Identifying marker genes in transcription profiling data using a mixture of feature relevance experts

2001 ◽  
Vol 5 (2) ◽  
pp. 99-111 ◽  
Author(s):  
M. L. Chow ◽  
E. J. Moler ◽  
I. S. Mian
Keyword(s):  
Decision Support ◽  
Experimental Studies ◽  
Colon Adenocarcinoma ◽  
Support Vector ◽  
Marker Genes ◽  
Published Data ◽  
Transcription Profiling ◽  
General Utility ◽  
Feature Relevance ◽  
The Impact

Transcription profiling experiments permit the expression levels of many genes to be measured simultaneously. Given profiling data from two types of samples, genes that most distinguish the samples (marker genes) are good candidates for subsequent in-depth experimental studies and developing decision support systems for diagnosis, prognosis, and monitoring. This work proposes a mixture of feature relevance experts as a method for identifying marker genes and illustrates the idea using published data from samples labeled as acute lymphoblastic and myeloid leukemia (ALL, AML). A feature relevance expert implements an algorithm that calculates how well a gene distinguishes samples, reorders genes according to this relevance measure, and uses a supervised learning method [here, support vector machines (SVMs)] to determine the generalization performances of different nested gene subsets. The mixture of three feature relevance experts examined implement two existing and one novel feature relevance measures. For each expert, a gene subset consisting of the top 50 genes distinguished ALL from AML samples as completely as all 7,070 genes. The 125 genes at the union of the top 50s are plausible markers for a prototype decision support system. Chromosomal aberration and other data support the prediction that the three genes at the intersection of the top 50s, cystatin C, azurocidin, and adipsin, are good targets for investigating the basic biology of ALL/AML. The same data were employed to identify markers that distinguish samples based on their labels of T cell/B cell, peripheral blood/bone marrow, and male/female. Selenoprotein W may discriminate T cells from B cells. Results from analysis of transcription profiling data from tumor/nontumor colon adenocarcinoma samples support the general utility of the aforementioned approach. Theoretical issues such as choosing SVM kernels and their parameters, training and evaluating feature relevance experts, and the impact of potentially mislabeled samples on marker identification (feature selection) are discussed.

Analysis of molecular profile data using generative and discriminative methods

2000 ◽  
Vol 4 (2) ◽  
pp. 109-126 ◽  
Author(s):  
E. J. Moler ◽  
M. L. Chow ◽  
I. S. Mian
Keyword(s):  
Graphical Models ◽  
Biological Networks ◽  
Domain Knowledge ◽  
Colon Adenocarcinoma ◽  
Comparative Sequence Analysis ◽  
Diagnostic Tools ◽  
Molecular Profile ◽  
Support Vector ◽  
Marker Genes ◽  
Profile Data

A modular framework is proposed for modeling and understanding the relationships between molecular profile data and other domain knowledge using a combination of generative (here, graphical models) and discriminative [Support Vector Machines (SVMs)] methods. As illustration, naive Bayes models, simple graphical models, and SVMs were applied to published transcription profile data for 1,988 genes in 62 colon adenocarcinoma tissue specimens labeled as tumor or nontumor. These unsupervised and supervised learning methods identified three classes or subtypes of specimens, assigned tumor or nontumor labels to new specimens and detected six potentially mislabeled specimens. The probability parameters of the three classes were utilized to develop a novel gene relevance, ranking, and selection method. SVMs trained to discriminate nontumor from tumor specimens using only the 50–200 top-ranked genes had the same or better generalization performance than the full repertoire of 1,988 genes. Approximately 90 marker genes were pinpointed for use in understanding the basic biology of colon adenocarcinoma, defining targets for therapeutic intervention and developing diagnostic tools. These potential markers highlight the importance of tissue biology in the etiology of cancer. Comparative analysis of molecular profile data is proposed as a mechanism for predicting the physiological function of genes in instances when comparative sequence analysis proves uninformative, such as with human and yeast translationally controlled tumour protein. Graphical models and SVMs hold promise as the foundations for developing decision support systems for diagnosis, prognosis, and monitoring as well as inferring biological networks.

scholarly journals The Impact of Hemodynamic Reflex Compensation Following Myocardial Infarction on Subsequent Ventricular Remodeling

2019 ◽  
Vol 141 (9) ◽  
Author(s):  
Colleen M. Witzenburg ◽  
Jeffrey W. Holmes
Keyword(s):  
Myocardial Infarction ◽  
Ventricular Remodeling ◽  
Experimental Studies ◽  
Left Ventricular ◽  
Published Data ◽  
Compensatory Mechanisms ◽  
Compensatory Response ◽  
Wide Range ◽  
Reflex Compensation ◽  
The Impact

