Human-in-the-loop active learning for goal-oriented molecule generation.

Machine learning (ML) systems have enabled the modelling of quantitative structure-property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug discovery by guiding generative artificial intelligence (AI) agents to explore desired chemical spaces. However, they often struggle to generalize due to the limited scope of the training data.

Exhaustive local chemical space exploration using a transformer model.

How many near-neighbors does a molecule have? This fundamental question in chemistry is crucial for molecular optimization problems under the similarity principle assumption. Generative models can sample molecules from a vast chemical space but lack explicit knowledge about molecular similarity. Therefore, these models need guidance from reinforcement learning to sample a relevant similar chemical space.

Evaluation of reinforcement learning in transformer-based molecular design.

Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules.

Relationships between Serotonin Transporter Availability and the Global Efficiency of the Executive Control Brain Network.

The diverse effects of serotonin on cognition may emerge from the modulation of large-scale brain networks that support distinct cognitive processes. Yet, the specific effect of serotoninergic modulation on the properties of these networks remains elusive. Here, we used a simultaneous PET-fMRI scanner combined with graph theory analyses to investigate the modulation of network properties by the Serotonin Transporter (SERT) availability measured in the dorsal raphe nucleus (DRN).

Mucocutaneous Ulcers Unmasking Severe Systemic Methotrexate Toxicity - A Case-Series and Review of Literature.

Background: Methotrexate is a widely used immunosuppressant with good efficacy and cost-effectiveness. However, one of the drawbacks of methotrexate has been toxicity due to accidental overdose. During the COVID pandemic, there was an alarming increase in the number of patients with methotrexate toxicity which prompted us to do this study.

Body mass index-dependent shifts along large-scale gradients in human cortical organization explain dietary regulatory success.

Making healthy dietary choices is essential for keeping weight within a normal range. Yet many people struggle with dietary self-control despite good intentions. What distinguishes neural processing in those who succeed or fail to implement healthy eating goals? Does this vary by weight status? To examine these questions, we utilized an analytical framework of gradients that characterize systematic spatial patterns of large-scale neural activity, which have the advantage of considering the entire suite of processes subserving self-control and potential regulatory tactics at the whole-brain level.

Neurocomputational mechanisms involved in adaptation to fluctuating intentions of others.

Humans frequently interact with agents whose intentions can fluctuate between competition and cooperation over time. It is unclear how the brain adapts to fluctuating intentions of others when the nature of the interactions (to cooperate or compete) is not explicitly and truthfully signaled. Here, we use model-based fMRI and a task in which participants thought they were playing with another player.

HSQC Spectra Simulation and Matching for Molecular Identification.

In the pursuit of improved compound identification and database search tasks, this study explores heteronuclear single quantum coherence (HSQC) spectra simulation and matching methodologies. HSQC spectra serve as unique molecular fingerprints, enabling a valuable balance of data collection time and information richness. We conducted a comprehensive evaluation of the following four HSQC simulation techniques: ACD/Labs (ACD), MestReNova (MNova), Gaussian NMR calculations (DFT), and a graph-based neural network (ML).

Sample efficient reinforcement learning with active learning for molecular design.

Reinforcement learning (RL) is a powerful and flexible paradigm for searching for solutions in high-dimensional action spaces. However, bridging the gap between playing computer games with thousands of simulated episodes and solving real scientific problems with complex and involved environments (up to actual laboratory experiments) requires improvements in terms of sample efficiency to make the most of expensive information. The discovery of new drugs is a major commercial application of RL, motivated by the very large nature of the chemical space and the need to perform multiparameter optimization (MPO) across different properties.

Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity setting.

We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property of interest. This problem arises in discovery processes that rely on screening funnels for trading off the overall costs against throughput and accuracy. Typically, individual stages in these processes are loosely connected and each one generates data at different scale and fidelity.

Reinvent 4: Modern AI-driven generative molecule design.

REINVENT 4 is a modern open-source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within the general machine learning optimization algorithms, transfer learning, reinforcement learning and curriculum learning.

COMPARISON OF THE EFFICACY OF TRAMADOL AND DICLOFENAC IN RELIEVING POSTOPERATIVE PAIN OF LAPAROSCOPIC CHOLECYSTECTOMY.

Tramadol and diclofenac are effective analgesics for pain relief of any complication, however, there are few studies showing the superiority of one over the other. This study aimed to evaluate and compare the analgesic efficacy of diclofenac and tramadol for postoperative pain treatment of laparoscopic surgery of cholecystectomy. There were 120 patients recently operated by laparoscopic surgery of cholecystectomy, who were randomly distributed in two groups: tramadol and diclofenac, administered intramuscularly for a maximum period of five days and demographic and clinical data were collected, as well as the pain evolution during the study period using the verbal numerical scale (VNS) and the functional activity scale (FAS).

