PaperPlayer biorxiv bioinformatics

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.17.387795v1?rss=1

Authors: Sun, T., Song, D., Li, W. V., Li, J. J.

Abstract:

In the burgeoning field of single-cell transcriptomics, a pressing challenge is to benchmark various experimental protocols and numerous computational methods in an unbiased manner. Although dozens of simulators have been developed for single-cell RNA-seq (scRNA-seq) data, they lack the capacity to simultaneously achieve all the three goals: preserving genes, capturing gene correlations, and generating any number of cells with varying sequencing depths. To fill in this gap, here we propose scDesign2, an interpretable simulator that achieves all the three goals and generates high-fidelity synthetic data for multiple scRNA-seq protocols and other single-cell gene expression count-based technologies. Compared with existing simulators, scDesign2 is advantageous in its transparent use of probabilistic models and is unique in its ability to capture gene correlations via copula. We verify that scDesign2 generates more realistic synthetic data for four scRNA-seq protocols (10x Genomics, CEL-Seq2, Fluidigm C1, and Smart-Seq2) and two single-cell spatial transcriptomics protocols (MERFISH and pciSeq) than existing simulators do. Under two typical computational tasks, cell clustering and rare cell type detection, we demonstrate that scDesign2 provides informative guidance on deciding the optimal sequencing depth and cell number in single-cell RNA-seq experimental design, and that scDesign2 can effectively benchmark computational methods under varying sequencing depths and cell numbers. With these advantages, scDesign2 is a powerful tool for single-cell researchers to design experiments, develop computational methods, and choose appropriate methods for specific data analysis needs.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.20.387738v1?rss=1

Authors: Arslan, A.

Abstract:

Motivation: The transport of proteins plays a crucial role in the cellular phenotype. Changes in the protein targeting sequence can result in missing protein delivery to the right destination and at the right time, and can disrupt various cellular pathways. Given the importance of single residue change(s) in the protein targeting sequence we developed a missing computational method. Results: By taking into account various protein features like conservation, protein modifications, charge, isoelectric effect and biochemical properties of peptides, the method, TransSite, assess the impact of mutations on the protein transportation. We applied this method to human cancer proteins and discovered several cancer proteins harbour recurring mutations in their targeting sequences. Availability: https://github.com/AhmedArslan/TransSite Contact: [email protected] Supplementary information: Supplementary data are available at # online.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.18.389213v1?rss=1

Authors: Srinivas, R., Verma, N., Larson, E. C., Kraka, E.

Abstract:

In their previous work , Srinivas et al have shown that implicit fingerprints capture ligands and proteins in a shared latent space, typically for the purposes of virtual screening with collaborative filtering models applied on known bioactivity data. In this work, we extend these implicit fingerprints/descriptors using deep learning techniques to translate latent descriptors into discrete representations of molecules (SMILES), without explicitly optimizing for chemical properties . This allows the design of new compounds based upon the latent representation of nearby proteins, thereby encoding drug-like properties including binding affinities to known proteins. The implicit descriptor method does not require any fingerprint similarity search, which makes the method free of any bias arising from the empirical nature of the fingerprint models cite{srinivas2018implicit}. We evaluate the properties of the novel drugs generated by our approach using physical properties of drug-like molecules and chemical complexity. Additionally, we analyze the reliability of the biological activity of the new compounds generated using this method by employing models of protein ligand interaction, which assists in assessing the potential binding affinity of the designed compounds. We find that the generated compounds exhibit properties of chemically feasible compounds and are likely to be excellent binders to known proteins. Furthermore, we also analyze the diversity of compounds created using the Tanimoto distance and conclude that there is a wide diversity in the generated compounds.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.19.390401v1?rss=1

Authors: Geread, R. S., Sivanandarajah, A., Brouwer, E., Wood, G., Androutsos, D., Faragalla, H., Khademi, A.