Patients who survive a myocardial infarction (MI) are at high risk for ventricular dilation and heart failure. While infarct size is an important determinant of post-MI remodeling, different patients with the same size infarct often display different levels of left ventricular (LV) dilation. The acute physiologic response to MI involves reflex compensation, whereby increases in heart rate (HR), arterial resistance, venoconstriction, and contractility of the surviving myocardium act to maintain mean arterial pressure (MAP). We hypothesized that variability in reflex compensation might underlie some of the reported variability in post-MI remodeling, a hypothesis that is difficult to test using experimental data alone because some reflex responses are difficult or impossible to measure directly. We, therefore, employed a computational model to estimate the balance of compensatory mechanisms from experimentally reported hemodynamic data. We found a strikingly wide range of compensatory reflex profiles in response to MI in dogs and verified that pharmacologic blockade of sympathetic and parasympathetic reflexes nearly abolished this variability. Then, using a previously published model of postinfarction remodeling, we showed that observed variability in compensation translated to variability in predicted LV dilation consistent with published data. Treatment with a vasodilator shifted the compensatory response away from arterial and venous vasoconstriction and toward increased HR and myocardial contractility. Importantly, this shift reduced predicted dilation, a prediction that matched prior experimental studies. Thus, postinfarction reflex compensation could represent both a source of individual variability in the extent of LV remodeling and a target for therapies aimed at reducing that remodeling.

Research on behavior recognition based on feature fusion of automatic coder and recurrent neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Behavior Pattern ◽  
Rapid Development ◽  
Video Data ◽  
Support Vector ◽  
Behavior Recognition ◽  
Learning Methods ◽  
The Impact ◽  
Internet Of Things Technology

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Thoracoabdominalis aortakirekesztés során fellépő elektrofiziológiai változások a gerincvelőben

2020 ◽  
Vol 73 (4) ◽  
pp. 160-166
Author(s):  
Csaba Dzsinich ◽  
Péter Gloviczki ◽  
Gabriella Nagy ◽  
Klaudia Vivien Nagy
Keyword(s):  
Spinal Cord ◽  
Motor Evoked Potentials ◽  
Spinal Cord Ischemia ◽  
Experimental Studies ◽  
Neuron Specific Enolase ◽  
Neurological Complications ◽  
Neurologic Outcome ◽  
Published Data ◽  
Aortic Clamping ◽  
Sensory Evoked

Összefoglaló. A thoracoabdominalis aortakirekesztés okozta gerincvelő ischemia súlyos neurológiai következményeit számos klinikai és kísérleti tanulmány bizonyítja. E nehezen kiszámítható, súlyos szövődmény megelőzésének érdekében régi törekvés megfelelő intra- és posztoperatív monitorizálás kifejlesztése, ami előre jelzi a gerincvelő-funkció romlását, illetve a kialakuló celluláris károsodást. A legelterjedtebb, a klinikai gyakorlatban széles körben alkalmazott megoldás a gerincvelői kiváltott motoros potenciál (MEP) folyamatos ellenőrzése. Ritkábban alkalmazott – bár ígéretes – eljárás a biokémiai változások nyomon követése, ami a sejtszintű károsodás markereit használja fel az ischemia okozta változások felismerésére. Korábbi dolgozatunkban kutyákon végzett kísérleteink azon eredményeit ismertettük, amelyekben a 60 perces thoracoabdominalis aortakirekesztés okozta neurológiai változások és a perfúzió adatainak összefüggéseit tárgyaltuk. Jelen tanulmányunkban a gerincvelői motoros (MEP) és szenzoros (SEP) kiváltott potenciálok változásait vizsgáljuk a neurológiai végállapot vonatkozásában. Megállapítottuk, hogy SEP változásai a neurológiai károsodás mértékével értékelhető összefüggést nem mutatnak. A MEP-amplitúdó és -latencia értékei biztonsággal jelzik a fenyegető gerincvelő ischemiát. A neurológiai deficit mélységét (Tarlov 2,1,0) a MEP-értékek változásai numerikusan nem értékelhetően követik. Summary. Severe neurological complications of the thoracoabdominal aortic clamping were published in numerous clinical and experimental studies. These hardly predictable, devastating consequences demanded to develop a monitoring system which might detect impending level of spinal cord ischemia in time – in order to introduce or enhance protective procedures and prevent permanent neurological deficit. The most widely used monitoring in clinical practice is the continuous surveillance of the motor evoked potentials (MEP) during and after thoracoabdominal aortic clamping. Much less used, but promising opportunity is to control the metabolic changes and cellular integrity utilizing specific markers like liquor lactate and neuron specific enolase (NSE) etc. In our earlier study we published data of our canine experiment related to coherencies between neurological outcome and specific perfusion of the spinal cord during and after one hour thoracoabdominal aortic clamping. In the present paper we investigate the behavior of motor evoked (MEP) and sensory evoked (SEP) potentials related to neurological changes. We conclude the behavior of SEP values hardly correlate with the neurologic outcome, meanwhile decrease of MEP amplitude provides reliable signal for developing spinal cord ischemia. We could not confirm a numeric correlation of these data and the level of the final neurologic outcome.

