'It wasn't the strategies on their own': Exploring caregivers' experiences of accessing services in the development of interventions for autistic people with intellectual disability

LAY ABSTRACT

Many autistic individuals with intellectual disability experience anxiety, and for those who use few or no words, anxiety may present as behaviour that challenges, such as self-injury and avoiding anxiety-provoking situations. Families report difficulty accessing support from services for autistic individuals experiencing anxiety. Moreover, once receiving support, effective interventions for autistic people with intellectual disability are limited. We completed individual and group discussions with 16 caregivers of autistic people with intellectual disability, to (a) explore their experiences of accessing services for anxiety and/or behaviour that challenges for their child; and (b) understand what matters to caregivers when developing interventions that have been designed for them and the autistic individual with intellectual disability that they support. Caregivers reported that services, in their experience, did not deliver the support that they expected, and that they often needed to 'fight' for support. Caregivers considered services and families working together, the inclusion of peer support, and families being offered interventions that are flexible to individual circumstances to be important. These considerations are valuable for clinicians and researchers developing interventions and aiming to improve outcomes for autistic people with intellectual disability and their families.

New approach methodologies (NAMs): identifying and overcoming hurdles to accelerated adoption

New approach methodologies (NAMs) can deliver improved chemical safety assessment through the provision of more protective and/or relevant models that have a reduced reliance on animals. Despite the widely acknowledged benefits offered by NAMs, there continue to be barriers that prevent or limit their application for decision-making in chemical safety assessment. These include barriers related to real and perceived scientific, technical, legislative and economic issues, as well as cultural and societal obstacles that may relate to inertia, familiarity, and comfort with established methods, and perceptions around regulatory expectations and acceptance. This article focuses on chemical safety science, exposure, hazard, and risk assessment, and explores the nature of these barriers and how they can be overcome to drive the wider exploitation and acceptance of NAMs. Short-, mid- and longer-term goals are outlined that embrace the opportunities provided by NAMs to deliver improved protection of human health and environmental security as part of a new paradigm that incorporates exposure science and a culture that promotes the use of protective toxicological risk assessments.

Reduced prosocial motivation and effort in adolescents with conduct problems and callous-unemotional traits

BACKGROUND

Prosocial behaviours - acts that benefit others - are of crucial importance for many species including humans. However, adolescents with conduct problems (CP), unlike their typically developing (TD) peers, demonstrate markedly reduced engagement in prosocial behaviours. This pattern is particularly pronounced in adolescents with CP and high levels of callous-unemotional traits (CP/HCU) who are at increased risk of developing psychopathy in adulthood. While a substantial amount of research has investigated the cognitive-affective mechanisms thought to underlie antisocial behaviour, much less is known about the mechanisms that could explain reduced prosocial behaviours in adolescents with CP.

METHODS

Here we examined the willingness to exert effort to benefit oneself (self) and another person (other, prosocial condition) in children with CP/HCU, CP and lower levels of CU traits (CP/LCU) and their TD peers. The task captured both prosocial choices, and actual effort exerted following prosocial choices, in adolescent boys aged 11-16 (27 CP/HCU; 34 CP/LCU; 33 TD). We used computational modelling to reveal the mechanistic processes involved when choosing prosocial acts.

RESULTS

We found that both CP/HCU and CP/LCU groups were more averse to initiating effortful prosocial acts than TD adolescents - both at a cognitive and at a behavioural level. Strikingly, even if they chose to initiate a prosocial act, the CP/HCU group exerted less effort following this prosocial choice than other groups.

CONCLUSIONS

Our findings indicate that reduced exertion of effort to benefit others may be an important factor that differentiates adolescents with CP/HCU from their peers with CP/LCU. They offer new insights into what might drive low prosocial behaviour in adolescents with CP, including vulnerabilities that may particularly characterise those with high levels of CU traits.

Parenting boys with conduct problems and callous-unemotional traits: parent and child perspectives

Parenting children with conduct problems (CP) is challenging, yet very little research has examined parenting using both quantitative and qualitative methods, from the perspective of the child and their parent/caregiver, and separately for those with high vs. low levels of callous-unemotional traits (HCU vs. LCU). One hundred and forty-six boys aged 11-16 [Typically developing (TD) n = 31; CP/HCU n = 35; CP/LCU n = 35] and their parents/caregivers completed the Alabama Parenting Questionnaire and provided a written qualitative statement describing their respective experiences of parenting/being parented. Parents/caregivers of CP/HCU boys reported more difficulty with child monitoring and supervision than parents of TD boys. This was echoed in qualitative reports of parents of CP/HCU boys reporting concerns regarding their child's safety. Parents/caregivers of both groups of CP boys reported more inconsistent discipline than parents of TD boys. Parental qualitative descriptions of challenging behavior in CP/HCU boys, and difficulties with setting boundaries and motivating CP/LCU boys, provided further insight to the potential triggers for inconsistent discipline. Qualitative reports from boys with CP indicated that they understood the parenting challenges their parents/caregivers faced. These findings replicate and extend previous work on the associations between parenting and CP. Children with CP/HCU and CP/LCU show some commonalities and differences in their parenting experiences and CP children and their parents/caregivers do not necessarily share all the same perceptions or concerns. CP interventions often involve parent/family engagement and this research highlights the continued importance of examining both parent and child perspectives.

A generative adversarial network model alternative to animal studies for clinical pathology assessment

Animal studies are unavoidable in evaluating chemical and drug safety. Generative Adversarial Networks (GANs) can generate synthetic animal data by learning from the legacy animal study results, thus may serve as an alternative approach to assess untested chemicals. AnimalGAN, a GAN method to simulate 38 rat clinical pathology measures, was developed with significant robustness even for the drugs that vary significantly from these used during training, both in terms of chemical structure, drug class, and the year of FDA approval. AnimalGAN showed comparable results in hepatotoxicity assessment as using the real animal data and outperformed 12 conventional quantitative structure-activity relationship approaches. Using AnimalGAN, a virtual experiment of 100,000 rats ranked hepatotoxicity of three structurally similar drugs in a similar trend that has been observed in human population. AnimalGAN represented a significant step with artificial intelligence towards the global effort in replacement, reduction, and refinement (3Rs) of animal use.

