Posters
Poster presentations at ISMB 2020 will be presented virtually. Authors will pre-record their poster talk (5-7 minutes) and will upload it to the virtual conference platform site along with a PDF of their poster.
All registered conference participants will have access to the poster and presentation through the conference and content until October 31, 2020. There are Q&A opportunities through a chat function to allow interaction between presenters and participants.
Preliminary information on preparing your poster and poster talk are available at:
https://www.iscb.org/ismb2020-general/presenterinfo#posters
Ideally authors should be available for interactive chat during the times noted below:
View Posters By Category
Poster Session A: July 13 & July 14 7:45 am - 9:15 am Eastern Daylight Time |
Session B: July 15 and July 16 between 7:45 am - 9:15 am Eastern Daylight Time |
|---|---|
| July 14 between 10:40 am - 2:00 pm EDT |
Short Abstract: Several recent metagenome studies deal with the microbial composition of public spaces in urban areas. In particular public transport systems are addressed and samples are taken from different surfaces, such as handholds, seats, or the passenger‘s palms (MetaSub International Consortium, 2016). Approaches are to investigate the differences in the functional composition, antibiotic resistances, or differenciate on the basis of abundances of species. (Danko et al., 2019 / Harris et al., 2019 ). This can be achieved by using machnie learning techniques, such as Random Forests, which we primarily use for our investigation.The goal was to find an optimal set of species that can be used for the assignment of the dataset and explore ecological implications and therefore we focus on a small group of species, in this case the top-abundant ones.
Short Abstract: Infection with human cytomegalovirus (HCMV) can cause severe complications in immunocompromised individuals and congenitally infected children. Characterizing heterogeneous viral populations and their evolution by high-throughput sequencing of clinical specimens requires the accurate assembly of individual strains or sequence variants and suitable variant calling methods. However, the performance of most methods has not been assessed for populations composed of low divergent viral strains with large genomes, such as HCMV. In an extensive benchmarking study, we evaluated 15 assemblers and 6 variant callers on ten lab-generated benchmark data sets created with two different library preparation protocols, to identify best practices and challenges for analyzing such data.
Most assemblers, especially metaSPAdes and IVA, performed well across a range of metrics in recovering abundant strains. However, only one, Savage, recovered low abundant strains and in a highly fragmented manner. Two variant callers, LoFreq and VarScan2, excelled across all strain abundances. Both shared a large fraction of false positive (FP) variant calls, which were strongly enriched in T to G changes in a “G.G” context. The magnitude of this context-dependent systematic error is linked to the experimental protocol.
Short Abstract: Drug-induced liver injury (DILI) is considered a primary factor in regulatory clearance for drug development, and there is a pressing need to develop and evaluate new prediction models for DILI. The CAMDA 2020 CMap Drug Safety Challenge included 422 drugs for training and 195 drugs with blinded labels for testing to predict four types of DILI classes (DILI1, DILI3, DILI5, and DILI6). Our approach utilized the machine learning (ML) approach focusing on drug perturbation gene expression signatures from the six human cell lines (PHH, HEPG2, HA1E, A375, MCF7, and PC3). We created representative expression signatures, the 250 most up-regulated and 250 down-regulated genes, for each drug using Kruskal-Borda merging of ranked z-scores profiles. Various ML algorithms, including random forest (RF), recursive partitioning and regression trees (RPART), support vector machine (SVM), generalized linear model (GLM), and naïve-Bayes classifier were built and evaluated using 100 times 5-fold cross-validation. The initial model results range from a ROC value of 0.818 in the RF DILI3 to 0.491 in GLM DILI6. These models are still a work in progress, in which data from Tox21, FAERS, and Mold2 will need to be incorporated alongside the gene expression response garnered from CMap.
Short Abstract: Many high-quality biological pathways are being presented in figures and text in the biomedical literature, which is a great resource for biological mechanism studies and precision medicine practices. They need to be carefully curated, reconciled, and transformed into a computable form. Current manual curation approaches are inadequate in keeping up with the pace of the literature growth. New bio-curation approaches are needed to streamline the identification of gene-interactions from pathway figures and text. In this work, we proposed a pathway curation approach for identifying genes and their interactions from figures of scientific literature. We customized visual object detection tool RetinaNet to detect rotated bounding boxes that described gene-interaction relations, from where we can further recognize gene names and gene-interaction categories by additional optical character recognition implementation and image processing. Our pipeline was evaluated on the figures from PubMed publications regarding a specific case i.e. non-small cell lung cancer (NSCLC). The results demonstrated that our model can effectively retrieve genes and their interactions from pathway figures. The proposed pipeline may accelerate various applications of the latest biomedical discoveries.
Short Abstract: We have used mechanistic models of pathway activities to generate complete catalogue of Cmap functional profiles that can be further used to detect reverse functional profiles in diseases, thus providing a functional basis and a potential biological interpretation for the drug-disease inverse matching.
Short Abstract: We present a novel approach to the Metagenomic Geolocation Challenge based on random projection of the sample reads for each location. Individual signatures are computed for all reads, and each location is characterised by an hierarchical vector space representation of the resulting clusters. Classification is then treated as a problem in ranked retrieval of locations, where similar signatures are taken as a proxy for underlying microbial similarity. We evaluate our approach based on the 2016 and 2020 Challenge datasets and obtain promising results based on nearest neighbour classification.
Short Abstract: Motivation: Drug-induced liver injury (DILI) is one of the primary problems in drug development. Early prediction of DILI, would bring a significant reduction in the cost of clinical trials and faster development of drugs. Current study is aims at building predictive models of DILI potential of chemical compounds.
Methods: We build predictive models for several alternative splits of compounds between DILI and non-DILI classes, using supervised Machine Learning algorithms.
To this end we use chemical properties of the compounds under scrutiny, their effects on gene expression levels in 6 human cell-lines treated with them and their toxicological profiles. We first identity the most informative variables and then use them to build ML models.
Individual models built using gene expression of single cell lines, chemical properties of compounds, their toxicology profiles are then combined using Super Learner approach.
Results: We have obtained weakly predictive model for using molecular descriptors and DILI statistics, with AUC exceeding 0.7 for some DILI definitions.
With one exception, gene expression profiles of human cell lines resulted were non-informative and resulted in random models. Gene expression profiles of HEPG2 cell line lead to statistically significant models (AUC=0.67) only for one definition of DILI.
Short Abstract: Considering the challenges in distinguishing morphological characteristics of cellular components between biological samples from confocal micrographs, we provide a quantitative approach to overcome such bias and inaccuracy. In confocal micrographs of tissue samples, pixel features estimated mathematically and the relationship between pixel intensity brings significant changes in morphological parameters. Here, we use the application of Max Contrast Projection followed by adaptive thresholding to segment cells from the stack of confocal fluorescent microscope images of cell walls and ER bodies, which are cellular components in Arabidopsis thaliana. Furthermore, we present a robust approach to estimate morphological (spatial, intensity and Haralick) features to distinguish between ER bodies at segmented cell resolution. Our method successfully distinguishes between A. thaliana wild type and aberrant ER body mutants based on the profiles of features and determines the correlation between cell types and features. Similar methodologies are applied in the field of medical sciences for cancer cell diagnosis. Here in plant sciences, we are first to report a comprehensive analysis with morphological features to distinguish plant phenotypes having similar cellular components. Through this study, we enabled multivariate analysis on morphological parameters with the robust estimation of cell organelles as complex as ER bodies in microscopic images.
