Guiding protein design choices by per-residue energy breakdown analysis with an interactive web application.

Artificial intelligencemethods for protein folding and design.

BackgroundMany HIV databases and applications focus on a limited domain of HIV knowledge. Since even a “simple” organism like HIV represents a very complex system with many interacting elements, the fractured structure of existing databases and applications likely limits our ability to investigate and understand HIV. To facilitate research, therefore, we have built HIVToolbox, which integrates much of the knowledge about HIV proteins and presents the data in an interactive web application. HIVToolbox allows quick and convenient hypotheses generation, experiment interpretation, and potential new drug structure creation.MethodsHIVToolbox was built as a standard three-tier J2EE web application, consisting of 1) an underlying relational MySQL database, 2) a set of standard Java data access objects that pull data from the database, and 3) a set of dynamic web pages the user interacts with. HIV-1 data from external sources such as the Protein Data Bank, NCBI, Los Alamos, etc. was collected, curated, and stored in the HIVToolbox database. Additional data, such as homology and position statistics matrices, was generated from existing data. Since version 1, drug binding site and drug resistant mutation data has also been added.ResultsHIVToolbox was used to create several new hypotheses about HIV-1 integrase, including predicting the location of a CK2 phosphorylation site, which was later confirmed by experiment. A new version of HIVToolbox support display of the 3D locations of drug resistant mutations on surface plots of HIV proteins and the drug binding sites for structures of complexes of HIV proteins with drugs.ConclusionHIVToolbox is an open-access web application that allows virologists and structural biologists to access detailed information about HIV-1 proteins, such as sequence, structure, functional sites and relationships, homology, drug binding sites, and drug resistant mutations, and to immediately see the relationships between any or all of them. Weblink: [http://hivtoolbox.bio-toolkit.com]

Management of an inventory data within an agency requires an interactive management system to provide ease and informative data presentation. Data processing using an interactive system makes it easy for users to understand and interact with data, especially if the agency concerned is an agency that is in charge of long-term data storage, complex data processing, data collection and data distribution processes, controlling inventory availability, and data collection conducted every day. Data storage and conventional data processing has several weaknesses such as high error rate in data processing, the system is not interactive so that it troubles and impedes the inventory data collection process by users, and can produce data ambiguity that can cause misinformation. By using the inventory control model Just-In-Time (JIT) Inventory method that allows the compilation of data collection and inventory stock requests as needed so that it can easily distribute and minimize wasted stock, the processing, storage, and data collection of a particular data inventory can be controlled well and can provide clearer information. As a result, implementing inventory control methods into a web application can provide web applications that have better functionality in processing, storing, and collecting data.

<title>Abstract</title> Background In recent years, Chinese medical postgraduate education has undergone significant transformation, with enrollment soaring to 156,000 students in 2023, accounting for 12% of the nation’s total postgraduate admissions. Recognizing high-achieving students at an early stage and learning from their success can change the way to influence future educational dilemmas. While the existing evaluation system remained limited in its ability to prospectively predict academic performance variability. This critical gap underscores the need for innovative, data-driven approaches to transcend conventional assessment paradigms. Our study used machine learning techniques to predict the academic outcomes (GPA) of medical postgraduate students in a certain university, providing evidence-based strategies that could be used to improve educational practices and improve student performance. Methods In this study, we worked with 1,133 postgraduate students at Southern Medical University (2020 cohort) while analyzing 42 variables, including demographic, undergraduate performance, postgraduate transition variables, and measures of their self-assessment. Using the Boruta algorithm, we identified the most important predicting features and then tested eight learning machine models to find the best one. Furthermore, we applied SHAP (Shapley Additive Explanations) to derive interpretable insights into the most critical features of success. Finally, we submitted this work as an interactive web application that allowed academic leaders to predict their students’ GPAs and provide much-needed proactive support. Results XGBoost model crushed the competitions, delivering higher predictions (AUC = 0.744, Accuracy = 82.8%, F1 = 0.902). SHAP analysis exposed the secret formula for success. A student’s career ambition, undergraduate ranking, and core subject mastery weren’t just important, but they were also game changers. Based on the results of our study, we built a smart web tool that could turn data into action, giving educators a crystal ball to flag high-potential students early, personalize support proactively, and allocate resources smartly. Our results were not just number crunching; it will also be a new playbook for medical postgraduate students’ education. Conclusion This research showed that XGBoost model did not just predict academic performance; it also revealed hidden pathways for students’ success. We found that students should focus on ambition, track record, and their mastery of core subjects to drive their success based on machine learning and SHAP models. More importantly, we developed a clever, user-friendly tool that might help educators identify students with high potential earlier and intervene with support ahead of challenges.

ABSTRACTThe grand challenge of protein engineering is the development of computational models to characterize and generate protein sequences for arbitrary functions. Progress is limited by lack of (1) benchmarking opportunities, (2) large protein function datasets, and (3) access to experimental protein characterization. We introduce the Protein Engineering Tournament—a fully‐remote competition designed to foster the development and evaluation of computational approaches in protein engineering. The tournament consists of a predictive round, predicting biophysical properties from protein sequences, followed by a generative round where novel protein sequences are designed, expressed, and characterized using automated methods. Upon completion, all datasets, experimental protocols, and methods are made publicly available. We detail the structure and outcomes of a pilot Tournament involving seven protein design teams, powered by six multi‐objective datasets, with experimental characterization by our partner, International Flavors and Fragrances. Forthcoming Protein Engineering Tournaments aim to mobilize the scientific community towards transparent evaluation of progress in the field.