PLM-ARG: antibiotic resistance gene identification using a pretrained protein language model

MOTIVATION

Antibiotic resistance presents a formidable global challenge to public health and the environment. While considerable endeavors have been dedicated to identify antibiotic resistance genes (ARGs) for assessing the threat of antibiotic resistance, recent extensive investigations using metagenomic and metatranscriptomic approaches have unveiled a noteworthy concern. A significant fraction of proteins defies annotation through conventional sequence similarity-based methods, an issue that extends to ARGs, potentially leading to their under-recognition due to dissimilarities at the sequence level.

RESULTS

Herein, we proposed an Artificial Intelligence-powered ARG identification framework using a pretrained large protein language model, enabling ARG identification and resistance category classification simultaneously. The proposed PLM-ARG was developed based on the most comprehensive ARG and related resistance category information (>28K ARGs and associated 29 resistance categories), yielding Matthew's correlation coefficients (MCCs) of 0.983 ± 0.001 by using a 5-fold cross-validation strategy. Furthermore, the PLM-ARG model was verified using an independent validation set and achieved an MCC of 0.838, outperforming other publicly available ARG prediction tools with an improvement range of 51.8%-107.9%. Moreover, the utility of the proposed PLM-ARG model was demonstrated by annotating resistance in the UniProt database and evaluating the impact of ARGs on the Earth's environmental microbiota.

AVAILABILITY AND IMPLEMENTATION

PLM-ARG is available for academic purposes at https://github.com/Junwu302/PLM-ARG, and a user-friendly webserver (http://www.unimd.org/PLM-ARG) is also provided.

An integrated approach for early in vitro seizure prediction utilizing hiPSC neurons and human ion channel assays

Seizure liability remains a significant cause of attrition throughout drug development. Advances in stem cell biology coupled with an increased understanding of the role of ion channels in seizure offer an opportunity for a new paradigm in screening. We assessed the activity of 15 pro-seizurogenic compounds (7 CNS active therapies, 4 GABA receptor antagonists, and 4 other reported seizurogenic compounds) using automated electrophysiology against a panel of 14 ion channels (Nav1.1, Nav1.2, Nav1.6, Kv7.2/7.3, Kv7.3/7.5, Kv1.1, Kv4.2, KCa4.1, Kv2.1, Kv3.1, KCa1.1, GABA α1β2γ2, nicotinic α4β2, NMDA 1/2A). These were selected based on linkage to seizure in genetic/pharmacological studies. Fourteen compounds demonstrated at least one "hit" against the seizure panel and 11 compounds inhibited 2 or more ion channels. Next, we assessed the impact of the 15 compounds on electrical signaling using human-induced pluripotent stem cell neurons in microelectrode array (MEA). The CNS active therapies (amoxapine, bupropion, chlorpromazine, clozapine, diphenhydramine, paroxetine, quetiapine) all caused characteristic changes to electrical activity in key parameters indicative of seizure such as network burst frequency and duration. The GABA antagonist picrotoxin increased all parameters, but the antibiotics amoxicillin and enoxacin only showed minimal changes. Acetaminophen, included as a negative control, caused no changes in any of the parameters assessed. Overall, pro-seizurogenic compounds showed a distinct fingerprint in the ion channel/MEA panel. These studies highlight the potential utility of an integrated in vitro approach for early seizure prediction to provide mechanistic information and to support optimal drug design in early development, saving time and resources.

DeepAmes: A deep learning-powered Ames test predictive model with potential for regulatory application

The Ames assay is required by the regulatory agencies worldwide to assess the mutagenic potential risk of consumer products. As well as this in vitro assay, in silico approaches have been widely used to predict Ames test results as outlined in the International Council for Harmonization (ICH) guidelines. Building on this in silico approach, here we describe DeepAmes, a high performance and robust model developed with a novel deep learning (DL) approach for potential utility in regulatory science. DeepAmes was developed with a large and consistent Ames dataset (>10,000 compounds) and was compared with other five standard Machine Learning (ML) methods. Using a test set of 1,543 compounds, DeepAmes was the best performer in predicting the outcome of Ames assay. In addition, DeepAmes yielded the best and most stable performance up to when compounds were >30% outside of the applicability domain (AD). Regarding the potential for regulatory application, a revised version of DeepAmes with a much-improved sensitivity of 0.87 from 0.47. In conclusion, DeepAmes provides a DL-powered Ames test predictive model for predicting the results of Ames tests; with its defined AD and clear context of use, DeepAmes has potential for utility in regulatory application.

TransOrGAN: An Artificial Intelligence Mapping of Rat Transcriptomic Profiles between Organs, Ages, and Sexes

Animal studies are required for the evaluation of candidate drugs to ensure patient and volunteer safety. Toxicogenomics is often applied in these studies to gain understanding of the underlying mechanisms of toxicity, which is usually focused on critical organs such as the liver or kidney in young male rats. There is a strong ethical reason to reduce, refine and replace animal use (the 3Rs), where the mapping of data between organs, sexes and ages could reduce the cost and time of drug development. Herein, we proposed a generative adversarial network (GAN)-based framework entitled TransOrGAN that allowed the molecular mapping of gene expression profiles in different rodent organ systems and across sex and age groups. We carried out a proof-of-concept study based on rat RNA-seq data from 288 samples in 9 different organs of both sexes and 4 developmental stages. First, we demonstrated that TransOrGAN could infer transcriptomic profiles between any 2 of the 9 organs studied, yielding an average cosine similarity of 0.984 between synthetic transcriptomic profiles and their corresponding real profiles. Second, we found that TransOrGAN could infer transcriptomic profiles observed in females from males, with an average cosine similarity of 0.984. Third, we found that TransOrGAN could infer transcriptomic profiles in juvenile, adult, and aged animals from adolescent animals with an average cosine similarity of 0.981, 0.983, and 0.989, respectively. Altogether, TransOrGAN is an innovative approach to infer transcriptomic profiles between ages, sexes, and organ systems, offering the opportunity to reduce animal usage and to provide an integrated assessment of toxicity in the whole organism irrespective of sex or age.

The Precision Toxicology Initiative

The goal of PrecisionTox is to overcome conceptual barriers to replacing traditional mammalian chemical safety testing by accelerating the discovery of evolutionarily conserved toxicity pathways that are shared by descent among humans and more distantly related animals. An international consortium is systematically testing the toxicological effects of a diverse set of chemicals on a suite of five model species comprising fruit flies, nematodes, water fleas, and embryos of clawed frogs and zebrafish along with human cell lines. Multiple forms of omics and comparative toxicology data are integrated to map the evolutionary origins of biomolecular interactions, which are predictive of adverse health effects, to major branches of the animal phylogeny. These conserved elements of adverse outcome pathways (AOPs) and their biomarkers are expect to provide mechanistic insight useful for regulating groups of chemicals based on their shared modes of action. PrecisionTox also aims to quantify risk variation within populations by recognizing susceptibility as a heritable trait that varies with genetic diversity. This initiative incorporates legal experts and collaborates with risk managers to address specific needs within European chemicals legislation, including the uptake of new approach methodologies (NAMs) for setting precise regulatory limits on toxic chemicals.

