Deep generative models have shown the ability to devise both valid and novel chemistry, which could significantly accelerate the identification of bioactive compounds. Many current models, however, use molecular descriptors or ligand-based predictive methods to guide molecule generation towards a desirable property space. This restricts their application to relatively data-rich targets, neglecting those where little data is available to sufficiently train a predictor. Moreover, ligand-based approaches often bias molecule generation towards previously established chemical space, thereby limiting their ability to identify truly novel chemotypes. In this work, we assess the ability of using molecular docking via Glide—a structure-based approach—as a scoring function to guide the deep generative model REINVENT and compare model performance and behaviour to a ligand-based scoring function. Additionally, we modify the previously published MOSES benchmarking dataset to remove any induced bias towards non-protonatable groups. We also propose a new metric to measure dataset diversity, which is less confounded by the distribution of heavy atom count than the commonly used internal diversity metric. With respect to the main findings, we found that when optimizing the docking score against DRD2, the model improves predicted ligand affinity beyond that of known DRD2 active molecules. In addition, generated molecules occupy complementary chemical and physicochemical space compared to the ligand-based approach, and novel physicochemical space compared to known DRD2 active molecules. Furthermore, the structure-based approach learns to generate molecules that satisfy crucial residue interactions, which is information only available when taking protein structure into account. Overall, this work demonstrates the advantage of using molecular docking to guide de novo molecule generation over ligand-based predictors with respect to predicted affinity, novelty, and the ability to identify key interactions between ligand and protein target. Practically, this approach has applications in early hit generation campaigns to enrich a virtual library towards a particular target, and also in novelty-focused projects, where de novo molecule generation either has no prior ligand knowledge available or should not be biased by it.

With a resurgence in interest in covalent drugs, there is need to identify new moieties capable of cysteine bond formation that are differentiated from commonly employed systems such as acrylamide. Herein, we report on the discovery of new alkynyl benzoxazine and dihydroquinazoline moieties capable of covalent reaction with cysteine. Their utility as alternative electrophilic warheads for chemical biological probes and drug molecules is demonstrated through site-selective protein modification and incorporation into kinase drug scaffolds. A potent covalent inhibitor of JAK3 kinase was identified with superior selectivity across the kinome and improvements in in vitro pharmacokinetic profile relative to the related acrylamide-based inhibitor. In addition, the use of a novel heterocycle as cysteine reactive warhead is employed to target Cys788 in c-KIT where acrylamide has previously failed to form covalent interactions. These new reactive and selective heterocyclic warheads supplement the current repertoire for cysteine covalent modification whilst avoiding some of the limitations generally associated with established moieties.

A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 105 molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale.

Background Culturally relevant interventions are needed to help American Indian and Alaska Native (AI/AN) teenagers and young adults navigate common risky situations involving family and friends, including drug and alcohol misuse, dating violence, and suicidality. Leveraging We R Native, a multimedia health resource for Native teenagers and young adults, staff of the Northwest Portland Area Indian Health Board designed the BRAVE intervention for Native youth. The program is delivered via SMS text messaging and includes role model videos, mental wellness strategies, links to culturally relevant resources, and social support from family and friends. Objective We aim to conduct a randomized controlled trial of the BRAVE intervention among AI/AN teenagers and young adults (aged 15-24 years) to assess its impact on their physical, mental, and spiritual health; their resilience and self-esteem; and their coping and help-seeking skills. Methods From October to December 2019, we recruited 2334 AI/AN teenagers and young adults nationwide via social media channels and SMS text messages and enrolled 1044 participants. AI/AN teenagers and young adults enrolled in the study received either BRAVE SMS text messages, designed to improve mental health, help-seeking skills, and cultural resilience, or 8 weeks of science, technology, engineering, and math (STEM) SMS text messages, designed to elevate and reaffirm Native voices in STEM and medicine and then received the BRAVE SMS text messages. The impacts of the BRAVE intervention were tested using linear mixed-effect models and linear regressions. Results A total of 833 AI/AN teenagers and young adults were included in the analysis. Individuals in the BRAVE and STEM arms showed significant positive trends over the course of the study for all outcomes, except cultural identity and help-seeking behavior. Mean scores were significantly different for health (P<.001), resilience (P<.001), negative coping (P=.03), positive coping (P<.001), self-efficacy (P=.02), and self-esteem (P<.001). Changes in help-seeking self-efficacy were significant in those exhibiting risky behaviors at baseline to exit (P=.01). Those who reported positive coping scores at baseline also reported better health on average; however, no difference was found in risky drug and alcohol use (P<.001). The number of participants who used SMS text messages to help themselves increased from 69.1% (427/618) at 3 months to 76% (381/501; P<.001) at 8 months. Similarly, the number of participants who used SMS text messages to help friends or family members increased from 22.4% (138/616) at 3 months to 54.6% (272/498) at 8 months. Conclusions This is the first national randomized controlled trial of a mobile health intervention among AI/AN teenagers and young adults to test the efficacy of a mental wellness intervention in relation to STEM career messages. This study provides new insights for supporting the next generation of AI/AN changemakers. Trial Registration ClinicalTrials.gov NCT04979481; https://clinicaltrials.gov/ct2/show/NCT04979481

Many barriers to genetic testing currently exist which delay or prevent diagnosis. These barriers include wait times, staffing, education, and cost. Specialists are able to identify patients with disease that may need genetic testing, but lack the genetics support to facilitate that testing in the most cost, time, and medically effective manner. The Nephrology Division and the Genetic Testing Stewardship Program at Nemours A.I. duPont Hospital for Children created a novel service delivery model in which nephrologists and genetic counselors collaborate in order to highlight their complementary strengths (clinical expertise of nephrologists and genetics and counseling skills of genetic counselors). This collaboration has reduced many barriers to care for our patients. This workflow facilitated the offering of genetic testing to 76 patients, with 86 tests completed over a 20‐month period. Thirty‐two tests were deferred. Twenty‐seven patients received a diagnosis, which lead to a change in their medical management, three of whom were diagnosed by cascade family testing. Forty‐two patients had a negative result and 16 patients had one or more variants of uncertain significance on testing. The inclusion of genetic counselors in the workflow is integral toward choosing the most cost and time effective genetic testing strategy, as well as providing psychosocial support to families. The genetic counselors obtain informed consent, and review genetic test results and recommendations with the patient and their family. The availability of this program to our patients increased access to genetic testing and helps to provide diagnoses and supportive care.