Nature produces a variety of materials with many functions, often out of simple and abundant materials, and at low energy. Such systems - examples of which include silk, bone, nacre or diatoms - provide broad inspiration for engineering. Here we explore the translation of biological composites to engineering applications, using a variety of tools including molecular modeling, AI and machine learning, and experimental synthesis and characterization. We review a series of studies focused on the mechanical behavior of materials, especially fracture, and how these phenomena can be modeled using a combination of molecular dynamics and machine learning. We also present various case studies of hierarchical material optimization using genetic algorithms, applied to 3D printed composites, and protein design.

Biological experiments often require a series of precisely timed operations, and small variations in treatment can result in inconsistent or biased results. To handle multiple samples in parallel with precise temporal resolution, experimentalists may stagger treatments by initiating the workflow of one sample during the wait or incubation time of another. However, as the number of samples processed in parallel and the number of operations increase, it becomes increasingly difficult to identify and execute valid treatment regimens that permit the handling of each sample. To address this, I developed StaggR, an interactive web application that calculates and visualizes compatible staggering intervals for parallelized execution of identical processing workflows. This tool provides a user-friendly interface for defining protocol operations, durations, and wait times. It can automatically calculate the shortest possible conflict-free interval for initiating sample treatments, or allow users to simulate specific intervals to explore potential treatment regimens or bottlenecks. Using StaggR, users of any experience level can rapidly generate complete, color-coded experimental schedules, visualize these workflows in an easy-to-read chart, and execute them using a built-in timer displaying a treatment schedule with live updates. The experimental designs can be saved, shared, and re-imported, ensuring full reproducibility and user control. The application of StaggR is expected to expedite the design and throughput of complex experimental workflows while maximizing reproducibility.

Biological experiments often require a series of precisely timed operations, and small variations in treatment can result in inconsistent or biased results. To handle multiple samples in parallel with precise temporal resolution, experimentalists may stagger treatments by initiating the workflow of one sample during the wait or incubation time of another. However, as the number of samples processed in parallel and the number of operations increase, it becomes increasingly difficult to identify and execute valid treatment regimens that permit the handling of each sample. To address this, I developed StaggR, an interactive web application that calculates and visualizes compatible staggering intervals for complex experimental workflows. This tool provides a user-friendly interface for defining protocol operations, durations, and wait times. It can automatically calculate the shortest possible conflict-free interval for initiating sample treatments, or allow users to simulate specific intervals to explore potential treatment regimens or bottlenecks. Using StaggR, users of any experience level can rapidly generate complete, color-coded experimental workflows, visualize these workflows in an easy-to-read chart, and execute them using a built-in timer displaying a treatment schedule with live updates. The experimental designs can be saved, shared, and re-imported, ensuring full reproducibility and user control. The application of StaggR is expected to expedite the design and throughput of complex experimental workflows while maximizing reproducibility.

We have previously developed a machine learning classifier that enables fast, accurate, and affordable classification of brain tumors based on genome-wide DNA methylation profiles that is widely employed in the clinic all over the world. Clinical and neuro-oncology research would benefit greatly from understanding the underlying artificial intelligence decision process, which currently remains largely unclear. Here, we describe an interpretable framework to explain the random forest classifier’s decisions and to uncover DNA methylation patterns distinguishing different tumor classes. We show that functional genomic regions of various sizes are predominantly employed to distinguish between different tumor classes, ranging from enhancers and CpG islands to large-scale heterochromatic domains. We detect a high degree of genomic redundancy, with many genes distinguishing individual tumor classes, explaining the robustness of the classifier and revealing potential targets for further therapeutic investigation. We anticipate that our resource will build up trust in machine learning in clinical settings, foster biomarker discovery and development of compact point-of-care assays, and enable further epigenome research of brain tumors. Our interpretable framework is accessible to the research community via an interactive web application (https://hovestadtlab.shinyapps.io/shinyMNP/).

The Indian Premier League (IPL) is one of the world’s most well-known league competitions that takes place in India during the summer, with people from the cricket fraternity competing for the coveted silverware. Using the concepts of machine learning, this research intends to help viewers gain good insight into how a team is placed in a particular scenario in a match and whether they have a good chance of winning or not. It will also assist investors and franchisees in determining which team to invest in to maximize profits. Coaches, sports analysts, and technicians also gain game facts and ideas about opposing teams, which aids them in making decisions and changing plans as needed. In this study, we have used three different ML algorithms to predict the percentage chances of winning of the competing teams: Logistic Regression, Decision Tree, and Random Forest. For this purpose, two datasets have been used, one containing the match result data and the other containing ball-wise data of the IPL matches played between 2008 and 2022. Our results show that the Random Forest algorithm achieves the highest accuracy score when compared to the other two algorithms. Also, an interactive web application has been developed and hosted using Streamlit so that users can use it as a service from any convenient device.