Artificial intelligence and real-world data for drug and food safety - A regulatory science perspective

In 2013, the Global Coalition for Regulatory Science Research (GCRSR) was established with members from over ten countries (www.gcrsr.net). One of the main objectives of GCRSR is to facilitate communication among global regulators on the rise of new technologies with regulatory applications through the annual conference Global Summit on Regulatory Science (GSRS). The 11th annual GSRS conference (GSRS21) focused on "Regulatory Sciences for Food/Drug Safety with Real-World Data (RWD) and Artificial Intelligence (AI)." The conference discussed current advancements in both AI and RWD approaches with a specific emphasis on how they impact regulatory sciences and how regulatory agencies across the globe are pursuing the adaptation and oversight of these technologies. There were presentations from Brazil, Canada, India, Italy, Japan, Germany, Switzerland, Singapore, the United Kingdom, and the United States. These presentations highlighted how various agencies are moving forward with these technologies by either improving the agencies' operation and/or preparing regulatory mechanisms to approve the products containing these innovations. To increase the content and discussion, the GSRS21 hosted two debate sessions on the question of "Is Regulatory Science Ready for AI?" and a workshop to showcase the analytical data tools that global regulatory agencies have been using and/or plan to apply to regulatory science. Several key topics were highlighted and discussed during the conference, such as the capabilities of AI and RWD to assist regulatory science policies for drug and food safety, the readiness of AI and data science to provide solutions for regulatory science. Discussions highlighted the need for a constant effort to evaluate emerging technologies for fit-for-purpose regulatory applications. The annual GSRS conferences offer a unique platform to facilitate discussion and collaboration across regulatory agencies, modernizing regulatory approaches, and harmonizing efforts.

US regulations to curb alleged cancer causes are ineffectual and compromised by scientific, constitutional and ethical violations

The 1958 Delaney amendment to the Federal Food Drug and Cosmetics Act prohibited food additives causing cancer in animals by appropriate tests. Regulators responded by adopting chronic lifetime cancer tests in rodents, soon challenged as inappropriate, for they led to very inconsistent results depending on the subjective choice of animals, test design and conduct, and interpretive assumptions. Presently, decades of discussions and trials have come to conclude it is impossible to translate chronic animal data into verifiable prospects of cancer hazards and risks in humans. Such conclusion poses an existential crisis for official agencies in the US and abroad, which for some 65 years have used animal tests to justify massive regulations of alleged human cancer hazards, with aggregated costs of $trillions and without provable evidence of public health advantages. This article addresses suitable remedies for the US and potentially worldwide, by critically exploring the practices of regulatory agencies vis-á-vis essential criteria for validating scientific evidence. According to this analysis, regulations of alleged cancer hazards and risks have been and continue to be structured around arbitrary default assumptions at odds with basic scientific and legal tests of reliable evidence. Such practices raise a manifold ethical predicament for being incompatible with basic premises of the US Constitution, and with the ensuing public expectations of testable truth and transparency from government agencies. Potential remedies in the US include amendments to the US Administrative Procedures Act, preferably requiring agencies to justify regulations compliant with the Daubert opinion of the Daubert ruling of the US Supreme Court, which codifies the criteria defining reliable scientific evidence. International reverberations are bound to follow what remedial actions may be taken in the US, the origin of current world regulatory procedures to control alleged cancer causing agents.

Science-led regulatory strategies in nonclinical development of new medicines

The development of a pharmaceutical is a stepwise process involving an evaluation of both animal and human efficacy and safety information. Regulations around drug development exist to protect people and the environment from harm and should create a level playing field for business, allowing well-run companies to thrive. However, adherence to good science should guide decisions rather than rigorously following guidelines, and there is almost always more than one way to get to the ultimate goal.

Effects of Integrated Vector Management in the Control of Malaria Infection: An Intervention Study in a Malaria Endemic Community in Nigeria

BACKGROUND/AIM

Malaria is a vector borne disease with high morbidity and mortality in endemic regions. In view to eliminating the disease, integrated vector and environmental hygiene practices have been advocated. There is paucity of studies on the effect of vector control measures on asymptomatic malaria infection which has been observed to be a reflection of malaria transmission.

METHODS

Longitudinal community-based intervention study carried out from October to December 2017. Study participants were 477 individuals living in 100 households selected by snow-balling sampling methods. Pre-intervention period included training of all heads of households on vector control methods. During the intervention period, each household received waste bins, two long lasting insecticide bed nets and had wire screen on their doors and windows; every household member was screened for malaria (antigen) using the pf rapid diagnostic test kits. Each household were monitored to ensure they comply with the environmental hygiene practices they were taught. Post-intervention malaria infection was obtained at 8 week being end of the intervention period.

RESULTS

Of the 100 households selected, 54.0% were from the lower social class, 45.0% middle class and only 1.0% upper class. Mean age [±] of the heads of the households was 37.1 ± 11.0 (range 16-68) years. There were 477 individuals recruited in the study from the 100 households; 234 (49.0%) females and 243 (51.0%) males; median age was 20.0 (range 1-100) years. Prevalence of malaria infection using mRDT during pre-intervention was 16.8% and an incidence of 1.3% post-intervention. There was 92.0% reduction in asymptomatic malaria infection showing marked reduction in malaria transmission in the study locale.

CONCLUSION

Some integrated vector control measures such as use of insecticide-treated net and sanitation were found effective methods for reducing malaria infection and transmission in endemic region.

