Deep Learning Analysis on Images of iPSC-derived Motor Neurons Carrying fALS-genetics Reveals Disease-Relevant Phenotypes

Rahul Atmaramani, Tommaso Dreossi, Kevin Ford, Lin Gan,Jana Mitchell, Shenjiang Tu, Jeevaa Velayutham, Haoyang Zeng, Tom Soare, Mukund Hari, Emiliano Hergenreder, Stephanie Redmond, Yujia Bao, Flora Yi, Difei Xu, Ryan Conrad, Nitya Mittal, Santiago Akle, Nick Atkeson, Jonathan Liu,Srinivasan Sivanandan, Syuan-Ming Guo, Elaine Lam, Ahmed Sandakli, Patrick Conrad, Liyuan Zhang, Aaron Topol, Michael Chickering,Brigham Hartley,Theofanis Karaletsos, Eva-Maria Krauel,Mark Labow,Richard Hargreaves, Matthew Trotter,Shameek Biswas,Angela Oliveira Pisco,Ajamete Kaykas,Daphne Koller, Samuel Sances

biorxiv(2024)

引用 0|浏览11
暂无评分
摘要
Amyotrophic lateral sclerosis (ALS) is a devastating condition with very limited treatment options. It is a heterogeneous disease with complex genetics and unclear etiology, making the discovery of disease-modifying interventions very challenging. To discover novel mechanisms underlying ALS, we leverage a unique platform that combines isogenic, induced pluripotent stem cell (iPSC)-derived models of disease-causing mutations with rich phenotyping via high-content imaging and deep learning models. We introduced eight mutations that cause familial ALS (fALS) into multiple donor iPSC lines, and differentiated them into motor neurons to create multiple isogenic pairs of healthy (wild-type) and sick (mutant) motor neurons. We collected extensive high-content imaging data and used machine learning (ML) to process the images, segment the cells, and learn phenotypes. Self-supervised ML was used to create a concise embedding that captured significant, ALS-relevant biological information in these images. We demonstrate that ML models trained on core cell morphology alone can accurately predict TDP-43 mislocalization, a known phenotypic feature related to ALS. In addition, we were able to impute RNA expression from these image embeddings, in a way that elucidates molecular differences between mutants and wild-type cells. Finally, predictors leveraging these embeddings are able to distinguish between mutant and wild-type both within and across donors, defining cellular, ML-derived disease models for diverse fALS mutations. These disease models are the foundation for a novel screening approach to discover disease-modifying targets for familial ALS. ### Competing Interest Statement The authors are current (R.A., T.D., K.F., L.G., J.M., S.T, J.V., H.Z., T.S., S.S., R.C., S.A., J.L., S.R., S.G., P.C., F.Y., N.A., D.X., A.M., E.H., M.H., A.S., N.M., A.T., B.H., E.L., E.K., A.O.P., A.K., D.K., S.S) or former (Y.B., L.Z.,T.K.,) employees and shareholders of insitro inc and current employees and shareholders of Brystol Myers Squibb (M.L., R.H., M.T., S.B.)
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要