The HASTE project is coming to an end by June 2023 and a final meeting was held on 2023-05-26 at the Ångström Laboratory, Uppsala. The participants were: Ola Spjuth (UU), Phil Harrison (UU), Ankit Gupta (UU), Ebba Bergman (UU), Andreina Francisco (UU), Tianru Zhang (UU), Carolina Wählby (UU), Salman Toor (UU), Alan Sabirsh (AstraZeneca), Andreas Hellander (UU), Ida-Maria Sintorn (Vironova).
The meeting program featured presentations reflecting on the HASTE project as a whole, but also presentations by PhD students on the completed projects and a more visionary future perspectives on the continuation of HASTE. One example is the new grants received by the HASTE PIs to carry on with parts of the projects, including an eSSENCE funded PhD project on streaming data analysis of microscopy imaging (PI: Ola Spjuth) and the award from UU Invest’s Venture Challenge 2023 (Ankit Gupta, Ida-Maria sintorn and Carolina Wählby) to continue the SimSearch application(see Gupta et al. IEEE J. Biomedical and Health informatics 26(8), 4079-4089, 2022).
It has been a great project with many successful scientific outcomes. The list of publications summarizes the scientific papers, but also highly important are the code contributions in GitHub and the datasets deposited as a result of the project.
During 2023, we look forward to two HASTE PhD students to defend their theses [updated]:
The HASTE project was featured in the June 2022 issue of Framtidens Forskning. It includes the statements from Carolina Wählby, the principal investigator of the project, Salman Toor, senior researcher in the project, and Ida-Maria Sintorn, the industry partner from Vironova AB.
Ebba Bergman presented a poster at the 11th Symposium on Pharmaceutical Profiling in Drug Discovery and Development with the title “Conformal Prediction applied to Cell Painting: Confidence in MoA Prediction”. The conference was held online on January 27th, 2022.
We are happy to announce that our paper “Proactive Autoscaling for Edge Computing Systems with Kubernetes” is now accepted at the 14th IEEE/ACM International Conference on Utility and Cloud Computing UCC 2021.
With the emergence of the Internet of Things and 5G technologies, the edge computing paradigm is playing increasingly important roles with better availability, latency-control and performance. However, existing autoscaling tools for edge computing applications do not utilize heterogeneous resources of edge systems efficiently, leaving scope for performance improvement. In this work, we propose a Proactive Pod Autoscaler (PPA) for edge computing applications on Kubernetes. The proposed PPA is able to forecast workloads in advance with multiple user-defined/customized metrics and to scale edge computing applications up and down correspondingly. The PPA is optimized and evaluated on an example CPU-intensive edge computing application further. It can be concluded that the proposed PPA outperforms the default pod autoscaler of Kubernetes on both efficiencies of resource utilization and application performance. The article also highlights future possible improvements on the proposed PPA.
We are happy to present the joining of Xiaobo Zhao as our newest member of HASTE. Xiaobo Zhao is joining the group of Andreas Hellander to work as a PostDoctoral Researcher. Xiaobo will be working on research and development of intelligent stream data processing pipelines, and the development of intelligent and efficient cloud systems capable of mapping data and compute to a variety of cloud computing and data storage e-infrastructure based on the quality and interestingness of the data.
Xiaobo Zhao received the M.S. degree in Communications and Information System from Northwestern Polytechnical University, Xi’an, China in 2015. He later received a Ph.D. degree in Electrical and Computer Engineering from Aarhus University, Aarhus, Denmark in 2020. Before joining the Hellander lab, he was a Research Assistant at Aarhus University and focused on efficient ML/DL service offloading to Edge/Cloud servers.
We are happy to announce that our paper “Deep learning models for lipid-nanoparticle-based drug delivery” is now available ahead of print and open access in the journal Nanomedicine.
Authors: Harrison PJ, Wieslander H, Sabirsh A, Karlsson J, Malmsjö V, Hellander A, Wählby C & Spjuth O.
Abstract: Background: Early prediction of time-lapse microscopy experiments enables intelligent data management and decision-making. Aim: Using time-lapse data of HepG2 cells exposed to lipid nanoparticles loaded with mRNA for expression of GFP, the authors hypothesized that it is possible to predict in advance whether a cell will express GFP. Methods: The first modeling approach used a convolutional neural network extracting per-cell features at early time points. These features were then combined and explored using either a long short-term memory network (approach 2) or time series feature extraction and gradient boosting machines (approach 3). Results: Accounting for the temporal dynamics significantly improved performance. Conclusion: The results highlight the benefit of accounting for temporal dynamics when studying drug delivery using high-content imaging.
In the figure below we show a schematic for the modelling approach used in the paper that combined convolutional and recurrent neural networks (long short-term memory, LSTM). This model is used for predicting information only present in the GFP channel at the end of the experiment from other imaging channels captured during the early time points of the experiment, prior to any GFP expression.
Following the win at the Adipocyte Imaging Challenge organized by AstraZeneca, two PhD students from the team, Ankit Gupta, and Håkan Wieslander were asked to comment in a technical report in Nature on the topic of virtual staining.
Fluorescence imaging is a valuable tool for biological analysis but is time-consuming and toxic to the cells. Using deep learning to virtually stain bright-field images is an active field of research that can alleviate these problems. Phil Harrison, a PhD student in the HASTE group, presented a poster at the Swedish Symposium on Deep Learning (SSDL) 2021 based on the HASTE team’s winning solution for the Adipocyte Cell Imaging Challenge. The poster presented our approach and results.
We are happy to present our newest member of HASTE: Dan Rosén! Dan is joining the group of Ola Spjuth to work as a Data Engineer. In his projects he will work with data pipelines and interact closely with microscopes to help reaching the goals of HASTE to act on collected image streams and make intelligent decisions and control microscopes to prioritize collecting the most interesting data.
AI Sweden and AstraZeneca organised the Adipocyte Cell Imaging Challenge, a two-week-long hackathon to help AstraZeneca accelerate the drug development process. The task was to use machine learning in solving the problem of labelling cell images without requiring toxic preprocessing of cell cultures by predicting the content of the fluorescence images from the corresponding bright-field images.
The solution used the Learning Under Privileged Information (LUPI) paradigm to solve the problem. LUPI enables the inclusion of additional (privileged) information when training machine learning models, data that is not available when making predictions. In this case, the segmentation masks of the nuclei were used as the privileged information during the training of machine learning models. Our solution will help AstraZeneca to speed up the drug discovery process and bring drugs to market quicker.