Early Childhood Exposures to Fluorides and Child Behavioral Development and Executive Function: A Population-Based Longitudinal Study

It is important to both protect the healthy development and maintain the oral health of the child population. The study examined the effect of early childhood exposures to water fluoridation on measures of school-age executive functioning and emotional and behavioral development in a population-based sample. This longitudinal follow-up study used information from Australia's National Child Oral Health Study 2012-14. Children aged 5 to 10 y at baseline were contacted again after 7 to 8 y, before they had turned 18 y of age. Percent lifetime exposed to fluoridated water (%LEFW) from birth to the age 5 y was estimated from residential history and postcode-level fluoride levels in public tap water. Measures of children's emotional and behavioral development were assessed by the Strength and Difficulties Questionnaire (SDQ), and executive functioning was measured by the Behavior Rating Inventory of Executive Function (BRIEF). Multivariable regression models were generated to compare the associations between the exposure and the primary outcomes and controlled for covariates. An equivalence test was also conducted to compare the primary outcomes of those who had 100% LEFW against those with 0% LEFW. Sensitivity analysis was also conducted. A total of 2,682 children completed the SDQ and BRIEF, with mean scores of 7.0 (95% confidence interval, 6.6-7.4) and 45.3 (44.7-45.8), respectively. Those with lower %LEFW tended to have poorer scores of the SDQ and BRIEF. Multivariable regression models reported no association between exposure to fluoridated water and the SDQ and BRIEF scores. Low household income, identifying as Indigenous, and having a neurodevelopmental diagnosis were associated with poorer SDQ/BRIEF scores. An equivalence test confirmed that the SDQ/BRIEF scores among those with 100% LEFW were equivalent to that of those who had 0% LEFW. Exposure to fluoridated water during the first 5 y of life was not associated with altered measures of child emotional and behavioral development and executive functioning.

Adaptability of AI for safety evaluation in regulatory science: A case study of drug-induced liver injury

Artificial intelligence (AI) has played a crucial role in advancing biomedical sciences but has yet to have the impact it merits in regulatory science. As the field advances, in silico and in vitro approaches have been evaluated as alternatives to animal studies, in a drive to identify and mitigate safety concerns earlier in the drug development process. Although many AI tools are available, their acceptance in regulatory decision-making for drug efficacy and safety evaluation is still a challenge. It is a common perception that an AI model improves with more data, but does reality reflect this perception in drug safety assessments? Importantly, a model aiming at regulatory application needs to take a broad range of model characteristics into consideration. Among them is adaptability, defined as the adaptive behavior of a model as it is retrained on unseen data. This is an important model characteristic which should be considered in regulatory applications. In this study, we set up a comprehensive study to assess adaptability in AI by mimicking the real-world scenario of the annual addition of new drugs to the market, using a model we previously developed known as DeepDILI for predicting drug-induced liver injury (DILI) with a novel Deep Learning method. We found that the target test set plays a major role in assessing the adaptive behavior of our model. Our findings also indicated that adding more drugs to the training set does not significantly affect the predictive performance of our adaptive model. We concluded that the proposed adaptability assessment framework has utility in the evaluation of the performance of a model over time.

Best practice and reproducible science are required to advance artificial intelligence in real-world applications

Drug-induced liver injury (DILI) is one of the most significant concerns in medical practice but yet it still cannot be fully recapitulated with existing in vivo, in vitro and in silico approaches. To address this challenge, Chen et al. [ 1] developed a deep learning-based DILI prediction model based on chemical structure information alone. The reported model yielded an outstanding prediction performance (i.e. 0.958, 0.976, 0.935, 0.947, 0.926 and 0.913 for AUC, accuracy, recall, precision, F1-score and specificity, respectively, on a test set), far outperforming all publicly available and similar in silico DILI models. This extraordinary model performance is counter-intuitive to what we know about the underlying biology of DILI and the principles and hypothesis behind this type of in silico approach. In this Letter to the Editor, we raise awareness of several issues concerning data curation, model validation and comparison practices, and data and model reproducibility.

Insulin Titration Guidelines for Patients With Type 1 Diabetes: It Is About Time!

PURPOSE

A proposal that an Insulin Advisory Committee develop insulin titration guidelines 100 years after its discovery.

FINDINGS

Glucose control metrics remain poor despite significant advances in diabetes technology.

SUMMARY

A century after the introduction of insulin, health care providers and patients with type 1 diabetes have worldwide access to a variety of insulin delivery devices (IDDs), glucose monitors, bolus calculators (BCs), continuous glucose monitors (CGMs), and automated insulin delivery (AID) systems. However, these advances have not enabled most patients to achieve today's clear A1c and time-in-range goals. Much of this failure arises from the lack of clear insulin titration guidelines for determining appropriate insulin doses. The lack of dosing clarity results in local physicians, clinics, and individual patients managing insulin titrations as they see fit, creating significant inefficiencies for reaching recommended glycemic goals. This review (1) details the widespread problems generated by nonphysiological dose settings in today's BCs, insulin pumps, and AID systems; (2) presents a method to develop and implement optimized total daily doses of insulin to correct the most common problem of hyperglycemia; (3) discusses using large device databases to provide clear insulin titration guidelines that optimize BC settings from an optimized total daily dose (TDD) of insulin for patients with T1D; and (4) recommends the formation of an Insulin Advisory Committee to clarify the steps to take toward universal insulin titration guidelines, optimized BC settings, and a systematic logic for their use in insulin delivery devices.

Towards accurate and reliable resolution of structural variants for clinical diagnosis

Structural variants (SVs) are a major source of human genetic diversity and have been associated with different diseases and phenotypes. The detection of SVs is difficult, and a diverse range of detection methods and data analysis protocols has been developed. This difficulty and diversity make the detection of SVs for clinical applications challenging and requires a framework to ensure accuracy and reproducibility. Here, we discuss current developments in the diagnosis of SVs and propose a roadmap for the accurate and reproducible detection of SVs that includes case studies provided from the FDA-led SEquencing Quality Control Phase II (SEQC-II) and other consortium efforts.

Social information use in adolescents with conduct problems and varying levels of callous-unemotional traits

Background

Adolescents with conduct problems (CP) are characterised by difficulties with social relationships and display atypical social cognition, such as when interpreting emotional expressions or engaging in social problem-solving. One important aspect of social cognition that warrants investigation is the degree to which these adolescents factor others' views into their already held beliefs, and strategies used to do so. Effective social information use enables attunement to social environment, cooperation, and social problem-solving. Difficulties in this regard could contribute to problems in social interactions in adolescents with CP, and may vary with adolescents' high (CP/HCU) versus low levels of callous-unemotional traits (CP/LCU).

Methods

We compared social information use in boys (11-16 years) with CP/HCU (n = 32), CP/LCU (n = 31) and typically developing (TD) peers (n = 45), matched for IQ. Participants provided estimates of numbers of animals on a screen, saw another adolescent's estimate, and could adjust their initial estimate. We compared two aspects of social information use: (1) degree of adjustment of initial estimate towards another's estimate and (2) strategy use when adjusting estimates.

