Search for: All records

Abstract MotivationThe field of geometric deep learning has recently had a profound impact on several scientific domains such as protein structure prediction and design, leading to methodological advancements within and outside of the realm of traditional machine learning. Within this spirit, in this work, we introduce GCPNet, a new chirality-aware SE(3)-equivariant graph neural network designed for representation learning of 3D biomolecular graphs. We show that GCPNet, unlike previous representation learning methods for 3D biomolecules, is widely applicable to a variety of invariant or equivariant node-level, edge-level, and graph-level tasks on biomolecular structures while being able to (1) learn important chiral properties of 3D molecules and (2) detect external force fields. ResultsAcross four distinct molecular-geometric tasks, we demonstrate that GCPNet’s predictions (1) for protein–ligand binding affinity achieve a statistically significant correlation of 0.608, more than 5%, greater than current state-of-the-art methods; (2) for protein structure ranking achieve statistically significant target-local and dataset-global correlations of 0.616 and 0.871, respectively; (3) for Newtownian many-body systems modeling achieve a task-averaged mean squared error less than 0.01, more than 15% better than current methods; and (4) for molecular chirality recognition achieve a state-of-the-art prediction accuracy of 98.7%, better than any other machine learning method to date. Availability and implementationThe source code, data, and instructions to train new models or reproduce our results are freely available at https://github.com/BioinfoMachineLearning/GCPNet. 

Abstract Motivation Protein function prediction, based on the patterns of connection in a protein–protein interaction (or association) network, is perhaps the most studied of the classical, fundamental inference problems for biological networks. A highly successful set of recent approaches use random walk-based low-dimensional embeddings that tend to place functionally similar proteins into coherent spatial regions. However, these approaches lose valuable local graph structure from the network when considering only the embedding. We introduce GLIDER, a method that replaces a protein–protein interaction or association network with a new graph-based similarity network. GLIDER is based on a variant of our previous GLIDE method, which was designed to predict missing links in protein–protein association networks, capturing implicit local and global (i.e. embedding-based) graph properties. Results GLIDER outperforms competing methods on the task of predicting GO functional labels in cross-validation on a heterogeneous collection of four human protein–protein association networks derived from the 2016 DREAM Disease Module Identification Challenge, and also on three different protein–protein association networks built from the STRING database. We show that this is due to the strong functional enrichment that is present in the local GLIDER neighborhood in multiple different types of protein–protein association networks. Furthermore, we introduce the GLIDER graph neighborhood as a way for biologists to visualize the local neighborhood of a disease gene. As an application, we look at the local GLIDER neighborhoods of a set of known Parkinson’s Disease GWAS genes, rediscover many genes which have known involvement in Parkinson’s disease pathways, plus suggest some new genes to study. Availability and implementation All code is publicly available and can be accessed here: https://github.com/kap-devkota/GLIDER. Supplementary information Supplementary data are available at Bioinformatics online. 

Motivation: Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme–substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme–substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) RSs; however, hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g. hierarchical, pairwise or groupings), remains a challenge. Results: We propose an innovative general RS framework, termed Boost-RS that enhances RS performance by ‘boosting’ embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme–substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors. 

Abstract Motivation Ribosome profiling, or Ribo-seq, is the state-of-the-art method for quantifying protein synthesis in living cells. Computational analysis of Ribo-seq data remains challenging due to the complexity of the procedure, as well as variations introduced for specific organisms or specialized analyses. Results We present riboviz 2, an updated riboviz package, for the comprehensive transcript-centric analysis and visualization of Ribo-seq data. riboviz 2 includes an analysis workflow built on the Nextflow workflow management system for end-to-end processing of Ribo-seq data. riboviz 2 has been extensively tested on diverse species and library preparation strategies, including multiplexed samples. riboviz 2 is flexible and uses open, documented file formats, allowing users to integrate new analyses with the pipeline. Availability and implementation riboviz 2 is freely available at github.com/riboviz/riboviz. 

Abstract Motivation This article introduces Vivarium—software born of the idea that it should be as easy as possible for computational biologists to define any imaginable mechanistic model, combine it with existing models and execute them together as an integrated multiscale model. Integrative multiscale modeling confronts the complexity of biology by combining heterogeneous datasets and diverse modeling strategies into unified representations. These integrated models are then run to simulate how the hypothesized mechanisms operate as a whole. But building such models has been a labor-intensive process that requires many contributors, and they are still primarily developed on a case-by-case basis with each project starting anew. New software tools that streamline the integrative modeling effort and facilitate collaboration are therefore essential for future computational biologists. Results Vivarium is a software tool for building integrative multiscale models. It provides an interface that makes individual models into modules that can be wired together in large composite models, parallelized across multiple CPUs and run with Vivarium’s discrete-event simulation engine. Vivarium’s utility is demonstrated by building composite models that combine several modeling frameworks: agent-based models, ordinary differential equations, stochastic reaction systems, constraint-based models, solid-body physics and spatial diffusion. This demonstrates just the beginning of what is possible—Vivarium will be able to support future efforts that integrate many more types of models and at many more biological scales. Availability and implementation The specific models, simulation pipelines and notebooks developed for this article are all available at the vivarium-notebooks repository: https://github.com/vivarium-collective/vivarium-notebooks. Vivarium-core is available at https://github.com/vivarium-collective/vivarium-core, and has been released on Python Package Index. The Vivarium Collective (https://vivarium-collective.github.io) is a repository of freely available Vivarium processes and composites, including the processes used in Section 3. Supplementary Materials provide with an extensive methodology section, with several code listings that demonstrate the basic interfaces. Supplementary information Supplementary data are available at Bioinformatics online. 