778-P: The Impact of Self-Management Blood Glucose (SMBG) Real-Time Decision Support on Glycemic Control in Adult with T1D in China

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 778-P
Author(s):  
ZIYU LIU ◽  
CHAOFAN WANG ◽  
XUEYING ZHENG ◽  
SIHUI LUO ◽  
DAIZHI YANG ◽  
...  
Keyword(s):  
Decision Support ◽  
Blood Glucose ◽  
Glycemic Control ◽  
Real Time ◽  
Self Management ◽  
The Impact

Воздействиеультразвуковогополянадинамическуювязкостьводы

2019 ◽  
pp. 27-29
Author(s):  
P. Vikulin ◽  
K. Khlopov ◽  
M. Cherkashin
Keyword(s):  
Dynamic Viscosity ◽  
Experimental Studies ◽  
Ultrasonic Field ◽  
Maximum Effect ◽  
Ultrasonic Frequency ◽  
Ultrasonic Vibrations ◽  
Wastewater Disposal ◽  
Laboratory Setup ◽  
Sonic Treatment ◽  
The Impact

Enhancing water purification processes is provided by various methods including physical ones, in particular, exposure to ultrasonic vibrations. The change in the dynamic viscosity of water affects the rate of deposition of particles in the aquatic environment which can be used in natural and wastewater treatment. At the Department Water Supply and Wastewater Disposal of the National Research Moscow State University of Civil Engineering experimental studies were conducted under laboratory conditions to study the effect of ultrasound on the change in the dynamic viscosity of water. A laboratory setup has been designed consisting of an ultrasonic frequency generator of the relative intensity, a transducer (concentrator) that transmits ultrasonic vibrations to the source water, and sonic treatment tanks. Experimental studies on the impact of the ultrasonic field in the cavitation mode on the dynamic viscosity of the aqueous medium were carried out the exposure time was obtained to achieve the maximum effect.Интенсификация процессов очистки воды осуществляется с помощью различных методов, в том числе и физических, в частности воздействием ультразвуковых колебаний. Изменение динамической вязкости воды влияет на скорость осаждения частиц в водной среде, что может быть использовано в процессах очистки природных и сточных вод. На кафедре Водоснабжение и водоотведение Национального исследовательского Московского государственного строительного университета в лабораторных условиях проведены экспериментальные исследования по изучению влияния ультразвука на изменение динамической вязкости воды. Разработана схема лабораторной установки, состоящая из генератора ультразвуковых частот с соответствующей интенсивностью, преобразователя (концентратора), передающего ультразвуковые колебания в исходную воду, и емкости для озвучивания. Выполнены экспериментальные исследования по влиянию ультразвукового поля в режиме кавитации на динамическую вязкость водной среды, получено время экспозиции для достижения максимального эффекта.

Prediction of Disease Comorbidity Using HeteSim Scores based on Multiple Heterogeneous Networks

2019 ◽  
Vol 19 (4) ◽  
pp. 232-241 ◽  
Author(s):  
Xuegong Chen ◽  
Wanwan Shi ◽  
Lei Deng
Keyword(s):  
Protein Interactions ◽  
Experimental Studies ◽  
Treatment Strategies ◽  
Computational Method ◽  
Biological Information ◽  
Support Vector ◽  
Protein Protein Interactions ◽  
Efficient Treatment ◽  
Disease Associations ◽  
Previous State

Background: Accumulating experimental studies have indicated that disease comorbidity causes additional pain to patients and leads to the failure of standard treatments compared to patients who have a single disease. Therefore, accurate prediction of potential comorbidity is essential to design more efficient treatment strategies. However, only a few disease comorbidities have been discovered in the clinic. Objective: In this work, we propose PCHS, an effective computational method for predicting disease comorbidity. Materials and Methods: We utilized the HeteSim measure to calculate the relatedness score for different disease pairs in the global heterogeneous network, which integrates six networks based on biological information, including disease-disease associations, drug-drug interactions, protein-protein interactions and associations among them. We built the prediction model using the Support Vector Machine (SVM) based on the HeteSim scores. Results and Conclusion: The results showed that PCHS performed significantly better than previous state-of-the-art approaches and achieved an AUC score of 0.90 in 10-fold cross-validation. Furthermore, some of our predictions have been verified in literatures, indicating the effectiveness of our method.

Family Influences on Youth Offending

2018 ◽  
pp. 377-403
Author(s):  
Abigail A. Fagan ◽  
Kristen M. Benedini
Keyword(s):  
Life Course ◽  
Family Environment ◽  
Parenting Practices ◽  
Experimental Studies ◽  
The United States ◽  
Parental Violence ◽  
Youth Delinquency ◽  
The Impact ◽  
Children’S Exposure

This chapter reviews the degree to which empirical evidence demonstrates that families influence youth delinquency. Because they are most likely to be emphasized in life-course theories, this chapter focuses on parenting practices such as parental warmth and involvement, supervision and discipline of children, and child maltreatment. It also summarizes literature examining the role of children's exposure to parental violence, family criminality, and young (teenage) parents in affecting delinquency. Because life-course theories are ideally tested using longitudinal data, which allow examination of, in this case, the impact of parenting practices on children's subsequent behaviors, this chapter focuses on evidence generated from prospective studies conducted in the United States and other countries. It also discusses findings from experimental studies designed to reduce youth substance use and delinquency by improving the family environment.

Sign in / Sign up

Export Citation Format

Share Document