Asking the right questions for mutagenicity prediction from BioMedical text.

Assessing the mutagenicity of chemicals is an essential task in the drug development process. Usually, databases and other structured sources for AMES mutagenicity exist, which have been carefully and laboriously curated from scientific publications. As knowledge accumulates over time, updating these databases is always an overhead and impractical. In this paper, we first propose the problem of predicting the mutagenicity of chemicals from textual information in scientific publications. More simply, given a chemical and evidence in the natural language form from publications where the mutagenicity of the chemical is described, the goal of the model/algorithm is to predict if it is potentially mutagenic or not. For this, we first construct a golden standard data set and then propose MutaPredBERT, a prediction model fine-tuned on BioLinkBERT based on a question-answering formulation of the problem. We leverage transfer learning and use the help of large transformer-based models to achieve a Macro F1 score of >0.88 even with relatively small data for fine-tuning. Our work establishes the utility of large language models for the construction of structured sources of knowledge bases directly from scientific publications.

Optimizing machine-learning models for mutagenicity prediction through better feature selection.

Assessing a compound's mutagenicity using machine learning is an important activity in the drug discovery and development process. Traditional methods of mutagenicity detection, such as Ames test, are expensive and time and labor intensive. In this context, in silico methods that predict a compound mutagenicity with high accuracy are important. Recently, machine-learning (ML) models are increasingly being proposed to improve the accuracy of mutagenicity prediction. While these models are used in practice, there is further scope to improve the accuracy of these models. We hypothesize that choosing the right features to train the model can further lead to better accuracy. We systematically consider and evaluate a combination of novel structural and molecular features which have the maximal impact on the accuracy of models. We rigorously evaluate these features against multiple classification models (from classical ML models to deep neural network models). The performance of the models was assessed using 5- and 10-fold cross-validation and we show that our approach using the molecule structure, molecular properties, and structural alerts as feature sets successfully outperform the state-of-the-art methods for mutagenicity prediction for the Hansen et al. benchmark dataset with an area under the receiver operating characteristic curve of 0.93. More importantly, our framework shows how combining features could benefit model accuracy improvements.

[Consideration on Industry-Academia Partnering in Drug Discovery Development: Based on a Questionnaire Survey of Pharmaceutical Companies and Academia].

Japanese pharmaceutical products continue to experience a trade deficit, since import values exceed export values. In drug discovery development, given the pace of technological innovations, there has been a major shift from low-molecular-weight compounds to biomedicine. It is anticipated that industry, academia and government will work more closely together in support of the pharmaceutical industry. Drug discovery requires much time and vast resources before the results can be put to practical use, and evidence suggests that many newly approved drugs derive from university-sourced technology. Pharmaceutical companies keep a close eye on technology evolving in universities. However, some reports state that there is a substantial difference compared to the development costs of the major Japanese pharmaceutical companies. Therefore, the authors hypothesized that there may be some issues hindering industrial-academic partnerships in drug discovery. In order to understand the actual situation and barriers to promoting industrial-academic collaboration, the Japan Pharmaceutical Manufacturers Association (JPMA), Japan Agency for Medical Research and Development (AMED), and the Medical Industry-Academia Collaboration Network (medU-net) Council will work together in issuing questionnaires and conducting an awareness survey. This survey sought the personal opinions of individuals belonging to JPMA and medU-net. Based on the results of this survey, we will introduce the issues related to industrial-academic collaboration and partnerships, and any gaps between industry and academia. Furthermore, we suggest solutions to promoting drug discovery innovation in Japan.