Andrew Delong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Andrew Delong has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Brendan J. Frey
University of Toronto
2 shared publications - David Duvenaud
Vector Institute Vector Institute Vector Institute University of Toronto University of Toronto Stanford University University of Toronto
2 shared publications - Leo J. Lee
Vector Institute
2 shared publications - Yuri Boykov
Computer Science University of Western Ontario Canada
2 shared publications - Amit G. Deshwar
Deep Genomics Inc
1 shared publication - Anton Osokin
National Research University Higher School of Economics
1 shared publication
Latest Publications
- Open Access
Transcriptome-Wide Off-Target Effects of Steric-Blocking Oligonucleotides
Steric-blocking oligonucleotides (SBOs) are short, single-stranded nucleic acids designed to modulate gene expression by binding to mRNA and blocking access from cellular machinery such as splicing factors. SBOs have the potential to bind to near-complementary sites in the transcriptome, causing off-target effects. In this study, we used RNA-seq to evaluate the off-target differential splicing events of 81 SBOs and differential expression events of 46 SBOs. Our results suggest that differential splicing events are predominantly hybridization-driven, while differential expression events are more common and driven by other mechanisms. We further evaluated the performance of in silico screens for off-target events, and found an edit distance cutoff of three to result in a sensitivity of 14% and false discovery rate of 99%. A machine learning model incorporating splicing predictions substantially improved the ability to prioritize low edit distance hits, increasing sensitivity from 4% to 26% at a fixed FDR. Despite these large improvements in performance, the approach does not detect the majority of events at a false discovery rate below 99%. Our results suggest that in silico methods are currently of limited use for predicting the off-target effects of SBOs.
Open AccessTranscriptome-Wide Off-Target Effects of Steric-Blocking Oligonucleotides
Steric-blocking oligonucleotides (SBOs) are short, single-stranded nucleic acids designed to modulate gene expression by binding to mRNA and blocking access from cellular machinery such as splicing factors. SBOs have the potential to bind to near-complementary sites in the transcriptome, causing off-target effects. In this study, we used RNA-seq to evaluate the off-target differential splicing events of 81 SBOs and differential expression events of 46 SBOs. Our results suggest that differential splicing events are predominantly hybridization-driven, while differential expression events are more common and driven by other mechanisms. We further evaluated the performance of in silico screens for off-target events, and found an edit distance cutoff of three to result in a sensitivity of 14% and false discovery rate of 99%. A machine learning model incorporating splicing predictions substantially improved the ability to prioritize low edit distance hits, increasing sensitivity from 4% to 26% at a fixed FDR. Despite these large improvements in performance, the approach does not detect the majority of events at a false discovery rate below 99%. Our results suggest that in silico methods are currently of limited use for predicting the off-target effects of SBOs.
- Open Access
Deep Inverse Optimization
Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpropagation to learn parameters that generate the observations. We demonstrate that by backpropagating through the interior point algorithm we can learn the coefficients determining the cost vector and the constraints, independently or jointly, for both non-parametric and parametric linear programs, starting from one or multiple observations. With this approach, inverse optimization can leverage concepts and algorithms from deep learning.
Open AccessDeep Inverse Optimization
Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpropagation to learn parameters that generate the observations. We demonstrate that by backpropagating through the interior point algorithm we can learn the coefficients determining the cost vector and the constraints, independently or jointly, for both non-parametric and parametric linear programs, starting from one or multiple observations. With this approach, inverse optimization can leverage concepts and algorithms from deep learning.
