FunHunt: model selection based on energy landscape characteristics

2008 ◽  
Vol 36 (6) ◽  
pp. 1418-1421 ◽  
Author(s):  
Nir London ◽  
Ora Schueler-Furman
Keyword(s):  
Model Selection ◽  
Interface Design ◽  
Learning Algorithm ◽  
Protein Complexes ◽  
Energy Landscape ◽  
Minimum Energy ◽  
Low Energy ◽  
General Applicability ◽  
Landscape Characteristics ◽  
Low Energy Conformations

Protein folding and binding is commonly depicted as a search for the minimum energy conformation in a vast energy landscape. Indeed, modelling of protein complex structures by RosettaDock often results in a set of low-energy conformations near the native structure. Ensembles of low-energy conformations can appear, however, in other regions of the energy landscape, especially when backbone movements occur upon binding. What then characterizes the energy landscape near the correct orientation? We have applied a machine learning algorithm to distinguish ensembles of low-energy conformations around the native conformation from other low-energy ensembles. FunHunt, the resulting classifier, identified the native orientation for 50/52 protein complexes in a test set, and for all of 12 recent CAPRI targets. FunHunt is also able to choose the near-native orientation among models created by algorithms other than RosettaDock, demonstrating its general applicability for model selection. The features used by FunHunt teach us about the nature of native interfaces. Remarkably, the energy decrease of trajectories toward near-native orientations is significantly larger than for other orientations. This provides a possible explanation for the stability of association in the native orientation. The FunHunt approach, discriminating models based on ensembles of structures that map the nearby energy landscape, can be adapted and extended to additional tasks, such as ab initio model selection, protein interface design and specificity predictions.

A FAST AND EFFECTIVE CONFORMATIONAL SEARCH METHOD FOR PEPTIDES

2003 ◽  
Vol 14 (07) ◽  
pp. 985-991 ◽  
Author(s):  
HANDAN ARKIN ◽  
TARIK ÇELIK
Keyword(s):  
Monte Carlo ◽  
Hybrid Algorithm ◽  
Energy Landscape ◽  
Search Method ◽  
Low Energy ◽  
Conformational Search ◽  
Energy Landscape Paving ◽  
Low Energy Conformations

We propose a hybrid algorithm, which combines the features of the energy landscape paving (ELP) and Monte Carlo Minimization (MCM) methods. We have tested its performance in studying the low-energy conformations of the heptapeptide deltorphin.

Structure and Conformations of GABA-Transaminase Inhibitors. IV. Transition State Analogs

1988 ◽  
Vol 41 (4) ◽  
pp. 493 ◽  
Author(s):  
PR Andrews ◽  
JM Gulbis ◽  
MN Iskander ◽  
MF Mackay ◽  
C Dipaola ◽  
...  
Keyword(s):  
Crystal Structure ◽  
Hydrogen Bonding ◽  
Transition State ◽  
Crystal Structures ◽  
Minimum Energy ◽  
Low Energy ◽  
Gaba Transaminase ◽  
Transition State Analogs ◽  
Potential Inhibitors ◽  
Low Energy Conformations

Crystal structures of three potential inhibitors [salicylamide derivative C16H15NO4 (5), pyridoxazine C11H16N2O5S (6) and benzoxazone C12H13NO4 (7).H2O] of GABA- transaminase (E.C.2.6.1.19, GABA-T) based on the calculated transition state of GABA-T were determined. The conformational analyses of these structures (non-bonded energies, MNDO,AM1) indicate that they can all fit the transition state in relatively low energy conformations. The crystal structures appear to be close to the calculated minimum energy conformations, except for the salicylamide derivative (5), which features internal hydrogen-bonding. The AM1 parametrization has been used successfully to predict two possible hydrogen-bonded conformations of (5), one of which is found in the crystal structure.

Scalable Approach to High Coverages on Oxides via Iterative Training of a Machine-Learning Algorithm

2019 ◽  
Author(s):  
Andrew Medford ◽  
Shengchun Yang ◽  
Fuzhu Liu
Keyword(s):  
Machine Learning ◽  
Chemical Potential ◽  
Learning Algorithm ◽  
Absolute Error ◽  
Low Energy ◽  
Training Data ◽  
High Coverage ◽  
Metal Compounds ◽  
Adsorption Energies ◽  
The Stability

