We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.

We present the DeepProfile framework, which learns a variational autoencoder (VAE) network from thousands of publicly available gene expression samples and uses this network to encode a low-dimensional representation (LDR) to predict complex disease phenotypes. To our knowledge, DeepProfile is the first attempt to use deep learning to extract a feature representation from a vast quantity of unlabeled (i.e, lacking phenotype information) expression samples that are not incorporated into the prediction problem. We use DeepProfile to predict acute myeloid leukemia patients' in vitro responses to 160 chemotherapy drugs. We show that, when compared to the original features (i.e., expression levels) and LDRs from two commonly used dimensionality reduction methods, DeepProfile: (1) better predicts complex phenotypes, (2) better captures known functional gene groups, and (3) better reconstructs the input data. We show that DeepProfile is generalizable to other diseases and phenotypes by using it to predict ovarian cancer patients' tumor invasion patterns and breast cancer patients' disease subtypes.

The trRosetta structure prediction method employs deep learning to generate predicted residue-residue distance and orientation distributions from which 3D models are built. We sought to improve the method by incorporating as inputs (in addition to sequence information) both language model embeddings and template information weighted by sequence similarity to the target. We also developed a refinement pipeline that recombines models generated by template-free and template utilizing versions of trRosetta guided by the DeepAccNet accuracy predictor.Both benchmark tests and CASP results show that the new pipeline is a considerable improvement over the original trRosetta, and it is faster and requires less computing resources, completing the entire modeling process in a median < 3 h in CASP14. Our human group improved results with this pipeline primarily by identifying additional homologous sequences for input into the network. We also used the DeepAccNet accuracy predictor to guide Rosetta high-resolution refinement for submissions in the regular and refinement categories; although performance was quite good on a CASP relative scale, the overall improvements were rather modest in part due to missing inter-domain or inter-chain contacts.

ChIP-seq is a technique to determine binding locations of transcription factors, which remains a central challenge in molecular biology. Current practice is to use a ‘control’ dataset to remove background signals from a immunoprecipitation (IP) ‘target’ dataset. We introduce the AIControl framework, which eliminates the need to obtain a control dataset and instead identifies binding peaks by estimating the distributions of background signals from many publicly available control ChIP-seq datasets. We thereby avoid the cost of running control experiments while simultaneously increasing the accuracy of binding location identification. Specifically, AIControl can (i) estimate background signals at fine resolution, (ii) systematically weigh the most appropriate control datasets in a data-driven way, (iii) capture sources of potential biases that may be missed by one control dataset and (iv) remove the need for costly and time-consuming control experiments. We applied AIControl to 410 IP datasets in the ENCODE ChIP-seq database, using 440 control datasets from 107 cell types to impute background signal. Without using matched control datasets, AIControl identified peaks that were more enriched for putative binding sites than those identified by other popular peak callers that used a matched control dataset. We also demonstrated that our framework identifies binding sites that recover documented protein interactions more accurately.

We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts. The network was trained on approximately 1 million alternative local energy minima for 7,510 different proteins exhibiting a wide diversity of errors, and outperforms other methods that similarly predict the accuracy of protein structure models without template or evolutionary information. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with resolution, and the network should be broadly useful for assessing accuracy of both predicted structure models and experimentally determined structures, and identifying specific regions likely to be in error. Guiding protein structure refinement by incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol led to improvements in model quality in 63 out of 73 test cases, illustrating how deep learning can improve search for global energy minima.

Determining the binding locations of regulatory factors, such as transcription factors and histone modifications, is essential to both basic biology research and many clinical applications. Obtaining such genome-wide location maps directly is often invasive and resource-intensive, so it is common to impute binding locations from DNA sequence or measures of chromatin accessibility. We introduce DeepATAC, a deep-learning approach for imputing binding locations that uses both DNA sequence and chromatin accessibility as measured by ATAC-seq. DeepATAC significantly outperforms current approaches such as FIMO motif predictions overlapped with ATAC-seq peaks, and models based only on DNA sequence, such as DeepSEA. Visualizing the input importances for the DeepATAC model reveals DNA sequence motifs and ATAC-seq signal patterns that are important for predicting binding events. The Keras implementation and analysis pipelines of DeepATAC are available at https://github.com/hiranumn/deepatac.

Sexual reproduction roots the eukaryotic tree of life, although its loss occurs across diverse taxa. Asexual reproduction and clonal lineages persist in these taxa despite theoretical arguments suggesting that individual clones should be evolutionarily short-lived due to limited phenotypic diversity. Here, we present quantitative evidence that an obligate asexual lineage emerged from a sexual population of the marine diatom Thalassiosira pseudonana and rapidly expanded throughout the world’s oceans. Whole genome comparisons identified two lineages with characteristics expected of sexually reproducing strains in Hardy-Weinberg equilibrium. A third lineage displays genomic signatures for the functional loss of sexual reproduction followed by a recent global colonization by a single ancestral genotype. Extant members of this lineage are genetically differentiated and phenotypically plastic, potentially allowing for rapid adaptation when they are challenged by natural selection. Such mechanisms may be expected to generate new clones within marginal populations of additional unicellular species, facilitating the exploration and colonization of novel environments, aided by exponential growth and ease of dispersal.

Motivation: Accurately identifying the binding sites of regulatory proteins remains a central and unresolved challenge in molecular biology. The most commonly used experimental technique to determine binding locations of transcription factors is chromatin immunoprecipitation followed by DNA sequencing (ChIP-seq). Because ChIP-seq is highly susceptible to background noise, the current practice obtains one matched "control" ChIP-seq dataset and estimates position-wise background distributions using ChIP-seq signals from nearby positions (e.g., within 5,000-10,000 bps). This approach poses the following four problems.