Predicting condensate formation of protein and RNA under various environmental conditions.

BACKGROUND: Liquid-liquid phase separation (LLPS) by biomolecules plays a central role in various biological phenomena and has garnered significant attention. The behavior of LLPS is strongly influenced by the characteristics of RNAs and environmental factors such as pH and temperature, as well as the properties of proteins. Recently, several databases recording LLPS-related biomolecules have been established, and prediction models of LLPS-related phenomena have been explored using these databases. However, a prediction model that concurrently considers proteins, RNAs, and experimental conditions has not been developed due to the limited information available from individual experiments in public databases. RESULTS: To address this challenge, we have constructed a new dataset, RNAPSEC, which serves each experiment as a data point. This dataset was accomplished by manually collecting data from public literature. Utilizing RNAPSEC, we developed two prediction models that consider a protein, RNA, and experimental conditions. The first model can predict the LLPS behavior of a protein and RNA under given experimental conditions. The second model can predict the required conditions for a given protein and RNA to undergo LLPS. CONCLUSIONS: RNAPSEC and these prediction models are expected to accelerate our understanding of the roles of proteins, RNAs, and environmental factors in LLPS.

AI-driven molecular generation of not-patented pharmaceutical compounds using world open patent data.

Developing compounds with novel structures is important for the production of new drugs. From an intellectual perspective, confirming the patent status of newly developed compounds is essential, particularly for pharmaceutical companies. The generation of a large number of compounds has been made possible because of the recent advances in artificial intelligence (AI). However, confirming the patent status of these generated molecules has been a challenge because there are no free and easy-to-use tools that can be used to determine the novelty of the generated compounds in terms of patents in a timely manner; additionally, there are no appropriate reference databases for pharmaceutical patents in the world. In this study, two public databases, SureChEMBL and Google Patents Public Datasets, were used to create a reference database of drug-related patented compounds using international patent classification. An exact structure search system was constructed using InChIKey and a relational database system to rapidly search for compounds in the reference database. Because drug-related patented compounds are a good source for generative AI to learn useful chemical structures, they were used as the training data. Furthermore, molecule generation was successfully directed by increasing and decreasing the number of generated patented compounds through incorporation of patent status (i.e., patented or not) into learning. The use of patent status enabled generation of novel molecules with high drug-likeness. The generation using generative AI with patent information would help efficiently propose novel compounds in terms of pharmaceutical patents. Scientific contribution: In this study, a new molecule-generation method that takes into account the patent status of molecules, which has rarely been considered but is an important feature in drug discovery, was developed. The method enables the generation of novel molecules based on pharmaceutical patents with high drug-likeness and will help in the efficient development of effective drug compounds.

Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images.

Deep learning systems (DLSs) have been developed for the histopathological assessment of various types of tumors, but none are suitable for differential diagnosis between follicular thyroid carcinoma (FTC) and follicular adenoma (FA). Furthermore, whether DLSs can identify the malignant characteristics of thyroid tumors based only on random views of tumor tissue histology has not been evaluated. In this study, we developed DLSs able to differentiate between FTC and FA based on 3 types of convolutional neural network architecture: EfficientNet, VGG16, and ResNet50. The performance of all 3 DLSs was excellent (area under the receiver operating characteristic curve = 0.91 ± 0.04; F1 score = 0.82 ± 0.06). Visual explanations using gradient-weighted class activation mapping suggested that the diagnosis of both FTC and FA was largely dependent on nuclear features. The DLSs were then trained with FTC images and linked information (presence or absence of recurrence within 10 years, vascular invasion, and wide capsular invasion). The ability of the DLSs to diagnose these characteristics was then determined. The results showed that, based on the random views of histology, the DLSs could predict the risk of FTC recurrence, vascular invasion, and wide capsular invasion with a certain level of accuracy (area under the receiver operating characteristic curve = 0.67 ± 0.13, 0.62 ± 0.11, and 0.65 ± 0.09, respectively). Further improvement of our DLSs could lead to the establishment of automated differential diagnosis systems requiring only biopsy specimens.

Quantitative analysis of protein dynamics using a deep learning technique combined with experimental cryo-EM density data and MD simulations.

