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

Data Mining Practical Machine Learning Tools and Techniques

Hypoxia inducible factorにより誘導される癌細胞の接着分子

Motivation Figures and captions convey essential information in biomedical documents. As such, there is a growing interest in mining published biomedical figures and in utilizing their respective captions as a source of knowledge. Notably, an essential step underlying such mining is the extraction of figures and captions from publications. While several PDF parsing tools that extract information from such documents are publicly available, they attempt to identify images by analyzing the PDF encoding and structure and the complex graphical objects embedded within. As such, they often incorrectly identify figures and captions in scientific publications, whose structure is often non-trivial. The extraction of figures, captions and figure-caption pairs from biomedical publications is thus neither well-studied nor yet well-addressed. Results We introduce a new and effective system for figure and caption extraction, PDFigCapX. Unlike existing methods, we first separate between text and graphical contents, and then utilize layout information to effectively detect and extract figures and captions. We generate files containing the figures and their associated captions and provide those as output to the end-user.We test our system both over a public dataset of computer science documents previously used by others, and over two newly collected sets of publications focusing on the biomedical domain. Our experiments and results comparing PDFigCapX to other state-of-the-art systems show a significant improvement in performance, and demonstrate the effectiveness and robustness of our approach. Availability and implementation Our system is publicly available for use at: https://www.eecis.udel.edu/~compbio/PDFigCapX. The two new datasets are available at: https://www.eecis.udel.edu/~compbio/PDFigCapX/Downloads.

Figure and caption extraction from biomedical documents.

Published literature is an important source of knowledge supporting biomedical research. Given the large and increasing number of publications, automated document classification plays an important role in biomedical research. Effective biomedical document classifiers are especially needed for bio-databases, in which the information stems from many thousands of biomedical publications that curators must read in detail and annotate. In addition, biomedical document classification often amounts to identifying a small subset of relevant publications within a much larger collection of available documents. As such, addressing class imbalance is essential to a practical classifier. We present here an effective classification scheme for automatically identifying papers among a large pool of biomedical publications that contain information relevant to a specific topic, which the curators are interested in annotating. The proposed scheme is based on a meta-classification framework using cluster-based under-sampling combined with named-entity recognition and statistical feature selection strategies. We examined the performance of our method over a large imbalanced data set that was originally manually curated by the Jackson Laboratory's Gene Expression Database (GXD). The set consists of more than 90 000 PubMed abstracts, of which about 13 000 documents are labeled as relevant to GXD while the others are not relevant. Our results, 0.72 precision, 0.80 recall and 0.75 f-measure, demonstrate that our proposed classification scheme effectively categorizes such a large data set in the face of data imbalance.

/pdf/an-effective-biomedical-document-classification-scheme-in-4mmyqfldtn.pdf

An effective biomedical document classification scheme in support of biocuration: addressing class imbalance.

Images form a rich information source, which remains underutilized in biomedical document classification. We present here work that uses both image- and text-based features in order to identify articles of interest, in this case, pertaining to cis-regulatory modules in the context of gene-networks. Extending on our new idea, which we have recently introduced, of using OCR-based features to identify DNA contents in images, we combine image and text based classifiers to categorize documents as relevant or irrelevant to cis-regulatory modules. Using a set of hundreds of articles, marked by experts as relevant or irrelevant to cis-regulatory modules, we train/test image and text based classifiers, as well as classifiers integrating both. Our results indicate that the latter show the best performance with Recall, F-measure and Utility measures all above 0.9, demonstrating the significance of incorporating image data, and specifically OCR-based features, into the document categorization process. Moreover, the use of character distribution properties to represent images is directly relevant to other biomedical images containing text (e.g. RNA, proteins). Diagrams and other images containing text are also prevalent outside the biomedical domain, hence the work stands to be applicable and beneficial in other application areas.

Utilizing image-based features in biomedical document classification

The CYRENE Project focuses on the study of cis-regulatory genomics and gene regulatory networks (GRN) and has three components: a cisGRN-Lexicon, a cisGRN-Browser, and the Virtual Sea Urchin software system. The project has been done in collaboration with Eric Davidson and is deeply inspired by his experimental work in genomic regulatory systems and gene regulatory networks. The current CYRENE cisGRN-Lexicon contains the regulatory architecture of 200 transcription factors encoding genes and 100 other regulatory genes in eight species: human, mouse, fruit fly, sea urchin, nematode, rat, chicken, and zebrafish, with higher priority on the first five species. The only regulatory genes included in the cisGRN-Lexicon (CYRENE genes) are those whose regulatory architecture is validated by what we call the Davidson Criterion: they contain functionally authenticated sites by site-specific mutagenesis, conducted in vivo, and followed by gene transfer and functional test. This is recognized as the most stringent experimental validation criterion to date for such a genomic regulatory architecture. The CYRENE cisGRN-Browser is a full genome browser tailored for cis-regulatory annotation and investigation. It began as a branch of the Celera Genome Browser (available as open source at http://sourceforge.net/projects/celeragb /) and has been transformed to a genome browser fully devoted to regulatory genomics. Its access paradigm for genomic data is zoom-to-the-DNA-base in real time. A more recent component of the CYRENE project is the Virtual Sea Urchin system (VSU), an interactive visualization tool that provides a four-dimensional (spatial and temporal) map of the gene regulatory networks of the sea urchin embryo.

/pdf/practical-computational-methods-for-regulatory-genomics-a-2h1s2n6zem.pdf

Practical Computational Methods for Regulatory Genomics: A cisGRN-Lexicon and cisGRN-Browser for Gene Regulatory Networks

Images form a significant and useful source of information in published biomedical articles, which is still under-utilized in biomedical document classification and retrieval. Much current work on biomedical image retrieval and classification employs simple, standard image features such as gray scale histograms and edge direction to represent and classify images. We have used such features as well to classify images in our early work [5], where we used image-class-tags to represent and classify articles. In the work presented here we focus on a different literature classification task, motivated by the need to identify articles discussing cis-regulatory elements and modules in the context of understanding complex gene-networks. The curators who try to identify such articles in the vast literature use as a major cue a certain type of image in which the conserved cis-regulatory region on the DNA is shown. Our experiments show that automatically identifying such images using common image features (like those mentioned above) can be highly error prone. However, using Optical Character Recognition (OCR) to extract alphabet characters from images, calculating character distribution and using the distribution parameters as image features, allows us to form a novel representation of images, and identify DNA-content in images with high precision and recall (over 0.9). Utilizing the occurrence of such DNA-rich images within articles, we train a classifier that identifies articles pertaining to cis-regulatory elements with a similarly high precision and recall. The use of OCR-based image features has much potential beyond the current task, to identify other types of biomedical sequence-based images showing DNA, RNA and proteins. Moreover, the ability to automatically identify such images has much potential to be widely applicable in other important biomedical document classification tasks.

/pdf/ocr-based-image-features-for-biomedical-image-and-article-2e3rc7yx02.pdf

Kyle Schutter

Papers

Utilizing image-based features in biomedical document classification

Practical Computational Methods for Regulatory Genomics: A cisGRN-Lexicon and cisGRN-Browser for Gene Regulatory Networks

OCR-based image features for biomedical image and article classification: identifying documents relevant to cis-regulatory elements

OCR-Based Image Features for Biomedical Image and Article Classification: Identifying Documents Relevant to Genomic Cis-Regulatory Elements.