Posters - Schedules
Poster presentations at ISMB/ECCB 2021 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 beginning July 19
and no later than July 23. All registered conference participants will have access to the poster and presentation
through the conference and content until October 31, 2021. There are Q&A opportunities through a chat
function and poster presenters can schedule small group discussions with up to 15 delegates during the conference.
Information on preparing your poster and poster talk are available at:
https://www.iscb.org/ismbeccb2021-general/presenterinfo#posters
Ideally authors should be available for interactive chat during the times noted below:
View Posters By Category
Session A: Sunday, July 25 between 15:20 - 16:20 UTC |
Session B: Monday, July 26 between 15:20 - 16:20 UTC |
|---|---|
Session C: Tuesday, July 27 between 15:20 - 16:20 UTC |
Session D: Wednesday, July 28 between 15:20 - 16:20 UTC |
|---|---|
Session E: Thursday, July 29 between 15:20 - 16:20 UTC |
|---|
Short Abstract: In this work, we study the representation of transcriptional, protein-protein and genetic interaction networks in E. coli and mouse through integrating the gene expression values with network structures leveraging the Graph Auto Encoders. Our results indicate that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further propose a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and show that it performs better at predicting unobserved gene expression values than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the graph feature auto-encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach.
Short Abstract: In this work, we study the representation of transcriptional, protein-protein and genetic interaction networks in E. coli and mouse through integrating the gene expression values with network structures leveraging the Graph Auto Encoders. Our results indicate that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further propose a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and show that it performs better at predicting unobserved gene expression values than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the graph feature auto-encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach.
Short Abstract: While next-gen high-throughput assays enable us to learn how capsid sequence changes affect capsid functionality, measuring and optimizing capsid properties in the most therapeutically relevant models, such as non-human primates (NHP), remains challenging. The rate of transduction in target organs is lower than ideal, and most of the sequence space is non-functional. To overcome these challenges, we investigated to what extent multi-task machine learning can improve the efficiency of AAV capsid design for high-performing capsids. We apply our method to a previously designed library containing 156,858 designed sequence variants derived from a natural AAV capsid serotype and measured their properties as delivery vectors. MPMs provide a coherent framework in which to connect information from experiments across cell lines, organs, and species to the most relevant outcomes in NHP studies, thereby reducing the high resource and ethical burdens of NHP experimentation. Additionally, MPMs help overcome data sparsity in traits that are hard to measure, thereby improving model accuracy and providing a more reliable interpretation of experimental results. With further refinement, MPMs will enable the design of highly optimized AAV capsids that open new frontiers in delivery, toward realizing the full potential of gene therapy.
Short Abstract: Accurate prediction of variant effects has broad impacts on protein engineering. Recent machine learning approaches toward this end are based on representation learning, often using large-scale, diverse datasets. However, it is still unclear how we can effectively learn the intrinsic evolutionary properties of an engineering target protein, specifically when the protein is composed of multiple domains. Additionally, no optimal protocols are established for incorporating such properties into Transformer-based variant effect predictors. In response, we propose evolutionary fine-tuning, or “evotuning”, protocols, considering various combinations of homology search, fine-tuning, and sequence embedding strategies, without the need for multiple sequence alignment. Exhaustive evaluations on diverse proteins indicate that the models obtained by our protocols achieve significantly better performances than previous methods. The visualizations of attention maps suggest that the structural information can be incorporated by evotuning without direct supervision, possibly leading to better prediction accuracy.
Short Abstract: Accurate prediction of variant effects has broad impacts on protein engineering. Recent machine learning approaches toward this end are based on representation learning, often using large-scale, diverse datasets. However, it is still unclear how we can effectively learn the intrinsic evolutionary properties of an engineering target protein, specifically when the protein is composed of multiple domains. Additionally, no optimal protocols are established for incorporating such properties into Transformer-based variant effect predictors. In response, we propose evolutionary fine-tuning, or “evotuning”, protocols, considering various combinations of homology search, fine-tuning, and sequence embedding strategies, without the need for multiple sequence alignment. Exhaustive evaluations on diverse proteins indicate that the models obtained by our protocols achieve significantly better performances than previous methods. The visualizations of attention maps suggest that the structural information can be incorporated by evotuning without direct supervision, possibly leading to better prediction accuracy.
Short Abstract: We present a state of the art multimodal deep learning model for cancer drug response prediction based on pharmacogenomic data. We featurize cell lines as protein-protein interaction graphs. Graph attention networks then allow us to examine potentially plausible biological interactions in protein-protein interactions graphs by examining the attention coefficients.
Short Abstract: The development of resistance to conventional antibiotics in pathogenic bacteria poses global health hazard. Antimicrobial peptides (AMPs) are an emerging group of compounds with the potential to become the new generation of antibiotics. Deep learning methods are widely used by wet-laboratory researchers to screen for the most promising candidates. We propose HydrAMP - a generative model based on a semi-supervised variational autoencoder, that can generate new AMPs, and perform analogue discovery. Novel features of our approach include: non-iterative training, parameter-regulated model creativity, and improvement of existing AMPs. We introduced multiple refinements to latent space modelling that allow us to sample novel AMPs despite the data scarcity. The peptides generated by HydrAMP are similar to the known AMPs in terms of physicochemical properties. We have successfully obtained and verified experimentally a new, more active analogue of Pexiganan, proving that HydrAMP is able to find potent analogues for existing peptides. The learnt representation enables fast and efficient discovery of peptides with desired biological activity.
