skip to main content


Title: Evolutionarily informed deep learning methods for predicting relative transcript abundance from DNA sequence
Deep learning methodologies have revolutionized prediction in many fields and show potential to do the same in molecular biology and genetics. However, applying these methods in their current forms ignores evolutionary dependencies within biological systems and can result in false positives and spurious conclusions. We developed two approaches that account for evolutionary relatedness in machine learning models: ( i ) gene-family–guided splitting and ( ii ) ortholog contrasts. The first approach accounts for evolution by constraining model training and testing sets to include different gene families. The second approach uses evolutionarily informed comparisons between orthologous genes to both control for and leverage evolutionary divergence during the training process. The two approaches were explored and validated within the context of mRNA expression level prediction and have the area under the ROC curve (auROC) values ranging from 0.75 to 0.94. Model weight inspections showed biologically interpretable patterns, resulting in the hypothesis that the 3′ UTR is more important for fine-tuning mRNA abundance levels while the 5′ UTR is more important for large-scale changes.  more » « less
Award ID(s):
1710618
NSF-PAR ID:
10099234
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the National Academy of Sciences
Volume:
116
Issue:
12
ISSN:
0027-8424
Page Range / eLocation ID:
5542 to 5549
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Motivation

    Alternative polyadenylation (polyA) sites near the 3′ end of a pre-mRNA create multiple mRNA transcripts with different 3′ untranslated regions (3′ UTRs). The sequence elements of a 3′ UTR are essential for many biological activities such as mRNA stability, sub-cellular localization, protein translation, protein binding and translation efficiency. Moreover, numerous studies in the literature have reported the correlation between diseases and the shortening (or lengthening) of 3′ UTRs. As alternative polyA sites are common in mammalian genes, several machine learning tools have been published for predicting polyA sites from sequence data. These tools either consider limited sequence features or use relatively old algorithms for polyA site prediction. Moreover, none of the previous tools consider RNA secondary structures as a feature to predict polyA sites.

    Results

    In this paper, we propose a new deep learning model, called DeepPASTA, for predicting polyA sites from both sequence and RNA secondary structure data. The model is then extended to predict tissue-specific polyA sites. Moreover, the tool can predict the most dominant (i.e. frequently used) polyA site of a gene in a specific tissue and relative dominance when two polyA sites of the same gene are given. Our extensive experiments demonstrate that DeepPASTA signisficantly outperforms the existing tools for polyA site prediction and tissue-specific relative and absolute dominant polyA site prediction.

    Availability and implementation

    https://github.com/arefeen/DeepPASTA

    Supplementary information

    Supplementary data are available at Bioinformatics online.

     
    more » « less
  2. Skolnick, Jeffrey (Ed.)
    Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space. 
    more » « less
  3. Abstract

    Sympatric diversification is recognized to have played an important role in the evolution of biodiversity. However, an in situ sympatric origin for codistributed taxa is difficult to demonstrate because different evolutionary processes can lead to similar biogeographic outcomes, especially in ecosystems that can readily facilitate secondary contact due to a lack of hard barriers to dispersal. Here we use a genomic (ddRADseq), model‐based approach to delimit a species complex of tropical sea anemones that are codistributed on coral reefs throughout the Tropical Western Atlantic. We use coalescent simulations infastsimcoal2and ordinary differential equations inMomentsto test competing diversification scenarios that span the allopatric‐sympatric continuum. Our results suggest that the corkscrew sea anemoneBartholomea annulatais a cryptic species complex whose members are codistributed throughout their range. Simulation and model selection analyses from both approaches suggest these lineages experienced historical and contemporary gene flow, supporting a sympatric origin, but an alternative secondary contact model receives appreciable model support infastsimcoal2. Leveraging the genome of the closely relatedExaiptasia diaphana,we identify five loci under divergent selection between crypticB. annulatalineages that fall within mRNA transcripts or CDS regions. Our study provides a rare empirical, genomic example of sympatric speciation in a tropical anthozoan and the first range‐wide molecular study of a tropical sea anemone, underscoring that anemone diversity is under‐described in the tropics, and highlighting the need for additional systematic studies into these ecologically and economically important species.

     
    more » « less
  4. null (Ed.)
    Abstract MicroRNAs (miRNAs) play important roles in post-transcriptional gene regulation and phenotype development. Understanding the regulation of miRNA genes is critical to understand gene regulation. One of the challenges to study miRNA gene regulation is the lack of condition-specific annotation of miRNA transcription start sites (TSSs). Unlike protein-coding genes, miRNA TSSs can be tens of thousands of nucleotides away from the precursor miRNAs and they are hard to be detected by conventional RNA-Seq experiments. A number of studies have been attempted to computationally predict miRNA TSSs. However, high-resolution condition-specific miRNA TSS prediction remains a challenging problem. Recently, deep learning models have been successfully applied to various bioinformatics problems but have not been effectively created for condition-specific miRNA TSS prediction. Here we created a two-stream deep learning model called D-miRT for computational prediction of condition-specific miRNA TSSs ( http://hulab.ucf.edu/research/projects/DmiRT/ ). D-miRT is a natural fit for the integration of low-resolution epigenetic features (DNase-Seq and histone modification data) and high-resolution sequence features. Compared with alternative computational models on different sets of training data, D-miRT outperformed all baseline models and demonstrated high accuracy for condition-specific miRNA TSS prediction tasks. Comparing with the most recent approaches on cell-specific miRNA TSS identification using cell lines that were unseen to the model training processes, D-miRT also showed superior performance. 
    more » « less
  5. Ribozymes are RNA molecules that catalyze biochemical reactions. Self-cleaving ribozymes are a common naturally occurring class of ribozymes that catalyze site-specific cleavage of their own phosphodiester backbone. In addition to their natural functions, self-cleaving ribozymes have been used to engineer control of gene expression because they can be designed to alter RNA processing and stability. However, the rational design of ribozyme activity remains challenging, and many ribozyme-based systems are engineered or improved by random mutagenesis and selection ( in vitro evolution). Improving a ribozyme-based system often requires several mutations to achieve the desired function, but extensive pairwise and higher-order epistasis prevent a simple prediction of the effect of multiple mutations that is needed for rational design. Recently, high-throughput sequencing-based approaches have produced data sets on the effects of numerous mutations in different ribozymes (RNA fitness landscapes). Here we used such high-throughput experimental data from variants of the CPEB3 self-cleaving ribozyme to train a predictive model through machine learning approaches. We trained models using either a random forest or long short-term memory (LSTM) recurrent neural network approach. We found that models trained on a comprehensive set of pairwise mutant data could predict active sequences at higher mutational distances, but the correlation between predicted and experimentally observed self-cleavage activity decreased with increasing mutational distance. Adding sequences with increasingly higher numbers of mutations to the training data improved the correlation at increasing mutational distances. Systematically reducing the size of the training data set suggests that a wide distribution of ribozyme activity may be the key to accurate predictions. Because the model predictions are based only on sequence and activity data, the results demonstrate that this machine learning approach allows readily obtainable experimental data to be used for RNA design efforts even for RNA molecules with unknown structures. The accurate prediction of RNA functions will enable a more comprehensive understanding of RNA fitness landscapes for studying evolution and for guiding RNA-based engineering efforts. 
    more » « less