TY - JOUR
T1 - Computational modeling of in vivo and in vitro protein-DNA interactions by multiple instance learning
AU - Gao, Zhen
AU - Ruan, Jianhua
N1 - Funding Information:
This work was supported in part by grants from the National Science Foundation (award number IIS-1218201, ABI-1565076) and the National Institutes of Health (award number G12MD007591).
PY - 2017/7/15
Y1 - 2017/7/15
N2 - Motivation: The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. While the development of both in vivo and in vitro profiling techniques have significantly enhanced our knowledge of transcription factor (TF)-DNA interactions, computational models of TF-DNA interactions are relatively simple and may not reveal sufficient biological insight. In particular, supervised learning based models for TF-DNA interactions attempt to map sequence-level features (k-mers) to binding event but usually ignore the location of k-mers, which can cause data fragmentation and consequently inferior model performance. Results: Here, we propose a novel algorithm based on the so-called multiple-instance learning (MIL) paradigm. MIL breaks each DNA sequence into multiple overlapping subsequences and models each subsequence separately, therefore implicitly takes into consideration binding site locations, resulting in both higher accuracy and better interpretability of the models. The result from both in vivo and in vitro TF-DNA interaction data show that our approach significantly outperform conventional single-instance learning based algorithms. Importantly, the models learned from in vitro data using our approach can predict in vivo binding with very good accuracy. In addition, the location information obtained by our method provides additional insight for motif finding results from ChIP-Seq data. Finally, our approach can be easily combined with other state-of-the-art TF-DNA interaction modeling methods.
AB - Motivation: The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. While the development of both in vivo and in vitro profiling techniques have significantly enhanced our knowledge of transcription factor (TF)-DNA interactions, computational models of TF-DNA interactions are relatively simple and may not reveal sufficient biological insight. In particular, supervised learning based models for TF-DNA interactions attempt to map sequence-level features (k-mers) to binding event but usually ignore the location of k-mers, which can cause data fragmentation and consequently inferior model performance. Results: Here, we propose a novel algorithm based on the so-called multiple-instance learning (MIL) paradigm. MIL breaks each DNA sequence into multiple overlapping subsequences and models each subsequence separately, therefore implicitly takes into consideration binding site locations, resulting in both higher accuracy and better interpretability of the models. The result from both in vivo and in vitro TF-DNA interaction data show that our approach significantly outperform conventional single-instance learning based algorithms. Importantly, the models learned from in vitro data using our approach can predict in vivo binding with very good accuracy. In addition, the location information obtained by our method provides additional insight for motif finding results from ChIP-Seq data. Finally, our approach can be easily combined with other state-of-the-art TF-DNA interaction modeling methods.
UR - http://www.scopus.com/inward/record.url?scp=85024502141&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85024502141&partnerID=8YFLogxK
U2 - 10.1093/bioinformatics/btx115
DO - 10.1093/bioinformatics/btx115
M3 - Article
C2 - 28334224
AN - SCOPUS:85024502141
VL - 33
SP - 2097
EP - 2105
JO - Bioinformatics
JF - Bioinformatics
SN - 1367-4803
IS - 14
ER -