Tissue-specific transfer-learning enables retasking of a general comprehensive model to a specific domain
Li, Q.; Perera, D.; Chen, Z.; Wen, W.; Wang, D.; Yan, J.; Shu, X.-o.; Zheng, W.; Guo, X.; Long, Q.
Show abstract
Machine learning (ML) has proven successful in biological data analysis. However, may require massive training data. To allow broader use of ML in the full spectrum of biology and medicine, including sample-sparse domains, re-directing established models to specific tasks by add-on training via a moderate sample may be promising. Transfer learning (TL), a technique migrating pre-trained models to new tasks, fits in this requirement. Here, by TL, we retasked Enformer, a comprehensive model trained by massive data, tailored to breast cancers using breast-specific data. Its performance has been validated through statistical accuracy of predictions, annotation of genetic variants, and mapping of variants associated with breast cancer. By allowing the flexibility of adding dedicated training data, our TL protocol unlocks future discovery within specific domains with moderate add-on samples by standing on the shoulders of giant models.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Enhancing Disease Risk Gene Discovery by Integrating Transcription Factor-Linked Trans-located Variants into Transcriptome-Wide Association Analyses 97%
- Integrating convolution and self-attention improves language model of human genome for interpreting non-coding regions at base-resolution 97%
- Interpretable deep learning for chromatin-informed inference of transcriptional programs driven by somatic alterations across cancers 97%
Similar papers in this journal
- EvoAug: improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentations 96%
- Inferring transcriptional regulators through integrative modeling ofpublic chromatin accessibility and ChIP-seq data 96%
- Deep-learning prediction of gene expression from personal genomes 96%
Similar papers in this journal
- Bayesian Markov models improve the prediction of binding motifs beyond first order 95%
- Towards Personalized Epigenomics: Learning Shared Chromatin Landscapes and Joint De-Noising of Histone Modification Assays 95%
- Integrating Protein and DNA Embeddings for Improving Genome-Wide Transcription Factor Binding Site Prediction 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.