Traditional drug discovery programs are being transformed by the advent of machine learning methods. Among these, Generative AI methods (GM) have gained attention due to their ability to design new molecules and enhance specific properties of existing ones. However, current GM methods have limitations, such as low affinity towards the target, unknown ADME/PK properties, or the lack of synthetic tractability. To improve the applicability domain of GM methods, we have developed a workflow based on a variational autoencoder coupled with active learning steps. The designed GM workflow iteratively learns from molecular metrics, including drug likeliness, synthesizability, similarity, and docking scores. In addition, we also included a hierarchical set of criteria based on advanced molecular modeling simulations during a final selection step. We tested our GM workflow on two model systems, CDK2 and KRAS. In both cases, our model generated chemically viable molecules with a high predicted affinity toward the targets. Particularly, the proportion of high-affinity molecules inferred by our GM workflow was significantly greater than that in the training data. Notably, we also uncovered novel scaffolds significantly dissimilar to those known for each target. These results highlight the potential of our GM workflow to explore novel chemical space for specific targets, thereby opening up new possibilities for drug discovery endeavors.

Sean Hannity discusses how Hunter Biden is pushing back against paying child support for his 4-year-old daughter in an Arkansas court case on'Hannity.' SEAN HANNITY – Is Hunter Biden too broke to pay child support?.… Continue watching… SAVE THE CHILDREN – I'm a doctor who survived stage IV cancer. 'MONSTROUS' – Hunter Biden's twisted attempts to keep his little girl from using his name are now in a new realm… Continue reading… IT STINKS! – Biden's quiet attack on rural America smells just as bad as manure… Continue reading… AI CRAZINESS – Why artificial intelligence can't bring the dead back to life… Continue reading… RUN, BUT CAN'T HIDE – These are Fauci's 3 biggest mistakes that no amount of media whitewashing can undo… Continue reading… REP. JODEY ARRINGTON – This crisis is flashing danger and America must change course or our children will pay is the greatest success story from the pandemic… Continue reading… MAJOR VICTORY – Here's why Texas court's ruling on FDA approval of abortion drugs is a huge win for women, girls… Continue reading… WATCH: MARK PENN – DeSantis has to'do a reset' to close the gap between President Trump… See the video… BATAAN SURVIVORS – These WWII heroes endured disease, starvation and beheadings. Here's why we should remember them… Continue reading…

Transformer-based large language models are rapidly advancing in the field of machine learning research, with applications spanning natural language, biology, chemistry, and computer programming. Extreme scaling and reinforcement learning from human feedback have significantly improved the quality of generated text, enabling these models to perform various tasks and reason about their choices. In this paper, we present an Intelligent Agent system that combines multiple large language models for autonomous design, planning, and execution of scientific experiments. We showcase the Agent's scientific research capabilities with three distinct examples, with the most complex being the successful performance of catalyzed cross-coupling reactions. Finally, we discuss the safety implications of such systems and propose measures to prevent their misuse.

Should artificial intelligence or machine learning (AI/ML) be allowed to alter FDA approved software in medical devices? If so, where should the guardrails be set? The discussions and debates surrounding AI/ML are heated; some believe the technology may destroy humanity, while others look forward to the speed of advancement it will allow. The FDA is getting out ahead on this debate. This week the agency drafted a list of “guiding principles” intended to begin developing best practices for machine learning within medical devices. A new framework envisioned by the FDA includes a “predetermined change control plan” in premarket submissions. This plan would include the types of anticipated modifications, referred to as “Software as a Medical Device Pre-Specifications”. The associated methodology used to implement those changes in a measured and controlled approach that manages risk the FDA calls the “Algorithm Change Protocol.”

While many approved products are applied for automated quantification, there are increasing numbers of approved products that move beyond quantification to detection and even diagnosis,

The Food and Drug Administration announced the availability of draft guidance that provides recommendations on lifecycle controls in submissions to market machine learning-enabled device software functions. In the "Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence/Machine Learning-Enabled Device Software Functions," the FDA proposes to ensure that AI/ML-enabled devices "can be safely, effectively and rapidly modified, updated, and improved in response to new data," said Brendan O'Leary, deputy director of the Digital Health Center of Excellence in the FDA's Center for Devices and Radiological Health, in a March 30 announcement. FDA says that companies must also describe how information about modifications will be clearly communicated to users in the PCCP. The agency explains that control plans are not just intended for the AI/ML-enabled software as a medical device – "but for all AI/ML-enabled device software functions." "The approach FDA is proposing in this draft guidance would ensure that important performance considerations, including with respect to race, ethnicity, disease severity, gender, age and geographical considerations, are addressed in the ongoing development, validation, implementation and monitoring of AI/ML-enabled devices," he said.

