VQLM: A Visual Query Language for Macromolecular Structural Databases

AAAI Conferences

They do this by providing a variety of data obtained under a number of different experimental conditions. Many new tools have been developed recently to aid in exploratory analysis of structural data. However, some queries of interest still require considerable manual filtering of data. In particular, studies attempting to make generalizations about complex axrangements of atoms or building blocks in macromolecular structures cannot be approached directly with existing tools. Such studies are frequently carried out on only a few structures or else require a laborintensive process.


Feature Selection Methods for Improving Protein Structure Prediction with Rosetta

Neural Information Processing Systems

Rosetta is one of the leading algorithms for protein structure prediction today. It is a Monte Carlo energy minimization method requiring many random restarts to find structures with low energy. In this paper we present a resampling technique for structure prediction of small alpha/beta proteins using Rosetta. From an initial roundof Rosetta sampling, we learn properties of the energy landscape that guide a subsequent round of sampling toward lower-energy structures. Rather than attempt to fit the full energy landscape, we use feature selection methods--both L1-regularized linear regression and decision trees--to identify structural features that give rise to low energy. We then enrich these structural features in the second sampling round. Results are presented across a benchmark set of nine small alpha/beta proteinsdemonstrating that our methods seldom impair, and frequently improve, Rosetta's performance.


Why-silk-orb-weaver-spiders-don-t-spin-control.html?ITO=1490&ns_mchannel=rss&ns_campaign=1490

Daily Mail

To learn more about dragline silk's tortional abilties, the researchers used a torsion pendulum - the same tool used by Henry Cavendish to weigh the Earth in the 1790s - to investigate dragline silk from two species of golden silk orb weavers, Nephila edulis and Nephila pilipes. To learn more about dragline silk's tortional abilties, the researchers used a torsion pendulum - the same tool used by Henry Cavendish to weigh the Earth in the 1790s - to investigate dragline silk from two species of golden silk orb weavers, Nephila edulis and Nephila pilipes. This microscopic image shows the glands in a spider's abdomen from which researchers collected double threads of dragline silk The researcher collected strands of silk from captive spiders, and then suspended the strands inside a cylinder - using two washers at the end to mimic a spider. The researchers used a torsion pendulum to investigate dragline silk's tortional abilties from two species of golden silk orb weavers, Nephila edulis (right) and Nephila pilipes (left) This deformation means that the silk releases more than 75 percent of its potential energy, and the oscillations rapidly slow, and after twisting, the silk partially snaps back.


Variational Selection of Features for Molecular Kinetics

arXiv.org Machine Learning

The modeling of atomistic biomolecular simulations using kinetic models such as Markov state models (MSMs) has had many notable algorithmic advances in recent years. The variational principle has opened the door for a nearly fully automated toolkit for selecting models that predict the long-time kinetics from molecular dynamics simulations. However, one yet-unoptimized step of the pipeline involves choosing the features, or collective variables, from which the model should be constructed. In order to build intuitive models, these collective variables are often sought to be interpretable and familiar features, such as torsional angles or contact distances in a protein structure. However, previous approaches for evaluating the chosen features rely on constructing a full MSM, which in turn requires additional hyperparameters to be chosen, and hence leads to a computationally expensive framework. Here, we present a method to optimize the feature choice directly, without requiring the construction of the final kinetic model. We demonstrate our rigorous preprocessing algorithm on a canonical set of twelve fast-folding protein simulations, and show that our procedure leads to more efficient model selection.


Computing Committor Functions for the Study of Rare Events Using Deep Learning

arXiv.org Machine Learning

Understanding transition events between metastable states is of great importance in the applied sciences. Wellknown examples of the transition events include nucleation events during phase transitions, conformational changes of bio-molecules, dislocation dynamics in crystalline solids, etc. The long time scale associated with these events is a consequence of the disparity between the effective thermal energy and typical energy barrier of the systems. The dynamics proceeds by long waiting periods around metastable states followed by sudden jumps from one state to another. For this reason, the transition event is called rare event. The main objective in the study of rare events is to understand the transition mechanism, such as the transition pathway and transition states.