PaperPlayer biorxiv bioinformatics

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.24.265116v1?rss=1

Authors: Manduchi, E., Fu, W., Romano, J. D., Ruberto, S., Moore, J. H.

Abstract:

Background: A typical task in bioinformatics consists of identifying which features are associated with a target outcome of interest and building a predictive model. Automated machine learning (AutoML) systems such as the Tree-based Pipeline Optimization Tool (TPOT) constitute an appealing approach to this end. However, in biomedical data, there are often baseline characteristics of the subjects in a study or batch effects that need to be adjusted for in order to better isolate the effects of the features of interest on the target. Thus, the ability to perform covariate adjustments becomes particularly important for applications of AutoML to biomedical big data analysis. Results: We present an approach to adjust for covariates affecting features and/or target in TPOT. Our approach is based on regressing out the covariates in a manner that avoids leakage during the cross-validation training procedure. We then describe applications of this approach to toxicogenomics and schizophrenia gene expression data sets. The TPOT extensions discussed in this work are available at https://github.com/EpistasisLab/tpot/tree/v0.11.1-resAdj. Conclusions: In this work, we address an important need in the context of AutoML, which is particularly crucial for applications to bioinformatics and medical informatics, namely covariate adjustments. To this end we present a substantial extension of TPOT, a genetic programming based AutoML approach. We show the utility of this extension by applications to large toxicogenomics and differential gene expression data. The method is generally applicable in many other scenarios from the biomedical field.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.23.263327v1?rss=1

Authors: Shan, G., Zhi, C., Xiufeng, J., Fang, W., Yibo, X., Hao, Z., Chang, L., Jishou, R., Guangyou, D., Xin, L.

Abstract:

Background: Coronavirus disease 19 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Although the replication and transcription mechanisms of SARS-CoV-2 have been preliminarily revealed recently, their regulation is still unclear. Results: By reanalysis of public data, we proposed a negative feedback model to explain the regulation of replication and transcription of, but not limited to coronavirus (CoVs). The key step leading to new discoveries is that we identified the cleavage sites of nps15, an RNA uridylate-specific endoribonuclease. According to this model, nsp15 regulates the synthesis of subgenomic RNAs (sgRNAs) or genomic RNAs (gRNAs) by cleavage of transcription regulatory sequences in the body. The expression level of nsp15 determines the relative proportions of sgRNAs and gRNAs. The increase of nsp15 results in the decrease of itself to reach equilibrium between the replication and transcription of CoVs. Conclusions: The replication and transcription of CoVs are regulated by a negative feedback strategy. This is a basic mechanism to influence the persistence of CoVs in hosts. Our study indicates that nsp15 is an important and ideal target for drug development against CoVs.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.23.263509v1?rss=1

Authors: Rasche, H., Gruening, B. A.

Abstract:

Background: Hands-on training, whether it is in Bioinformatics or other scientific domains, requires significant resources and knowledge to setup and run. Trainers must have access to infrastructure that can support the sudden spike in usage, with classes of 30 or more trainees simultaneously running resource-intensive tools. For efficient classes, the jobs must run quickly, without queuing delays, lest they disrupt the timetable set out for the class. Often times this is achieved via running on a private server where there is no contention for the queue, and therefore no or minimal waiting time. However, this requires the teacher or trainer to have the technical knowledge to manage compute infrastructure, in addition to their didactic responsibilities. This presents significant burdens to potential training events, in terms of infrastructure cost, person-hours of preparation, technical knowledge, and available staff to manage such events. Findings: Galaxy Europe has developed Training Infrastructure as a Service (TIaaS) which we provide to the scientific commnuity as a service built on top of the Galaxy Platform. Training event organisers request a training and Galaxy administrators can allocate private queues specifically for the training. Trainees are transparently placed in a private queue where their jobs run without delay. Trainers access the dashboard of the TIaaS Service and can remotely follow the progress of their trainees without in-person interactions. Conclusions: TIaaS on Galaxy Europe provides reusable and fast infrastructure for Galaxy training. The instructor dashboard provides visibility into class progress, making in-person trainings more efficient and remote training possible. In the past 24 months, $>110$ trainings with over 3000 trainees have used this infrastructure for training, across scientific domains, all enjoying the accessibility and reproducibility of Galaxy for training the next generation of bioinformaticians. TIaaS itself is an extension to Galaxy which can be deployed by any Galaxy administrator to provide similar benefits for their users. https://galaxyproject.eu/tiaas

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.21.261313v1?rss=1

Authors: Zola, J., Zheng, V., Sariyuce, A. E.

Abstract:

With the emergence of portable DNA sequencers, such as Oxford Nanopore Technology MinION, metagenomic DNA sequencing can be performed in real-time and directly in the field. However, because metagenomic DNA analysis is computationally and memory intensive, and the current methods are designed for batch processing, the current metagenomic tools are not well suited for mobile~devices. In this paper, we propose a new memory-efficient method to identify Operational Taxonomic Units (OTUs) in metagenomic DNA streams. Our method is based on finding connected components in overlap graphs constructed over a real-time stream of long DNA reads as produced by MinION platform. We propose an efficient algorithm to maintain connected components when an overlap graph is streamed, and show how redundant information can be removed from the stream by transitive closures. Through experiments on simulated and real-world metagenomic data, we demonstrate that the resulting solution is able to recover OTUs with high precision while remaining suitable for mobile computing devices.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.21.260992v1?rss=1

Authors: Rytky, S. J. O., Huang, L., Tanska, P., Tiulpin, A., Panfilov, E., Herzog, W., Korhonen, R. K., Saarakkala, S., Finnilä, M. A. J.

Abstract:

Purpose: Only little is known how calcified cartilage (CC) structure changes during exercise, aging and disease. CC thickness (CC.Th) can be analyzed using conventional histological sections. Micro-computed tomography (CT) allows for three-dimensional (3D) imaging of mineralized tissues, however, the segmentation between bone and CC is challenging. Here, we present state-of-the-art deep learning segmentation for CT images to enable assessment of CC morphology. Methods: Sixteen knees from twelve New Zealand White rabbits were dissected into osteochondral samples from six anatomical regions: lateral and medial femoral condyles, lateral and medial tibial plateaus, femoral groove and patella (n = 96). Samples were imaged with CT and processed for conventional histology. Manually segmented CC from the histology and reconstructed CT images was used as the gold standard to train segmentation models with different encoder-decoder architectures. The models with the greatest out-of-fold evaluation Dice score were used for automated CC.Th analysis. Subsequently, the automated CC.Th analysis was compared across a total of 24 regions, co-registered between the imaging modalities, using Pearson correlation and Bland-Altman analyses. Finally, the anatomical variation in CC.Th was assessed via a Linear Mixed Model analysis. Results: The best segmentation models yielded average Dice scores of 0.891 and 0.807 for histology and CT segmentation, respectively. The correlation between the co-registered regions across the modalities was strong (r = 0.897). The Bland-Altman analysis yielded a bias of 21.9 m and a standard deviation of 21.5 m between the methods. Finally, both methods could separate the CC morphology between the patella, femoral, and tibial regions (p < 0.001). Conclusion: The presented method allows for ex vivo 3D assessment of CC.Th in an automated and non-destructive manner. We demonstrated its utility by quantifying CC.Th in different anatomical regions. CC.Th was the thickest in the patella and the thinnest in the tibial plateau.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.20.259598v1?rss=1

Authors: Amodio, M., Shung, D., Burkhardt, D. B., Wong, P., Simonov, M., Yamamoto, Y., van Dijk, D., Wilson, F. P., Iwasaki, A., Krishnaswamy, S.

Abstract:

In many important contexts involving measurements of biological entities, there are distinct categories of information: some information is easy-to-obtain information (EI) and can be gathered on virtually every subject of interest, while other information is hard-to-obtain information (HI) and can only be gathered on some of the biological samples. For example, in the context of drug discovery, measurements like the chemical structure of a drug are EI, while measurements of the transcriptome of a cell population perturbed with the drug is HI. In the clinical context, basic health monitoring is EI because it is already being captured as part of other processes, while cellular measurements like flow cytometry or even ultimate patient outcome are HI. We propose building a model to make probabilistic predictions of HI from EI on the samples that have both kinds of measurements, which will allow us to generalize and predict the HI on a large set of samples from just the EI. To accomplish this, we present a conditional Generative Adversarial Network (cGAN) framework we call the Feature Mapping GAN (FMGAN). By using the EI as conditions to map to the HI, we demonstrate that FMGAN can accurately predict the HI, with heterogeneity in cases of distributions of HI from EI. We show that FMGAN is flexible in that it can learn rich and complex mappings from EI to HI, and can take into account manifold structure in the EI space where available. We demonstrate this in a variety of contexts including generating RNA sequencing results on cell lines subjected to drug perturbations using drug chemical structure, and generating clinical outcomes from patient lab measurements. Most notably, we are able to generate synthetic flow cytometry data from clinical variables on a cohort of COVID-19 patients---effectively describing their immune response in great detail, and showcasing the power of generating expensive FACS data from ubiquitously available patient monitoring data.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.20.259226v1?rss=1

Authors: Bharadhwaj, V. S., Ali, M., Birkenbihl, C., Mubeen, S., Lehmann, J., Hofmann-Apitius, M., Hoyt, C. T., Domingo-Fernandez, D.

