Compressed learning and its applications to subcellular localization

One of the main challenges faced by biological applications is to predict protein subcellular localization in automatic fashion accurately. To achieve this in these applications, a wide variety of machine learning methods have been proposed in recent years. Most of them focus on finding the optimal classification scheme and less of them take the simplifying the complexity of biological systems into account. Traditionally, such bio-data are analyzed by first performing a feature selection before classification. Motivated by CS (Compressed Sensing) theory, we propose the methodology which performs compressed learning with a sparseness criterion such that feature selection and dimension reduction are merged into one analysis. The proposed methodology decreases the complexity of biological system, while increases protein subcellular localization accuracy. Experimental results are quite encouraging, indicating that the aforementioned sparse methods are quite promising in dealing with complicated biological problems, such as predicting the subcellular localization of Gram-negative bacterial proteins.     

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.     

Machine learning applications in systems metabolic engineering

1. Download : Download high-res image (118KB)
2. Download : Download full-size image

     

一种新型相干辐射--THz辐射在生物学中的应用

脉冲THz辐射是一种新型的远红外相干辐射源,近年来在不同的研究领域得到了广泛的应用。本文简要介绍THz辐射产生、探测的基本原理和方法;THz辐射的基本性质和它在生物学研究中应用的物理基础;对生物体系进行时域光谱分析和成像研究所取得的成果和最新进展,以及对该领域研究前景的展望。     

Machine learning approaches in MALDI-MSI: clinical applications

Introduction: Despite the unquestionable advantages of Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Imaging in visualizing the spatial distribution and the relative abundance of biomolecules directly on-tissue, the yielded data is complex and high dimensional. Therefore, analysis and interpretation of this huge amount of information is mathematically, statistically and computationally challenging.

Areas covered: This article reviews some of the challenges in data elaboration with particular emphasis on machine learning techniques employed in clinical applications, and can be useful in general as an entry point for those who want to study the computational aspects. Several characteristics of data processing are described, enlightening advantages and disadvantages. Different approaches for data elaboration focused on clinical applications are also provided. Practical tutorial based upon Orange Canvas and Weka software is included, helping familiarization with the data processing.

Expert commentary: Recently, MALDI-MSI has gained considerable attention and has been employed for research and diagnostic purposes, with successful results. Data dimensionality constitutes an important issue and statistical methods for information-preserving data reduction represent one of the most challenging aspects. The most common data reduction methods are characterized by collecting independent observations into a single table. However, the incorporation of relational information can improve the discriminatory capability of the data.     

Text mining and its potential applications in systems biology

With biomedical literature increasing at a rate of several thousand papers per week, it is impossible to keep abreast of all developments; therefore, automated means to manage the information overload are required. Text mining techniques, which involve the processes of information retrieval, information extraction and data mining, provide a means of solving this. By adding meaning to text, these techniques produce a more structured analysis of textual knowledge than simple word searches, and can provide powerful tools for the production and analysis of systems biology models.     

Catalytic RNA,ribozyme, and its applications in synthetic biology

Ribozymes are functional RNA molecules that can catalyze biochemical reactions. Since the discovery of the first catalytic RNA, various functional ribozymes (e.g., self-cleaving ribozymes, splicing ribozymes, RNase P, etc.) have been uncovered, and their structures and mechanisms have been identified. Ribozymes have the advantage of possessing features of “RNA” molecules; hence, they are highly applicable for manipulating various biological systems. To fully employ ribozymes in a broad range of biological applications in synthetic biology, a variety of ribozymes have been developed and engineered. Here, we summarize the main features of ribozymes and the methods used for engineering their functions. We also describe the past and recent efforts towards exploiting ribozymes for effective and novel applications in synthetic biology. Based on studies on their significance in biological applications till date, ribozymes are expected to advance technologies in artificial biological systems.     

