Abstract
Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans. Previous comparative studies of mouse and human tissues were limited by the use of bulk-cell material. Here we show that transfer learning—the branch of machine learning that concerns passing information from one domain to another—can be used to efficiently map bone marrow biology between species, using data obtained from single-cell RNA sequencing. We first trained a multiclass logistic regression model to recognize different cell types in mouse bone marrow achieving equivalent performance to more complex artificial neural networks. Furthermore, it was able to identify individual human bone marrow cells with 83% overall accuracy. However, some human cell types were not easily identified, indicating important differences in biology. When re-training the mouse classifier using data from human, less than 10 human cells of a given type were needed to accurately learn its representation. In some cases, human cell identities could be inferred directly from the mouse classifier via zero-shot learning. These results show how simple machine learning models can be used to reconstruct complex biology from limited data, with broad implications for biomedical research.
Highlights
Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans
We found a strong overlap in the sets of important genes identified by the artificial neural network (ANN) and multinomial logistic regression (MLR), indicating that the two models classify cells on the basis of similar biological criteria
As with the mouse data, we found that misclassification of human cells was commonly proximal in nature (15.7% versus 12.0% for distal misclassification; the corresponding values of the ANN are 13.9% proximal and 8% distal), suggesting that the mouse classifiers had partially learnt human cellular identities, and misclassification was not entirely artefactual (Fig. 2b–d)
Summary
Biomedical research often involves conducting experiments on model organisms in the anticipation that the biology learnt will transfer to humans. We show that transfer learning—the branch of machine learning that concerns passing information from one domain to another—can be used to efficiently map bone marrow biology between species, using data obtained from single-cell RNA sequencing. Human cell identities could be inferred directly from the mouse classifier via zero-shot learning These results show how simple machine learning models can be used to reconstruct complex biology from limited data, with broad implications for biomedical research. In the transfer learning process, information gained from solving a problem in a source domain is passed to another related problem in a target domain, thereby improving target domain performance. We demonstrate how using a machine learning model to encode cell-type information in mouse enables cell-type comparison with humans, providing new insight into the effective transfer of information between species and the amount of domain-specific information that is required to train a machine learning model using single-cell data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
