Machine learning accelerates MD-based binding pose prediction between ligands and proteins

Motivation

Fast and accurate prediction of protein–ligand binding structures is indispensable for structure-based drug design and accurate estimation of binding free energy of drug candidate molecules in drug discovery. Recently, accurate pose prediction methods based on short Molecular Dynamics (MD) simulations, such as MM-PBSA and MM-GBSA, among generated docking poses have been used. Since molecular structures obtained from MD simulation depend on the initial condition, taking the average over different initial conditions leads to better accuracy. Prediction accuracy of protein–ligand binding poses can be improved with multiple runs at different initial velocity.

Results

This paper shows that a machine learning method, called Best Arm Identification, can optimally control the number of MD runs for each binding pose. It allows us to identify a correct binding pose with a minimum number of total runs. Our experiment using three proteins and eight inhibitors showed that the computational cost can be reduced substantially without sacrificing accuracy. This method can be applied for controlling all kinds of molecular simulations to obtain best results under restricted computational resources.

Availability and implementation

Code and data are available on GitHub at https://github.com/tsudalab/bpbi.

Supplementary information

Supplementary data are available at Bioinformatics online.

Hunting for Organic Molecules with Artificial Intelligence: Molecules Optimized for Desired Excitation Energies

This work presents a proof-of-concept study in artificial-intelligence-assisted (AI-assisted) chemistry where a machine-learning-based molecule generator is coupled with density functional theory (DFT) calculations, synthesis, and measurement. Although deep-learning-based molecule generators have shown promise, it is unclear to what extent they can be useful in real-world materials development. To assess the reliability of AI-assisted chemistry, we prepared a platform using a molecule generator and a DFT simulator, and attempted to generate novel photofunctional molecules whose lowest excited states lie at desired energetic levels. A 10 day run on the 12-core server discovered 86 potential photofunctional molecules around target lowest excitation levels, designated as 200, 300, 400, 500, and 600 nm. Among the molecules discovered, six were synthesized, and five were confirmed to reproduce DFT predictions in ultraviolet visible absorption measurements. This result shows the potential of AI-assisted chemistry to discover ready-to-synthesize novel molecules with modest computational resources.

Machine-Learning-Guided Mutagenesis for Directed Evolution of Fluorescent Proteins

Molecular evolution based on mutagenesis is widely used in protein engineering. However, optimal proteins are often difficult to obtain due to a large sequence space. Here, we propose a novel approach that combines molecular evolution with machine learning. In this approach, we conduct two rounds of mutagenesis where an initial library of protein variants is used to train a machine-learning model to guide mutagenesis for the second-round library. This enables us to prepare a small library suited for screening experiments with high enrichment of functional proteins. We demonstrated a proof-of-concept of our approach by altering the reference green fluorescent protein (GFP) so that its fluorescence is changed into yellow. We successfully obtained a number of proteins showing yellow fluorescence, 12 of which had longer wavelengths than the reference yellow fluorescent protein (YFP). These results show the potential of our approach as a powerful method for directed evolution of fluorescent proteins.

Functional Nanoparticles-Coated Nanomechanical Sensor Arrays for Machine Learning-Based Quantitative Odor Analysis

A sensing signal obtained by measuring an odor usually contains varied information that reflects an origin of the odor itself, while an effective approach is required to reasonably analyze informative data to derive the desired information. Herein, we demonstrate that quantitative odor analysis was achieved through systematic material design-based nanomechanical sensing combined with machine learning. A ternary mixture consisting of water, ethanol, and methanol was selected as a model system where a target molecule coexists with structurally similar species in a humidified condition. To predict the concentration of each species in the system via the data-driven approach, six types of nanoparticles functionalized with hydroxyl, aminopropyl, phenyl, and/or octadecyl groups were synthesized as a receptor coating of a nanomechanical sensor. Then, a machine learning model based on Gaussian process regression was trained with sensing data sets obtained from the samples with diverse concentrations. As a result, the octadecyl-modified nanoparticles enhanced prediction accuracy for water while the use of both octadecyl and aminopropyl groups was indicated to be a key for a better prediction accuracy for ethanol and methanol. As the prediction accuracy for ethanol and methanol was improved by introducing two additional nanoparticles with finely controlled octadecyl and aminopropyl amount, the feedback obtained by the present machine learning was effectively utilized to optimize material design for better performance. We demonstrate through this study that various information which was extracted from plenty of experimental data sets was successfully combined with our knowledge to produce wisdom for addressing a critical issue in gas phase sensing.