Protein functions associated with biological activity are precisely regulated by both tertiary structure and dynamic behavior. Thus, elucidating the high-resolution structures and quantitative information on in-solution dynamics is essential for understanding the molecular mechanisms. The main experimental approaches for determining tertiary structures include nuclear magnetic resonance (NMR), X-ray crystallography, and cryogenic electron microscopy (cryo-EM). Among these procedures, recent remarkable advances in the hardware and analytical techniques of cryo-EM have increasingly determined novel atomic structures of macromolecules, especially those with large molecular weights and complex assemblies. In addition to these experimental approaches, deep learning techniques, such as AlphaFold 2, accurately predict structures from amino acid sequences, accelerating structural biology research. Meanwhile, the quantitative analyses of the protein dynamics are conducted using experimental approaches, such as NMR and hydrogen-deuterium mass spectrometry, and computational approaches, such as molecular dynamics (MD) simulations. Although these procedures can quantitatively explore dynamic behavior at high resolution, the fundamental difficulties, such as signal crowding and high computational cost, greatly hinder their application to large and complex biological macromolecules. In recent years, machine learning techniques, especially deep learning techniques, have been actively applied to structural data to identify features that are difficult for humans to recognize from big data. Here, we review our approach to accurately estimate dynamic properties associated with local fluctuations from three-dimensional cryo-EM density data using a deep learning technique combined with MD simulations.

Selective Inhibitor Design for Kinase Homologs Using Multiobjective Monte Carlo Tree Search.

Designing highly selective molecules for a drug target protein is a challenging task in drug discovery. This task can be regarded as a multiobjective problem that simultaneously satisfies criteria for various objectives, such as selectivity for a target protein, pharmacokinetic endpoints, and drug-like indices. Recent breakthroughs in artificial intelligence have accelerated the development of molecular structure generation methods, and various researchers have applied them to computational drug designs and successfully proposed promising drug candidates. However, designing efficient selective inhibitors with releasing activities against various homologs of a target protein remains a difficult issue. In this study, we developed a de novo structure generator based on reinforcement learning that is capable of simultaneously optimizing multiobjective problems. Our structure generator successfully proposed selective inhibitors for tyrosine kinases while optimizing 18 objectives consisting of inhibitory activities against 9 tyrosine kinases, 3 pharmacokinetics endpoints, and 6 other important properties. These results show that our structure generator and optimization strategy for selective inhibitors will contribute to the further development of practical structure generators for drug designs.

A Novel Three-Dimensional Imaging System Based on Polysaccharide Staining for Accurate Histopathological Diagnosis of Inflammatory Bowel Diseases.

BACKGROUND & AIMS: Tissue-clearing and three-dimensional (3D) imaging techniques aid clinical histopathological evaluation; however, further methodological developments are required before use in clinical practice. METHODS: We sought to develop a novel fluorescence staining method based on the classical periodic acid-Schiff stain. We further attempted to develop a 3D imaging system based on this staining method and evaluated whether the system can be used for quantitative 3D pathological evaluation and deep learning-based automatic diagnosis of inflammatory bowel diseases. RESULTS: We successfully developed a novel periodic acid-FAM hydrazide (PAFhy) staining method for 3D imaging when combined with a tissue-clearing technique (PAFhy-3D). This strategy enabled clear and detailed imaging of the 3D architectures of crypts in human colorectal mucosa. PAFhy-3D imaging also revealed abnormal architectural changes in crypts in ulcerative colitis tissues and identified the distributions of neutrophils in cryptitis and crypt abscesses. PAFhy-3D revealed novel pathological findings including spiral staircase-like crypts specific to inflammatory bowel diseases. Quantitative analysis of crypts based on 3D morphologic changes enabled differential diagnosis of ulcerative colitis, Crohn's disease, and non-inflammatory bowel disease; such discrimination could not be achieved by pathologists. Furthermore, a deep learning-based system using PAFhy-3D images was used to distinguish these diseases The accuracies were excellent (macro-average area under the curve = 0.94; F1 scores = 0.875 for ulcerative colitis, 0.717 for Crohn's disease, and 0.819 for non-inflammatory bowel disease). CONCLUSIONS: PAFhy staining and PAFhy-3D imaging are promising approaches for next-generation experimental and clinical histopathology.

AI-Driven Synthetic Route Design Incorporated with Retrosynthesis Knowledge.

