MOTIVATION: Target discovery is crucial in drug development, especially for complex chronic diseases. Recent advances in high-throughput technologies and the explosion of biomedical data have highlighted the potential of computational druggability prediction methods. However, most current methods rely on sequence-based features with machine learning, which often face challenges related to hand-crafted features, reproducibility, and accessibility. Moreover, the potential of raw sequence and protein structure has not been fully investigated. RESULTS: Here, we leveraged both protein sequence and structure using deep learning techniques, revealing that protein sequence, especially pre-trained embeddings, is more informative than protein structure. Next, we developed DrugTar, a high-performance deep learning algorithm integrating sequence embeddings from the ESM-2 pre-trained protein language model with gene ontologies to predict druggability. DrugTar achieved areas under the curve and precision-recall curve values of 0.94, outperforming state-of-the-art methods. In conclusion, DrugTar streamlines target discovery as a bottleneck in developing novel therapeutics. AVAILABILITY AND IMPLEMENTATION: DrugTar is available as a web server at www.DrugTar.com. The data and source code are at https://github.com/NBorhani/DrugTar.

MOTIVATION: The recent availability of omics data allows the construction of holistic maps of interactions between numerous role-playing biomolecules. However, these networks are often static, ignoring the dynamic behavior of biological processes. On the other hand, dynamic models are commonly constructed on small scales. Hence, the construction of large-scale dynamic models that can quantitatively predict the time-course cellular behaviors remains a big challenge. RESULTS: In this study, a pipeline is proposed for the automatic construction of large-scale dynamic models. The pipeline uses a list of biomolecules and their time-course trajectories in a given phenomenon as input. First, the interaction network of the biomolecules is constructed. To state the underlying molecular events of each interaction, it is translated into a map of biochemical reactions. Next, to define the kinetics of the reactions, an ordinary differential equation (ODE) is generated for each involved biomolecule. Finally, the parameters of the ODE system are estimated by a novel large-scale parameter approximation method. The high performance of the pipeline is demonstrated by modeling the response of a colorectal cancer cell line to different chemotherapy regimens. In conclusion, Systematic Protein Association Dynamic ANalyzer constructs genome-scale dynamic models, filling the gap between large-scale static and small-scale dynamic modeling strategies. This simulation approach allows for holistic quantitative predictions which are critical for the simulation of therapeutic interventions in precision medicine. AVAILABILITY AND IMPLEMENTATION: Detailed information about the constructed large-scale model of colorectal cancer is available in supplementary data. The SPADAN toolbox source code is also available on GitHub (https://github.com/PooyaBorzou/SPADAN). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Flooding of alarms is a very crucial problem in process industries. An alarm flood makes an operator ineffective of taking necessary actions, and often risking an emergency shutdown or a major upset. In this work, the flooding of alarms is discussed based on the standards presented in ISA 18.2. A new analysis method is proposed to investigate similar alarm floods from the historic alarm data and group them on the basis of the patterns of alarm occurrences. A case study on real industrial alarm data is also presented to demonstrate the utility of the proposed analysis.

Accuracy and efficiency of alarm systems are of paramount importance in safe operations of industrial processes. Accuracy is measured by false and missed alarm rates (probabilities); while efficiency relates to the detection delay and complexity of the technique used. Moving average filters are often employed in industry for improved alarm accuracy. Can one do better than moving average filters? The following two problems are studied in this paper: First, given both normal and abnormal statistic distributions, how to design an optimal alarm filter (of fixed complexity) for best alarm accuracy, minimizing a weighted sum of false and missed alarm rates? Second, in what cases are moving average filters optimal? For the first problem, design of optimal linear FIR alarm filters is studied, and a numerical optimization based procedure is proposed. For the second problem, a sufficient condition is given under which the moving average filters are optimal.

The performance of a univariate alarm system can be assessed in many cases by three indices, namely, the false alarm rate (FAR), missed alarm rate (MAR), and averaged alarm delay (AAD). First, this paper studies the definition and computation of the FAR, MAR, and AAD for the basic mechanism of alarm generation solely based on a trip point, and for the advanced mechanism of alarm generation by exploiting alarm on/off delays. Second, a systematic design of alarm systems is investigated based on the three performance indices and the tradeoffs among them. The computation of FAR, MAR, and AAD and the design of alarm systems require the probability density functions (PDFs) of the univariate process variable in the normal and abnormal conditions. Thus, a new method based on mean change detection is proposed to estimate the two PDFs. Numerical examples and an industrial case study are provided to validate the obtained theoretical results on the FAR, MAR and AAD, and to illustrate the proposed performance assessment and alarm system design procedures.