ChemTS: an efficient python library for de novo molecular generation

Automatic design of organic materials requires black-box optimization in a vast chemical space. In conventional molecular design algorithms, a molecule is built as a combination of predetermined fragments. Recently, deep neural network models such as variational autoencoders and recurrent neural networks (RNNs) are shown to be effective in de novo design of molecules without any predetermined fragments. This paper presents a novel Python library ChemTS that explores the chemical space by combining Monte Carlo tree search and an RNN. In a benchmarking problem of optimizing the octanol-water partition coefficient and synthesizability, our algorithm showed superior efficiency in finding high-scoring molecules. ChemTS is available at https://github.com/tsudalab/ChemTS.

RNA inverse folding using Monte Carlo tree search

Background

Artificially synthesized RNA molecules provide important ways for creating a variety of novel functional molecules. State-of-the-art RNA inverse folding algorithms can design simple and short RNA sequences of specific GC content, that fold into the target RNA structure. However, their performance is not satisfactory in complicated cases.

Result

We present a new inverse folding algorithm called MCTS-RNA, which uses Monte Carlo tree search (MCTS), a technique that has shown exceptional performance in Computer Go recently, to represent and discover the essential part of the sequence space. To obtain high accuracy, initial sequences generated by MCTS are further improved by a series of local updates. Our algorithm has an ability to control the GC content precisely and can deal with pseudoknot structures. Using common benchmark datasets for evaluation, MCTS-RNA showed a lot of promise as a standard method of RNA inverse folding.

Conclusion

MCTS-RNA is available at https://github.com/tsudalab/MCTS-RNA.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1882-7) contains supplementary material, which is available to authorized users.

Machine learning reveals orbital interaction in materials

We propose a novel representation of materials named an 'orbital-field matrix (OFM)', which is based on the distribution of valence shell electrons. We demonstrate that this new representation can be highly useful in mining material data. Experimental investigation shows that the formation energies of crystalline materials, atomization energies of molecular materials, and local magnetic moments of the constituent atoms in bimetal alloys of lanthanide metal and transition-metal can be predicted with high accuracy using the OFM. Knowledge regarding the role of the coordination numbers of the transition-metal and lanthanide elements in determining the local magnetic moments of the transition-metal sites can be acquired directly from decision tree regression analyses using the OFM.

MDTS: automatic complex materials design using Monte Carlo tree search

Complex materials design is often represented as a black-box combinatorial optimization problem. In this paper, we present a novel python library called MDTS (Materials Design using Tree Search). Our algorithm employs a Monte Carlo tree search approach, which has shown exceptional performance in computer Go game. Unlike evolutionary algorithms that require user intervention to set parameters appropriately, MDTS has no tuning parameters and works autonomously in various problems. In comparison to a Bayesian optimization package, our algorithm showed competitive search efficiency and superior scalability. We succeeded in designing large Silicon-Germanium (Si-Ge) alloy structures that Bayesian optimization could not deal with due to excessive computational cost. MDTS is available at https://github.com/tsudalab/MDTS.

LAMPLINK: detection of statistically significant SNP combinations from GWAS data

One of the major issues in genome-wide association studies is to solve the missing heritability problem. While considering epistatic interactions among multiple SNPs may contribute to solving this problem, existing software cannot detect statistically significant high-order interactions. We propose software named LAMPLINK, which employs a cutting-edge method to enumerate statistically significant SNP combinations from genome-wide case-control data. LAMPLINK is implemented as a set of additional functions to PLINK, and hence existing procedures with PLINK can be applicable. Applied to the 1000 Genomes Project data, LAMPLINK detected a combination of five SNPs that are statistically significantly accumulated in the Japanese population.

AVAILABILITY AND IMPLEMENTATION

LAMPLINK is available at http://a-terada.github.io/lamplink/ CONTACT: terada@cbms.k.u-tokyo.ac.jp or sese.jun@aist.go.jpSupplementary information: Supplementary data are available at Bioinformatics online.

CellTree: an R/bioconductor package to infer the hierarchical structure of cell populations from single-cell RNA-seq data

BACKGROUND

Single-cell RNA sequencing is fast becoming one the standard method for gene expression measurement, providing unique insights into cellular processes. A number of methods, based on general dimensionality reduction techniques, have been suggested to help infer and visualise the underlying structure of cell populations from single-cell expression levels, yet their models generally lack proper biological grounding and struggle at identifying complex differentiation paths.

RESULTS

Here we introduce cellTree: an R/Bioconductor package that uses a novel statistical approach, based on document analysis techniques, to produce tree structures outlining the hierarchical relationship between single-cell samples, while identifying latent groups of genes that can provide biological insights.

