Distance plus attention for binding affinity prediction.

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π -stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap. Scientific Contribution StatementThis study innovatively introduces distance-based features to predict protein-ligand binding affinity, capitalizing on unique molecular interactions. Furthermore, the incorporation of protein sequence features of specific residues enhances the model's proficiency in capturing intricate binding patterns. The predictive capabilities are further strengthened through the use of a deep learning architecture with attention mechanisms, and an ensemble approach, averaging the outputs of five models, is implemented to ensure robust and reliable predictions.

"Safe, connected, supported in a complex system." Exploring the views of women who had a First Nations baby at one of three maternity services offering culturally tailored continuity of midwife care in Victoria, Australia. A qualitative analysis of free-text survey responses.

BACKGROUND: In Australia, continuity of midwife care is recommended for First Nations women to address the burden of inequitable perinatal outcomes experienced by First Nations women and newborns. AIMS: This study aimed to explore the experiences of women having a First Nations baby who received care at one of three maternity services in Naarm (Melbourne), Victoria, where culturally tailored midwife continuity models had been implemented. METHODS: Women having a First Nations baby who were booked for care at one of three study sites were invited to participate in an evaluation of care. Thematic analysis was used to analyse qualitative data from responses to free-text, open ended questions that were included in a follow-up questionnaire at 3-6 months after the birth. RESULTS: In total, 213 women (of whom 186 had continuity of midwife care) participated. The global theme for what women liked about their care was 'Safe, connected, supported' including emotional and clinical safety, having a known midwife and being supported 'my way'. The global theme for what women did not like about their care was 'A complex, fragmented and unsupportive system' including not being listened to, things not being explained, and a lack of cultural safety. CONCLUSIONS: Culturally tailored caseload midwifery models appear to make maternity care feel safer for women having a First Nations baby, however, the mainstream maternity care system remained challenging for some. These models should be implemented for First Nations women, and evidence-based frameworks, such as the RISE framework, should be used to facilitate change.

What is the significance of the chloroform stabilizer C5H10 and its association with MeOH in concentration-dependent polymeric solutions?

The understanding of excitonic transitions associated with polymeric aggregates is fundamental, as such transitions have implications on coherence lengths, coherence numbers and inter- and intra-chain binding parameters. In this context, the investigation of efficient solvents and other ways to control polymer aggregate formation is key for their consolidation as materials for new technologies. In this manuscript, we use Poly(3-hexothiophene) (P3HT) as a probe to investigate the significance of amylene (C5H10) and its association with methanol (MeOH) in both pure and C5H10-stabilized chloroform (CHCl3)-based polymeric solutions. Using the intensity ratio between the first and second vibronic transitions of the P3HT H-aggregates formed, values for their exciton bandwidths and interchain interactions are obtained and correlated with the presence of C5H10 and MeOH as agents determining the CHCl3 quality.

Troubleshooting spectral artifacts from biplate retarders for reliable Stokes spectropolarimetry.

Polarimetry is generally used to determine the polarization state of light beams in various research fields, such as biomedicine, astronomy, and materials science. In particular, the rotating quarter-wave plate polarimeter is an inexpensive and versatile option used in several single-wavelength applications to determine the four Stokes parameters. Extending this technique to broadband spectroscopic measurements is of great scientific interest since the information on light polarization is highly sensitive to anisotropic phenomena. However, the need for achromatic polarizing elements, especially quarter-wave plates, requires special attention in their modeling. In this study, we implemented a rotating retarder spectropolarimeter for broadband measurements using a commercially available quasi-achromatic biplate retarder over the visible range. Here, we present a comprehensive approach for troubleshooting this type of spectropolarimeter through the observation of artifacts stemming from the standard single-plate retarder model. Then, we derive a more suitable model for a quasi-achromatic retarder consisting of a biplate junction. This new biplate model requires knowledge of the intrinsic dispersive properties of the biplate, namely the equivalent retardance, fast axis tilt, and rotatory angle. Hence, in this study, we also show a self-consistent methodology to determine these biplate properties using the same polarimeter apparatus so that accurate Stokes parameters can be determined independently. Finally, the comparison of data generated with the standard single-plate and new biplate models shows a significant improvement in the measurement precision of the investigated polarization states, which confirms that remodeling the retarder for reliable spectropolarimetry is necessary.

Exploring satisfaction among women having a First Nations baby at one of three maternity hospitals offering culturally specific continuity of midwife care in Victoria, Australia: A cross-sectional survey.

