Abstract
This special issue includes a selection of articles presented at the 19th International Symposium on Bioinformatics Research and Applications (ISBRA 2023), which was held at the Łukasiewicz Research Network—PORT Polish Center for Technology Development, Wrocław, Poland, on October 9–12, 2023. ISBRA provides a forum for the exchange of ideas and results among researchers, developers, and practitioners working on all aspects of bioinformatics and computational biology and their applications.
In 2023, 89 abstracts were submitted in response to the call for papers, out of which 28 full papers and 16 short papers appeared in the ISBRA proceedings published as volume 14,248 of Springer Verlag’s Lecture Notes in Bioinformatics series. The authors of 19 papers were invited to submit an extended version of their abstracts to this 2-part special issue. This first part contains 10 papers, while the second part contains 8 papers, after one author withdrew.
In “Generative AI Models for the Protein Scaffold Filling Problem,” the authors present several approaches to the protein scaffold filling program based on generative AI techniques, including convolutional denoising autoencoders and GPT models. The paper “PDFll: Predictors of Disorder and Function of Proteins from the Language of Life” presents a series of computational predictors based on embeddings produced by protein language models input to deep-learning models. In “AFMDD: Analyzing Functional Connectivity Feature of Major Depressive Disorder by Graph Neural Network-Based Model”, the authors present a graph neural network-based model of the brain to assess brain functional connectivity. The authors of “Pathway Realizability in Chemical Networks” present a framework for specifying and searching for pathways that are realizable, based on reachability in Petri nets. In “Estimating Enzyme Expression and Metabolic Pathway Activity in Borreliella-Infected and Uninfected Mice,” the authors propose a maximum likelihood pipeline based on the expectation-maximization algorithm, which is capable of evaluating enzyme expression and metabolic pathway activity level, and apply it to infected and uninfected mice. The authors of “BiRNN-DDI: A Drug-drug Interaction Event Type Prediction Model based on Bidirectional Recurrent Neural Network and Graph2Seq Representation” present an approach for predicting drug–drug interaction event types by converting a drug feature graph representation into a sequence representation and then applying a bidirectional recurrent neural network on the resulting sequences representation. In “CFINet: Cross-modality MRI Feature Interaction Network for Pseudoprogression Prediction of Glioblastoma” develop a cross-modality MRI feature interaction method using T1 and T2 MRI for better pseudoprogression prediction of glioblastoma. The authors of “Attention-Guided Residual U-Net with SE Connection and ASPP for Watershed-based Cell Segmentation in Microscopy Images” present a novel framework that incorporates residual blocks, an attention mechanism, a squeeze and excitation connection, and atrous spatial pyramid pooling for precise and robust cell segmentation.