Semi-supervised learning of Hidden Markov Models for biological sequence analysis

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Motion Sensor–Based Fall Prevention for Senior Care: A Hidden Markov Model with Generative Adversarial Network Approach

Whereas modern medicine has enabled humans to live longer and more robust lives, recent years have seen a significant increase in chronic care costs. The prevention of threats to mobility is critical for chronic disease management. Researchers and physicians often analyze data from wearable motion sensor–based information systems (IS) to prevent falls. However, prior studies on fall prevention often achieve suboptimal performance because of their limited capacities in modeling data distributions. In this study, we adopt the computational design science paradigm to develop a novel fall prevention framework, which includes the hidden Markov model with generative adversarial network (HMM-GAN) that extracts temporal and sequential patterns from sensor signals and recognizes snippet states and a logistic regression that utilizes the snippet states and determines whether and when to trigger protective devices to prevent fall injuries. We evaluate the proposed framework against prevailing fall-prevention models and the HMM-GAN component against state-of-the-art sensor analytics models on large-scale data sets. Through an in-depth case study, we demonstrate how the proposed framework can lead to significantly reduced potentially catastrophic falls. Besides practical health information technology contributions, HMM-GAN offers methodological contributions to the IS knowledge base for scholars designing novel IT artifacts for healthcare applications.

Real-Time Assembly Support System with Hidden Markov Model and Hybrid Extensions

This paper presents a context-aware adaptive assembly assistance system meant to support factory workers by embedding predictive capabilities. The research is focused on the predictor which suggests the next assembly step. Hidden Markov models are analyzed for this purpose. Several prediction methods have been previously evaluated and the prediction by partial matching, which was the most efficient, is considered in this work as a component of a hybrid model together with an optimally configured hidden Markov model. The experimental results show that the hidden Markov model is a viable choice to predict the next assembly step, whereas the hybrid predictor is even better, outperforming in some cases all the other models. Nevertheless, an assembly assistance system meant to support factory workers needs to embed multiple models to exhibit valuable predictive capabilities.

Spectroscopy Approaches for Food Safety Applications: Improving Data Efficiency Using Active Learning and Semi-supervised Learning

The past decade witnessed rapid development in the measurement and monitoring technologies for food science. Among these technologies, spectroscopy has been widely used for the analysis of food quality, safety, and nutritional properties. Due to the complexity of food systems and the lack of comprehensive predictive models, rapid and simple measurements to predict complex properties in food systems are largely missing. Machine Learning (ML) has shown great potential to improve the classification and prediction of these properties. However, the barriers to collecting large datasets for ML applications still persists. In this paper, we explore different approaches of data annotation and model training to improve data efficiency for ML applications. Specifically, we leverage Active Learning (AL) and Semi-Supervised Learning (SSL) and investigate four approaches: baseline passive learning, AL, SSL, and a hybrid of AL and SSL. To evaluate these approaches, we collect two spectroscopy datasets: predicting plasma dosage and detecting foodborne pathogen. Our experimental results show that, compared to the de facto passive learning approach, advanced approaches (AL, SSL, and the hybrid) can greatly reduce the number of labeled samples, with some cases decreasing the number of labeled samples by more than half.

Significant non-existence of sequences in genomes and proteomes

Minimal absent words (MAWs) are minimal-length oligomers absent from a genome or proteome. Although some artificially synthesized MAWs have deleterious effects, there is still a lack of a strategy for the classification of non-occurring sequences as potentially malicious or benign. In this work, by using Markovian models with multiple-testing correction, we reveal significant absent oligomers, which are statistically expected to exist. This suggests that their absence is due to negative selection. We survey genomes and proteomes covering the diversity of life and find thousands of significant absent sequences. Common significant MAWs are often mono- or dinucleotide tracts, or palindromic. Significant viral MAWs are often restriction sites and may indicate unknown restriction motifs. Surprisingly, significant mammal genome MAWs are often present, but rare, in other mammals, suggesting that they are suppressed but not completely forbidden. Significant human MAWs are frequently present in prokaryotes, suggesting immune function, but rarely present in human viruses, indicating viral mimicry of the host. More than one-fourth of human proteins are one substitution away from containing a significant MAW, with the majority of replacements being predicted harmful. We provide a web-based, interactive database of significant MAWs across genomes and proteomes.

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.

Developing Sustainable Classification of Diseases via Deep Learning and Semi-Supervised Learning

Disease classification based on machine learning has become a crucial research topic in the fields of genetics and molecular biology. Generally, disease classification involves a supervised learning style; i.e., it requires a large number of labelled samples to achieve good classification performance. However, in the majority of the cases, labelled samples are hard to obtain, so the amount of training data are limited. However, many unclassified (unlabelled) sequences have been deposited in public databases, which may help the training procedure. This method is called semi-supervised learning and is very useful in many applications. Self-training can be implemented using high- to low-confidence samples to prevent noisy samples from affecting the robustness of semi-supervised learning in the training process. The deep forest method with the hyperparameter settings used in this paper can achieve excellent performance. Therefore, in this work, we propose a novel combined deep learning model and semi-supervised learning with self-training approach to improve the performance in disease classification, which utilizes unlabelled samples to update a mechanism designed to increase the number of high-confidence pseudo-labelled samples. The experimental results show that our proposed model can achieve good performance in disease classification and disease-causing gene identification.