BACKGROUND: Continuity of midwife care is recommended to redress the inequitable perinatal outcomes experienced by Aboriginal and Torres Strait Islander (First Nations) mothers and babies, however more evidence is needed about First Nations women's views and experiences of their care. AIMS: This study aimed to explore levels of satisfaction among women having a First Nations baby, who received maternity care at one of three maternity services, where new culturally specific midwife continuity models had been recently implemented. METHODS: Women having a First Nations baby who were booked for care at one of three study sites in Naarm (Melbourne), Victoria, were invited to complete one questionnaire during pregnancy and then a follow up questionnaire, 3 months after the birth. RESULTS: Follow up questionnaires were completed by 213 women, of whom 186 had received continuity of midwife care. Most women rated their pregnancy (80 %) and labour and birth care (81 %) highly ('6 or '7' on a scale of 1-7). Women felt informed, that they had an active say in decisions, that their concerns were taken seriously, and that the midwives were kind, understanding and there when needed. Ratings of inpatient postnatal care were lower (62 %), than care at home (87 %). CONCLUSIONS: Women having a First Nations baby at one of three maternity services, where culturally specific, continuity of midwife care models were implemented reported high levels of satisfaction with care. It is recommended that these programs are upscaled, implemented and sustained.

Real-to-bin conversion for protein residue distances.

Protein Structure Prediction (PSP) has achieved significant progress lately. Prediction of inter-residue distances by machine learning and their exploitation during the conformational search is largely among the critical factors behind the progress. Real values than bin probabilities could more naturally represent inter-residue distances, while the latter, via spline curves more naturally helps obtain differentiable objective functions than the former. Consequently, PSP methods that exploit predicted binned distances perform better than those that exploit predicted real-valued distances. To leverage the advantage of bin probabilities in getting differentiable objective functions, in this work, we propose techniques to convert real-valued distances into distance bin probabilities. Using standard benchmark proteins, we then show that our real-to-bin converted distances help PSP methods obtain three-dimensional structures with 4%-16% better root mean squared deviation (RMSD), template modeling score (TM-Score), and global distance test (GDT) values than existing similar PSP methods. Our proposed PSP method is named real to bin (R2B) inter-residue distance predictor, and its code is available from https://gitlab.com/mahnewton/r2b.

Trust, privacy, community, and culture: Important elements of maternity care for Aboriginal and Torres Strait Islander women giving birth in Victoria.

BACKGROUND: The Australian maternity system must enhance its capacity to meet the needs of Aboriginal and Torres Strait Islander (First Nations) mothers and babies, however evidence regarding what is important to women is limited. AIMS: The aim of this study was to explore what women having a First Nations baby rate as important for their maternity care as well as what life stressors they may be experiencing. METHODS: Women having a First Nations baby who booked for care at one of three urban Victorian maternity services were invited to complete a questionnaire. RESULTS: 343 women from 76 different language groups across Australia. Almost one third of women reported high levels of psychological distress, mental illness and/or were dealing with serious illness or death of relatives or friends. Almost one quarter reported three or more coinciding life stressors. Factors rated as most important were privacy and confidentiality (98 %), feeling that staff were trustworthy (97 %), unrestricted access to support people during pregnancy appointments, (87 %) birth (66 %) and postnatally (75 %), midwife home visits (78 %), female carers (66 %), culturally appropriate artwork, brochures (68 %) and access to Elders (65 %). CONCLUSIONS: This study provides important information about what matters to women who are having a First Nations baby in Victoria, Australia, bringing to the forefront social and cultural complexities experienced by many women that need to be considered in programme planning. It is paramount that maternity services partner with First Nations communities to implement culturally secure programmes that respond to the needs of local communities.

Dephasing Dynamics across Different Local Vibrational Modes and Crystalline Environments.

The perturbed free induction decay (PFID) observed in ultrafast infrared spectroscopy was used to unveil the rates at which different vibrational modes of the same atomic-scale defect can interact with their environment. The N_{3}VH^{0} defect in diamond provided a model system, allowing a comparison of stretch and bend vibrational modes within different crystal lattice environments. The observed bend mode (first overtone) exhibited dephasing times T_{2}=2.8(1) ps, while the fundamental stretch mode had surprisingly faster dynamics T_{2}<1.7 ps driven by its more direct perturbation of the crystal lattice, with increased phonon coupling. Further, at high defect concentrations the stretch mode's dephasing rate was enhanced. The ability to reliably measure T_{2} via PFID provides vital insights into how vibrational systems interact with their local environment.

