PaperPlayer biorxiv bioinformatics

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.06.327585v1?rss=1

Authors: Ju, F., Zhu, J., Shao, B., Kong, L., Liu, T.-Y., Zheng, W.-M., Bu, D.

Abstract:

Protein functions are largely determined by the final details of their tertiary structures, and the structures could be accurately reconstructed based on inter-residue distances. Residue co-evolution has become the primary principle for estimating inter-residue distances since the residues in close spatial proximity tend to co-evolve. The widely-used approaches infer residue co-evolution using an indirect strategy, i.e., they first extract from the multiple sequence alignment (MSA) of query protein some handcrafted features, say, co-variance matrix, and then infer residue co-evolution using these features rather than the raw information carried by MSA. This indirect strategy always leads to considerable information loss and inaccurate estimation of inter-residue distances. Here, we report a deep neural network framework (called CopulaNet) to learn residue co-evolution directly from MSA without any handcrafted features. The CopulaNet consists of two key elements: i) an encoder to model context-specific mutation for each residue, and ii) an aggregator to model correlations among residues and thereafter infer residue co-evolutions. Using the CASP13 (the 13th Critical Assessment of Protein Structure Prediction) target proteins as representatives, we demonstrated the successful application of CopulaNet for estimating inter-residue distances and further predicting protein tertiary structure with improved accuracy and efficiency. Head-to-head comparison suggested that for 24 out of the 31 free modeling CASP13 domains, ProFOLD outperformed AlphaFold, one of the state-of-the-art prediction approaches.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.314039v1?rss=1

Authors: Cobanoglu, M. C.

Abstract:

One of the key challenges in single-cell data analysis is the annotation of cells with their cell types. This task is divided into two different sub-tasks: identifying known cell types and identifying novel cell types. We propose that both of these problems can be solved by generative Bayesian Dirichlet-multinomial models. In the supervised learning context, we propose a generative Bayesian Dirichlet-multinomial classifier. In the unsupervised learning context, we propose a Bayesian Dirichlet-multinomial mixture model. We show that the proposed models learn meaningful models where the predicted cell types and the genes associated with them overlap with ground truth. Furthermore, there are no density or connectivity based clustering assumptions in this model, which differs with almost every approach in this field. Consequently the clustering results from the generative method can effectively represent nuanced differences among cells.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.324566v1?rss=1

Authors: Zhou, C. E., Kimbrel, J., Edwards, R. A., McNair, K., Souza, B. A., Malfatti, S.

Abstract:

To address the need for improved tools for annotation and comparative genomics of bacteriophage genomes, we developed multiPhATE2. As an extension of the multiPhATE code, multiPhATE2 performs gene finding and functional sequence annotation of predicted gene and protein sequences, and additional search algorithms and databases extend the search space of the original functional annotation subsystem. MultiPhATE2 includes comparative genomics codes for gene matching among sets of input bacteriophage genomes, and scales well to large input data sets with the incorporation of multiprocessing in the functional annotation and comparative genomics subsystems. MultiPhATE2 was implemented in Python 3.7 and runs as a command-line code under Linux or MAC-OS. MultiPhATE2 is freely available under an open- source GPL-3 license at https://github.com/carolzhou/multiPhATE2. Instructions for acquiring the databases and third party codes used by multiPhATE2 are found in the README file included with the distribution. Users may report bugs by submitting issues to the project GitHub repository webpage. Contact: [email protected] or [email protected]. Supplementary materials, which demonstrate the outputs of multiPhATE2, are available in a GitHub repository, at https://github.com/carolzhou/multiPhATE2_supplementaryData/.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.06.327601v1?rss=1

Authors: Goyal, M., Serrano, G., Shomorony, I., Hernaez, M., Ochoa, I.

