There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

BIOE 402. Medical Technology Assessment. 2 or 3 hours. Bioentrepreneur course. Assessment of medical technology in the context of commercialization. Objectives, competition, market share, funding, pricing, manufacturing, growth, and intellectual property; many issues unique to biomedical products. Course Information: 2 undergraduate hours. 3 graduate hours. Prerequisite(s): Junior standing or above and consent of the instructor.

“Bioinformatics” 특집을 내면서

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

A morphable model for the synthesis of 3D faces

Expression microarrays provide a platform for the investigation of thousands of genes simultaneously. There are various methods which aim to identify differentially expressed significant gene list over a microarray experiment [1]. Many of those analyses focus in pairwise comparison of the selected subset data of the experiment rather than considering the entire data. The aim of this study is to extract gene expression patterns with computational clustering techniques using not only a subset but the entire experimental microarray dataset. Therefore we applied a hybrid computational method to identify expression patterns on an affymetrix microarray dataset containing 54000 probe sets of 6 different cell fates with 3 replicates for each stage. The raw probe data were normalized by RMA pre-processing method. Subsequently K-means clustering algorithm [2] was applied to explore a group of genes which were in similar behavior at each experimental cell fate. We set the total number of clusters to 100 in K-means algorithm. In order to identify significant clusters, the variance in cell fates for each cluster was computed and the most variant 13 clusters were selected as candidate sets. Among 13 candidate clusters, we selected an expressing pattern cluster; called as promising cluster which seemed biologically significant based the experimental design. The promising cluster then was used as the profile to train a hidden Markov model (HMM) [3]. Before training of HMM, outlier genes were removed according to their mean and standard deviations. In other words, the expression value of a gene should be in a valid range higher or lower than the standard deviation, otherwise that gene is removed from promising cluster. Our HMM comprised of 6 states and each state generates one of the 3 observation symbols: up regulated, down regulated and no-change. HMM was trained with Baum-Welch method by using expression value of 83 genes in the promising cluster. In order to explore genes that showed expression patterns similar to that of promising cluster profile, we tested all genes in the data set over the trained HMM. The genes which gave higher probability in HMM test process were labeled as significant. There were 620 significant genes. We have observed that the profiles of these significant genes were very similar to that of the profile of the promising cluster. Therefore, our hybrid method could achieve to identify a group of genes sharing a similar expression pattern.

A Hybrid Method For The Identification of Expression Patterns From Microarray Data

Subcellular localization is crucial for determining the functions of proteins. A system called prediction of protein subcellular localization (P2SL) that predicts the subcellular localization of proteins in eukaryotic organisms based on the amino acid content of primary sequences using amino acid order is designed. The approach for prediction is to find the most frequent motifs for each protein in a given class based on clustering via self organizing maps and then to use these most frequent motifs as features for classification by the help of multilayer perceptrons. This approach allows a classification independent of the length of the sequence. In addition to these, the use of a new encoding scheme is described for the amino acids that conserves biological function based on the point of accepted mutations (PAM) substitution matrix. The statistical test results of the system are presented on a four class problem. P2SL achieves slightly higher prediction accuracy than the similar studies.

Prediction of protein subcellular localization based on primary sequence data

Image-based Extraction of Material Reflectance Properties of a 3D Rigid Object.

Number of connected devices is steadily increasing and these devices continuously generate data streams. These data streams are often high dimensional and contain concept drift. Real-time processing of data streams is arousing interest despite many challenges. Clustering is a method that does not need labeled instances (it is unsupervised) and it can be applied with less prior information about the data. These properties make clustering one of the most suitable methods for real-time data stream processing. Moreover, data embedding is a process that may simplify clustering and makes visualization of high dimensional data possible. There exist several data stream clustering algorithms in the literature, however no data stream embedding method exists. UMAP is a data embedding algorithm that is suitable to be applied on data streams, but it cannot adopt concept drift. In this study, we have developed a new method to apply UMAP on data streams, adopt concept drift and cluster embedded data instances using any distance based clustering algorithms.

Online Embedding and Clustering of Data Streams

In this study, we combined the ChIP-seq and the transcriptome data and integrated these data into signaling cascades. Integration was realized through a framework based on data- and model-driven hybrid approach. An enrichment model was constructed to evaluate signaling cascades which resulted in specic cellular processes. We used ChIP-seq and microarray data from public databases which were obtained from HeLa cells under oxidative stress having similar experimental setups. Both ChIP-seq and array data were analyzed by percentile ranking for the sake of simultaneous data integration on specic genes. Signaling cascades from KEGG pathway database were subsequently scored by taking sum of the individual scores of the genes involved within the cascade. This scoring information is then transferred to en route of the signaling cascade to form the nal score. Signaling cascade model based framework that we describe in this study is a novel approach which calculates scores for the target process of the analyzed signaling cascade, rather than assigning scores to gene product nodes.

/pdf/evaluation-of-signaling-cascades-based-on-the-weights-from-2zj7z054sm.pdf

Volkan Atalay

Papers

A Hybrid Method For The Identification of Expression Patterns From Microarray Data

Prediction of protein subcellular localization based on primary sequence data

Image-based Extraction of Material Reflectance Properties of a 3D Rigid Object.

Online Embedding and Clustering of Data Streams

Evaluation of Signaling Cascades Based on the Weights from Microarray and ChIP-seq Data