Short Abstract: Although knowing where a protein functions in a cell is important to characterize biological processes, this information remains unavailable for most known proteins. Machine learning narrows the gap through predictions from expertly chosen input features leveraging evolutionary information that is resource expensive to generate. We showcase using embeddings from protein language models for competitive localization predictions not relying on evolutionary information. Our lightweight deep neural network architecture uses a softmax weighted aggregation mechanism with linear complexity in sequence length referred to as light attention (LA). The method significantly outperformed the state-of-the-art for ten localization classes by about eight percentage points (Q10). The novel models are available as a web-service and as a stand-alone application at embed.protein.properties.
Short Abstract: Cellular systems of organisms are composed of multiple interacting entities that control cellular processes at multiple levels by tightly regulated molecular networks. In recent years, the advent of high-throughput experimental methods has resulted in the increase of large-scale molecular and functional interaction networks such as gene co-expression, protein–protein interaction (PPI) , genetic interaction, and metabolic networks. These networks are rich source[s] of information that could be used to infer the functional annotations of genes or proteins. Extracting relevant biological information from their topologies essential in understanding the functioning of the cell and its building blocks (proteins). Therefore, it is necessary to obtain an informative representation of the proteins and their proximity that is not fully captured by features that are extracted directly from single input networks. Here, we propose BraneMF, a random walk-based matrix factorization of a multi-layer network for protein function prediction.
Short Abstract: Cellular systems of organisms are composed of multiple interacting entities that control cellular processes at multiple levels by tightly regulated molecular networks. In recent years, the advent of high-throughput experimental methods has resulted in the increase of large-scale molecular and functional interaction networks such as gene co-expression, protein–protein interaction (PPI) , genetic interaction, and metabolic networks. These networks are rich source[s] of information that could be used to infer the functional annotations of genes or proteins. Extracting relevant biological information from their topologies essential in understanding the functioning of the cell and its building blocks (proteins). Therefore, it is necessary to obtain an informative representation of the proteins and their proximity that is not fully captured by features that are extracted directly from single input networks. Here, we propose BraneMF, a random walk-based matrix factorization of a multi-layer network for protein function prediction.
Short Abstract: Predicting the physical interaction of proteins is a cornerstone problem in computational biology. New classes of learning-based algorithms are actively being developed, and are typically trained end-to-end on protein structures extracted from the Protein Data Bank. These training datasets tend to be large and difficult to use for prototyping and, unlike image or natural language datasets, they are not easily interpretable by non-experts. In this paper we propose Dock2D-IP and Dock2D-FI, two toy datasets that can be used to select algorithms predicting protein-protein interactions---or any other type of molecular interactions. Using two-dimensional shapes as input, each example from Dock2D-FI describes the fact of interaction between two shapes and each example from Dock2D-IP describes the interaction pose of two shapes known to interact. With the hope that it will stimulate further research, we also propose a number of baselines that represent different approaches to the problem.
Short Abstract: Building a prediction model for translation initiation sites (TISs) and determining their important features may aid in uncovering new translation mechanisms and give emphasis to already existing ones. However, interpretation is difficult, as many machine learning models are black box in nature. Therefore, to better understand the features relevant to the predictions made, we investigate the use of synthetic data in the context of TIS prediction for A. thaliana and, through transfer learning, for H. sapiens. From our experiments, we found that the model trained with synthetic data (SBBM) and the model trained with real data (RBBM) learn from similar features. Furthermore, the model trained with both real and synthetic data (CBBM), obtained a similar effectiveness as RBBM. We also found that CBBM could be used to reduce overfitting when training with small datasets. In addition, we observed that consensus sequence and nucleotide frequency are the most positively influencing features, while codon usage was found to be a negatively influencing feature. Finally, the models seemed to learn leaky scanning, as shown by the less influential nature of upstream ATG. Through this case study on TIS prediction, we were able to gain insight into (1) the potential of leveraging synthetic data for the interpretation of black-box prediction models and (2) the prediction potential of models trained using a combination of synthetic and real data.
Short Abstract: Building a prediction model for translation initiation sites (TISs) and determining their important features may aid in uncovering new translation mechanisms and give emphasis to already existing ones. However, interpretation is difficult, as many machine learning models are black box in nature. Therefore, to better understand the features relevant to the predictions made, we investigate the use of synthetic data in the context of TIS prediction for A. thaliana and, through transfer learning, for H. sapiens. From our experiments, we found that the model trained with synthetic data (SBBM) and the model trained with real data (RBBM) learn from similar features. Furthermore, the model trained with both real and synthetic data (CBBM), obtained a similar effectiveness as RBBM. We also found that CBBM could be used to reduce overfitting when training with small datasets. In addition, we observed that consensus sequence and nucleotide frequency are the most positively influencing features, while codon usage was found to be a negatively influencing feature. Finally, the models seemed to learn leaky scanning, as shown by the less influential nature of upstream ATG. Through this case study on TIS prediction, we were able to gain insight into (1) the potential of leveraging synthetic data for the interpretation of black-box prediction models and (2) the prediction potential of models trained using a combination of synthetic and real data.