Abstract:

In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and wholeslide images (WSI), representing a diverse multicentre dataset for evaluating Ki67 quantification. Compared to state of the art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to a number of innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images and it was posed as a detection problem to mimic pathologists workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumour cells, which reduces false positives from non-tumour cells without needing the usual pre-requisite tumour segmentation step for Ki67 quantification. Thirdly, the concept of learning background regions through weak supervision is introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain significant activity.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.20.391573v1?rss=1

Authors: Mastrantonio, G., Bibbona, E., Furlan, M.

Abstract:

We propose a hierarchical Bayesian approach to infer the RNA synthesis, processing, and degradation rates from sequencing data. We parametrise kinetic rates with novel functional forms and estimate the parameters through a Dirichlet process defined at a low level of hierarchy. Despite the complexity of this approach, we manage to perform inference, clusterisation and model selection simultaneously. We apply our method to investigate transcriptional and post-transcriptional responses of murine fibroblasts to the activation of proto-oncogene MYC. We uncover a widespread choral regulation of the three rates, which was not previously observed in this biological system.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.18.389189v1?rss=1

Authors: Kang, J. B., Nathan, A., Millard, N., Rumker, L., Moody, D. B., Korsunsky, I., Raychaudhuri, S.

Abstract:

Recent advances in single-cell technologies and integration algorithms make it possible to construct large, comprehensive reference atlases from multiple datasets encompassing many donors, studies, disease states, and sequencing platforms. Much like mapping sequencing reads to a reference genome, it is essential to be able to map new query cells onto complex, multimillion-cell reference atlases to rapidly identify relevant cell states and phenotypes. We present Symphony, a novel algorithm for building compressed, integrated reference atlases of [≥]106 cells and enabling efficient query mapping within seconds. Based on a linear mixture model framework, Symphony precisely localizes query cells within a low-dimensional reference embedding without the need to reintegrate the reference cells, facilitating the downstream transfer of many types of reference-defined annotations to the query cells. We demonstrate the power of Symphony by (1) mapping a query containing multiple levels of experimental design to predict pancreatic cell types in human and mouse, (2) localizing query cells along a smooth developmental trajectory of human fetal liver hematopoiesis, and (3) harnessing a multimodal CITE-seq reference atlas to infer query surface protein expression in memory T cells. Symphony will enable the sharing of comprehensive integrated reference atlases in a convenient, portable format that powers fast, reproducible querying and downstream analyses.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.19.386565v1?rss=1

Authors: Haase, R., Jain, A., Rigaud, S., Vorkel, D., Rajasekhar, P., Suckert, T., Lambert, T. J., Nunez-Iglesias, J., Poole, D. P., Tomancak, P., Myers, E. W.

Abstract:

Modern life science relies heavily on fluorescent microscopy and subsequent quantitative bio-image analysis. The current rise of graphics processing units (GPUs) in the context of image processing enables batch processing large amounts of image data at unprecedented speed. In order to facilitate adoption of this technology in daily practice, we present an expert system based on the GPU-accelerated image processing library CLIJ: The CLIJ-assistant keeps track of which operations formed an image and suggests subsequent operations. It enables new ways of interaction with image data and image processing operations because its underlying GPU-accelerated image data flow graphs (IDFGs) allow changes to parameters of early processing steps and instantaneous visualization of their final results. Operations, their parameters and connections in the IDFG are stored at any point in time enabling the CLIJ-assistant to offer an undo-function for virtually unlimited rewinding parameter changes. Furthermore, to improve reproducibility of image data analysis workflows and interoperability with established image analysis platforms, the CLIJ-assistant can generate code from IDFGs in programming languages such as ImageJ Macro, Java, Jython, JavaScipt, Groovy, Python and C++ for later use in ImageJ, Fiji, Icy, Matlab, QuPath, Jupyter Notebooks and Napari. We demonstrate the CLIJ-assistant for processing image data in multiple scenarios to highlight its general applicability. The CLIJ-assistant is open source and available online: https://clij.github.io/assistant/

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.20.391904v1?rss=1

Authors: Mohanty, S. D., Lekan, D., McCoy, T. P., Jenkins, M., Manda, P.

