Accurate proteome-wide missense variant effect prediction with AlphaMissense.

The vast majority of missense variants observed in the human genome are of unknown clinical significance. We present AlphaMissense, an adaptation of AlphaFold fine-tuned on human and primate variant population frequency databases to predict missense variant pathogenicity. By combining structural context and evolutionary conservation, our model achieves state-of-the-art results across a wide range of genetic and experimental benchmarks, all without explicitly training on such data. The average pathogenicity score of genes is also predictive for their cell essentiality, capable of identifying short essential genes that existing statistical approaches are underpowered to detect. As a resource to the community, we provide a database of predictions for all possible human single amino acid substitutions and classify 89% of missense variants as either likely benign or likely pathogenic.

Deep Audio-Visual Speech Recognition.

The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is complementary to audio speech recognition, especially when the audio signal is noisy; (3) we introduce and publicly release a new dataset for audio-visual speech recognition, LRS2-BBC, consisting of thousands of natural sentences from British television. The models that we train surpass the performance of all previous work on a lip reading benchmark dataset by a significant margin.

Applying and improving AlphaFold at CASP14.

We describe the operation and improvement of AlphaFold, the system that was entered by the team AlphaFold2 to the "human" category in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The AlphaFold system entered in CASP14 is entirely different to the one entered in CASP13. It used a novel end-to-end deep neural network trained to produce protein structures from amino acid sequence, multiple sequence alignments, and homologous proteins. In the assessors' ranking by summed z scores (>2.0), AlphaFold scored 244.0 compared to 90.8 by the next best group. The predictions made by AlphaFold had a median domain GDT_TS of 92.4; this is the first time that this level of average accuracy has been achieved during CASP, especially on the more difficult Free Modeling targets, and represents a significant improvement in the state of the art in protein structure prediction. We reported how AlphaFold was run as a human team during CASP14 and improved such that it now achieves an equivalent level of performance without intervention, opening the door to highly accurate large-scale structure prediction.

Highly accurate protein structure prediction with AlphaFold.

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1-4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence-the structure prediction component of the 'protein folding problem'8-has been an important open research problem for more than 50 years9. Despite recent progress10-14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.

Highly accurate protein structure prediction for the human proteome.

Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure1. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold2, at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.

Emergency management of neck stoma patients during the coronavirus pandemic: a national nurse survey.

BACKGROUND: Neck stoma patient care involves significant clinical complexity. Inadequate staff training, equipment provision and infrastructure have all been highlighted as causes for avoidable patient harm. AIMS: To establish the perception of knowledge and confidence levels relating to the emergency management of neck stomas among UK nurses during the COVID-19 pandemic. METHOD: A nationwide prospective electronic survey of both primary and secondary care nurses via the Royal College of Nursing and social media. FINDINGS: 402 responses were collated: 81 primary care and 321 secondary care; the majority (n=130) were band 5. Forty-nine per cent could differentiate between a laryngectomy and a tracheostomy; ENT nurses scored highest (1.56; range 0-2) on knowledge. Fifty-seven per cent could oxygenate a tracheostomy stoma correctly and 54% could oxygenate a laryngectomy stoma correctly. Sixty-five per cent cited inadequate neck stoma training and 91% felt inclusion of neck stoma training was essential within the nursing curriculum. CONCLUSION: Clinical deficiencies of management identified by nurses can be attributed to a lack of confidence secondary to reduced clinical exposure and education.

The impact of the coronavirus (COVID-19) pandemic on elective paediatric otolaryngology outpatient services - An analysis of virtual outpatient clinics in a tertiary referral centre using the modified paediatric otolaryngology telemedicine satisfaction survey (POTSS).

INTRODUCTION: Virtual outpatient clinics (VOPC) have been integrated into both paediatric and based adult outpatient services due to a multitude of factors, including increased demand for services, technological advances and rising morbidity secondary to ageing populations. The novel coronavirus disease (COVID-19) has accentuated pressures on the National Health Service (NHS) infrastructure, particularly elective services, whilst radically altering patterns of practice. AIM: To evaluate the impact of the COVID-19 pandemic on paediatric otolaryngology outpatient services whilst collating patient feedback to elicit long-term sustainability post COVID-19. METHOD: A retrospective analysis of VOPCs was undertaken at a tertiary paediatric referral centre over a 3-month capture period during the COVID-19 pandemic. Demographic, generic clinic (presenting complaint, new vs. follow-up, consultation type), as well as outcome data (medical or surgical intervention, discharge vs. ongoing review, onward referral, investigations, and conversion to face-to-face) was collated. Additionally a modified 15-point patient satisfaction survey was created. The Paediatric Otolaryngology Telemedicine Satisfaction survey (POTSS), was an adaptation of 4 validated patient satisfaction tools including the General Medical Council (GMC) patient questionnaire, the telehealth satisfaction scale (TESS), the telehealth usability questionnaire (TUQ), and the telemedicine satisfaction and usefulness questionnaire (TSUQ). RESULTS: Of 514 patients reviewed virtually over a 3-month period, 225 (45%) were randomly selected to participate, of which 200 met our inclusion criteria. The most common mode of consultation was telephony (92.5%, n = 185). Non-attendance rates were reduced when compared to face-to-face clinics during an equivalent period prior to the COVID-19 pandemic. A significant proportion of patients (29% compared to 26% pre-VOPC) were discharged to primary care. Nine percent were listed for surgery compared to 19% pre-VOPC. A subsequent face-to-face appointment was required in 10% of participants. Overall, the satisfaction when assessing the doctor-patient relationship, privacy & trust, as well as consultation domains was high, with the overwhelming majority of parents' content with the future integration and participation in VOPCs. CONCLUSION: An evolving worldwide pandemic has accelerated the need for healthcare services to reform in order to maintain a steady flow of patients within an elective outpatient setting without compromising patient care. Solutions must be sustainable long-term to account for future disruptions, whilst accounting for evolving patient demographics. Our novel survey has demonstrated the vast potential that the integration of VOPCs can offer paediatric otolaryngology services within a carefully selected cohort of patients.