Abstract:

Single-cell RNA-seq is a powerful tool in the study of the cellular composition of different tissues and organisms. A key step in the analysis pipeline is the annotation of cell-types based on the expression of specific marker genes. Since manual annotation is labor-intensive and does not scale to large datasets, several methods for automated cell-type annotation have been proposed based on supervised learning. However, these methods generally require feature extraction and batch alignment prior to classification, and their performance may become unreliable in the presence of cell-types with very similar transcriptomic profiles, such as differentiating cells. We propose JIND, a framework for automated cell-type identification based on neural networks that directly learns a low-dimensional representation (latent code) in which cell-types can be reliably determined. To account for batch effects, JIND performs a novel asymmetric alignment in which the transcriptomic profile of unseen cells is mapped onto the previously learned latent space, hence avoiding the need of retraining the model whenever a new dataset becomes available. JIND also learns cell-type-specific confidence thresholds to identify and reject cells that cannot be reliably classified. We show on datasets with and without batch effects that JIND classifies cells more accurately than previously proposed methods while rejecting only a small proportion of cells. Moreover, JIND batch alignment is parallelizable, being more than five or six times faster than Seurat integration. Availability: https://github.com/mohit1997/JIND .

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.326140v1?rss=1

Authors: Li, Y., Zhang, C., Bell, E. W., Zheng, W., Zhou, X., Yu, D.-J., Zhang, Y.

Abstract:

The topology of protein folds can be specified by the inter-residue contact-maps and accurate contact-map prediction can help ab initio structure folding. We developed TripletRes to deduce protein contact-maps from discretized distance profiles by end-to-end training of deep residual neural-networks. Compared to previous approaches, the major advantage of TripletRes is in its ability to learn and directly fuse a triplet of coevolutionary matrices extracted from the whole-genome and metagenome databases and therefore minimize the information loss during the course of contact model training. TripletRes was tested on a large set of 245 non-homologous proteins from CASP and CAMEO experiments, and outperformed other state-of-the-art methods by at least 58.4% for the CASP 11&12 and 44.4% for the CAMEO targets in the top-L long-range contact precision. On the 31 FM targets from the latest CASP13 challenge, TripletRes achieved the highest precision (71.6%) for the top-L/5 long-range contact predictions. These results demonstrate a novel efficient approach to extend the power of deep convolutional networks for high-accuracy medium- and long-range protein contact-map predictions starting from primary sequences, which are critical for constructing 3D structure of proteins that lack homologous templates in the PDB library. Availability: The training and testing data, standalone package, and the online server for TripletRes are available at https://zhanglab.ccmb.med.umich.edu/TripletRes/.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.324798v1?rss=1

Authors: VanHorn, K. C., Cobanoglu, M. C. C.

Abstract:

Dimensionality reduction (DR) is often integral when analyzing high-dimensional data across scientific, economic, and social networking applications. For data with a high order of complexity, nonlinear approaches are often needed to identify and represent the most important components. We propose a novel DR approach that can incorporate a known underlying hierarchy. Specifically, we extend the widely used t-Distributed Stochastic Neighbor Embedding technique (t-SNE) to include hierarchical information and demonstrate its use with known or unknown class labels. We term this approach "H-tSNE." Such a strategy can aid in discovering and understanding underlying patterns of a dataset that is heavily influenced by parent-child relationships. Without integrating information that is known a priori, we suggest that DR cannot function as effectively. In this regard, we argue for a DR approach that enables the user to incorporate known, relevant relationships even if their representation is weakly expressed in the dataset.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.326777v1?rss=1

Authors: Petukhov, V., Khodosevich, K., Soldatov, R. A., Kharchenko, P. V.