Constraint Guided Beta-Sheet Refinement for Protein Structure Prediction.

Protein structure prediction (PSP) is a crucial issue in Bioinformatics. PSP has its important use in many vital research areas that include drug discovery. One of the important intermediate steps in PSP is predicting a protein's beta-sheet structures. Because of non-local interactions among numerous irregular areas in beta-sheets, their highly accurate prediction is challenging. The challenge is compounded when a given protein's structure has a large number of beta-sheets. In this paper, we specifically refine the beta-sheets of a protein structure by using a local search method. Then, we use another local search method to refine the full structure. Our search methods analyse residue-residue distance-based scores and apply geometric restrictions gained from deep learning models. Moreover, our search methods recognise the regions of the current conformations prompting the nether scores and generate neighbouring conformations focusing on that identified regions and making alterations there. On a set of standard 88 proteins of various sizes between 46 and 450 residues, our method successfully outperforms state-of-the-art PSP search algorithms. The improvements are more than 12% in average root mean squared distance (RMSD), template modelling score (TM-score), and global distance test (GDT) values.

A stacked meta-ensemble for protein inter-residue distance prediction.

Predicted inter-residue distances are a key behind recent success in high quality protein structure prediction (PSP). However, prediction of both short and long distance values together is challenging. Consequently, predicted short distances are mostly used by existing PSP methods. In this paper, we use a stacked meta-ensemble method to combine deep learning models trained for different ranges of real-valued distances. On five benchmark sets of proteins, our proposed inter-residue distance prediction method improves mean Local Distance Different Test (LDDT) scores at least by 5% over existing such methods. Moreover, using a real-valued distance based conformational search algorithm, we also show that predicted long distances help obtain significantly better protein conformations than when only predicted short distances are used. Our method is named meta-ensemble for distance prediction (MDP) and its program is available from https://gitlab.com/mahnewton/mdp.

Enhancing protein contact map prediction accuracy via ensembles of inter-residue distance predictors.

Protein contact maps capture coevolutionary interactions between amino acid residue pairs that are spatially within certain proximity threshold. Predicted contact maps are used in many protein related problems that include drug design, protein design, protein function prediction, and protein structure prediction. Contact map prediction has achieved significant progress lately but still further challenges remain with prediction of contacts between residues that are separated in the amino acid residue sequence by large numbers of other residues. In this paper, with experimental results on 5 standard benchmark datasets that include membrane proteins, we show that contact map prediction could be significantly enhanced by using ensembles of various state-of-the-art short distance predictors and then by converting predicted distances into contact probabilities. Our program along with its data is available from https://gitlab.com/mahnewton/ecp.

Erratum: Anharmonicity and Universal Response of Linear Carbon Chain Mechanical Properties under Hydrostatic Pressure [Phys. Rev. Lett. 125, 105501 (2020)].

This corrects the article DOI: 10.1103/PhysRevLett.125.105501.

Erratum: Anharmonicity and Universal Response of Linear Carbon Chain Mechanical Properties under Hydrostatic Pressure [Phys. Rev. Lett. 125, 105501 (2020)].

This corrects the article DOI: 10.1103/PhysRevLett.125.105501.

Enhancing protein inter-residue real distance prediction by scrutinising deep learning models.

Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp .

Secondary structure specific simpler prediction models for protein backbone angles.

MOTIVATION: Protein backbone angle prediction has achieved significant accuracy improvement with the development of deep learning methods. Usually the same deep learning model is used in making prediction for all residues regardless of the categories of secondary structures they belong to. In this paper, we propose to train separate deep learning models for each category of secondary structures. Machine learning methods strive to achieve generality over the training examples and consequently loose accuracy. In this work, we explicitly exploit classification knowledge to restrict generalisation within the specific class of training examples. This is to compensate the loss of generalisation by exploiting specialisation knowledge in an informed way. RESULTS: The new method named SAP4SS obtains mean absolute error (MAE) values of 15.59, 18.87, 6.03, and 21.71 respectively for four types of backbone angles [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text]. Consequently, SAP4SS significantly outperforms existing state-of-the-art methods SAP, OPUS-TASS, and SPOT-1D: the differences in MAE for all four types of angles are from 1.5 to 4.1% compared to the best known results. AVAILABILITY: SAP4SS along with its data is available from https://gitlab.com/mahnewton/sap4ss .