Improved protein structure prediction using potentials from deep learning.

Protein structure prediction can be used to determine the three-dimensional shape of a protein from its amino acid sequence1. This problem is of fundamental importance as the structure of a protein largely determines its function2; however, protein structures can be difficult to determine experimentally. Considerable progress has recently been made by leveraging genetic information. It is possible to infer which amino acid residues are in contact by analysing covariation in homologous sequences, which aids in the prediction of protein structures3. Here we show that we can train a neural network to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions. Using this information, we construct a potential of mean force4 that can accurately describe the shape of a protein. We find that the resulting potential can be optimized by a simple gradient descent algorithm to generate structures without complex sampling procedures. The resulting system, named AlphaFold, achieves high accuracy, even for sequences with fewer homologous sequences. In the recent Critical Assessment of Protein Structure Prediction5 (CASP13)-a blind assessment of the state of the field-AlphaFold created high-accuracy structures (with template modelling (TM) scores6 of 0.7 or higher) for 24 out of 43 free modelling domains, whereas the next best method, which used sampling and contact information, achieved such accuracy for only 14 out of 43 domains. AlphaFold represents a considerable advance in protein-structure prediction. We expect this increased accuracy to enable insights into the function and malfunction of proteins, especially in cases for which no structures for homologous proteins have been experimentally determined7.

Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13).

We describe AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13. Submissions were made by three free-modeling (FM) methods which combine the predictions of three neural networks. All three systems were guided by predictions of distances between pairs of residues produced by a neural network. Two systems assembled fragments produced by a generative neural network, one using scores from a network trained to regress GDT_TS. The third system shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation. In the CASP13 FM assessors' ranking by summed z-scores, this system scored highest with 68.3 vs 48.2 for the next closest group (an average GDT_TS of 61.4). The system produced high-accuracy structures (with GDT_TS scores of 70 or higher) for 11 out of 43 FM domains. Despite not explicitly using template information, the results in the template category were comparable to the best performing template-based methods.

Unilateral vocal cord palsy and dysphagia: an unusual presentation of cerebellopontine angle meningioma.

Cerebellopontine angle (CPA) tumours are the most common neoplasms in the posterior fossa, accounting for 5-10% of intracranial tumours. Most CPA tumours are benign, with most being vestibular schwannomas. Meningiomas arising from the jugular foramen are among the rarest of all with very few being described in the literature. Treatment options vary considerably as experience with these tumours is limited. One option is a skull base approach, but this depends on size, location and ability to preserve lower cranial nerve function. This can be extremely challenging and is accompanied by high mortality risk; therefore, a more conservative option must be considered. This case report highlights the difficulty in management of patients with jugular fossa meningiomas, including appropriate investigations, analysis of surgical versus conservative treatment and associated complications. Furthermore, we elaborate the decision-making process pertaining to the tailoring of the surgical route used for the resection of jugular foramen meningiomas. (Jugular Foramen Meningioma, cerebellopontine angle).

A rare case of acute on chronic gastric volvulus with Borchardt's triad.

Gastric volvulus is a rare condition with two forms of presentation, either acute or chronic. Since its discovery, there have been no cases of acute on chronic volvulus discussed in the literature. Its vague presentation makes diagnosis and subsequent management difficult. The diagnosis of acute gastric volvulus is made on clinical grounds via Borchardt's triad; however, barium swallow and oesophagogastroduodenoscopy have been shown to play a role. We describe a case of a 95-year-old Caucasian woman who presented with worsening dysphagia, epigastric pain, retching without vomiting and hiccups of 5 months. Initially diagnosed as a hiatus hernia, the patient subsequently died following an acute on chronic gastric volvulus. This rare, life-threatening diagnosis provides an opportunity to discuss characteristics of gastric volvulus and the difficulties in management.

Public knowledge of the symptoms of myocardial infarction: a street survey in Birmingham, England.

BACKGROUND: Myocardial infarction (MI) is a leading cause of death in the UK. A good clinical outcome depends on rapid treatment following the onset of symptoms. A person's knowledge of typical symptoms determines how quickly they present to the medical services. OBJECTIVES: To investigate knowledge of MI symptoms among the general population and the relationship between age, gender and socio-economic status with knowledge. METHODS: Street survey of 302 participants in Birmingham, UK, using an interviewer-assisted questionnaire. RESULTS: Of seven symptoms accepted in the medical literature as typical of an MI, central chest pain was the most frequently identified (75% of the sample), followed by arm pain or numbness (40%), shortness of breath (35%), fainting or dizziness (21%) and sweating (21%). Feeling or being sick and neck or jaw pain were mentioned by 8.1% and 5.9%, respectively, while an atypical or inapplicable symptom, collapse (9.9%) was mentioned more often than these. Over half the sample knew only two or fewer MI symptoms. The mean number of typical symptoms identified was 2.2 (SD = 1.28). Respondents from professional occupations and those with previous experience of MI, whether direct or indirect, showed better awareness. CONCLUSIONS: The study demonstrated a paucity of knowledge of MI symptoms among the general public. Such findings provide a baseline to guide public health campaigns targeting awareness of MI.