Automatic Text Summarization is the process of condensing an input text into a concise output without losing any core information, the importance of which is increasing rapidly in this digital era. Text summarization is broadly divided into two approaches, i.e., extractive and abstractive. These approaches are implemented using many techniques, which are commonly grouped into five categories: statistical, graph-based, machine learning, deep learning, and transformer-based methods. To conduct a thorough investigation of the strengths and weaknesses of these techniques, we evaluated nine popular and reproducible text summarization models, including four Large Language Models (LLM), i.e., Gemma 2, LLaMa 3.3, Mistral, and DeepSeek-R1, based on their performance in Bengali text summarization. We found out that the abstractive summaries produced by LLMs like Gemma and especially LLaMa are very coherent and human-like, but they either sufer linguistically (Gemma) or factually (LLaMa). Extractive models, especially ML and DL models, are very competent at creating Bengali summaries that are contextually and factually correct but are less coherent. These trends are also seen in the overall comparison of extractive and abstractive methods. This study highlights the viability of a hybrid approach to create both coherent and factually correct summaries in low-resource languages by revealing the strengths and weaknesses of different techniques.

MOTIVATION: The negative binomial distribution has been shown to be a good model for counts data from both bulk and single-cell RNA-sequencing (RNA-seq). Gaussian process (GP) regression provides a useful non-parametric approach for modelling temporal or spatial changes in gene expression. However, currently available GP regression methods that implement negative binomial likelihood models do not scale to the increasingly large datasets being produced by single-cell and spatial transcriptomics. RESULTS: The GPcounts package implements GP regression methods for modelling counts data using a negative binomial likelihood function. Computational efficiency is achieved through the use of variational Bayesian inference. The GP function models changes in the mean of the negative binomial likelihood through a logarithmic link function and the dispersion parameter is fitted by maximum likelihood. We validate the method on simulated time course data, showing better performance to identify changes in over-dispersed counts data than methods based on Gaussian or Poisson likelihoods. To demonstrate temporal inference, we apply GPcounts to single-cell RNA-seq datasets after pseudotime and branching inference. To demonstrate spatial inference, we apply GPcounts to data from the mouse olfactory bulb to identify spatially variable genes and compare to two published GP methods. We also provide the option of modelling additional dropout using a zero-inflated negative binomial. Our results show that GPcounts can be used to model temporal and spatial counts data in cases where simpler Gaussian and Poisson likelihoods are unrealistic. AVAILABILITY AND IMPLEMENTATION: GPcounts is implemented using the GPflow library in Python and is available at https://github.com/ManchesterBioinference/GPcounts along with the data, code and notebooks required to reproduce the results presented here. The version used for this paper is archived at https://doi.org/10.5281/zenodo.5027066. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: The Gaussian Process Latent Variable Model (GPLVM) is a popular approach for dimensionality reduction of single-cell data and has been used for pseudotime estimation with capture time information. However, current implementations are computationally intensive and will not scale up to modern droplet-based single-cell datasets which routinely profile many tens of thousands of cells. Results: We provide an efficient implementation which allows scaling up this approach to modern single-cell datasets. We also generalize the application of pseudotime inference to cases where there are other sources of variation such as branching dynamics. We apply our method on microarray, nCounter, RNA-seq, qPCR and droplet-based datasets from different organisms. The model converges an order of magnitude faster compared to existing methods whilst achieving similar levels of estimation accuracy. Further, we demonstrate the flexibility of our approach by extending the model to higher-dimensional latent spaces that can be used to simultaneously infer pseudotime and other structure such as branching. Thus, the model has the capability of producing meaningful biological insights about cell ordering as well as cell fate regulation. Availability and implementation: Software available at github.com/ManchesterBioinference/GrandPrix. Supplementary information: Supplementary data are available at Bioinformatics online.