Results

Degree of adjustment towards another's estimate did not vary across groups, but strategy use did. Adolescents with CP/LCU compromised less following social information than TD peers.

Conclusions

Findings suggest that while adolescents with CP are able to take social information into account, those with CP/LCU use this information in a way that differs from other groups and could be less efficient. This warrants further systematic investigation as it could represent a target for behaviour management strategies. Overall, this study highlights the need for more research delineating the social-cognitive profile of adolescents with CP/LCU.

Tox-GAN: An AI Approach Alternative to Animal Studies-a Case Study with Toxicogenomics

Animal studies are a critical component in biomedical research, pharmaceutical product development, and regulatory submissions. There is a worldwide effort in toxicology towards "reducing, refining and replacing" (3Rs) animal use. Here, we proposed a deep generative adversarial network (GAN)-based framework capable of deriving new animal results from existing animal studies without additional experiments. To prove the concept, we employed this Tox-GAN framework to generate both gene activities and expression profiles for multiple doses and treatment durations in toxicogenomics (TGx). Using the pre-existing rat liver TGx data from the Open TG-GATEs, we generated Tox-GAN transcriptomic profiles with high similarity (0.997 ± 0.002 in intensity and 0.740 ± 0.082 in fold change) to the corresponding real gene expression profiles. Consequently, Tox-GAN showed an outstanding performance in two critical TGx applications, gaining a molecular understanding of underlying toxicological mechanisms and gene expression-based biomarker development. For the former, over 87% agreement in Gene Ontology was found between Tox-GAN results and real gene expression data. For the latter, the concordance of biomarkers between real and generated data was high in both predictive performance and biomarker genes. We also demonstrated that the Tox-GAN models constructed with TG-GATEs data were capable of generating transcriptomic profiles reported in DrugMatrix. Finally, we demonstrated potential utility for Tox-GAN in aiding chemical-based read-across. To the best of our knowledge, the proposed Tox-GAN model is novel in its ability to generate in vivo transcriptomic profiles at different treatment conditions from chemical structures. Overall, Tox-GAN holds great promise for generating high-quality toxicogenomic profiles without animal experimentation.

Key Characteristics of Human Hepatotoxicants as a Basis for Identification and Characterization of the Causes of Liver Toxicity

Hazard identification regarding adverse effects on the liver is a critical step in safety evaluations of drugs and other chemicals. Current testing paradigms for hepatotoxicity rely heavily on preclinical studies in animals and human data (epidemiology and clinical trials). Mechanistic understanding of the molecular and cellular pathways that may cause or exacerbate hepatotoxicity is well advanced and holds promise for identification of hepatotoxicants. One of the challenges in translating mechanistic evidence into robust decisions about potential hepatotoxicity is the lack of a systematic approach to integrate these data to help identify liver toxicity hazards. Recently, marked improvements were achieved in the practice of hazard identification of carcinogens, female and male reproductive toxicants, and endocrine disrupting chemicals using the key characteristics approach. Here, we describe the methods by which key characteristics of human hepatotoxicants were identified and provide examples for how they could be used to systematically identify, organize, and use mechanistic data when identifying hepatotoxicants.

DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation

Carcinogenicity testing plays an essential role in identifying carcinogens in environmental chemistry and drug development. However, it is a time-consuming and label-intensive process to evaluate the carcinogenic potency with conventional 2-years rodent animal studies. Thus, there is an urgent need for alternative approaches to providing reliable and robust assessments on carcinogenicity. In this study, we proposed a DeepCarc model to predict carcinogenicity for small molecules using deep learning-based model-level representations. The DeepCarc Model was developed using a data set of 692 compounds and evaluated on a test set containing 171 compounds in the National Center for Toxicological Research liver cancer database (NCTRlcdb). As a result, the proposed DeepCarc model yielded a Matthews correlation coefficient (MCC) of 0.432 for the test set, outperforming four advanced deep learning (DL) powered quantitative structure-activity relationship (QSAR) models with an average improvement rate of 37%. Furthermore, the DeepCarc model was also employed to screen the carcinogenicity potential of the compounds from both DrugBank and Tox21. Altogether, the proposed DeepCarc model could serve as an early detection tool (https://github.com/TingLi2016/DeepCarc) for carcinogenicity assessment.

DICE: A Drug Indication Classification and Encyclopedia for AI-Based Indication Extraction

Drug labeling contains an ‘INDICATIONS AND USAGE’ that provides vital information to support clinical decision making and regulatory management. Effective extraction of drug indication information from free-text based resources could facilitate drug repositioning projects and help collect real-world evidence in support of secondary use of approved medicines. To enable AI-powered language models for the extraction of drug indication information, we used manual reading and curation to develop a Drug Indication Classification and Encyclopedia (DICE) based on FDA approved human prescription drug labeling. A DICE scheme with 7,231 sentences categorized into five classes (indications, contradictions, side effects, usage instructions, and clinical observations) was developed. To further elucidate the utility of the DICE, we developed nine different AI-based classifiers for the prediction of indications based on the developed DICE to comprehensively assess their performance. We found that the transformer-based language models yielded an average MCC of 0.887, outperforming the word embedding-based Bidirectional long short-term memory (BiLSTM) models (0.862) with a 2.82% improvement on the test set. The best classifiers were also used to extract drug indication information in DrugBank and achieved a high enrichment rate (>0.930) for this task. We found that domain-specific training could provide more explainable models without performance sacrifices and better generalization for external validation datasets. Altogether, the proposed DICE could be a standard resource for the development and evaluation of task-specific AI-powered, natural language processing (NLP) models.

X-CNV: genome-wide prediction of the pathogenicity of copy number variations

Background

Gene copy number variations (CNVs) contribute to genetic diversity and disease prevalence across populations. Substantial efforts have been made to decipher the relationship between CNVs and pathogenesis but with limited success.

Results

We have developed a novel computational framework X-CNV (www.unimd.org/XCNV), to predict the pathogenicity of CNVs by integrating more than 30 informative features such as allele frequency (AF), CNV length, CNV type, and some deleterious scores. Notably, over 14 million CNVs across various ethnic groups, covering nearly 93% of the human genome, were unified to calculate the AF. X-CNV, which yielded area under curve (AUC) values of 0.96 and 0.94 in training and validation sets, was demonstrated to outperform other available tools in terms of CNV pathogenicity prediction. A meta-voting prediction (MVP) score was developed to quantitively measure the pathogenic effect, which is based on the probabilistic value generated from the XGBoost algorithm. The proposed MVP score demonstrated a high discriminative power in determining pathogenetic CNVs for inherited traits/diseases in different ethnic groups.