A new draft guidance by the US Food and Drug Administration (FDA) would allow developers of artificial intelligence (AI) and machine learning (ML) digital health solutions to make changes to their products without submitting a new application. The plan would let submissions include predetermined change control plans (PCCP) that would lay out how developers would ensure changes are safe and effective. According to Ferdous Al-Farique, "While the agency has already allowed more than 500 AI/ML products on the market, many of which already allow PCCP, Congress passed legislation as part of the 2023 Consolidated Appropriations Act that gave FDA explicit authority to approve PCCPs as part of AI/ML product applications." To read more, click here.

Publicly available collections of drug-like molecules have grown to comprise 10s of billions of possibilities in recent history due to advances in chemical synthesis. Traditional methods for identifying ``hit'' molecules from a large collection of potential drug-like candidates have relied on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug to its protein target. A major drawback of the approaches is that they require exceptional computing capabilities to consider for even relatively small collections of molecules. Hyperdimensional Computing (HDC) is a recently proposed learning paradigm that is able to leverage low-precision binary vector arithmetic to build efficient representations of the data that can be obtained without the need for gradient-based optimization approaches that are required in many conventional machine learning and deep learning approaches. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated for a range of application areas. We consider existing HDC approaches for molecular property classification and introduce two novel encoding algorithms that leverage the extended connectivity fingerprint (ECFP) algorithm. We show that HDC-based inference methods are as much as 90 times more efficient than more complex representative machine learning methods and achieve an acceleration of nearly 9 orders of magnitude as compared to inference with molecular docking. We demonstrate multiple approaches for the encoding of molecular data for HDC and examine their relative performance on a range of challenging molecular property prediction and drug-protein binding classification tasks. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools.

The discovery of novel drug-target (DT) interactions is an important step in the drug development process. The majority of computer techniques for predicting DT interactions have focused on binary classification, with the goal of determining whether or not a DT pair interacts. Protein-ligand interactions, on the other hand, assume a continuous range of binding strength values, also known as binding affinity, and forecasting this value remains a difficulty. As the amount of affinity data in DT knowledge-bases grows, advanced learning techniques such as deep learning architectures can be used to predict binding affinities. In this paper, we present a deep-learningbased methodology for predicting DT binding affinities using just sequencing information from both targets and drugs. The results show that the proposed deep learning-based model that uses the 1D representations of targets and drugs is an effective approach for drug target binding affinity prediction and it does not require additional chemical domain knowledge to work with. The model in which high-level representations of a drug and a target are constructed via CNNs that uses residual skip connections and also with an additional stream to create a highlevel combined representation of the drug-target pair achieved the best Concordance Index (CI) [1] performance in one of the largest benchmark datasets [2], outperforming the recent state-of-the-art method AttentionDTA [3] and many other machine-learning [4,5] and deep-learning [6-10] based baseline methods for DT binding affinity prediction that uses the 1D representations of targets and drugs.

Deep brain stimulation (DBS) has shown great promise toward treating motor symptoms caused by Parkinson's disease (PD), by delivering electrical pulses to the Basal Ganglia (BG) region of the brain. However, DBS devices approved by the U.S. Food and Drug Administration (FDA) can only deliver continuous DBS (cDBS) stimuli at a fixed amplitude; this energy inefficient operation reduces battery lifetime of the device, cannot adapt treatment dynamically for activity, and may cause significant side-effects (e.g., gait impairment). In this work, we introduce an offline reinforcement learning (RL) framework, allowing the use of past clinical data to train an RL policy to adjust the stimulation amplitude in real time, with the goal of reducing energy use while maintaining the same level of treatment (i.e., control) efficacy as cDBS. Moreover, clinical protocols require the safety and performance of such RL controllers to be demonstrated ahead of deployments in patients. Thus, we also introduce an offline policy evaluation (OPE) method to estimate the performance of RL policies using historical data, before deploying them on patients. We evaluated our framework on four PD patients equipped with the RC+S DBS system, employing the RL controllers during monthly clinical visits, with the overall control efficacy evaluated by severity of symptoms (i.e., bradykinesia and tremor), changes in PD biomakers (i.e., local field potentials), and patient ratings. The results from clinical experiments show that our RL-based controller maintains the same level of control efficacy as cDBS, but with significantly reduced stimulation energy. Further, the OPE method is shown effective in accurately estimating and ranking the expected returns of RL controllers.