Effect of Bicycle Ergometer Training and Nordic Walking Training on Improving Functional Exercise Capacity in Asthma Patients.

Introduction Asthma is a chronic respiratory condition characterized by inflammation of the airway leading to breathlessness. Exercise training has been recognized as a valuable component in the management of asthma, enhancing lung function and overall well-being. Bicycle ergometer training and Nordic walking are two distinct forms of exercise that have been shown to improve cardiovascular fitness and respiratory function.

Modelling local and general quantum mechanical properties with attention-based pooling.

Atom-centred neural networks represent the state-of-the-art for approximating the quantum chemical properties of molecules, such as internal energies. While the design of machine learning architectures that respect chemical principles has continued to advance, the final atom pooling operation that is necessary to convert from atomic to molecular representations in most models remains relatively undeveloped. The most common choices, sum and average pooling, compute molecular representations that are naturally a good fit for many physical properties, while satisfying properties such as permutation invariance which are desirable from a geometric deep learning perspective.

Clinical significance of end of induction measurable residual disease monitoring in B-cell acute lymphoblastic leukemia: A single center experience.

The assessment of measurable residual disease (MRD) has emerged as a powerful prognostic tool for both pediatric and adult acute lymphoblastic leukemia (ALL). This retrospective study aimed to evaluate the prognostic relevance of the end of induction MRD in B-cell acute lymphoblastic leukemia (B ALL) patients. The study included 481 patients who underwent treatment for B ALL between August 2012 and March 2019 and had their MRD at the end of induction assessed by flow cytometry.

Biosorption of Using ZnO-Trimethyl Chitosan Nanocomposite Hydrogel Formed by the Green Synthesis Route.

In this study, we tested the biosorption capacity of trimethyl chitosan (TMC)-ZnO nanocomposite (NC) for the adsorptive removal of () in aqueous suspension. For the formation of ZnO NPs, we followed the green synthesis route involving (TM) aqueous leaf extract as a reducing agent, and the formed ZnO particles were surface-coated with TMC biopolymer. On testing of the physicochemical characteristics, the TM@ZnO/TMC (NC) hydrogel showed a random spherical morphology with an average size of 31.

Combining structural and coevolution information to unveil allosteric sites.

Understanding allosteric regulation in biomolecules is of great interest to pharmaceutical research and computational methods emerged during the last decades to characterize allosteric coupling. However, the prediction of allosteric sites in a protein structure remains a challenging task. Here, we integrate local binding site information, coevolutionary information, and information on dynamic allostery into a structure-based three-parameter model to identify potentially hidden allosteric sites in ensembles of protein structures with orthosteric ligands.

Automated relative binding free energy calculations from SMILES to ΔΔG.

In drug discovery, computational methods are a key part of making informed design decisions and prioritising experiments. In particular, optimizing compound affinity is a central concern during the early stages of development. In the last 10 years, alchemical free energy (FE) calculations have transformed our ability to incorporate accurate in silico potency predictions in design decisions, and represent the 'gold standard' for augmenting experiment-driven drug discovery.

Pancreatoduodenectomy Following Preoperative Biliary Drainage Using Endoscopic Ultrasound-Guided Choledochoduodenostomy Versus a Transpapillary Stent: A Multicenter Comparative Cohort Study of the ACHBT-FRENCH-SFED Intergroup.

Background: It is unclear whether preoperative biliary drainage (PBD) by endoscopic retrograde cholangiopancreatography (ERCP) is equivalent to electrocautery-enhanced lumen-apposing metal stent (ECE-LAMS) before pancreatoduodenectomy (PD).

Methods: Patients who underwent PBD for distal malignant biliary obstruction (DMBO) followed by PD were retrospectively included in nine expert centers between 2015 and 2022. ERCP or endoscopic ultrasound-guided choledochoduodenostomy with ECE-LAMS were performed.

MF-PCBA: Multifidelity High-Throughput Screening Benchmarks for Drug Discovery and Machine Learning.

High-throughput screening (HTS), as one of the key techniques in drug discovery, is frequently used to identify promising drug candidates in a largely automated and cost-effective way. One of the necessary conditions for successful HTS campaigns is a large and diverse compound library, enabling hundreds of thousands of activity measurements per project. Such collections of data hold great promise for computational and experimental drug discovery efforts, especially when leveraged in combination with modern deep learning techniques, and can potentially lead to improved drug activity predictions and cheaper and more effective experimental design.

Artificial intelligence in molecular de novo design: Integration with experiment.

In this mini review, we capture the latest progress of applying artificial intelligence (AI) techniques based on deep learning architectures to molecular de novo design with a focus on integration with experimental validation. We will cover the progress and experimental validation of novel generative algorithms, the validation of QSAR models and how AI-based molecular de novo design is starting to become connected with chemistry automation. While progress has been made in the last few years, it is still early days.