Conclusions

The ability of the X-CNV framework to quantitatively prioritize functional, deleterious, and disease-causing CNV on a genome-wide basis outperformed current CNV-annotation tools and will have broad utility in population genetics, disease-association studies, and diagnostic screening.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13073-021-00945-4.

Barriers and facilitators to mood and confidence in pregnancy and early parenthood during COVID-19 in the UK: mixed-methods synthesis survey

BACKGROUND

Parental well-being during pregnancy and early parenthood is critical for child development. Environmental stressors can significantly challenge parental well-being.

AIMS

To investigate how COVID-19 and associated restrictions influence mood and parenting confidence of expectant parents and those in early parenthood, identifying barriers and facilitators.

METHOD

We used a cross-sectional online survey to collect data from 590 expectant parents and parents of infants (564 women) during the most restrictive phase of lockdown in the UK. We included a mixture of forced-choice and open-ended questions pertaining to mood, perceived social support, media use, online interactions and parenting expectations. Quantitative data were analysed with multiple linear regression and proportional odds models; an inductive thematic analysis was used for qualitative data. Quantitative and qualitative data were qualitatively synthesised.

RESULTS

Since COVID-19, expectant parents and parents of new-borns reported a decrease in mood and parenting confidence. Barriers included practical difficulties (finding essentials, reliable health information), social difficulties (loss of physical contact, decreased support) and uncertainty during pregnancy. Facilitators included support from others and, for first-time parents, loss of child care resulting in greater parenting confidence. Although online resources and communication were not preferable to face-to-face interactions, technology was a helpful tool for communicating, getting support, and finding essentials and information during lockdown.

CONCLUSIONS

By mid-May 2020, mood and parenting confidence among expectant and parents of new-borns in the UK were significantly reduced. Consideration of barriers and facilitators in healthcare and psychological support provided is likely important for promoting parental mental health and healthy parent-child relationships.

InferBERT: A Transformer-Based Causal Inference Framework for Enhancing Pharmacovigilance

Background: T ransformer-based language models have delivered clear improvements in a wide range of natural language processing (NLP) tasks. However, those models have a significant limitation; specifically, they cannot infer causality, a prerequisite for deployment in pharmacovigilance, and health care. Therefore, these transformer-based language models should be developed to infer causality to address the key question of the cause of a clinical outcome.

Results: In this study, we propose an innovative causal inference model–InferBERT, by integrating the A Lite Bidirectional Encoder Representations from Transformers (ALBERT) and Judea Pearl’s Do-calculus to establish potential causality in pharmacovigilance. Two FDA Adverse Event Reporting System case studies, including Analgesics-related acute liver failure and Tramadol-related mortalities, were employed to evaluate the proposed InferBERT model. The InferBERT model yielded accuracies of 0.78 and 0.95 for identifying Analgesics-related acute liver failure and Tramadol-related death cases, respectively. Meanwhile, the inferred causes of the two clinical outcomes, (i.e. acute liver failure and death) were highly consistent with clinical knowledge. Furthermore, inferred causes were organized into a causal tree using the proposed recursive do-calculus algorithm to improve the model’s understanding of causality. Moreover, the high reproducibility of the proposed InferBERT model was demonstrated by a robustness assessment.

Conclusion: The empirical results demonstrated that the proposed InferBERT approach is able to both predict clinical events and to infer their causes. Overall, the proposed InferBERT model is a promising approach to establish causal effects behind text-based observational data to enhance our understanding of intrinsic causality.

Availability and implementation: The InferBERT model and preprocessed FAERS data sets are available on GitHub at https://github.com/XingqiaoWang/DeepCausalPV-master.

Unraveling Gene Fusions for Drug Repositioning in High-Risk Neuroblastoma

High-risk neuroblastoma (NB) remains a significant therapeutic challenge facing current pediatric oncology patients. Structural variants such as gene fusions have shown an initial promise in enhancing mechanistic understanding of NB and improving survival rates. In this study, we performed a comprehensive in silico investigation on the translational ability of gene fusions for patient stratification and treatment development for high-risk NB patients. Specifically, three state-of-the-art gene fusion detection algorithms, including ChimeraScan, SOAPfuse, and TopHat-Fusion, were employed to identify the fusion transcripts in a RNA-seq data set of 498 neuroblastoma patients. Then, the 176 high-risk patients were further stratified into four different subgroups based on gene fusion profiles. Furthermore, Kaplan-Meier survival analysis was performed, and differentially expressed genes (DEGs) for the redefined high-risk group were extracted and functionally analyzed. Finally, repositioning candidates were enriched in each patient subgroup with drug transcriptomic profiles from the LINCS L1000 Connectivity Map. We found the number of identified gene fusions was increased from clinical the low-risk stage to the high-risk stage. Although the technical concordance of fusion detection algorithms was suboptimal, they have a similar biological relevance concerning perturbed pathways and regulated DEGs. The gene fusion profiles could be utilized to redefine high-risk patient subgroups with significant onset age of NB, which yielded the improved survival curves (Log-rank p value ≤ 0.05). Out of 48 enriched repositioning candidates, 45 (93.8%) have antitumor potency, and 24 (50%) were confirmed with either on-going clinical trials or literature reports. The gene fusion profiles have a discrimination power for redefining patient subgroups in high-risk NB and facilitate precision medicine-based drug repositioning implementation.

Towards population-specific pharmacogenomics in the era of next-generation sequencing

Pharmacogenomics (PGx) has essential roles in identifying optimal drug responders, optimizing dosage regimens and avoiding adverse events. Population-specific therapeutic interventions that tackle the genetic root causes of clinical outcomes are an important precision medicine strategy. In this perspective, we discuss next-generation sequencing genotyping and its significance for population-specific PGx applications. We emphasize the potential of NGS for preemptive pharmacogenotyping, which is crucial to population-specific clinical studies and patient care. We also provide examples that use publicly available population-based genomics data for population-specific PGx studies. Last, we discuss the remaining challenges and regulatory efforts towards improvements in this field.

