Explore the vast range of titles available.

The arrangement (syntax) of transcription factor (TF) binding motifs is an important part of the cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that uses DNA sequence to predict base-resolution chromatin immunoprecipitation (ChIP)–nexus binding profiles of pluripotency TFs. We develop interpretation tools to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions. Strikingly, Nanog preferentially binds with helical periodicity, and TFs often cooperate in a directional manner, which we validate using clustered regularly interspaced short palindromic repeat (CRISPR)-induced point mutations. Our model represents a powerful general approach to uncover the motifs and syntax of cis-regulatory sequences in genomics data. BPNet is an interpretable deep learning tool that predicts transcription-factor binding profiles from DNA sequence at base-pair resolution, enabling the identification of motifs and the regulatory syntax underlying transcription-factor binding.

Transcription factors (TF) are proteins that bind DNA in a sequence-specific manner to regulate gene transcription. Despite their unique intrinsic sequence preferences, genomic occupancy profiles of TFs differ across cellular contexts. Hence, deciphering the sequence determinants of TF binding, both intrinsic and context-specific, is essential to understand gene regulation and the impact of regulatory, non-coding genetic variation. Biophysical models trained on TF binding assays can estimate intrinsic affinity landscapes and predict occupancy based on TF concentration and affinity. However, these models cannot adequately explain context-specific, binding profiles. Conversely, deep learning models, trained on TF binding assays, effectively predict and explain genomic occupancy profiles as a function of complex regulatory sequence syntax, albeit without a clear biophysical interpretation. To reconcile these complementary models of and TF binding, we developed Affinity Distillation (AD), a method that extracts thermodynamic affinities from deep learning models of TF chromatin immunoprecipitation (ChIP) experiments by marginalizing away the influence of genomic sequence context. Applied to neural networks modeling diverse classes of yeast and mammalian TFs, AD predicts energetic impacts of sequence variation within and surrounding motifs on TF binding as measured by diverse assays with superior dynamic range and accuracy compared to motif-based methods. Furthermore, AD can accurately discern affinities of TF paralogs. Our results highlight thermodynamic affinity as a key determinant of binding, suggest that deep learning models of binding implicitly learn high-resolution affinity landscapes, and show that these affinities can be successfully distilled using AD. This new biophysical interpretation of deep learning models enables high-throughput experiments to explore the influence of sequence context and variation on both intrinsic affinity and occupancy.

Short tandem repeats (STRs) are enriched in eukaryotic cis-regulatory elements and their polymorphisms alter gene expression, yet how they regulate transcription remains unknown. We find that STRs can modulate transcription factor (TF)-DNA affinities and on rates by up to 70-fold by directly binding TF DNA-binding domains, with energetic impacts approaching or exceeding mutations to consensus sites. STRs maximize the number of weakly preferred microstates near target sites, thereby increasing TF density near motifs to speed target search. Confirming that STRs also impact TF binding in cells, neural networks trained only on in vivo occupancies predict identical effects to those observed in vitro. Approximately 90% of TFs preferentially bind STRs that need not resemble known motifs, providing a novel cis-regulatory mechanism to target TFs to cognate sites. Competing Interest Statement The authors have declared no competing interest. Footnotes * https://osf.io/gbxhz/ * https://github.com/FordyceLab/STR_analysis

Convolutional neural networks are rapidly gaining popularity in regulatory genomics. Typically, these networks have a stack of convolutional and pooling layers, followed by one or more fully connected layers. In genomics, the same positional patterns are often present across multiple convolutional channels. Therefore, in current state-of-the-art networks, there exists significant redundancy in the representations learned by standard fully connected layers. We present a new separable fully connected layer that learns a weights tensor that is the outer product of positional weights and cross-channel weights, thereby allowing the same positional patterns to be applied across multiple convolutional channels. Decomposing positional and cross-channel weights further enables us to readily impose biologically-inspired constraints on positional weights, such as symmetry. We also propose a novel regularizer and constraint that act on curvature in the positional weights. Using experiments on simulated and in vivo datasets, we show that networks that incorporate our separable fully connected layer outperform conventional models with analogous architectures and the same number of parameters. Additionally, our networks are more robust to hyperparameter tuning, have more informative gradients, and produce importance scores that are more consistent with known biology than conventional deep neural networks. Availability: Implementation: https://github.com/kundajelab/keras/tree/keras_1. A gist illustrating model setup is at: goo.gl/gYooaa.

