Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, NLP based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely-used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

Neuralink is one step closer to selling brain implants that can transmit human thought. The neurotechnology company in May announced that it had received approval from the U.S. Food and Drug Administration (FDA) to launch its first in-human clinical trial. A statement on its Twitter account said the approval "represents an important first step that will one day allow our technology to help many people." Cofounded by Elon Musk in 2016, Neuralink plans to implant devices in human brains that would allow people with neurological disorders to control computers or robotic limbs with their minds. Musk has said he also wants to "achieve a sort of symbiosis with artificial intelligence" and possibly enable telepathic communication with the device.

In April and May, surgeons at West Virginia University placed thin strips of a cellophane-like material on the brains of three patients. Made by New York-based startup Precision Neuroscience, the thumbnail-sized strips are designed to conform to the surface of the brain without damaging its delicate tissue. During the 15 minutes the devices were in place, the implants were able to read, record, and map electrical activity in part of the patients' temporal lobes, which helps process sensory input. The patients were already in the hospital to have brain tumors removed, and doctors used Precision's devices alongside standard electrodes to determine the location of their tumors. Although just a small pilot study, it puts Precision one step closer to building a brain-computer interface, or BCI--a system that provides a direct communication link between the brain and an external device.

Knowledge graphs (KGs) are an important tool for representing complex relationships between entities in the biomedical domain. Several methods have been proposed for learning embeddings that can be used to predict new links in such graphs. Some methods ignore valuable attribute data associated with entities in biomedical KGs, such as protein sequences, or molecular graphs. Other works incorporate such data, but assume that entities can be represented with the same data modality. This is not always the case for biomedical KGs, where entities exhibit heterogeneous modalities that are central to their representation in the subject domain. We propose a modular framework for learning embeddings in KGs with entity attributes, that allows encoding attribute data of different modalities while also supporting entities with missing attributes. We additionally propose an efficient pretraining strategy for reducing the required training runtime. We train models using a biomedical KG containing approximately 2 million triples, and evaluate the performance of the resulting entity embeddings on the tasks of link prediction, and drug-protein interaction prediction, comparing against methods that do not take attribute data into account. In the standard link prediction evaluation, the proposed method results in competitive, yet lower performance than baselines that do not use attribute data. When evaluated in the task of drug-protein interaction prediction, the method compares favorably with the baselines. We find settings involving low degree entities, which make up for a substantial amount of the set of entities in the KG, where our method outperforms the baselines. Our proposed pretraining strategy yields significantly higher performance while reducing the required training runtime. Our implementation is available at https://github.com/elsevier-AI-Lab/BioBLP .

Elon Musk's brain-implant company Neuralink last week received regulatory approval to conduct the first clinical trial of its experimental device in humans. But the billionaire executive's bombastic promotion of the technology, his leadership record at other companies and animal welfare concerns relating to Neuralink experiments have raised alarm. "I was surprised," said Laura Cabrera, a neuroethicist at Penn State's Rock Ethics Institute about the decision by the US Food and Drug Administration to let the company go ahead with clinical trials. Musks' erratic leadership at Twitter and his "move fast" techie ethos raise questions about Neuralink's ability to responsibly oversee the development of an invasive medical device capable of reading brain signals, Cabrera argued. "Is he going to see a brain implant device as something that requires not just extra regulation, but also ethical consideration?" she said.

As the importance of high-throughput screening (HTS) continues to grow due to its value in early stage drug discovery and data generation for training machine learning models, there is a growing need for robust methods for pre-screening compounds to identify and prevent false-positive hits. Small, colloidally aggregating molecules are one of the primary sources of false-positive hits in high-throughput screens, making them an ideal candidate to target for removal from libraries using predictive pre-screening tools. However, a lack of understanding of the causes of molecular aggregation introduces difficulty in the development of predictive tools for detecting aggregating molecules. Herein, we present an examination of the molecular features differentiating datasets of aggregating and non-aggregating molecules, as well as a machine learning approach to predicting molecular aggregation. Our method uses explainable graph neural networks and counterfactuals to reliably predict and explain aggregation, giving additional insights and design rules for future screening. The integration of this method in HTS approaches will help combat false positives, providing better lead molecules more rapidly and thus accelerating drug discovery cycles.

Artificial intelligence (AI) models trained on published scientific findings have been used to invent valuable materials and targeted therapies, but they typically ignore the human scientists who continually alter the landscape of discovery. Here we show that incorporating the distribution of human expertise by training unsupervised models on simulated inferences cognitively accessible to experts dramatically improves (up to 400%) AI prediction of future discoveries beyond those focused on research content alone, especially when relevant literature is sparse. These models succeed by predicting human predictions and the scientists who will make them. By tuning human-aware AI to avoid the crowd, we can generate scientifically promising "alien" hypotheses unlikely to be imagined or pursued without intervention until the distant future, which hold promise to punctuate scientific advance beyond questions currently pursued. Accelerating human discovery or probing its blind spots, human-aware AI enables us to move toward and beyond the contemporary scientific frontier.

Doctors believe Artificial Intelligence is now saving lives, after a major advancement in breast cancer screenings. A.I. is detecting early signs of the disease, in some cases years before doctors would find the cancer on a traditional scan. Meet Ezra, the full-body cancer screener that just might save your life. Combining MRI imaging technology with artificial intelligence, Ezra scans for possible cancer in the human body in up to 13 organs. It also monitors for hundreds of other conditions, such as brain aneurysms or fatty liver disease.

Artificial Intelligence (AI) has received an increasing amount of attention in multiple areas. The uncertainties and risks in AI-powered systems have created reluctance in their wild adoption. As an economic solution to compensate for potential damages, AI liability insurance is a promising market to enhance the integration of AI into daily life. In this work, we use an AI-powered E-diagnosis system as an example to study AI liability insurance. We provide a quantitative risk assessment model with evidence-based numerical analysis. We discuss the insurability criteria for AI technologies and suggest necessary adjustments to accommodate the features of AI products. We show that AI liability insurance can act as a regulatory mechanism to incentivize compliant behaviors and serve as a certificate of high-quality AI systems. Furthermore, we suggest premium adjustment to reflect the dynamic evolution of the inherent uncertainty in AI. Moral hazard problems are discussed and suggestions for AI liability insurance are provided.

This copy is for your personal, non-commercial use only. For non-personal use or to order multiple copies, please contact Dow Jones Reprints at 1-800-843-0008 or visit www.djreprints.com.