A target safety assessment of the potential toxicological risks of targeting plasmepsin IX/X for the treatment of malaria

The aspartic proteases plasmepsin IX/X are important antimalarial drug targets due to their specificity to the malaria parasite and their vital role as mediators of disease progression. Focusing on parasite-specific targets where no human homologue exists reduces the possibility of on-target drug toxicity. However, there is a risk of toxicity driven by inadequate selectivity for plasmepsins IX/X in Plasmodium over related mammalian aspartic proteases. Of these, CatD/E may be of most toxicological relevance as CatD is a ubiquitous lysosomal enzyme present in most cell types and CatE is found in the gut and in erythrocytes, the clinically significant site of malarial infection. Based on mammalian aspartic protease physiology and adverse drug reactions (ADRs) to FDA-approved human immunodeficiency virus (HIV) aspartic protease inhibitors, we predicted several potential toxicities including β-cell and congenital abnormalities, hypotension, hypopigmentation, hyperlipidaemia, increased infection risk and respiratory, renal, gastrointestinal, dermatological, and other epithelial tissue toxicities. These ADRs to the HIV treatments are likely to be a result of host aspartic protease inhibition due a lack of specificity for the HIV protease; plasmepsins are much more closely related to human CatD than to HIV proteinase. Plasmepsin IX/X inhibition presents an opportunity to specifically target Plasmodium as an effective antimalarial treatment, providing adequate selectivity can be obtained. Potential plasmepsin IX/X inhibitors should be assayed for inhibitory activity against the main human aspartic proteases and particularly CatD/E. An investigative rodent study conducted early in drug discovery would serve as an initial risk assessment of the potential hazards identified.

Freezing kinetics and microstructure of ice cream from high-pressure-jet processing of ice cream mix

The effect of high-pressure-jet (HPJ) processing (0-500 MPa) on low-fat (6% fat) ice cream was studied by evaluating physiochemical properties before freezing, during dynamic freezing, and after hardening. An HPJ treatment ≥400 MPa decreased the density, increased the apparent size of colloidal particles, and altered rheological behavior (increased non-Newtonian behavior and consistency coefficients) of low-fat ice cream mix before freezing. During dynamic freezing, the particle size and consistency coefficient decreased but remained higher in 400 MPa-treated samples vs. non-HPJ-treated controls at the conclusion of freezing. The resulting ice creams (400 and 500 MPa-treated) had similar hardness values (3,372 ± 25 and 3,825 ± 14 g) and increased melting rates (2.91 ± 0.13 and 2.61 ± 0.31 g/min) compared with a control sample containing polysorbate 80 (3,887 ± 2 and 1.62 ± 0.25 g/min). Visualization of ice cream samples using transmission electron microscopy provided evidence of casein micelle and fat droplet disruption by HPJ treatment ≥400 MPa. In the 400 MPa-treated samples, a unique microstructure consisting of dispersed protein congregated around coalesced fat globules likely contributed to the altered physiochemical properties of this ice cream. High-pressure-jet processing can alter the microstructure, rheological properties, and hardness of a low-fat ice cream, and further modification of the formulation and processing parameters may allow the development of products with enhanced properties.

Can We Panelize Seizure?

Seizure liability remains a significant cause of attrition in drug discovery and development, leading to loss of competitiveness, delays, and increased costs. Current detection methods rely on observations made in in vivo studies intended to support clinical trials, such as tremors or other abnormal movements. These signs could be missed or misinterpreted; thus, definitive confirmation of drug-induced seizure requires a follow-up electroencephalogram study. There has been progress in in vivo detection of seizure using automated video systems that record and analyze animal movements. Nonetheless, it would be preferable to have earlier prediction of seizurogenic risk that could be used to eliminate liabilities early in discovery while there are options for medicinal chemists making potential new drugs. Attrition due to cardiac adverse events has benefited from routine early screening; could we reduce attrition due to seizure using a similar approach? Specifically, microelectrode arrays could be used to detect potential seizurogenic signals in stem-cell-derived neurons. In addition, there is clear evidence implicating neuronal voltage-gated and ligand-gated ion channels, GPCRs and transporters in seizure. Interactions with surrounding glial cells during states of stress or inflammation can also modulate ion channel function in neurons, adding to the challenge of seizure prediction. It is timely to evaluate the opportunity to develop an in vitro assessment of seizure linked to a panel of ion channel assays that predict seizure, with the aim of influencing structure-activity relationship at the design stage and eliminating compounds predicted to be associated with pro-seizurogenic state.

A modular testbed for mechanized spreading of powder layers for additive manufacturing

Powder bed additive manufacturing (AM) processes, including binder jetting (BJAM) and powder bed fusion (PBF), can manufacture complex three-dimensional components from a variety of materials. A fundamental understanding of the spreading of thin powder layers is essential to develop robust process parameters for powder bed AM and to assess the influence of powder feedstock characteristics on the subsequent process outcomes. Toward meeting these needs, this work presents the design, fabrication, and qualification of a testbed for modular, mechanized, multi-layer powder spreading. The testbed is designed to replicate the operating conditions of commercial AM equipment, yet features full control over motion parameters including the translation and rotation of a roller spreading tool and precision motion of a feed piston and the build platform. The powder spreading mechanism is interchangeable and therefore can be customized, including the capability for dispensing of fine, cohesive powders using a vibrating hopper. Validation of the resolution and accuracy of the machine and its subsystems, as well as the spreading of exemplary layers from a range of powder sizes typical of BJAM and PBF processes, are described. The precision engineered testbed can therefore enable the optimization of powder spreading parameters for AM and correlation to build process parameters in future work, as well as exploration of spreading of specialized powders for AM and other techniques.

DeepDILI: Deep Learning-Powered Drug-Induced Liver Injury Prediction Using Model-Level Representation

Drug-induced liver injury (DILI) is the most frequently reported single cause of safety-related withdrawal of marketed drugs. It is essential to identify drugs with DILI potential at the early stages of drug development. In this study, we describe a deep learning-powered DILI (DeepDILI) prediction model created by combining model-level representation generated by conventional machine learning (ML) algorithms with a deep learning framework based on Mold2 descriptors. We conducted a comprehensive evaluation of the proposed DeepDILI model performance by posing several critical questions: (1) Could the DILI potential of newly approved drugs be predicted by accumulated knowledge of early approved ones? (2) is model-level representation more informative than molecule-based representation for DILI prediction? and (3) could improved model explainability be established? For question 1, we developed the DeepDILI model using drugs approved before 1997 to predict the DILI potential of those approved thereafter. As a result, the DeepDILI model outperformed the five conventional ML algorithms and two state-of-the-art ensemble methods with a Matthews correlation coefficient (MCC) value of 0.331. For question 2, we demonstrated that the DeepDILI model's performance was significantly improved (i.e., a MCC improvement of 25.86% in test set) compared with deep neural networks based on molecule-based representation. For question 3, we found 21 chemical descriptors that were enriched, suggesting a strong association with DILI outcome. Furthermore, we found that the DeepDILI model has more discrimination power to identify the DILI potential of drugs belonging to the World Health Organization therapeutic category of 'alimentary tract and metabolism'. Moreover, the DeepDILI model based on Mold2 descriptors outperformed the ones with Mol2vec and MACCS descriptors. Finally, the DeepDILI model was applied to the recent real-world problem of predicting any DILI concern for potential COVID-19 treatments from repositioning drug candidates. Altogether, this developed DeepDILI model could serve as a promising tool for screening for DILI risk of compounds in the preclinical setting, and the DeepDILI model is publicly available through https://github.com/TingLi2016/DeepDILI.