Sources of information during pregnancy and the early parenting period: Exploring the views of women and their partners.

OBJECTIVE: There are a wide variety of information sources available during pregnancy and the early parenting period, but limited understanding of their usefulness, particularly for partners. We explored the views of both women and their partners regarding sources of information, their frequency of use, and their preferred formats. DESIGN AND SETTING: Data were collected as part of a large cluster randomised controlled trial at a tertiary maternity hospital in 2015-2016, in Melbourne, Australia. The overall evaluation was of a parenting kit ('Growing Together'), an evidence-based information source for prospective and new parents covering the period from conception until one year postpartum. This paper uses data collected from women when their baby was two months of age, and women's partners when the baby was six months of age, via postal or online survey. PARTICIPANTS: Women were eligible if they booked for pregnancy care at The Royal Women's Hospital during the recruitment period, were having their first baby, able to read and speak English without an interpreter, and <30 weeks pregnant at their first hospital appointment (n = 1034). All eligible women were included unless they opted out. MEASUREMENTS AND FINDINGS: In total 92 women were excluded. Of the women sent the two-month survey, 42% (392/941) responded. Partner surveys were returned by 252/791 partners (32%). Respondents received information from a range of sources, most frequently face to face from health professionals through childbirth education or midwife discussion/education, followed by friends and family members. Information received from a health professional was also reported as being the most useful. For both women and their partners, the most important factor related to information was that it was from a trusted and reliable source. KEY CONCLUSIONS AND IMPLICATIONS FOR PRACTICE: Women and their partners highlighted the importance of quality and access to evidence based resources and information. The internet is frequently favoured by women and their partners due to its convenience, accessibility, and timely access to information. Overall, women and their partners reported information directly from a health care professional to be the most useful and health services should ensure that women and their partners have adequate access to their health care professional.

Effects of meso-tetrakis (4-sulfonatophenyl) porphyrin (TPPS4) aggregation on its spectral and kinetic characteristics and singlet oxygen production.

The present work reports the effects of meso-tetrakis (4-sulfonatophenyl) porphyrin (TPPS4) aggregation on its excited states absorption spectra, triplet states quenching by molecular oxygen and singlet oxygen production. Experimental techniques such as optical absorption, Z-scan with a white light continuum source and the Laser Flash Photolysis were used to fulfil the study. J-aggregates possess reverse saturable absorption in the 505-660 nm spectral range with a peak centered close to 540 nm. These facts together with their fast relaxation time suggest that they can be employed as material for ultrafast optical limiting and switching. Even though aggregation reduces the porphyrin excited-state lifetimes and quantum yields, it does not reduce the probability of the contact between the quencher and the excited aggregate. Aggregation does not change the contribution of energy transfer mechanisms to triplet state quenching by molecular oxygen. The production of singlet oxygen, the intense absorption in the phototherapeutic window and the high efficiency of conversion of light energy into heat, allow consider J-aggregates as a theranostic agent for photomedicine. It is proposed to use J-aggregates for diagnostics by photoacoustic images and in combination with a near-infrared photodynamic/photothermal dual mode therapy, thus improving synergistically the therapeutic response.

Quantitative Toxicity Prediction via Meta Ensembling of Multitask Deep Learning Models.

Toxicity prediction using quantitative structure-activity relationship has achieved significant progress in recent years. However, most existing machine learning methods in toxicity prediction utilize only one type of feature representation and one type of neural network, which essentially restricts their performance. Moreover, methods that use more than one type of feature representation struggle with the aggregation of information captured within the features since they use predetermined aggregation formulas. In this paper, we propose a deep learning framework for quantitative toxicity prediction using five individual base deep learning models and their own base feature representations. We then propose to adopt a meta ensemble approach using another separate deep learning model to perform aggregation of the outputs of the individual base deep learning models. We train our deep learning models in a weighted multitask fashion combining four quantitative toxicity data sets of LD50, IGC50, LC50, and LC50-DM and minimizing the root-mean-square errors. Compared to the current state-of-the-art toxicity prediction method TopTox on LD50, IGC50, and LC50-DM, that is, three out of four data sets, our method, respectively, obtains 5.46, 16.67, and 6.34% better root-mean-square errors, 6.41, 11.80, and 12.16% better mean absolute errors, and 5.21, 7.36, and 2.54% better coefficients of determination. We named our method QuantitativeTox, and our implementation is available from the GitHub repository https://github.com/Abdulk084/QuantitativeTox.