Alkaloids, a class of organic compounds that contain nitrogen bases, are mainly synthesized as secondary metabolites in plants and fungi, and they have a wide range of bioactivities. Although there are thousands of compounds in this class, few of their biosynthesis pathways are fully identified. In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network. Molecular similarity is a crucial metric in the analysis of qualitative structure–activity relationships. However, it is sometimes difficult for current fingerprint representations to emphasize specific features for the target problems efficiently. It is advantageous to allow the model to select the appropriate features according to data-driven decisions for extracting more useful information, which influences a classification or regression problem substantially. In this study, we applied a neural network architecture for undirected graph representation of molecules. By encoding a molecule as an abstract graph and applying "convolution" on the graph and training the weight of the neural network framework, the neural network can optimize feature selection for the training problem. By incorporating the effects from adjacent atoms recursively, graph convolutional neural networks can extract the features of latent atoms that represent chemical features of a molecule efficiently. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%. We have showed that our model can predict more accurately compared to the random forest and general neural network when the variables and fingerprints are not selected, while the performance is comparable when we carefully select 507 variables from 18000 dimensions of descriptors. The prediction of pathways contributes to understanding of alkaloid synthesis mechanisms and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 12000 alkaloids found in various organisms and found power-low-like distribution.

Background: Social skills training by human trainers is a well-established method to provide appropriate social interaction skills and strengthen social self-efficacy. In our previous work, we attempted to automate social skills training by developing a virtual agent that taught social skills through interaction. Previous research has not investigated the visual design of virtual agents for social skills training. Thus, we investigated the effect of virtual agent visual design on automated social skills training. Objective: The 3 main purposes of this research were to investigate the effect of virtual agent appearance on automated social skills training, the relationship between acceptability and other measures (eg, likeability, realism, and familiarity), and the relationship between likeability and individual user characteristics (eg, gender, age, and autistic traits). Methods: We prepared images and videos of a virtual agent, and 1218 crowdsourced workers rated the virtual agents through a questionnaire. In designing personalized virtual agents, we investigated the acceptability, likeability, and other impressions of the virtual agents and their relationship to individual characteristics. Results: We found that there were differences between the virtual agents in all measures (P<.001). A female anime-type virtual agent was rated as the most likeable. We also confirmed that participants’ gender, age, and autistic traits were related to their ratings. Conclusions: We confirmed the effect of virtual agent design on automated social skills training. Our findings are important in designing the appearance of an agent for use in personalized automated social skills training.

Directly translating spoken utterances from a source language to a target language is challenging because it requires a fundamental transformation in both linguistic and para/non-linguistic features. Traditional speech-to-speech translation approaches concatenate automatic speech recognition (ASR), text-to-text machine translation (MT), and text-to-speech synthesizer (TTS) by text information. The current state-of-the-art models for ASR, MT, and TTS have mainly been built using deep neural networks, in particular, an attention-based encoder-decoder neural network with an attention mechanism. Recently, several works have constructed end-to-end direct speech-to-text translation by combining ASR and MT into a single model. However, the usefulness of these models has only been investigated on language pairs of similar syntax and word order (e.g., English-French or English-Spanish). For syntactically distant language pairs (e.g., English-Japanese), speech translation requires distant word reordering. Furthermore, parallel texts with corresponding speech utterances that are suitable for training end-to-end speech translation are generally unavailable. Collecting such corpora is usually time-consuming and expensive. This paper proposes the first attempt to build an end-to-end direct speech-to-text translation system on syntactically distant language pairs that suffer from long-distance reordering. We train the model on English (subject-verb-object (SVO) word order) and Japanese (SOV word order) language pairs. To guide the attention-based encoder-decoder model on this difficult problem, we construct end-to-end speech translation with transcoding and utilize curriculum learning (CL) strategies that gradually train the network for end-to-end speech translation tasks by adapting the decoder or encoder parts. We use TTS for data augmentation to generate corresponding speech utterances from the existing parallel text data. Our experiment results show that the proposed approach provides significant improvements compared with conventional cascade models and the direct speech translation approach that uses a single model without transcoding and CL strategies.

Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acquire. Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i.e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i.e., target domain). However, without co-training source and target data, source domain knowledge might be forgotten during the fine-tuning process, while simply co-training them may cause negative transfer due to domain gaps. Moreover, identity label spaces of source data and target data are generally disjoint and therefore conventional category-level Domain Adaptation (DA) is not directly applicable. To address these issues, we propose an Instance-level Heterogeneous Domain Adaptation (IHDA) framework. We apply the fine-tuning strategy for identity label learning, aiming to transfer the instance-level knowledge in an inductive transfer manner. Meanwhile, labeled attributes from the source data are selected to form a shared label space for source and target domains. Guided by shared attributes, DA is utilized to bridge cross-dataset domain gaps and heterogeneous domain gaps, which transfers instance-level knowledge in a transductive transfer manner. Experiments show that our method has set a new state of the art on three sketch-to-photo image retrieval benchmarks without extra annotations, which opens the door to train more effective models on limited-labeled heterogeneous image retrieval tasks.

Speech-to-speech translation (S2ST) is a technology that translates speech across languages, which can remove barriers in cross-lingual communication. In the conventional S2ST systems, the linguistic meaning of speech was translated, but paralinguistic information conveying other features of the speech such as emotion or emphasis were ignored. In this paper, we propose a method to translate paralinguistic information, specifically focusing on emphasis. The method consists of a series of components that can accurately translate emphasis using all acoustic features of speech. First, linear-regression hidden semi-Markov models (LRHSMMs) are used to estimate a real-numbered emphasis value for every word in an utterance, resulting in a sequence of values for the utterance. After that the emphasis translation module translates the estimated emphasis sequence into a target language emphasis sequence using a conditional random field model considering the features of emphasis levels, words, and part-of-speech tags. Finally, the speech synthesis module synthesizes emphasized speech with LR-HSMMs, taking into account the translated emphasis sequence and transcription. The results indicate that our translation model can translate emphasis information, correctly emphasizing words in the target language with 91.6% F-measure by objective evaluation. A listening test with human subjects further showed that they could identify the emphasized words with 87.8% F-measure, and that the naturalness of the audio was preserved.