Identifying Risk Factors for Anthracycline Chemotherapy-induced Phlebitis in Women with Breast Cancer: An Observational Study

AIMS

Anthracycline chemotherapy administered via a peripheral cannula results in severe anthracycline chemotherapy-induced phlebitis (ACIP) in about 20-30% of patients. Administering chemotherapy via a central venous catheter (CVC) prevents ACIP. However, CVCs are associated with an increased risk of thrombosis and sepsis. Our aim was to identify risk factors associated with severe ACIP and to provide evidence about the individual risk of developing symptoms.

MATERIALS AND METHODS

A prospective observational study of 263 women with breast cancer receiving peripheral administration of anthracycline chemotherapy at a UK cancer centre was conducted between May 2016 and January 2018. Data were collected at baseline and every 3 weeks following each chemotherapy treatment, using both healthcare professional- and participant-reported symptom assessments.

RESULTS

After three cycles of chemotherapy, 27% of participants experienced severe ACIP. Factors associated with symptom severity were identified as: arm used for chemotherapy administration, epirubicin dose, age, pre-existing hypertension, comorbidity, ethnic group and pain during chemotherapy administration. The sequence of arm used for chemotherapy administration was the single most significant factor (P < 0.001). When alternating arms were used no other risk factor was influential. Where alternating arms were not used, younger age and higher dose were associated with higher-grade symptoms, with age being more influential than dose. The cumulative effect of increasing symptom severity with repeated cycles was also identified (P < 0.001).

CONCLUSION

It is recommended that a CVC is not routinely required for women with breast cancer who have not undergone an axillary node clearance and receive chemotherapy in alternate arms. The need for a CVC for women who are planned to receive all anthracycline chemotherapy cycles in the same arm should be assessed in the light of peripheral venous access assessment and the key risk factors of age, dose and number of cycles.

Justification for species selection for pharmaceutical toxicity studies

Toxicity studies using mammalian species are generally required to provide safety data to support clinical development and licencing registration for potential new pharmaceuticals. International regulatory guidelines outline recommendations for the order (rodent and/or non-rodent) and number of species, retaining flexibility for development of a diverse range of drug modalities in a manner relevant for each specific new medicine. Selection of the appropriate toxicology species involves consideration of scientific, ethical and practical factors, with individual companies likely having different perspectives and preferences regarding weighting of various aspects dependent upon molecule characteristics and previous experience of specific targets or molecule classes. This article summarizes presentations from a symposium at the 2019 Annual Congress of the British Toxicology Society on the topic of species selection for pharmaceutical toxicity studies. This symposium included an overview of results from a National Centre for the Replacement, Refinement and Reduction of Animals in Research (NC3Rs) and Association of British Pharmaceutical Industry (ABPI) international collaboration that reviewed the use of one or two species in regulatory toxicology studies and justification for the species selected within each programme. Perspectives from two pharmaceutical companies described their processes for species selection for evaluation of biologics, and justification for selection of the minipig as a toxicological species for small molecules. This article summarizes discussions on the scientific justification and other considerations taken into account to ensure the most appropriate animal species are used for toxicity studies to meet regulatory requirements and to provide the most value for informing project decisions.

Deep Learning on High-Throughput Transcriptomics to Predict Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is one of the most cited reasons for the high drug attrition rate and drug withdrawal from the market. The accumulated large amount of high throughput transcriptomic profiles and advances in deep learning provide an unprecedented opportunity to improve the suboptimal performance of DILI prediction. In this study, we developed an eight-layer Deep Neural Network (DNN) model for DILI prediction using transcriptomic profiles of human cell lines (LINCS L1000 dataset) with the current largest binary DILI annotation data [i.e., DILI severity and toxicity (DILIst)]. The developed models were evaluated by Monte Carlo cross-validation (MCCV), permutation test, and an independent validation (IV) set. The developed DNN model achieved the area under the receiver operating characteristic curve (AUC) of 0.802 and 0.798, and balanced accuracy of 0.741 and 0.721 for training and an IV set, respectively, outperforming the conventional machine learning algorithms, including K-nearest neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF). Moreover, the developed DNN model provided a more balanced sensitivity of 0.839 and specificity of 0.603. Besides, we found the developed DNN model had a superior predictive performance for oncology drugs. Also, the functional and network analysis of genes driving the predictions revealed their relevance to the underlying mechanisms of DILI. The proposed DNN model could be a promising tool for early detection of DILI potential in the pre-clinical setting.

Thinking about Others' Minds: Mental State Inference in Boys with Conduct Problems and Callous-Unemotional Traits

Children with conduct problems (CP) and high levels of callous-unemotional traits (CP/HCU) have been found to have an intact ability to represent other minds, however, they behave in ways that indicate a reduced propensity to consider other people’s thoughts and feelings. Here we report findings from three tasks assessing different aspects of mentalising in 81 boys aged 11–16 [Typically developing (TD) n = 27; CP/HCU n = 28; CP and low levels of callous-unemotional traits (CP/LCU) n = 26]. Participants completed the Movie Assessment of Social Cognition (MASC), a task assessing ability/propensity to incorporate judgements concerning an individual’s mind into mental state inference; provided a written description of a good friend to assess mind-mindedness; and completed the Social Judgement Task (SJT), a new measure assessing mentalising about antisocial actions. Boys with CP/HCU had more difficulty in accurately inferring others’ mental states in the MASC than TD and CP/LCU boys. There were no group differences in the number of mind-related comments as assessed by the mind-mindedness protocol or in responses to the SJT task. These findings suggest that although the ability to represent mental states is intact, CP/HCU boys are less likely to update mental state inferences as a function of different minds.