Incorporating Machine Learning into Established Bioinformatics Frameworks

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.     

Improved activity and thermostability of Candida antarctica lipase B by DNA family shuffling

DNA family shuffling was used to create chimeric lipase B proteins with improved activity toward the hydrolysis of diethyl 3-(3',4'-dichlorophenyl)glutarate (DDG). Three homologous lipases from Candida antarctica ATCC 32657, Hyphozyma sp. CBS 648.91 and Crytococcus tsukubaensis ATCC 24555 were cloned and shuffled to generate a diverse gene library. A high-throughput screening assay was developed and used successfully to identify chimeric lipase B proteins having a 20-fold higher activity toward DDG than lipase B from C.antarctica ATCC 32657 and a 13-fold higher activity than the most active parent derived from C.tsukubaensis ATCC 24555. In addition, the stability characteristics of several highly active chimeric proteins were also improved as a result of family shuffling. For example, the half-life at 45 degrees C and melting point (T(m)) of one chimera exceeded those of lipase B from C.antarctica ATCC 32657 by 11-fold and 6.4 degrees C, respectively, which closely approached the stability characteristics of the most thermostable parent derived from Hyphozyma sp. CBS 648.91.     

Algorithmic Aspects of Acyclic Edge Colorings

Abstract. A proper coloring of the edges of a graph G is called acyclic if there is no two-colored cycle in G . The acyclic edge chromatic number of G , denoted by a'(G) , is the least number of colors in an acyclic edge coloring of G . For certain graphs G , a'(G)\geq Δ(G)+2 where Δ(G) is the maximum degree in G . It is known that a'(G)≤ Δ + 2 for almost all Δ -regular graphs, including all Δ -regular graphs whose girth is at least cΔ log Δ . We prove that determining the acyclic edge chromatic number of an arbitrary graph is an NP-complete problem. For graphs G with sufficiently large girth in terms of Δ(G) , we present deterministic polynomial-time algorithms that color the edges of G acyclically using at most Δ(G)+2 colors.     

Monitoring Interfaces for Faults

We consider the problem of a module interacting with an external interface (environment) where the interaction is expected to satisfy some system specification Φ. While we have the full implementation details of the module, we are only given a partial external specification for the interface. The interface specification being partial (incomplete) means that the interface displays only a strict subset of the behaviors allowed by the interface specification.Based on the assumption that interface specifications are typically incomplete, we address the question of whether we can tighten the interface specification into a strategy, consistent with the given partial specification, that will guarantee that all possible interactions resulting from possible behaviors of the module will satisfy the system specification Φ. We refer to such a tighter specification as Φ-guaranteeing specification. Rather than verifying whether the interface, which is often an off-the-shelf component, satisfies the tighter specification, the paper proposes a construction of a run-time monitor which continuously checks the existence of a Φ-guaranteeing interface.We view the module and the external interface as players in a 2-player game. The interface has a winning strategy if it can guarantee that no matter what the module does, the overall specification Φ is met. The problem of incomplete specifications is resolved by allowing the interface to follow any strategy consistent with the interface specification. Our approach essentially combines traditional run-time monitoring and static analysis. This allows going beyond the focus of traditional run-time monitoring tools – error detection in the execution trace, towards the focus of the static analysis – bug detection in the programs.     

Efficient elections in chordal ring networks

We study the message complexity of the problem of distributively electing a leader in chordal rings. Such networks consist of a basic ring with additional links, the extreme cases being the oriented ring and the complete graph with a full sense of direction. We present a general election algorithm for these networks, and prove its optimality. As a corollary, we show thatO(logn) chords at each processor suffice to obtain an algorithm that uses at mostO(n) messages; this improves and extends a previous work, where an algorithm, also usingO(n) messages, was suggested for the case where alln-1 chords exist (the oriented complete network).