Abstract Motivation Membrane proteins are encoded by approximately one fifth of human genes but account for more than half of all US FDA approved drug targets. Thanks to new technological advances, the number of membrane proteins archived in the PDB is growing rapidly. However, automatic identification of membrane proteins or inference of membrane location is not a trivial task. Results We present recent improvements to the RCSB Protein Data Bank web portal (RCSB PDB, rcsb.org) that provide a wealth of new membrane protein annotations integrated from four external resources: OPM, PDBTM, MemProtMD and mpstruc. We have substantially enhanced the presentation of data on membrane proteins. The number of membrane proteins with annotations available on rcsb.org was increased by ∼80%. Users can search for these annotations, explore corresponding tree hierarchies, display membrane segments at the 1D amino acid sequence level, and visualize the predicted location of the membrane layer in 3D. Availability and implementation Annotations, search, tree data and visualization are available at our rcsb.org web portal. Membrane visualization is supported by the open-source Mol* viewer (molstar.org and github.com/molstar/molstar). Supplementary information Supplementary data are available at Bioinformatics online. 

Abstract Motivation Improvements in DNA sequencing technology and computational methods have led to a substantial increase in the creation of high-quality genome assemblies of many species. To understand the biology of these genomes, annotation of gene features and other functional elements is essential; however, for most species, only the reference genome is well-annotated. Results One strategy to annotate new or improved genome assemblies is to map or ‘lift over’ the genes from a previously annotated reference genome. Here, we describe Liftoff, a new genome annotation lift-over tool capable of mapping genes between two assemblies of the same or closely related species. Liftoff aligns genes from a reference genome to a target genome and finds the mapping that maximizes sequence identity while preserving the structure of each exon, transcript and gene. We show that Liftoff can accurately map 99.9% of genes between two versions of the human reference genome with an average sequence identity >99.9%. We also show that Liftoff can map genes across species by successfully lifting over 98.3% of human protein-coding genes to a chimpanzee genome assembly with 98.2% sequence identity. Availability and implementation Liftoff can be installed via bioconda and PyPI. In addition, the source code for Liftoff is available at https://github.com/agshumate/Liftoff. Supplementary information Supplementary data are available at Bioinformatics online. 

Abstract Motivation Protein structure prediction remains as one of the most important problems in computational biology and biophysics. In the past few years, protein residue–residue contact prediction has undergone substantial improvement, which has made it a critical driving force for successful protein structure prediction. Boosting the accuracy of contact predictions has, therefore, become the forefront of protein structure prediction. Results We show a novel contact map refinement method, ContactGAN, which uses Generative Adversarial Networks (GAN). ContactGAN was able to make a significant improvement over predictions made by recent contact prediction methods when tested on three datasets including protein structure modeling targets in CASP13 and CASP14. We show improvement of precision in contact prediction, which translated into improvement in the accuracy of protein tertiary structure models. On the other hand, observed improvement over trRosetta was relatively small, reasons for which are discussed. ContactGAN will be a valuable addition in the structure prediction pipeline to achieve an extra gain in contact prediction accuracy. Availability and implementation https://github.com/kiharalab/ContactGAN. Supplementary information Supplementary data are available at Bioinformatics online. 

Abstract Summary Peptide microarrays have emerged as a powerful technology in immunoproteomics as they provide a tool to measure the abundance of different antibodies in patient serum samples. The high dimensionality and small sample size of many experiments challenge conventional statistical approaches, including those aiming to control the false discovery rate (FDR). Motivated by limitations in reproducibility and power of current methods, we advance an empirical Bayesian tool that computes local FDR statistics and local false sign rate statistics when provided with data on estimated effects and estimated standard errors from all the measured peptides. As the name suggests, the MixTwice tool involves the estimation of two mixing distributions, one on underlying effects and one on underlying variance parameters. Constrained optimization techniques provide for model fitting of mixing distributions under weak shape constraints (unimodality of the effect distribution). Numerical experiments show that MixTwice can accurately estimate generative parameters and powerfully identify non-null peptides. In a peptide array study of rheumatoid arthritis, MixTwice recovers meaningful peptide markers in one case where the signal is weak, and has strong reproducibility properties in one case where the signal is strong. Availabilityand implementation MixTwice is available as an R software package https://cran.r-project.org/web/packages/MixTwice/. Supplementary information Supplementary data are available at Bioinformatics online. 

Abstract Motivation Detailed mechanistic models of biological processes can pose significant challenges for analysis and parameter estimations due to the large number of equations used to track the dynamics of all distinct configurations in which each involved biochemical species can be found. Model reduction can help tame such complexity by providing a lower-dimensional model in which each macro-variable can be directly related to the original variables. Results We present CLUE, an algorithm for exact model reduction of systems of polynomial differential equations by constrained linear lumping. It computes the smallest dimensional reduction as a linear mapping of the state space such that the reduced model preserves the dynamics of user-specified linear combinations of the original variables. Even though CLUE works with non-linear differential equations, it is based on linear algebra tools, which makes it applicable to high-dimensional models. Using case studies from the literature, we show how CLUE can substantially lower model dimensionality and help extract biologically intelligible insights from the reduction. Availabilityand implementation An implementation of the algorithm and relevant resources to replicate the experiments herein reported are freely available for download at https://github.com/pogudingleb/CLUE. Supplementary information Supplementary data are available at Bioinformatics online.