With the increasing research and development (R&D) difficulty of new molecular entities (NMEs), novel drug delivery systems (DDSs) are attracting widespread attention. This review investigated the current distribution of Food and Drug Administration (FDA)-approved pharmaceutical products and evaluated the technical barrier for the entry of generic drugs and highlighted the success and failure of advanced drug delivery systems. According to the ratio of generic to new drugs and the four-quadrant classification scheme for evaluating the commercialization potential of DDSs, the results showed that the traditional dosage forms (e.g., conventional tablets, capsules and injections) with a lower technology barrier were easier to reproduce, while advanced drug delivery systems (e.g., inhalations and nanomedicines) with highly technical barriers had less competition and greater market potential. Our study provides a comprehensive insight into FDA-approved products and deep analysis of the technical barriers for advanced drug delivery systems. In the future, the R&D of new molecular entities may combine advanced delivery technologies to make drug candidates into more therapeutically effective formulations.

A Comprehensive Map of FDA-Approved Pharmaceutical Products

The data sets available to train models for in silico drug discovery efforts are often small. Indeed, the sparse availability of labeled data is a major barrier to artificial-intelligence-assisted drug discovery. One solution to this problem is to develop algorithms that can cope with relatively heterogeneous and scarce data. Transfer learning is a type of machine learning that can leverage existing, generalizable knowledge from other related tasks to enable learning of a separate task with a small set of data. Deep transfer learning is the most commonly used type of transfer learning in the field of drug discovery. This Perspective provides an overview of transfer learning and related applications to drug discovery to date. Furthermore, it provides outlooks on the future development of transfer learning for drug discovery.

Transfer Learning for Drug Discovery

M3DISEEN: A novel machine learning approach for predicting the 3D printability of medicines

Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amount of data collected in a wide array of scientific domains is dramatically increasing in both size and complexity. Taken together, this suggests many exciting opportunities for deep learning applications in scientific settings. But a significant challenge to this is simply knowing where to start. The sheer breadth and diversity of different deep learning techniques makes it difficult to determine what scientific problems might be most amenable to these methods, or which specific combination of methods might offer the most promising first approach. In this survey, we focus on addressing this central issue, providing an overview of many widely used deep learning models, spanning visual, sequential and graph structured data, associated tasks and different training methods, along with techniques to use deep learning with less data and better interpret these complex models --- two central considerations for many scientific use cases. We also include overviews of the full design process, implementation tips, and links to a plethora of tutorials, research summaries and open-sourced deep learning pipelines and pretrained models, developed by the community. We hope that this survey will help accelerate the use of deep learning across different scientific domains.

A Survey of Deep Learning for Scientific Discovery

Climate change, increasing populations, competing demands on land for production of biofuels and declining soil quality are challenging global food security. Finding sustainable solutions requires bold new approaches and integration of knowledge from diverse fields, such as materials science and informatics. The convergence of precision agriculture, in which farmers respond in real time to changes in crop growth with nanotechnology and artificial intelligence, offers exciting opportunities for sustainable food production. Coupling existing models for nutrient cycling and crop productivity with nanoinformatics approaches to optimize targeting, uptake, delivery, nutrient capture and long-term impacts on soil microbial communities will enable design of nanoscale agrochemicals that combine optimal safety and functionality profiles.

Nanotechnology and artificial intelligence to enable sustainable and precision agriculture.

Predicting physical stability of solid dispersions by machine learning techniques.

Deep learning for in vitro prediction of pharmaceutical formulations.

Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques.

Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, and excretion prediction models still have limited accuracy. Aim: This study aims to construct an integrated transfer learning and multitask learning approach for developing quantitative structure–activity relationship models to predict four human pharmacokinetic parameters. Methods: A pharmacokinetic data set included 1104 U.S. FDA approved small molecule drugs. The data set included four human pharmacokinetic parameter subsets (oral bioavailability, plasma protein binding rate, apparent volume of distribution at steady-state, and elimination half-life). The pretrained model was trained on over 30 million bioactivity data entries. An integrated transfer learning and multitask learning approach was established to enhance the model generalization. Results: The pharmacokinetic data set was split into three parts (60:20:20) for training, validation, and ...

An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction

Current pharmaceutical formulation development still strongly relies on the traditional trial-and-error approach by individual experiences of pharmaceutical scientists, which is laborious, time-consuming and costly. Recently, deep learning has been widely applied in many challenging domains because of its important capability of automatic feature extraction. The aim of this research is to use deep learning to predict pharmaceutical formulations. In this paper, two different types of dosage forms were chosen as model systems. Evaluation criteria suitable for pharmaceutics were applied to assessing the performance of the models. Moreover, an automatic dataset selection algorithm was developed for selecting the representative data as validation and test datasets. Six machine learning methods were compared with deep learning. The result shows the accuracies of both two deep neural networks were above 80% and higher than other machine learning models, which showed good prediction in pharmaceutical formulations. In summary, deep learning with the automatic data splitting algorithm and the evaluation criteria suitable for pharmaceutical formulation data was firstly developed for the prediction of pharmaceutical formulations. The cross-disciplinary integration of pharmaceutics and artificial intelligence may shift the paradigm of pharmaceutical researches from experience-dependent studies to data-driven methodologies.

Zhuyifan Ye

Papers

Predicting physical stability of solid dispersions by machine learning techniques.

Deep learning for in vitro prediction of pharmaceutical formulations.

Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques.

An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction

Deep learning for in vitro prediction of pharmaceutical formulations