Understanding the interaction of multiple types of adsorbate molecules on solid surfaces is crucial to establishing the stability of catalysts under various chemical environments. Computational studies on the high coverage and mixed coverages of reaction intermediates are still challenging, especially for transition-metal compounds. In this work, we present a framework to predict differential adsorption energies and identify low-energy structures under high- and mixed-adsorbate coverages on oxide materials. The approach uses Gaussian process machine-learning models with quantified uncertainty in conjunction with an iterative training algorithm to actively identify the training set. The framework is demonstrated for the mixed adsorption of CH<sub>x</sub>, NH<sub>x</sub> and OH<sub>x</sub> species on the oxygen vacancy and pristine rutile TiO<sub>2</sub>(110) surface sites. The results indicate that the proposed algorithm is highly efficient at identifying the most valuable training data, and is able to predict differential adsorption energies with a mean absolute error of ~0.3 eV based on <25% of the total DFT data. The algorithm is also used to identify 76% of the low-energy structures based on <30% of the total DFT data, enabling construction of surface phase diagrams that account for high and mixed coverage as a function of the chemical potential of C, H, O, and N. Furthermore, the computational scaling indicates the algorithm scales nearly linearly (N<sup>1.12</sup>) as the number of adsorbates increases. This framework can be directly extended to metals, metal oxides, and other materials, providing a practical route toward the investigation of the behavior of catalysts under high-coverage conditions.

scholarly journals A Q-Learning Rescheduling Approach to the Flexible Job Shop Problem Combining Energy and Productivity Objectives

2021 ◽  
Vol 13 (23) ◽  
pp. 13016
Author(s):  
Rami Naimi ◽  
Maroua Nouiri ◽  
Olivier Cardin
Keyword(s):  
Artificial Intelligence ◽  
Energy Consumption ◽  
Job Shop ◽  
Learning Algorithm ◽  
Minimum Energy ◽  
Flexible Job Shop ◽  
Q Learning ◽  
Minimum Energy Consumption ◽  
Machine Failure ◽  
Flexible Job Shop Problem

The flexible job shop problem (FJSP) has been studied in recent decades due to its dynamic and uncertain nature. Responding to a system’s perturbation in an intelligent way and with minimum energy consumption variation is an important matter. Fortunately, thanks to the development of artificial intelligence and machine learning, a lot of researchers are using these new techniques to solve the rescheduling problem in a flexible job shop. Reinforcement learning, which is a popular approach in artificial intelligence, is often used in rescheduling. This article presents a Q-learning rescheduling approach to the flexible job shop problem combining energy and productivity objectives in a context of machine failure. First, a genetic algorithm was adopted to generate the initial predictive schedule, and then rescheduling strategies were developed to handle machine failures. As the system should be capable of reacting quickly to unexpected events, a multi-objective Q-learning algorithm is proposed and trained to select the optimal rescheduling methods that minimize the makespan and the energy consumption variation at the same time. This approach was conducted on benchmark instances to evaluate its performance.

Sulfamoyl nitrenes: singlet or triplet ground state?

2018 ◽  
Vol 54 (48) ◽  
pp. 6136-6139 ◽  
Author(s):  
Yan Lu ◽  
Hongmin Li ◽  
Manabu Abe ◽  
Didier Bégué ◽  
Huabin Wan ◽  
...  
Keyword(s):  
Triplet State ◽  
Ground State ◽  
Singlet State ◽  
Minimum Energy ◽  
Closed Shell ◽  
Low Energy ◽  
Energy Minimum ◽  
Triplet Ground State ◽  
Crossing Point

Two prototypical sulfamoyl nitrenes R2NS(O)2–N (R = H and Me) in the triplet state were generated via the closed-shell singlet state by passing a low-energy minimum energy crossing point (MECP).

Spatial Structure of the Acth-(6-9)-PGP Molecule

2021 ◽  
Vol 43 (5) ◽  
pp. 500-500
Author(s):  
Namiq Akhmedov Namiq Akhmedov ◽  
Leyla Agayeva Leyla Agayeva ◽  
Gulnara Akverdieva Gulnara Akverdieva ◽  
Rena Abbasli and Larisa Ismailova Rena Abbasli and Larisa Ismailova
Keyword(s):  
Amino Acid ◽  
Spatial Structure ◽  
Main Chain ◽  
Low Energy ◽  
Dihedral Angles ◽  
Amino Acid Residues ◽  
Analysis Method ◽  
Theoretical Conformational Analysis ◽  
Energy Of Hydrogen Bonds ◽  
Low Energy Conformations

The spatial structure of ACTH-(6-9)-PGP molecule has been investigated using theoretical conformational analysis method. Amino acid sequence of the N-terminal pentapeptide fragment of His-Phe-Arg-Trp-Pro of this molecule conforms to the fragment 6-9 of ACTH hormone. Calculations of conformational states of this molecule are carried out regarding nonvalent, electrostatic and torsional interactions and the energy of hydrogen bonds. The spatial structure of the His-Phe-Arg-Trp-Pro-Gly-Pro molecule was estimated on the low–energy conformations of the N-terminal tetrapeptide fragment His-Phe-Arg-Trp and C-terminal tripeptide fragment Pro-Gly-Pro of this molecule. It is shown that the spatial structure of heptapeptide molecule can be presented by 11 low-energy forms of the main chain. The low–energy conformations of this molecule, the values of dihedral angles of the backbone and side chains of the amino acid residues were founded and the energies of intra- and inter-residual interactions were determined.

scholarly journals Enzyme-hydrolyzed Fruit of Jurinea mollis: A Rich Source of (-)-(8R,8′R)-Arctigenin