In safety-critical applications of machine learning, it is often important to abstain from making predictions on low confidence examples. Standard abstention methods tend to be focused on optimizing top-k accuracy, but in many applications, accuracy is not the metric of interest. Further, label shift (a shift in class proportions between training time and prediction time) is ubiquitous in practical settings, and existing abstention methods do not handle label shift well. In this work, we present a general framework for abstention that can be applied to optimize any metric of interest, that is adaptable to label shift at test time, and that works out-of-the-box with any classifier that can be calibrated. Our approach leverages recent reports that calibrated probability estimates can be used as a proxy for the true class labels, thereby allowing us to estimate the change in an arbitrary metric if an example were abstained on. We present computationally efficient algorithms under our framework to optimize sensitivity at a target specificity, auROC, and the weighted Cohen's Kappa, and introduce a novel strong baseline based on JS divergence from prior class probabilities. Experiments on synthetic, biological, and clinical data support our findings.

Deep learning, which describes a class of machine learning algorithms, has recently showed impressive results across a variety of domains. Biology and medicine are data rich, but the data are complex and often ill-understood. Problems of this nature may be particularly well-suited to deep learning techniques. We examine applications of deep learning to a variety of biomedical problems - patient classification, fundamental biological processes, and treatment of patients - and discuss whether deep learning will transform these tasks or if the biomedical sphere poses unique challenges. We find that deep learning has yet to revolutionize or definitively resolve any of these problems, but promising advances have been made on the prior state of the art. Even when improvement over a previous baseline has been modest, we have seen signs that deep learning methods may speed or aid human investigation. More work is needed to address concerns related to interpretability and how to best model each problem. Furthermore, the limited amount of labeled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning powering changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Label shift refers to the phenomenon where the prior class probability p(y) changes between the training and test distributions, while the conditional probability p(x|y) stays fixed. Label shift arises in settings like medical diagnosis, where a classifier trained to predict disease given symptoms must be adapted to scenarios where the baseline prevalence of the disease is different. Given estimates of p(y|x) from a predictive model, Saerens et al. proposed an efficient maximum likelihood algorithm to correct for label shift that does not require model retraining, but a limiting assumption of this algorithm is that p(y|x) is calibrated, which is not true of modern neural networks. Recently, Black Box Shift Learning (BBSL) and Regularized Learning under Label Shifts (RLLS) have emerged as state-of-the-art techniques to cope with label shift when a classifier does not output calibrated probabilities, but both methods require model retraining with importance weights and neither has been benchmarked against maximum likelihood. Here we (1) show that combining maximum likelihood with a type of calibration we call bias-corrected calibration outperforms both BBSL and RLLS across diverse datasets and distribution shifts, (2) prove that the maximum likelihood objective is concave, and (3) introduce a principled strategy for estimating source-domain priors that improves robustness to poor calibration. This work demonstrates that the maximum likelihood with appropriate calibration is a formidable and efficient baseline for label shift adaptation; notebooks reproducing experiments available at https://github.com/kundajelab/labelshiftexperiments

The arrangement of transcription factor (TF) binding motifs (syntax) is an important part of the cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that uses DNA sequence to predict base-resolution ChIP-nexus binding profiles of pluripotency TFs. We develop interpretation tools to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions. Strikingly, Nanog preferentially binds with helical periodicity, and TFs often cooperate in a directional manner, which we validate using CRISPR-induced point mutations. Our model represents a powerful general approach to uncover the motifs and syntax of cis-regulatory sequences in genomics data. The neural network BPNet accurately predicts TF binding data at base-resolution. Model interpretation discovers TF motifs and TF interactions dependent on soft syntax. Motifs for Nanog and partners are preferentially spaced at ∼10.5 bp periodicity. Directional cooperativity is validated: Sox2 enhances Nanog binding, but not vice versa.

Genes are regulated through enhancer sequences, in which transcription factor binding motifs and their specific arrangements (syntax) form a cis-regulatory code. To understand the relationship between motif syntax and transcription factor binding, we train a deep learning model that uses DNA sequence to predict base-resolution binding profiles of four pluripotency transcription factors Oct4, Sox2, Nanog, and Klf4. We interpret the model to accurately map hundreds of thousands of motifs in the genome, learn novel motif representations and identify rules by which motifs and syntax influence transcription factor binding. We find that instances of strict motif spacing are largely due to retrotransposons, but that soft motif syntax influences motif interactions at protein and nucleosome range. Most strikingly, Nanog binding is driven by motifs with a strong preference for ~10.5 bp spacings corresponding to helical periodicity. Interpreting deep learning models applied to high-resolution binding data is a powerful and versatile approach to uncover the motifs and syntax of cis-regulatory sequences.