Sensorimotor information plays a fundamental role in cognition. However, the existing materials that measure the sensorimotor basis of word meanings and concepts have been restricted in terms of their sample size and breadth of sensorimotor experience. Here we present norms of sensorimotor strength for 39,707 concepts across six perceptual modalities (touch, hearing, smell, taste, vision, and interoception) and five action effectors (mouth/throat, hand/arm, foot/leg, head excluding mouth/throat, and torso), gathered from a total of 3,500 individual participants using Amazon’s Mechanical Turk platform. The Lancaster Sensorimotor Norms are unique and innovative in a number of respects: They represent the largest-ever set of semantic norms for English, at 40,000 words × 11 dimensions (plus several informative cross-dimensional variables), they extend perceptual strength norming to the new modality of interoception, and they include the first norming of action strength across separate bodily effectors. In the first study, we describe the data collection procedures, provide summary descriptives of the dataset, and interpret the relations observed between sensorimotor dimensions. We then report two further studies, in which we (1) extracted an optimal single-variable composite of the 11-dimension sensorimotor profile (Minkowski 3 strength) and (2) demonstrated the utility of both perceptual and action strength in facilitating lexical decision times and accuracy in two separate datasets. These norms provide a valuable resource to researchers in diverse areas, including psycholinguistics, grounded cognition, cognitive semantics, knowledge representation, machine learning, and big-data approaches to the analysis of language and conceptual representations. The data are accessible via the Open Science Framework (http://osf.io/7emr6/) and an interactive web application (https://www.lancaster.ac.uk/psychology/lsnorms/).

Abstract. With the rapid development in infrastructure, the need to document man-made structures is in increasing demand and inevitable. Such a process of digital documentation of buildings is called Building Information Modelling (BIM). Conventional techniques of BIM involve manual drafting &amp;amp; modelling using computer aided design, drafting &amp;amp; modelling software. Although these techniques are more accurate, given the increase in the size and complexity of modern structures, it would be tedious and time consuming for such manual work. It is in this context LiDAR shows great potential to simplify this task. Laser scanning enables rapid mapping of a building with a high degree of spatial accuracy. Since the spatial point sampling distance of any LiDAR scanner is usually in the order of centimetres or millimetres, this has potential not only to generate high density scans of the building but also to identify even the smallest defects in a structure. This facilitates using LiDAR to study the serviceability of a building. In this project, the feasibility of using a terrestrial laser scanner (TLS) to scan a multi-storey building was investigated. Additionally, the reliability of Potree for visualising point cloud data was tested. Potree is an open-source WebGL based point cloud renderer. Potree enables us to render point clouds and visualise in a portable web application. This application is also capable of making measurements of high accuracy on the 3D model of the library. This could serve to be of great utility in surveying applications. The object of study was chosen as a six-storey building, each floor having differing layouts. Two of these storeys were below ground surface level which also proved to be a test for the reliability of TLS in challenging terrain. The building has a towering height and large footprint which made it a perfect candidate for this project. A total of 54 scans (44 interior scans and 10 exterior scans of the library) were acquired with each subsequent scan station not more than 10m apart from the previous one. This data was brought to the lab for further processing. The processing was carried out using open-source software packages (LAStools, CloudCompare, etc). After processing, the complete point cloud data had 483,292,994 points. In order to make the data easier to handle, spatial sub-sampling of the data was done after which the final point cloud had 87,789,548 points. Finally, this sub-sampled point cloud was published using the open source Potree Converter into an interactive web application.

Web applications for biology and medicine often need to integrate data from Entrez services provided by the National Center for Biotechnology Information. However, direct access to Entrez from a web browser is not possible due to 'same-origin' security restrictions. The use of "Asynchronous JavaScript and XML" (AJAX) to create rich, interactive web applications is now commonplace. The ability to access Entrez via AJAX would be advantageous in the creation of integrated biomedical web resources. We describe EntrezAJAX, which provides access to Entrez eUtils and is able to circumvent same-origin browser restrictions. EntrezAJAX is easily implemented by JavaScript developers and provides identical functionality as Entrez eUtils as well as enhanced functionality to ease development. We provide easy-to-understand developer examples written in JavaScript to illustrate potential uses of this service. For the purposes of speed, reliability and scalability, EntrezAJAX has been deployed on Google App Engine, a freely available cloud service. The EntrezAJAX webpage is located at http://entrezajax.appspot.com/

A Curated Web Tracker of Global Development of Treatments and Vaccines for COVID-19

MathEdit (Su et al., 2006) is a browser-based tool implemented in JavaScript that provides a convenient and intuitive graphical user interface for creating and editing mathematical expressions as well as a well-defined API for interoperating with its containing Web page. MathEdit can produce MathML Content and Presentation Markup as well as infix expressions for Web applications. The results returned can be displayed in a Web page or used in further computations. Here, we describe the methods of expression editing, visual navigation, and the MathEdit API. We also present the actual use of MathEdit in such interactive Web applications as curve plotting and Math-capable BBS.