CONCLUSIONS

With cellTree, we provide experimentalists with an easy-to-use tool, based on statistically and biologically-sound algorithms, to efficiently explore and visualise single-cell RNA data. The cellTree package is publicly available in the online Bionconductor repository at: http://bioconductor.org/packages/cellTree/ .

Cervical Invasion of Endometrial Carcinoma — Evaluation by Parasagittal MR Imaging

Twenty-seven consecutive patients were examined by T2-(1 800/70 ms) and postcontrast T1-weighted (600/15) spin echo (SE) or dynamic (200/15) SE MR imaging to determine the usefulness of parasagittal MR imaging in assessing cervical invasion of endometrial carcinoma. The images were obtained in a direction parallel to the longitudinal axis of the uterus (parasagittal). The cervical epithelium, being hyperintense on the late phase dynamic and postcontrast T1-weighted SE images, had disappeared partially or totally in all 4 patients with cervical invasion. The enhanced cervical epithelium was completely seen in one patient with the tumor protruding into the cervical canal in a polyp-like form without cervical epithelial invasion. The same was also seen in the 22 patients with the tumor remaining in the corpus cavity. The enhanced parasagittal MR images facilitated the evaluation of the extent of the endometrial carcinoma.

Multishot Echo-Planar Imaging with Gadopentetate Dimeglumine: Preliminary study of efficacy for detection of hypovascular metastatic liver tumors

Objective: To evaluate the usefulness of sequential T2-weighted spin-echo type multishot echo-planar (T2-EP) imaging with gadopentetate dimeglumine for the detection of hypovascular metastatic liver tumors.

Material and Methods: Fifteen consecutive patients with 56 proven hypovascular metastatic liver tumors were included in the study. Three observers blindly and independently read the whole-liver images obtained with T2-weighted spin-echo, T2-weighted single-shot fast spin-echo, T1-weighted fast multiplanar spoiled GRASS and T2-EP images obtained before and 25, 60, 90 and 120 s after injection of 0.2 mmol/kg b.w. of gadopentetate dimeglumine. The diagnostic accuracy was estimated by calculating the area under the observer-specific binomial receiver operating characteristics curves (Az).

Results: T2-EP images obtained 60 s after contrast injection showed significantly higher contrast-to-noise (C/N) ratios than the other imaging techniques. A combination of all phases of the T2-EP images produced the highest sensitivity and specificity. In terms of the Az value, the diagnostic accuracy for tumor detection achieved with a combination of all phases of the T2-EP images was significantly higher than that with T1-SPGR and T2-SSFSE images ( p < 0.01). The Az values of the T2-EP images (Az = 0.975) were higher than those of T2-CSE images (Az = 0.948), but the difference was not significant.

Conclusion: Our preliminary study revealed that sequential imaging with enhanced T2-EP images was useful for the detection of hypovascular metastatic liver tumors because of its superior C/N ratio and sensitivity.

Detection of Viable Tumor Cells in Hepatocellular Carcinoma following Transcatheter Arterial Chemoembolization with Iodized Oil

To evaluate the effect of transcatheter arterial chemoembolization (TACE) with iodized oil for hepatocellular carcinoma (HCC), dynamic turbo-fast low angle shot (turbo-FLASH) (TR/TE/flip angle/TI, 8.5/4.6/10/200) MR imaging with gadopentetate dimeglumine was performed in 10 patients with HCC after TACE with iodized oil and before partial hepatectomy. Immediately after 0.05 mmol/kg b.w. of gadopentetate dimeglumine was administered intravenously, 10 images were obtained in the first 20 s (early phase). Then, one image every 30 s from 1 to 3 min (late phase), and images at 5 min and 7 min (delayed phase) were obtained serially. In the early phase, HCC showed no enhancement in 5 patients, partial hyperintense enhancement in 4, and total hyperintense enhancement in one. Viable regions of the tumor, evaluated at histopathology, showed hyperintense enhancement relative to the surrounding liver parenchyma in the early phase, while necrotic regions showed no enhancement. Both viable and necrotic regions showed lower signal intensities than the surrounding liver parenchyma in both late and delayed phases. By using dynamic turbo-FLASH MR imaging, we were able to accurately evaluate the effect of TACE with iodized oil for HCC in 8 of the 10 patients. In 2 patients, in whom small viable cells were seen in the HCC, viable regions could not be detected with our technique. It is concluded that turbo-FLASH dynamic MR imaging was useful for evaluating the effect of TACE for HCC.