A structure-based Multiple-Instance Learning approach to predicting in vitro transcription factor-DNA interaction

Understanding the mechanism of transcriptional regulation remains an inspiring stage of molecular biology. Recently, in vitro protein-binding microarray experiments have greatly improved the understanding of transcription factor-DNA interaction. We present a method - MIL3D - which predicts in vitro transcription factor binding by multiple-instance learning with structural properties of DNA. Evaluation on in vitro data of twenty mouse transcription factors shows that our method outperforms a method based on simple-instance learning with DNA structural properties, and the widely used k-mer counting method, for nineteen out of twenty of the transcription factors. Our analysis showed that the MIL3D approach can utilize subtle structural similarities when a strong sequence consensus is not available. Combining multiple-instance learning and structural properties of DNA has promising potential for studying biological regulatory networks.

• Publication year

  2015

• Venue

  BMC Genomics

• Publication date

  2015-04-21

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1186/1471-2164-16-S4-S3PMID 25917392PMCID 4416172
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Comprehensive meta-analysis of Signal Transducers and Activators of Transcription (STAT) genomic binding patterns discerns cell-specific cis-regulatory modules

  2013cited by this paper
• Evaluation of methods for modeling transcription factor sequence specificity

  2013influential reference
• A genome-wide cis-regulatory element discovery method based on promoter sequences and gene co-expression networks

  2012cited by this paper
• c-Jun binding site identification in K562 cells.

  2011cited by this paper
• Binding Site Specificity and Factor Redundancy in Activator Protein-1-driven Human Papillomavirus Chromatin-dependent Transcription*

  2011cited by this paper
• Direct measurement of DNA affinity landscapes on a high-throughput sequencing instrument

  2011cited by this paper
• A particle swarm optimization-based algorithm for finding gapped motifs

  2010cited by this paper
• Using Sequence-Specific Chemical and Structural Properties of DNA to Predict Transcription Factor Binding Sites

  2010influential reference
• Distinguishing direct versus indirect transcription factor-DNA interactions.

  2009cited by this paper
• The WEKA data mining software: an update

  2009cited by this paper
• Diversity and Complexity in DNA Recognition by Transcription Factors

  2009cited by this paper
• Dialogue on Reverse‐Engineering Assessment and Methods

  2007cited by this paper
• A Systems Approach to Measuring the Binding Energy Landscapes of Transcription Factors

  2007influential reference
• Finding Short DNA Motifs Using Permuted Markov Models

  2004cited by this paper
• Rapid analysis of the DNA-binding specificities of transcription factors with DNA microarrays

  2004cited by this paper
• Simulation and modeling of nucleic acid structure, dynamics and interactions.

  2004cited by this paper
• A biophysical approach to transcription factor binding site discovery.

  2003cited by this paper
• Applying propositional learning algorithms to multi-instance data

  2003cited by this paper
• MATCHTM: a tool for searching transcription factor binding sites in DNA sequences

  2003cited by this paper
• Support Vector Machines for Multiple-Instance Learning

  2002cited by this paper
• A standard reference frame for the description of nucleic acid base-pair geometry.

  2001cited by this paper
• Solving the Multiple-Instance Problem: A Lazy Learning Approach

  2000cited by this paper
• A Framework for Multiple-Instance Learning

  1997cited by this paper
• On Learning From Multi-Instance Examples: Empirical Evaluation of a Theoretical Approach

  1997cited by this paper
• MATRIX SEARCH 1.0: a computer program that scans DNA sequences for transcriptional elements using a database of weight matrices

  1995cited by this paper
• Consensus patterns in DNA.

  1990influential reference
• Selection of DNA binding sites by regulatory proteins. Statistical-mechanical theory and application to operators and promoters.

  1987influential reference
• Editorial: On Machine Learning

  1986cited by this paper

• Chemical complexity challenge: Is multi‐instance machine learning a solution?

  2023influential citation
• Positional weight matrices have sufficient prediction power for analysis of noncoding variants

  2022cites this paper
• PhyloPGM: boosting regulatory function prediction accuracy using evolutionary information

  2022cites this paper
• Positional weight matrices have sufficient prediction power for analysis of noncoding variants.

  2022cites this paper
• Positional weight matrices have sufficient prediction power for analysis of noncoding variants.

  2022cites this paper
• 4acCPred: Weakly supervised prediction of N4-acetyldeoxycytosine DNA modification from sequences

  2022cites this paper
• Weakly supervised learning of RNA modifications from low-resolution epitranscriptome data

  2021cites this paper
• Functional Site Discovery From Incomplete Training Data: A Case Study With Nucleic Acid–Binding Proteins

  2019cites this paper
• Effects of Rate of Drying, Life History Phase, and Ecotype on the Ability of the Moss Bryum Argenteum to Survive Desiccation Events and the Influence on Conservation and Selection of Material for Restoration

  2019cites this paper
• Computational modeling of in vivo and in vitro protein‐DNA interactions by multiple instance learning

  2017influential citation
• The Genetics of Transcription Factor DNA Binding Variation.

  2016cites this paper
• Decoding the non‐coding genome: elucidating genetic risk outside the coding genome

  2016cites this paper