A systems biology approach to learning autophagy

With its relevance to our understanding of eukaryotic cell function in the normal and disease state, autophagy is an important topic in modern cell biology; yet, few textbooks discuss autophagy beyond a two- or three-sentence summary. Here, we report an undergraduate/graduate class lesson for the in-depth presentation of autophagy using an active learning approach. By our method, students will work in small groups to solve problems and interpret an actual data set describing genes involved in autophagy. The problem-solving exercises and data set analysis will instill within the students a much greater understanding of the autophagy pathway than can be achieved by simple rote memorization of lecture materials; furthermore, the students will gain a general appreciation of the process by which data are interpreted and eventually formed into an understanding of a given pathway. As the data sets used in these class lessons are largely genomic and complementary in content, students will also understand first-hand the advantage of an integrative or systems biology study: No single data set can be used to define the pathway in full-the information from multiple complementary studies must be integrated in order to recapitulate our present understanding of the pathways mediating autophagy. In total, our teaching methodology offers an effective presentation of autophagy as well as a general template for the discussion of nearly any signaling pathway within the eukaryotic kingdom.     

Directed evolution and synthetic biology applications to microbial systems

1. Download : Download high-res image (219KB)
2. Download : Download full-size image

     

Students' studying and approaches to learning in introductory biology

This exploratory study was conducted in an introductory biology course to determine 1) how students used the large lecture environment to create their own learning tasks during studying and 2) whether meaningful learning resulted from the students' efforts. Academic task research from the K-12 education literature and student approaches to learning research from the postsecondary education literature provided the theoretical framework for the mixed methods study. The subject topic was cell division. Findings showed that students 1) valued lectures to develop what they believed to be their own understanding of the topic; 2) deliberately created and engaged in learning tasks for themselves only in preparation for the unit exam; 3) used course resources, cognitive operations, and study strategies that were compatible with surface and strategic, rather than deep, approaches to learning; 4) successfully demonstrated competence in answering familiar test questions aligned with their surface and strategic approaches to studying and learning; and 5) demonstrated limited meaningful understanding of the significance of cell division processes. Implications for introductory biology education are discussed.     

Using a learning log to support students' learning in biology lessons

Providing copies of an instructor's lecture notes before lectures is enthusiastically approved of by university students in introductory biology classes. Surprisingly, students who use the notes tend to perform less well onexams than students who avoid using the notes. However, there is no evidence that using the notes is harmful to learning; rather, those students who choose not to use the notes enter the course with better preparation or knowledge than the class as a whole. Pre-circulated notes may improve the clarity of lectures and encourage advance preparation by students — a learning discipline possibly as valuable as organising and reviewing one's own notes.     

Probabilistic logic methods and some applications to biology and medicine

For the computational analysis of biological problems-analyzing data, inferring networks and complex models, and estimating model parameters-it is common to use a range of methods based on probabilistic logic constructions, sometimes collectively called machine learning methods. Probabilistic modeling methods such as Bayesian Networks (BN) fall into this class, as do Hierarchical Bayesian Networks (HBN), Probabilistic Boolean Networks (PBN), Hidden Markov Models (HMM), and Markov Logic Networks (MLN). In this review, we describe the most general of these (MLN), and show how the above-mentioned methods are related to MLN and one another by the imposition of constraints and restrictions. This approach allows us to illustrate a broad landscape of constructions and methods, and describe some of the attendant strengths, weaknesses, and constraints of many of these methods. We then provide some examples of their applications to problems in biology and medicine, with an emphasis on genetics. The key concepts needed to picture this landscape of methods are the ideas of probabilistic graphical models, the structures of the graphs, and the scope of the logical language repertoire used (from First-Order Logic [FOL] to Boolean logic.) These concepts are interlinked and together define the nature of each of the probabilistic logic methods. Finally, we discuss the initial applications of MLN to genetics, show the relationship to less general methods like BN, and then mention several examples where such methods could be effective in new applications to specific biological and medical problems.     

Sleeping Beauty transposition: from biology to applications

Sleeping Beauty (SB) is the first synthetic DNA transposon that was shown to be active in a wide variety of species. Here, we review studies from the last two decades addressing both basic biology and applications of this transposon. We discuss how host–transposon interaction modulates transposition at different steps of the transposition reaction. We also discuss how the transposon was translated for gene delivery and gene discovery purposes. We critically review the system in clinical, pre-clinical and non-clinical settings as a non-viral gene delivery tool in comparison with viral technologies. We also discuss emerging SB-based hybrid vectors aimed at combining the attractive safety features of the transposon with effective viral delivery. The success of the SB-based technology can be fundamentally attributed to being able to insert fairly randomly into genomic regions that allow stable long-term expression of the delivered transgene cassette. SB has emerged as an efficient and economical toolkit for safe and efficient gene delivery for medical applications.