2016 ◽  
Vol 11 (10) ◽  
pp. 1934578X1601101 ◽  
Author(s):  
Rita Könye ◽  
Ágnes Evelin Ress ◽  
Anna Sólyomváry ◽  
Gergő Tóth ◽  
András Darcsi ◽  
...  
Keyword(s):  
Low Energy ◽  
Plant Tissues ◽  
Selective Isolation ◽  
Isolation Method ◽  
Specific Accumulation ◽  
Fruit Wall ◽  
Lignan Glycoside ◽  
Nmr Methods ◽  
First Time ◽  
Low Energy Conformations

In Jurinea mollis fruit, the dibenzylbutyrolactone-type lignan glycoside arctiin and its aglycone arctigenin were determined for the first time using a combination of optimized enzymatic treatment and complementary spectrometric (HPLC-MS, GC-MS) and spectroscopic (CD and NMR) methods. Analysis of separated fruit parts, i.e., the fruit wall and embryo, demonstrated the specific accumulation of arctiin, since it was exclusively found in the embryo. Arctiin in the embryo samples (71.5 mg/g) was found to be quantitatively converted into arctigenin (50.7 mg/g) by endogenous enzymatic hydrolysis, resulting in one of the highest arctigenin-containing plant tissues reported to date and allowing the selective isolation of arctigenin by our recently reported three-step isolation method. The absolute configuration of the isolated arctigenin was determined to be (-)-(8 R,8′ R). Conformational analysis of arctigenin was also performed, resulting in three major low energy conformations.

scholarly journals Braiding topology and the energy landscape of chromosome organization proteins

2019 ◽  
Vol 117 (3) ◽  
pp. 1468-1477 ◽  
Author(s):  
Dana Krepel ◽  
Aram Davtyan ◽  
Nicholas P. Schafer ◽  
Peter G. Wolynes ◽  
José N. Onuchic
Keyword(s):  
Structural Information ◽  
Protein Complexes ◽  
Energy Landscape ◽  
Critical Role ◽  
Coiled Coil ◽  
Structural Data ◽  
Atomic Scale ◽  
Integrative Approach ◽  
Chromosome Organization ◽  
Conformational Ensemble

Assemblies of structural maintenance of chromosomes (SMC) proteins and kleisin subunits are essential to chromosome organization and segregation across all kingdoms of life. While structural data exist for parts of the SMC−kleisin complexes, complete structures of the entire complexes have yet to be determined, making mechanistic studies difficult. Using an integrative approach that combines crystallographic structural information about the globular subdomains, along with coevolutionary information and an energy landscape optimized force field (AWSEM), we predict atomic-scale structures for several tripartite SMC−kleisin complexes, including prokaryotic condensin, eukaryotic cohesin, and eukaryotic condensin. The molecular dynamics simulations of the SMC−kleisin protein complexes suggest that these complexes exist as a broad conformational ensemble that is made up of different topological isomers. The simulations suggest a critical role for the SMC coiled-coil regions, where the coils intertwine with various linking numbers. The twist and writhe of these braided coils are coupled with the motion of the SMC head domains, suggesting that the complexes may function as topological motors. Opening, closing, and translation along the DNA of the SMC−kleisin protein complexes would allow these motors to couple to the topology of DNA when DNA is entwined with the braided coils.

A Statistical Design of Experiments Approach to Machine Learning Model Selection in Engineering Applications

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
T. Munger ◽  
S. Desa
Keyword(s):  
Machine Learning ◽  
Model Selection ◽  
Real World ◽  
Ad Hoc ◽  
Learning Algorithm ◽  
Random Search ◽  
Statistical Design ◽  
Orthogonal Arrays ◽  
Statistical Design Of Experiments ◽  
Engineering Applications

Abstract An important but insufficiently addressed issue for machine learning in engineering applications is the task of model selection for new problems. Existing approaches to model selection generally focus on optimizing the learning algorithm and associated hyperparameters. However, in real-world engineering applications, the parameters that are external to the learning algorithm, such as feature engineering, can also have a significant impact on the performance of the model. These external parameters do not fit into most existing approaches for model selection and are therefore often studied ad hoc or not at all. In this article, we develop a statistical design of experiment (DOEs) approach to model selection based on the use of the Taguchi method. The key idea is that we use orthogonal arrays to plan a set of build-and-test experiments to study the external parameters in combination with the learning algorithm. The use of orthogonal arrays maximizes the information learned from each experiment and, therefore, enables the experimental space to be explored extremely efficiently in comparison with grid or random search methods. We demonstrated the application of the statistical DOE approach to a real-world model selection problem involving predicting service request escalation. Statistical DOE significantly reduced the number of experiments necessary to fully explore the external parameters for this problem and was able to successfully optimize the model with respect to the objective function of minimizing total cost in addition to the standard evaluation metrics such as accuracy, f-measure, and g-mean.

Sign in / Sign up

Export Citation Format

Share Document