- Open Access
cDeepbind: A context sensitive deep learning model of RNA-protein binding
Motivation: Determining RNA binding protein(RBP) binding specificity is crucial for understanding many cellular processes and genetic disorders. RBP binding is known to be affected by both the sequence and structure of RNAs. Deep learning can be used to learn generalizable representations of raw data and has improved state of the art in several fields such as image classification, speech recognition and even genomics. Previous work on RBP binding has either used shallow models that combine sequence and structure or deep models that use only the sequence. Here we combine both abilities by augmenting and refining the original Deepbind architecture to capture structural information and obtain significantly better performance. Results: We propose two deep architectures, one a lightweight convolutional network for transcriptome wide inference and another a Long Short-Term Memory(LSTM) network that is suitable for small batches of data. We incorporate computationally predicted secondary structure features as input to our models and show its effectiveness in boosting prediction performance. Our models achieved significantly higher correlations on held out in-vitro test data compared to previous approaches, and generalise well to in-vivo CLIP-SEQ data achieving higher median AUCs than other approaches. We analysed the output from our model for VTS1 and CPO and provided intuition into its working. Our models confirmed known secondary structure preferences for some proteins as well as found new ones where secondary structure might play a role. We also demonstrated the strengths of our model compared to other approaches such as the ability to combine information from long distances along the input. Availability: Software and models are available at https://github.com/shreshthgandhi/cDeepbind Contact: ljlee@psi.toronto.edu , frey@psi.toronto.edu
Open AccesscDeepbind: A context sensitive deep learning model of RNA-protein binding
Motivation: Determining RNA binding protein(RBP) binding specificity is crucial for understanding many cellular processes and genetic disorders. RBP binding is known to be affected by both the sequence and structure of RNAs. Deep learning can be used to learn generalizable representations of raw data and has improved state of the art in several fields such as image classification, speech recognition and even genomics. Previous work on RBP binding has either used shallow models that combine sequence and structure or deep models that use only the sequence. Here we combine both abilities by augmenting and refining the original Deepbind architecture to capture structural information and obtain significantly better performance. Results: We propose two deep architectures, one a lightweight convolutional network for transcriptome wide inference and another a Long Short-Term Memory(LSTM) network that is suitable for small batches of data. We incorporate computationally predicted secondary structure features as input to our models and show its effectiveness in boosting prediction performance. Our models achieved significantly higher correlations on held out in-vitro test data compared to previous approaches, and generalise well to in-vivo CLIP-SEQ data achieving higher median AUCs than other approaches. We analysed the output from our model for VTS1 and CPO and provided intuition into its working. Our models confirmed known secondary structure preferences for some proteins as well as found new ones where secondary structure might play a role. We also demonstrated the strengths of our model compared to other approaches such as the ability to combine information from long distances along the input. Availability: Software and models are available at https://github.com/shreshthgandhi/cDeepbind Contact: ljlee@psi.toronto.edu , frey@psi.toronto.edu
- Open Access
Generating and designing DNA with deep generative models
We propose generative neural network methods to generate DNA sequences and tune them to have desired properties. We present three approaches: creating synthetic DNA sequences using a generative adversarial network; a DNA-based variant of the activation maximization ("deep dream") design method; and a joint procedure which combines these two approaches together. We show that these tools capture important structures of the data and, when applied to designing probes for protein binding microarrays, allow us to generate new sequences whose properties are estimated to be superior to those found in the training data. We believe that these results open the door for applying deep generative models to advance genomics research.
Open AccessGenerating and designing DNA with deep generative models
We propose generative neural network methods to generate DNA sequences and tune them to have desired properties. We present three approaches: creating synthetic DNA sequences using a generative adversarial network; a DNA-based variant of the activation maximization ("deep dream") design method; and a joint procedure which combines these two approaches together. We show that these tools capture important structures of the data and, when applied to designing probes for protein binding microarrays, allow us to generate new sequences whose properties are estimated to be superior to those found in the training data. We believe that these results open the door for applying deep generative models to advance genomics research.
- 9 May 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 100 (1) , 38-58
Minimizing Energies with Hierarchical Costs
- 9 May 2012
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 100 (1) , 38-58
Minimizing Energies with Hierarchical Costs
- Top Cited Papers
- 12 July 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 96 (1) , 1-27
Fast Approximate Energy Minimization with Label Costs
- 12 July 2011
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 96 (1) , 1-27
Top Cited PapersFast Approximate Energy Minimization with Label Costs