Cambridge Rindge and Latin School
Daniel King and Cotton Seed
Stanley Center for Psychiatric Disease
It seems obvious that the brain is the home of psychiatric disease; however, science has still not found a clinical-grade, biological marker for psychiatric disease. Ilora, with her partner Jonathan, hypothesized that biological markers are hidden among the immense complexity of brain images. She suspected machine learning techniques could distinguish the portions of brain images due to heritable traits (i.e. genetics) from those due to non-heritable traits (i.e. environmental factors). Specifically, Ilora postulated that MRI images could be used to train a special type of neural network known as an autoencoder, which, when trained properly, would reduce all of the extremely complex phenotypes present in an MRI image down to a handful of patterns that make up these complex phenotypes, known as latent phenotypes. Ilora’s project involved proving that, in principle, this idea could work; to do so, she trained an autoencoder using a dataset of faces that had been constructed using a deep convolutional neural network in order to see if heritability information about these faces could be captured by just a few latent phenotypes. Her preliminary results were extremely promising, meaning that seeing someone’s genetic information from an MRI image may not be science fiction for much longer! “I liked knowing that the work I was doing this summer could be used in the real world to potentially help individuals struggling with psychiatric disease in the future,” said Ilora about her project. “Being able to make an impact on a greater population is incredibly important to me and this program and project enabled me to do so.” When speaking about BSSP, Ilora said "I came into BSSP with no coding experience and was honestly a bit intimidated by it, however after 6 weeks of coding I feel far more confident with CS and am open to more coding experiences and opportunities. This program really helped me see how interlocked biological wet lab work and computational work is, it gave me a deeper appreciation for CS as it’s so versatile and can be used to support really any field of science."