Application of TensorFlow to recognition of visualized results of fragment molecular orbital (FMO) calculations

We have applied Google's TensorFlow deep learning toolkit to recognize the visualized results of the fragment molecular orbital (FMO) calculations. Typical protein structures of alpha-helix and beta-sheet provide some characteristic patterns in the two-dimensional map of inter-fragment interaction energy termed as IFIE-map (Kurisaki et al., Biophys. Chem. 130 (2007) 1). A thousand of IFIE-map images with labels depending on the existences of alpha-helix and beta-sheet were prepared by employing 18 proteins and 3 non-protein systems and were subjected to training by TensorFlow. Finally, TensorFlow was fed with new data to test its ability to recognize the structural patterns. We found that the characteristic structures in test IFIE-map images were judged successfully. Thus the ability of pattern recognition of IFIE-map by TensorFlow was proven.

[1]  Kaori Fukuzawa,et al.  Fragment molecular orbital (FMO) study on stabilization mechanism of neuro-oncological ventral antigen (NOVA)–RNA complex system , 2010 .

[2]  Junwei Zhang,et al.  VISCANA: Visualized Cluster Analysis of Protein-Ligand Interaction Based on the ab Initio Fragment Molecular Orbital Method for Virtual Ligand Screening , 2006, J. Chem. Inf. Model..

[3]  Vijay S. Pande,et al.  Low Data Drug Discovery with One-Shot Learning , 2016, ACS central science.

[4]  K. Kitaura,et al.  Fragment molecular orbital method: an approximate computational method for large molecules , 1999 .

[5]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[6]  Kazuo Kitaura,et al.  Exploring chemistry with the fragment molecular orbital method. , 2012, Physical chemistry chemical physics : PCCP.

[7]  Umpei Nagashima,et al.  A parallelized integral-direct second-order Møller–Plesset perturbation theory method with a fragment molecular orbital scheme , 2004 .

[8]  C. Hu,et al.  Peptoid nanotubes: an oligomer macrocycle that reversibly sequesters water via single-crystal-to-single-crystal transformations. , 2013, Chemical communications.

[9]  M. Scheffler,et al.  The face of crystals: insightful classification using deep learning , 2017 .

[10]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Abhinav Vishnu,et al.  Deep learning for computational chemistry , 2017, J. Comput. Chem..

[12]  David W Toth,et al.  The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics , 2017, Chemical science.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Kaori Fukuzawa,et al.  A configuration analysis for fragment interaction , 2005 .

[15]  Kaori Fukuzawa,et al.  Explicit solvation of a single-stranded DNA, a binding protein, and their complex: a suitable protocol for fragment molecular orbital calculation , 2017 .

[16]  Kaori Fukuzawa,et al.  Possibility of mutation prediction of influenza hemagglutinin by combination of hemadsorption experiment and quantum chemical calculation for antibody binding. , 2009, The journal of physical chemistry. B.

[17]  Spencer R Pruitt,et al.  Fragmentation methods: a route to accurate calculations on large systems. , 2012, Chemical reviews.

[18]  J. Pople,et al.  Self—Consistent Molecular Orbital Methods. XII. Further Extensions of Gaussian—Type Basis Sets for Use in Molecular Orbital Studies of Organic Molecules , 1972 .

[19]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[20]  Yuto Komeiji,et al.  Visualization analysis of inter-fragment interaction energies of CRP-cAMP-DNA complex based on the fragment molecular orbital method. , 2007, Biophysical chemistry.

[21]  Kaori Fukuzawa,et al.  Large scale FMO-MP2 calculations on a massively parallel-vector computer , 2008 .

[22]  Yuji Mochizuki,et al.  Large scale MP2 calculations with fragment molecular orbital scheme , 2004 .

[23]  Holger Gohlke,et al.  The Amber biomolecular simulation programs , 2005, J. Comput. Chem..

[24]  Kazuo Kitaura,et al.  The Fragment Molecular Orbital Method: Practical Applications to Large Molecular Systems , 2009 .

[25]  Yuto Komeiji,et al.  Electron-correlated fragment-molecular-orbital calculations for biomolecular and nano systems. , 2014, Physical chemistry chemical physics : PCCP.