Abstract:

As machine learning and artificial intelligence become more useful in the interpretation of biomedical data, their utility depends on the data used to train them. Due to the complexity and high dimensionality of biomedical data, there is a need for approaches that combine prior knowledge around known biological interactions with patient data. Here, we present CLEP, a novel approach that generates new patient representations by leveraging both prior knowledge and patient-level data. First, given a patient-level dataset and a knowledge graph containing relations across features that can be mapped to the dataset, CLEP incorporates patients into the knowledge graph as new nodes connected to their most characteristic features. Next, CLEP employs knowledge graph embedding models to generate new patient representations that can ultimately be used for a variety of downstream tasks, ranging from clustering to classification. We demonstrate how using new patient representations generated by CLEP significantly improves performance in classifying between cognitively impaired patients and healthy controls for a variety of machine learning models, as compared to the use of the original transcriptomics data. Furthermore, we also show how incorporating patients into a knowledge graph can foster the interpretation and identification of biological features characteristic of a specific disease or patient subgroup. Finally, we released CLEP as an open source Python package together with examples and documentation.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.21.261404v1?rss=1

Authors: Cavasotto, C. N., Sanchez Lamas, M., Maggini, J.

Abstract:

The infectious coronavirus disease (COVID-19) pandemic, caused by the coronavirus SARS-CoV-2, appeared in December 2019 in Wuhan, China, and has spread worldwide. As of today, more than 22 million people have been infected, with almost 800,000 fatalities. With the purpose of contributing to the development of effective therapeutics, this work provides an overview of the viral machinery and functional role of each SARS-CoV-2 protein, and a thorough analysis of the structure and druggability assessment of the viral proteome. All structural, non-structural, and accessory proteins of SARS-CoV-2 have been studied, and whenever experimental structural data of SARS-CoV-2 proteins were not available, homology models were built based on solved SARS-CoV structures. Several potential allosteric or protein-protein interaction druggable sites on different viral targets were identified, knowledge that could be used to expand current drug discovery endeavors beyond the cysteine proteases and the polymerase complex. It is our hope that this study will support the efforts of the scientific community both in understanding the molecular determinants of this disease and in widening the repertoire of viral targets in the quest for repurposed or novel drugs against COVID-19.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.20.259721v1?rss=1

Authors: Saha, O., Shatadru, R. N., Rakhi, N. N., Islam, I., Hossain, M. S., Rahaman, M. M.

Abstract:

Along with intrinsic evolution, adaptation to selective pressure in new environments might have resulted in the circulatory SARS-CoV-2 strains in response to the geoenvironmental conditions of a country and the demographic profile of its population. Thus the analysis of genomic mutations of these circulatory strains may give an insight into the molecular basis of SARS-CoV-2 pathogenesis and evolution favoring the development of effective treatment and containment strategies. With this target, the current study traced the evolutionary route and mutational frequency of 198 Bangladesh originated SARS-CoV-2 genomic sequences available in the GISAID platform over a period of 13 weeks as of 14 July 2020. The analyses were performed using MEGA 7, Swiss Model Repository, Virus Pathogen Resource and Jalview visualization. Our analysis identified that majority of the circulating strains in the country belong to B and/or L type among cluster A to Z and strikingly differ from both the reference genome and the first sequenced genome from Bangladesh. Mutations in Nonspecific protein 2 (NSP2), NSP3, RNA dependent RNA polymerase (RdRp), Helicase, Spike, ORF3a, and Nucleocapsid (N) protein were common in the circulating strains with varying degrees and the most unique mutations(UM) were found in NSP3 (UM-18). But no or limited changes were observed in NSP9, NSP11, E (Envelope), NSP7a, ORF 6, and ORF 7b suggesting the possible conserved functions of those proteins in SARS-CoV-2 propagation. However, along with D614G mutation, more than 20 different mutations in the Spike protein were detected basically in the S2 domain. Besides, mutations in SR-rich region of N protein and P323L in RDRP were also present. However, the mutation accumulation showed an association with sex and age of the COVID-19 positive cases. So, identification of these mutational accumulation patterns may greatly facilitate drug/ vaccine development deciphering the age and the sex dependent differential susceptibility to COVID-19.

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

Link to bioRxiv paper:

http://biorxiv.org/cgi/content/short/2020.08.21.261347v1?rss=1

Authors: Cacciabue, M., Aguilera, P., Gismondi, M. I., Taboga, O.

Abstract:

Covidex is an open-source, alignment-free machine learning subtyping tool for viral species. It is a shiny app that allows a fast and accurate classification in pre-defined clusters for SARS-CoV-2 and FMDV genome sequences. The user can also build its own classification models with the Covidex model generator.

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