A reaction network scheme for hidden Markov model parameter learning.

With a view towards artificial cells, molecular communication systems, molecular multiagent systems and federated learning, we propose a novel reaction network scheme (termed the Baum-Welch (BW) reaction network) that learns parameters for hidden Markov models (HMMs). All variables including inputs and outputs are encoded by separate species. Each reaction in the scheme changes only one molecule of one species to one molecule of another. The reverse change is also accessible but via a different set of enzymes, in a design reminiscent of futile cycles in biochemical pathways. We show that every positive fixed point of the BW algorithm for HMMs is a fixed point of the reaction network scheme, and vice versa. Furthermore, we prove that the 'expectation' step and the 'maximization' step of the reaction network separately converge exponentially fast and compute the same values as the E-step and the M-step of the BW algorithm. We simulate example sequences, and show that our reaction network learns the same parameters for the HMM as the BW algorithm, and that the log-likelihood increases continuously along the trajectory of the reaction network.

A new algorithm to train hidden Markov models for biological sequences with partial labels.

BACKGROUND: Hidden Markov models (HMM) are a powerful tool for analyzing biological sequences in a wide variety of applications, from profiling functional protein families to identifying functional domains. The standard method used for HMM training is either by maximum likelihood using counting when sequences are labelled or by expectation maximization, such as the Baum-Welch algorithm, when sequences are unlabelled. However, increasingly there are situations where sequences are just partially labelled. In this paper, we designed a new training method based on the Baum-Welch algorithm to train HMMs for situations in which only partial labeling is available for certain biological problems. RESULTS: Compared with a similar method previously reported that is designed for the purpose of active learning in text mining, our method achieves significant improvements in model training, as demonstrated by higher accuracy when the trained models are tested for decoding with both synthetic data and real data. CONCLUSIONS: A novel training method is developed to improve the training of hidden Markov models by utilizing partial labelled data. The method will impact on detecting de novo motifs and signals in biological sequence data. In particular, the method will be deployed in active learning mode to the ongoing research in detecting plasmodesmata targeting signals and assess the performance with validations from wet-lab experiments.

Introduction to Hidden Markov Models and Its Applications in Biology.

A number of real-world systems have common underlying patterns among them and deducing these patterns is important for us in order to understand the environment around us. These patterns in some instances are apparent upon observation while in many others especially those found in nature are well hidden. Moreover, the inherent stochasticity in these systems introduces sufficient noise that we need models capable to handling it in order to decipher the underlying pattern. Hidden Markov model (HMM) is a probabilistic model that is frequently used for studying the hidden patterns in an observed sequence or sets of observed sequences. Since its conception in the late 1960s it has been extensively applied in biology to capture patterns in various disciplines ranging from small DNA and protein molecules, their structure and architecture that forms the basis of life to multicellular levels such as movement analysis in humans. This chapter aims at a gentle introduction to the theory of HMM, the statistical problems usually associated with HMMs and their uses in biology.

A Novel Assessment of Various Bio-Imaging Methods for Lung Tumor Detection and Treatment by using 4-D and 2-D CT Images.

Lung Cancer is known as one of the most difficult cancer to cure, and the number of deaths that it causes generally increasing. A detection of the Lung Cancer in its early stage can be helpful for Medical treatment to limit the danger, but it is a challenging problem due to Cancer cell structure. Interpretation of Medical image is often difficult and time consuming, even for the experienced Physicians. The aid of image analysis Based on machine learning can make this process easier. This paper describes fully Automatic Decision Support system for Lung Cancer diagnostic from CT Lung images. Most traditional medical diagnosis systems are founded on huge quantity of training data and takes long processing time. However, on the occasion that very little volume of data is available, the traditional diagnosis systems derive defects such as larger error, Time complexity. Focused on the solution to this problem, a Medical Diagnosis System based on Hidden Markov Model (HMM) is presented. In this paper we describe a pre-processing stage involving some Noise removal techniques help to solve this problem, we preprocess an images (by Mean Error Square Filtering and Histogram analysis)obtained after scanning the Lung CT images. Secondly separate the lung areas from an image by a segmentation process (by Thresholding and region growing techniques). Finally we developed HMM for the classification of Cancer Nodule. Results are checked for 2D and 4D CT images. This automation process reduces the time complexity and increases the diagnosis confidence.