Dataset Information

Learning to translate sequence and structure to function: identifying DNA binding and membrane binding proteins.

ABSTRACT: A protein's function depends in a large part on interactions with other molecules. With an increasing number of protein structures becoming available every year, a corresponding structural annotation approach identifying such interactions grows more expedient. At the same time, machine learning has gained popularity in bioinformatics providing robust annotation of genes and proteins without sequence homology. Here we have developed a general machine learning protocol to identify proteins that bind DNA and membrane. In general, there is no theory or even rule of thumb to pick the best machine learning algorithm. Thus, a systematic comparison of several classification algorithms known to perform well is investigated. Indeed, the boosted tree classifier is found to give the best performance, achieving 93% and 88% accuracy to discriminate non-homologous proteins that bind membrane and DNA, respectively, significantly outperforming all previously published works. We also attempted to address the importance of the attributes in function prediction and the relationships between relevant attributes. A graphical model based on boosted trees is applied to study the important features in discriminating DNA-binding proteins. In summary, the current protocol identified physical features important in DNA and membrane binding, rather than annotating function through sequence similarity.

SUBMITTER: Langlois RE

PROVIDER: S-EPMC2706547 | biostudies-literature | 2007 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Learning to translate sequence and structure to function: identifying DNA binding and membrane binding proteins.

Langlois Robert E RE Carson Matthew B MB Bhardwaj Nitin N Lu Hui H

Annals of biomedical engineering 20070413 6

A protein's function depends in a large part on interactions with other molecules. With an increasing number of protein structures becoming available every year, a corresponding structural annotation approach identifying such interactions grows more expedient. At the same time, machine learning has gained popularity in bioinformatics providing robust annotation of genes and proteins without sequence homology. Here we have developed a general machine learning protocol to identify proteins that bi ...[more]

PMID: 17436108

Similar Datasets

Project description:Studies on four membrane protein systems, which combine information derived from crystal structures and biophysical studies have emphasized, as a precursor to crystallization, demonstration of functional activity. These assays have relied on sensitive spectrophotometric, electrophysiological, and microbiological assays of activity to select purification procedures that lead to functional complexes and with greater likelihood to successful crystallization: (I), Hetero-oligomeric proteins involved in electron transport/proton translocation. (1) Crystal structures of the eight subunit hetero-oligomeric trans-membrane dimeric cytochrome b(6)f complex were obtained from cyanobacteria using a protocol that allowed an analysis of the structure and function of internal lipids at specific intra-membrane, intra-protein sites. Proteolysis and monomerization that inactivated the complex and prevented crystallization was minimized through the use of filamentous cyanobacterial strains that seem to have a different set of membrane-active proteases. (2) An NADPH-quinone oxido-reductase isolated from cyanobacteria contains an expanded set of 17 monotopic and polytopic hetero-subunits. (II) ?-Barrel outer membrane proteins (OMPs). High resolution structures of the vitamin B(12) binding protein, BtuB, solved in meso and in surfo, provide the best example of the differences in such structures that were anticipated in the first application of the lipid cubic phase to membrane proteins [1]. A structure of the complex of BtuB with the colicin E3 and E2 receptor binding domain established a "fishing pole" model for outer membrane receptor function in cellular import of nuclease colicins. (III) A modified faster purification procedure contributed to significantly improved resolution (1.83Å) of the universal porin, OmpF, the first membrane protein for which meaningful 3D crystals have been obtained [2]. A crystal structure of the N-terminal translocation domain of colicin E3 complexed to OmpF established the role of OmpF as an import channel for colicin nuclease cytotoxins. (IV) ?-Synuclein, associated with the etiology of Parkinson's Disease, is an example of a protein, which is soluble and disordered in solution, but which can assume an ordered predominantly ?-helical conformation upon binding to membranes. When subjected in its membrane-bound form to a trans-membrane electrical potential, ?-synuclein can form voltage-gated ion channels. Summary of methods to assay functions/activities: (i) sensitive spectrophotometric assay to measure electron transfer activities; (ii) hydrophobic chromatography to deplete lipids, allowing reconstitution with specific lipids for studies on lipid-protein interactions; (iii) microbiological screen to assay high affinity binding of colicin receptor domains to Escherichia coli outer membrane receptors; (iv) electrophysiology/channel analysis (a) to select channel-occluding ligands for co-crystallization with ion channels of OmpF, and (b) to provide a unique description of voltage-gated ion channels of ?-synuclein.

Project description: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.

Dataset Information

Learning to translate sequence and structure to function: identifying DNA binding and membrane binding proteins.

Publications

Learning to translate sequence and structure to function: identifying DNA binding and membrane binding proteins.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets