Multi-task bioassay pre-training for protein-ligand binding affinity prediction.

Protein-ligand binding affinity (PLBA) prediction is the fundamental task in drug discovery. Recently, various deep learning-based models predict binding affinity by incorporating the three-dimensional (3D) structure of protein-ligand complexes as input and achieving astounding progress. However, due to the scarcity of high-quality training data, the generalization ability of current models is still limited. Although there is a vast amount of affinity data available in large-scale databases such as ChEMBL, issues such as inconsistent affinity measurement labels (i.e. IC50, Ki, Kd), different experimental conditions, and the lack of available 3D binding structures complicate the development of high-precision affinity prediction models using these data. To address these issues, we (i) propose Multi-task Bioassay Pre-training (MBP), a pre-training framework for structure-based PLBA prediction; (ii) construct a pre-training dataset called ChEMBL-Dock with more than 300k experimentally measured affinity labels and about 2.8M docked 3D structures. By introducing multi-task pre-training to treat the prediction of different affinity labels as different tasks and classifying relative rankings between samples from the same bioassay, MBP learns robust and transferrable structural knowledge from our new ChEMBL-Dock dataset with varied and noisy labels. Experiments substantiate the capability of MBP on the structure-based PLBA prediction task. To the best of our knowledge, MBP is the first affinity pre-training model and shows great potential for future development. MBP web-server is now available for free at: https://huggingface.co/spaces/jiaxianustc/mbp.

Towards Exploring Large Molecular Space: An Efficient Chemical Genetic Algorithm.

Generating molecules with desired properties is an important task in chemistry and pharmacy. An efficient method may have a positive impact on finding drugs to treat diseases like COVID-19. Data mining and artificial intelligence may be good ways to find an efficient method. Recently, both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule's properties. However, existing methods need to be improved in efficiency and performance. To solve these problems, we propose a method named the Chemical Genetic Algorithm for Large Molecular Space (CALM). Specifically, CALM employs a scalable and efficient molecular representation called molecular matrix. Then, we design corresponding crossover, mutation, and mask operators inspired by domain knowledge and previous studies. We apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular optimization. The results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods, where the z tests performed on the results of several experiments show that our method is more than 99% likely to be significant. At the same time, based on the experimental results, we point out the insufficiency in the experimental evaluation standard which affects the fair evaluation of previous work. Supplementary Information: The online version contains supplementary material available at 10.1007/s11390-021-0970-3.

Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers.

Despite the remarkable progress of machine learning (ML) techniques in chemistry, modeling the optoelectronic properties of long conjugated oligomers and polymers with ML remains challenging due to the difficulty in obtaining sufficient training data. Here, we use transfer learning to address the data scarcity issue by pre-training graph neural networks using data from short oligomers. With only a few hundred training data, we are able to achieve an average error of about 0.1 eV for the excited-state energy of oligothiophenes against time-dependent density functional theory (TDDFT) calculations. We show that the success of our transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers. Finally, we demonstrate the transferability of our approach by modeling the lowest-lying excited-state energies of poly(3-hexylthiophene) in its single-crystal and solution phases using the transfer learning models trained with the data of gas-phase oligothiophenes. The transfer learning predicted excited-state energy distributions agree quantitatively with TDDFT calculations and capture some important qualitative features observed in experimental absorption spectra.

A Graph-Based Author Name Disambiguation Method and Analysis via Information Theory.

Name ambiguity, due to the fact that many people share an identical name, often deteriorates the performance of information integration, document retrieval and web search. In academic data analysis, author name ambiguity usually decreases the analysis performance. To solve this problem, an author name disambiguation task is designed to divide documents related to an author name reference into several parts and each part is associated with a real-life person. Existing methods usually use either attributes of documents or relationships between documents and co-authors. However, methods of feature extraction using attributes cause inflexibility of models while solutions based on relationship graph network ignore the information contained in the features. In this paper, we propose a novel name disambiguation model based on representation learning which incorporates attributes and relationships. Experiments on a public real dataset demonstrate the effectiveness of our model and experimental results demonstrate that our solution is superior to several state-of-the-art graph-based methods. We also increase the interpretability of our method through information theory and show that the analysis could be helpful for model selection and training progress.

Investigations on acousto-optically Q-switched frequency-shifted feedback laser with Nd:YVO(4) crystal.

An acousto-optically Q-switched frequency-shifted feedback (FSF) diode-pumped laser with a Nd:YVO(4) crystal is demonstrated. The laser emits more than 1W average power with multi-ten ns duration at up to 50 kHz repetition rate, and peak power higher than 1 kW is achieved at frequency of 20 kHz. This kind of pulsed laser has special value for some applications with outstanding features of broadband continuous spectrum and chirping frequency in the oscillation spectrum. Simulation results of the FSF laser through rate equations in Q-switched regime are also presented.