + e −h 2 , e −h 2 and |h| in earlier research [17]. In the following section, we use the proposed new HGF in (17) to model the volatility in Kalman filtering procedure in equation (1). Subsequently, (1) and ( 2) using ( 17) are explained in details to elaborate more our proposed NNH approach.…”

Section: Iii-a Estimation Of Hgfmentioning

confidence: 99%

“…Non-linear and non-Gaussian state-space models have attracted an increasing attention in recent years due to their significant importance to a wide range of applications such as radar, biomedical signal and image processing, and wireless communications [1]- [8]. In these practical dynamic systems, the jump process is found to be helpful when abrupt changes occur within limited time intervals.…”

Section: Introductionmentioning

confidence: 99%

Non-Linear Non-Stationary Heteroscedasticity Volatility for Tracking of Jump Processes

Fouladi,

Hajiramezanali

2019

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce a new jump process modeling which involves a particular kind of non-Gaussian stochastic processes with random jumps at random time points. The main goal of this study is to provide an accurate tracking technique based on non-linear non-stationary heteroscedasticity (NNH) time series. It is, in fact, difficult to track jump processes regarding the fact that non-Gaussianity is an inherent feature in these processes. The proposed NNH model is conditionally Gaussian whose conditional variance is time-varying. Therefore, we use Kalman filter for state tracking. We show analytically that the proposed NNH model is superior to the traditional methods. Furthermore, to validate the findings, simulations are performed. Finally, the comparison between the proposed method and other alternatives techniques has been made.

show abstract

“…Keeping in view the aforementioned challenges, there is an emerging need to investigate new sophisticated solutions for the investigation of malignancy status in lung nodules. A useful approach towards joint estimation of tumor malignancy and its stage can involve tracking of tumor characteristics using temporal analysis of CT images [14], [15]. Such an approach also offers good potential to address the problem of smaller data sets in medical imaging.…”

Section: Introductionmentioning

confidence: 99%

Radiomics Based Bayesian Inversion Method for Prediction of Cancer and Pathological Stage

Shakir¹,

Khan

Rasheed

et al. 2021

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

To develop a Bayesian inversion framework on longitudinal chest CT scans which can perform efficient multi-class classification of lung cancer. Methods: While the unavailability of large number of training medical images impedes the performance of lung cancer classifiers, the purpose built deep networks have not performed well in multi-class classification. The presented framework employs particle filtering approach to address the non-linear behaviour of radiomic features towards benign and cancerous (stages I, II, III, IV) nodules and performs efficient multi-class classification (benign, early stage cancer, advanced stage cancer) in terms of posterior probability function. A joint likelihood function incorporating diagnostic radiomic features is formulated which can compute likelihood of cancer and its pathological stage. The proposed research study also investigates and validates diagnostic features to discriminate accurately between early stage (I, II) and advanced stage (III, IV) cancer. Results: The proposed stochastic framework achieved 86% accuracy on the benchmark database which is better than the other prominent cancer detection methods. Conclusion: The proposed classification framework can aid radiologists in accurate interpretation of lung CT images at an early stage and can lead to timely medical treatment of cancer patients. Index Terms-Bayesian inversion; cancer stage estimation; nodule classification; particle filter; radiomic features Clinical and Translational Impact Statement: The proposed diagnostic framework offers reliable and efficient multiclass classification of lung cancer which can help radiologists improve diagnostic accuracy who work with large number of low dose chest CT scans.

show abstract

Scalable Optimal Bayesian Classification of Single-Cell Trajectories under Regulatory Model Uncertainty

Cited by 7 publications

References 29 publications

Identifying GPCR-drug interaction based on wordbook learning from sequences

Identifying GPCR-drug interaction based on wordbook learning from sequences

Non-Linear Non-Stationary Heteroscedasticity Volatility for Tracking of Jump Processes

Radiomics Based Bayesian Inversion Method for Prediction of Cancer and Pathological Stage

Contact Info

Product

Resources

About