ClusterEnG: an interactive educational web resource for clustering and visualizing high-dimensional data

Accelerating Energy-Economic Simulation Models via Machine Learning-Based Emulation and Time Series Aggregation

Energy-economic simulation models with high levels of detail, high time resolutions, or large populations (e.g., distribution networks, households, electric vehicles, energy communities) are often limited due to their computational complexity. This paper introduces a novel methodology, combining cluster-based time series aggregation and sampling methods, to efficiently emulate simulation models using machine learning and significantly reduce both simulation and training time. Machine learning-based emulation models require sufficient and high-quality data to generalize the dataset. Since simulations are computationally complex, their maximum number is limited. Sampling methods come into play when selecting the best parameters for a limited number of simulations ex ante. This paper introduces and compares multiple sampling methods on three energy-economic datasets and shows their advantage over a simple random sampling for small sample-sizes. The results show that a k-means cluster sampling approach (based on unsupervised learning) and adaptive sampling (based on supervised learning) achieve the best results especially for small sample sizes. While a k-means cluster sampling is simple to implement, it is challenging to increase the sample sizes if the emulation model does not achieve sufficient accuracy. The iterative adaptive sampling is more complex during implementation, but can be re-applied until a certain accuracy threshold is met. Emulation is then applied on a case study, emulating an energy-economic simulation framework for peer-to-peer pricing models in Germany. The evaluated pricing models are the “supply and demand ratio” (SDR) and “mid-market rate pricing” (MMR). A time series aggregation can reduce time series data of municipalities by 99.4% with less than 5% error for 98.2% (load) and 95.5% (generation) of all municipalities and hence decrease the simulation time needed to create sufficient training data. This paper combines time series aggregation and emulation in a novel approach and shows significant acceleration by up to 88.9% of the model’s initial runtime for the simulation of the entire population of around 12,000 municipalities. The time for re-calculating the population (e.g., for different scenarios or sensitivity analysis) can be increased by a factor of 1100 while still retaining high accuracy. The analysis of the simulation time shows that time series aggregation and emulation, considered individually, only bring minor improvements in the runtime but can, however, be combined effectively. This can significantly speed up both the simulation itself and the training of the emulation model and allows for flexible use, depending on the capabilities of the models and the practitioners. The results of the peer-to-peer pricing for approximately 12,000 German municipalities show great potential for energy communities. The mechanisms offer good incentives for the addition of necessary flexibility.

FGFR-inhibitor-mediated dismissal of SWI/SNF complexes from YAP-dependent enhancers induces adaptive therapeutic resistance

How cancer cells adapt to evade the therapeutic effects of drugs targeting oncogenic drivers is poorly understood. Here we report an epigenetic mechanism leading to the adaptive resistance of triple-negative breast cancer (TNBC) to fibroblast growth factor receptor (FGFR) inhibitors. Prolonged FGFR inhibition suppresses the function of BRG1-dependent chromatin remodelling, leading to an epigenetic state that derepresses YAP-associated enhancers. These chromatin changes induce the expression of several amino acid transporters, resulting in increased intracellular levels of specific amino acids that reactivate mTORC1. Consistent with this mechanism, addition of mTORC1 or YAP inhibitors to FGFR blockade synergistically attenuated the growth of TNBC patient-derived xenograft models. Collectively, these findings reveal a feedback loop involving an epigenetic state transition and metabolic reprogramming that leads to adaptive therapeutic resistance and provides potential therapeutic strategies to overcome this mechanism of resistance.

Deep learning for cancer type classification and driver gene identification

Background

Genetic information is becoming more readily available and is increasingly being used to predict patient cancer types as well as their subtypes. Most classification methods thus far utilize somatic mutations as independent features for classification and are limited by study power. We aim to develop a novel method to effectively explore the landscape of genetic variants, including germline variants, and small insertions and deletions for cancer type prediction.

Results

We proposed DeepCues, a deep learning model that utilizes convolutional neural networks to unbiasedly derive features from raw cancer DNA sequencing data for disease classification and relevant gene discovery. Using raw whole-exome sequencing as features, germline variants and somatic mutations, including insertions and deletions, were interactively amalgamated for feature generation and cancer prediction. We applied DeepCues to a dataset from TCGA to classify seven different types of major cancers and obtained an overall accuracy of 77.6%. We compared DeepCues to conventional methods and demonstrated a significant overall improvement (p < 0.001). Strikingly, using DeepCues, the top 20 breast cancer relevant genes we have identified, had a 40% overlap with the top 20 known breast cancer driver genes.

Conclusion

Our results support DeepCues as a novel method to improve the representational resolution of DNA sequencings and its power in deriving features from raw sequences for cancer type prediction, as well as discovering new cancer relevant genes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04400-4.

Bioinformatic analysis linking genomic defects to chemosensitivity and mechanism of action

A joint analysis of the NCI60 small molecule screening data, their genetically defective genes, and mechanisms of action (MOA) of FDA approved cancer drugs screened in the NCI60 is proposed for identifying links between chemosensitivity, genomic defects and MOA. Self-Organizing-Maps (SOMs) are used to organize the chemosensitivity data. Student’s t-tests are used to identify SOM clusters with enhanced chemosensitivity for tumor cell lines with versus without genetically defective genes. Fisher’s exact and chi-square tests are used to reveal instances where defective gene to chemosensitivity associations have enriched MOAs. The results of this analysis find a relatively small set of defective genes, inclusive of ABL1, AXL, BRAF, CDC25A, CDKN2A, IGF1R, KRAS, MECOM, MMP1, MYC, NOTCH1, NRAS, PIK3CG, PTK2, RPTOR, SPTBN1, STAT2, TNKS and ZHX2, as possible candidates for roles in chemosensitivity for compound MOAs that target primarily, but not exclusively, kinases, nucleic acid synthesis, protein synthesis, apoptosis and tubulin. These results find exploitable instances of enhanced chemosensitivity of compound MOA’s for selected defective genes. Collectively these findings will advance the interpretation of pre-clinical screening data as well as contribute towards the goals of cancer drug discovery, development decision making, and explanation of drug mechanisms.

SequencEnG: an interactive knowledge base of sequencing techniques

SUMMARY

Next-generation sequencing (NGS) techniques are revolutionizing biomedical research by providing powerful methods for generating genomic and epigenomic profiles. The rapid progress is posing an acute challenge to students and researchers to stay acquainted with the numerous available methods. We have developed an interactive online educational resource called Sequencing Techniques Engine for Genomics (SequencEnG) to provide a tree-structured knowledge base of 66 different sequencing techniques and step-by-step NGS data analysis pipelines comparing popular tools. SequencEnG is designed to facilitate barrier-free learning of current NGS techniques and provides a user-friendly interface for searching through experimental and analysis methods.

AVAILABILITY AND IMPLEMENTATION

SequencEnG is part of the project Knowledge Engine for Genomics (KnowEnG) and is freely available at http://education.knoweng.org/sequenceng/.