Abstract:

Healthcare costs that can be attributed to unplanned readmissions are staggeringly high and negatively impact health and wellness of patients. In the United States, hospital systems and care providers have strong financial motivations to reduce readmissions in accordance with several government guidelines. One of the critical steps to reducing readmissions is to recognize the factors that lead to readmission and correspondingly identify at-risk patients based on these factors. The availability of large volumes of electronic health care records make it possible to develop and deploy automated machine learning models that can predict unplanned readmissions and pinpoint the most important factors of readmission risk. While hospital readmission is an undesirable outcome for any patient, it is more so for medically frail patients. Here, we develop and compare four machine learning models (Random Forest, XGBoost, CatBoost, and Logistic Regression) for predicting 30-day unplanned readmission for patients deemed frail (Age [≥] 50). Variables that indicate frailty, comorbidities, high risk medication use, demographic, hospital and insurance were incorporated in the models for prediction of unplanned 30-day readmission. Our findings indicate that CatBoost outperforms the other three models (AUC 0.80) and prior work in this area. We find that constructs of frailty, certain categories of high risk medications, and comorbidity are all strong predictors of readmission for elderly patients.

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.19.390500v1?rss=1

Authors: Hou, Q., Stringer, B., Waury, K., Capel, H., Haydarlou, R., Abeln, S., Heringa, J., Feenstra, K. A.

Abstract:

Motivation: Antibodies play an important role in clinical research and biotechnology, with their specificity determined by the interaction with the antigen's epitope region, as a special type of protein-protein interaction (PPI) interface. The ubiquitous availability of sequence data, allows us to predicting epitopes from sequence in order to focus time-consuming wet-lab experiments onto the most promising epitope regions. Here, we extend our previously developed sequence-based predictors for homodimer and heterodimer PPI interfaces to predict epitope residues that have the potential to bind an antibody. Results: We collected and curated a high quality epitope dataset from the SAbDaB database. Our generic PPI heterodimer predictor obtained an AUC-ROC of 0.666 when evaluated on the epitope test set. We then trained a random forest model specifically on the epitope dataset, reaching AUC 0.694. Further training on the combined heterodimer and epitope datasets, improves our final predictor to AUC 0.703 on the epitope test set. This is better than the best state-of-the-art sequence-based epitope predictor BepiPred-2.0. On one solved antibody-antigen structure of the COVID19 virus spike RNA binding domain, our predictor reaches AUC 0.778. We added the SeRenDIP-CE Conformational Epitope predictors to our webserver, which is simple to use and only requires a single antigen sequence as input, which will help make the method immediately applicable in a wide range of biomedical and biomolecular research. Availability: Webserver, source code and datasets are available at www.ibi.vu.nl/programs/serendipwww/ Contact: [email protected]

Copy rights belong to original authors. Visit the link for more info

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.11.18.388579v1?rss=1

Authors: Valcarcel, L. V., San Jose-Eneriz, E., Cendoya, X., Rubio, A., Agirre, X., Prosper, F., Planes, F. J.

Abstract:

Motivation: With the frenetic growth of high-dimensional datasets in different biomedical domains, there is an urgent need to develop predictive methods able to deal with this complexity. Feature selection is a relevant strategy in machine learning to address this challenge. Results: We introduce a novel feature selection algorithm for linear regression called BOSO (Bilevel Optimization Selector Operator). We conducted a benchmark of BOSO with key algorithms in the literature, finding a superior performance in high-dimensional datasets. Proof-of-concept of BOSO for predicting drug sensitivity in cancer is presented. A detailed analysis is carried out for methotrexate, a well-studied drug targeting cancer metabolism.

Copy rights belong to original authors. Visit the link for more info