Abstract:

Spatial transcriptomics is an emerging stack of technologies, which adds spatial dimension to conventional single-cell RNA-sequencing. New protocols, based on in situ sequencing or multiplexed RNA fluorescent in situ hybridization register positions of single molecules in fixed tissue slices. Analysis of such data at the level of individual cells, however, requires accurate identification of cell boundaries. While many existing methods are able to approximate cell center positions using nuclei stains, current protocols do not report robust signal on the cell membranes, making accurate cell segmentation a key barrier for downstream analysis and interpretation of the data. To address this challenge, we developed a tool for Bayesian Segmentation of Spatial Transcriptomics Data (Baysor), which optimizes segmentation considering the likelihood of transcriptional composition, size and shape of the cell. The Bayesian approach can take into account nuclear or cytoplasm staining, however can also perform segmentation based on the detected transcripts alone. We show that Baysor segmentation can in some cases nearly double the number of the identified cells, while reducing contamination. Importantly, we demonstrate that Baysor performs well on data acquired using five different spatially-resolved protocols, making it a useful general tool for analysis of high-resolution spatial data.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.04.325662v1?rss=1

Authors: Biswas, S., Saha, S., Bandyopadhyay, S., Bhattacharyya, M.

Abstract:

With an increasing number of SARS-CoV-2 sequences available day by day, new genomic information is getting revealed to us. As SARS-CoV-2 sequences highlight wide changes across the samples, we aim to explore whether these changes reveal the geographical origin of the corresponding samples. The k-mer distributions, denoting normalized frequency counts of all possible combinations of nucleotide of size upto k, are often helpful to explore sequence level patterns. Given the SARS-CoV-2 sequences are highly imbalanced by its geographical origin (relatively with a higher number samples collected from the USA), we observe that with proper under-sampling k-mer distributions in the SARS-CoV-2 sequences predict its geographical origin with more than 90% accuracy. The experiments are performed on the samples collected from six countries with maximum number of sequences available till July 07, 2020. This comprises SARS-CoV-2 sequences from Australia, USA, China, India, Greece and France. Moreover, we demonstrate that the changes of genomic sequences characterize the continents as a whole. We also highlight that the network motifs present in the sequence similarity networks have a significant difference across the said countries. This, as a whole, is capable of predicting the geographical shift of SARS-CoV-2.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.04.325555v1?rss=1

Authors: Ferruz, N., Noske, J., Hoecker, B.

Abstract:

Motivation: Gene duplication and recombination of protein fragments have led to the highly diverse protein space that we observe today. By mimicking this natural process, the design of protein chimeras via fragment recombination has proven experimentally successful and has opened a new era for the design of customizable proteins. The in-silico building of structural models for these chimeric proteins, however, remains a manual task that requires a considerable degree of expertise and is not amenable for high-throughput studies. Energetic and structural analysis of the designed proteins often require the use of several tools, each with their unique technical difficulties and available in different programming languages or web servers. Results: We have implemented a Python package that enables automated, high-throughput design of chimeras and their structural analysis. First, it is possible to fetch evolutionarily conserved fragments from a built-in database (also available at fuzzle.uni-bayreuth.de). These relationships can then be represented via networks or further selected for chimera construction via recombination. Designed chimeras or natural proteins are then scored and minimised with the Charmm and Amber forcefields and their diverse structural features can be analysed at ease. Here, we showcase Protlego's pipeline by exploring the relationships between the P-loop and Rossmann superfolds and building and characterising their offspring chimeras. We believe that Protlego provides a powerful new tool for the protein design community. Availability and implementation: Protlego is freely available at (https://hoecker- lab.github.io/protlego/) with tutorials and documentation.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.10.05.327015v1?rss=1

Authors: Wert-Carvajal, C., Sanchez-Garcia, R., Macias, J. R., Sanz-Pamplona, R., Mendez Perez, A., Alemany, R., Veiga Chacon, E., Sorzano, C. O. S., Munoz-Barrutia, A.

Abstract:

Motivation: Lack of a dedicated integrated pipeline for neoantigen discovery in mice hinders cancer immunotherapy research. Novel sequential approaches through recurrent neural networks can improve the accuracy of T-cell epitope immunogenity predictions in mice. Results: We have developed a web server tool (NAP-CNB), based on recurrent neural networks, able to predict putative neoantigens of a tumor. The developed software is able to estimate H-2 peptide ligands with an AUC of 0.95. As a proof-of-concept, we used the B16 melanoma model to test the predictive capabilities of the system and we report its putative neoantigens.

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