Show Notes
Dr. Hayden Metsky begins by introducing the ADAPT method for doing large-scale detection of viruses. ADAPT is a computational method that aids the design of CRISPR-based viral testing. He then discusses the motivation for ADAPT and how it relates to his previous works like CATCH. In comparing ADAPT to other work, Dr. Metsky discusses, for instance, differences between CRISPR-based testing and more traditional testing like qPCR. In discussing the challenges of designing diagnostic tests and detection assays, Dr. Metsky then describes how he breaks these challenges into three different components.
Dr. Metsky goes on to talk about how they designed an assay based around the Cas13 enzyme. He describes how they used this approach for targeting viruses and explains how they designed a large-scale library of 20,000 pairs of target viral sequences and guide RNAs. He then explains how they used this library as training data for a machine learning model. He also explains his thought process of designing and training the convolutional neural network model that they ended up using for predicting how well the guide RNAs would work.
As our conversation continues, Dr. Metsky points out an interesting observation that his team made while working on this project. He points out that it could be the case that it may not be best to only design diagnostics around a highly or universally conserved region. He explains that taking into account other considerations, like how well the diagnostic technology works for a particular target sequence, may produce even better results. He also points out how it can be really challenging to only consider the highly conserved or totally conserved regions because those regions are going to be the most likely to be shared by other viruses or organisms which induce false positives in tests. Dr. Metsky explains his thought process for how you take a problem like this, figure out the characteristics of the problem, and match it well to a closely related problem or other scientific works, explaining the process of figuring out how to optimize the final objective function in ADAPT. Final topics include a discussion on the speed of ADAPT and the availability of the software.
To learn more about ADAPT, you can read the ADAPT manuscript at https://www.biorxiv.org/content/10.1101/2020.11.28.401877v2 or visit the software page at https://github.com/broadinstitute/adapt
More from The Bioinformatics and Beyond Podcast
Dr. Justin Siegel begins this episode by explaining what enzymes are, how they have evolved, and why Dr. Siegel is motivated to try to engineer enzymes to perform functions tailored to help humanity instead of to perform functions based on how they evolved in nature. He explains the primary goal of the work discussed and relating enzyme sequence to function. Dr. Siegel also explains how his work was the first of its kind by scaling up enzyme design to hundreds of mutants instead of dozens.
Dr. Justin Siegel explains the past, present, and future of wet lab work and wet lab automation. We start by hearing a description of what it is like to work in a wet lab, covering the contrast between the excitement of seeing life changing results and the countless hours of monotony that is often involved to produce these results.
Dr. Afshin Beheshti begins this episode by explaining what microRNAs are and why they are emerging as an important area of biological research. He then explains how microRNAs relate to viruses, which is a recently developing area of research in this already young field of study. Dr. Beheshti then tells the story of how he started to discover that microRNAs could be a driver of COVID-19 infections.
This episode concludes the podcast’s series of episodes focused on space biology and space omics. NASA scientist Dr. Afshin Beheshti discusses the many high level hazards and corresponding molecular features of spaceflight throughout this episode. For instance, we begin with a discussion of the hazards of radiation and microgravity. Dr. Beheshti spends time explaining a high level view of what each hazard is, why it is a concern for spaceflight, and educates us on many useful and interesting pieces of information for each hazard. Further hazards discussed include confinement and isolation, hostile and closed environment, and distance from Earth.
This episode discusses Dr. Tejaswini Mishra’s recent publication in Nature Biomedical Engineering: https://www.nature.com/articles/s41551-020-00640-6 Dr. Mishra begins the episode by explaining the origin story of this work and how the idea for this paper came to be. She then explains how this study enrolled thousands of participants and used the participants’ smartwatch or wearable device data to detect COVID-19 infections. After explaining how this study began, Dr. Mishra discusses how she and her team came up with two main algorithms for detecting COVID-19 infections from wearables data. Dr. Mishra also discusses the many variables that could be monitored with wearables in addition to standard measures used for predicting illnesses like heart rate. Finally, we hear about the main results of this study including the successful detection of several active COVID-19 infections in study participants. We also hear a comparison of this work against the COVID-19 wearables study featured previously on the podcast. We end by hearing Dr. Mishra’s thoughts on the future of wearables for detecting infectious diseases and for improving human health in general.