Computer-aided synthesis planning (CASP) aims to assist chemists in performing retrosynthetic analysis for which they utilize their experiments, intuition, and knowledge. Recent breakthroughs in machine learning (ML) techniques, including deep neural networks, have significantly improved data-driven synthetic route designs without human intervention. However, learning chemical knowledge by ML for practical synthesis planning has not yet been adequately achieved and remains a challenging problem. In this study, we developed a data-driven CASP application integrated with various portions of retrosynthesis knowledge called "ReTReK" that introduces the knowledge as adjustable parameters into the evaluation of promising search directions. The experimental results showed that ReTReK successfully searched synthetic routes based on the specified retrosynthesis knowledge, indicating that the synthetic routes searched with the knowledge were preferred to those without the knowledge. The concept of integrating retrosynthesis knowledge as adjustable parameters into a data-driven CASP application is expected to enhance the performance of both existing data-driven CASP applications and those under development.

kGCN: a graph-based deep learning framework for chemical structures.

Deep learning is developing as an important technology to perform various tasks in cheminformatics. In particular, graph convolutional neural networks (GCNs) have been reported to perform well in many types of prediction tasks related to molecules. Although GCN exhibits considerable potential in various applications, appropriate utilization of this resource for obtaining reasonable and reliable prediction results requires thorough understanding of GCN and programming. To leverage the power of GCN to benefit various users from chemists to cheminformaticians, an open-source GCN tool, kGCN, is introduced. To support the users with various levels of programming skills, kGCN includes three interfaces: a graphical user interface (GUI) employing KNIME for users with limited programming skills such as chemists, as well as command-line and Python library interfaces for users with advanced programming skills such as cheminformaticians. To support the three steps required for building a prediction model, i.e., pre-processing, model tuning, and interpretation of results, kGCN includes functions of typical pre-processing, Bayesian optimization for automatic model tuning, and visualization of the atomic contribution to prediction for interpretation of results. kGCN supports three types of approaches, single-task, multi-task, and multi-modal predictions. The prediction of compound-protein interaction for four matrixmetalloproteases, MMP-3, -9, -12 and -13, in the inhibition assays is performed as a representative case study using kGCN. Additionally, kGCN provides the visualization of atomic contributions to the prediction. Such visualization is useful for the validation of the prediction models and the design of molecules based on the prediction model, realizing "explainable AI" for understanding the factors affecting AI prediction. kGCN is available at https://github.com/clinfo.

CompRet: a comprehensive recommendation framework for chemical synthesis planning with algorithmic enumeration.

In computer-assisted synthesis planning (CASP) programs, providing as many chemical synthetic routes as possible is essential for considering optimal and alternative routes in a chemical reaction network. As the majority of CASP programs have been designed to provide one or a few optimal routes, it is likely that the desired one will not be included. To avoid this, an exact algorithm that lists possible synthetic routes within the chemical reaction network is required, alongside a recommendation of synthetic routes that meet specified criteria based on the chemist's objectives. Herein, we propose a chemical-reaction-network-based synthetic route recommendation framework called "CompRet" with a mathematically guaranteed enumeration algorithm. In a preliminary experiment, CompRet was shown to successfully provide alternative routes for a known antihistaminic drug, cetirizine. CompRet is expected to promote desirable enumeration-based chemical synthesis searches and aid the development of an interactive CASP framework for chemists.

Prediction and Interpretable Visualization of Retrosynthetic Reactions Using Graph Convolutional Networks.

Recently, many research groups have been addressing data-driven approaches for (retro)synthetic reaction prediction and retrosynthetic analysis. Although the performances of the data-driven approach have progressed because of recent advances of machine learning and deep learning techniques, problems such as improving capability of reaction prediction and the black-box problem of neural networks persist for practical use by chemists. To spread data-driven approaches to chemists, we focused on two challenges: improvement of retrosynthetic reaction prediction and interpretability of the prediction. In this paper, we propose an interpretable prediction framework using graph convolutional networks (GCN) for retrosynthetic reaction prediction and integrated gradients (IG) for visualization of contributions to the prediction to address these challenges. As a result, from the viewpoint of balanced accuracies, our model showed better performances than the approach using an extended-connectivity fingerprint. Furthermore, IG-based visualization of the GCN prediction successfully highlighted reaction-related atoms.