Types Of Tasks Research Articles

Prediction of Individual Learning Experience in Terms of “Number Of Steps” as Solution Components of Arithmetic Tasks

The paper is devoted to the study of learning in solving arithmetic problems in the conditions of digital learning. Learning is considered as a functional system, the level of differentiation of which can be related to the number of steps in problem solving. The goal of the paper is to find out the model that could more accurately describe the relationships between the number of steps and task types on Addition data and predict the number of steps on Multiplication data. The hypothesis is that with a given similarity, there is a correlation between the number of steps in solution of addition and multiplication tasks. We have created two experimental courses, “Addition” and “Multiplication” to make participants learn optimal methods of calculation of arithmetic tasks. The courses have the same structure and belong to a common domain (arithmetic tasks). It is a condition for similarity of learning. We have found out significant positive correlation between the number of steps in solution of addition and multiplication tasks on average for the sample. We have used a regression-based classification. Few models have been built for each individual personally and trained on the Addition data, then applied on the Multiplication data. The best of these models correctly predict the number of steps in 33–40% of tasks (SD = 17–22%, max = 88%), in other tasks they give a prediction with a small error of 1–2 units, which indicates its medium predictive ability.

Neural correlates of working memory training: An fMRI meta-analysis

Working memory (WM) can be improved by cognitive training. Numerous studies examined neural mechanisms underlying WM training, although with differing conclusions. Therefore, we conducted a meta-analysis to examine the neural substrates underlying WM training in healthy adults. Findings from global analyses showed substantial neural changes in the frontoparietal and subcortical regions. Results from training dosage analyses of WM training showed that shorter WM training could produce neural changes in the frontoparietal regions, whereas longer WM training could produce changes in the subcortical regions (striatum, anterior cingulate cortex, and insula). WM training-induced neural changes were also moderated by the type of training task, with updating tasks inducing neural changes in more regions than maintenance tasks. Overall, these results indicate that the neural changes associated with WM training occur in the frontoparietal network and dopamine-related brain areas, extending previous meta-analyses on WM training and advancing our understanding of the neural underpinnings of WM training effects.

The Influence of Task and Group Disparities Over Users’ Attitudes Toward Using Large Language Models for Psychotherapy

The population suffering from mental health disorders has kept increasing in recent years. With the advancements in large language models (LLMs) in diverse fields, LLM-based psychotherapy has also attracted increasingly more attention. However, the factors influencing users’ attitudes to LLM-based psychotherapy have rarely been explored. As the first attempt, this paper investigated the influence of task and group disparities on user attitudes toward LLM-based psychotherapy tools. Utilizing the Technology Acceptance Model (TAM) and Automation Acceptance Model (AAM), based on an online survey, we collected and analyzed responses from 222 LLM-based psychotherapy users in mainland China. The results revealed that group disparity (i.e., mental health conditions) can influence users’ attitudes toward LLM tools. Further, one of the typical task disparities, that is, the privacy concern, was not found to have a significant effect on trust and usage intention. These findings can guide the design of future LLM-based psychotherapy services.

ФОРМИРОВАНИЕ ЦИФРОВОЙ КОМПЕТЕНТНОСТИ НА УРОКАХ ЛИТЕРАТУРЫ С ПОМОЩЬЮ ИСПОЛЬЗОВАНИЯ ИКТ

Digital technologies have made great changes in the daily way of life of society. In the modern world, it becomes very difficult to keep track of the flow of constantly updated information: a person needs to process and filter a large amount of information every day, selecting only reliable ones. Digitalization of information generates a need for skills to work with digital technologies. Today, the formation of digital competence is becoming one of the relevant topics. This article discusses the issue of the formation of digital competence among students in literature lessons. The purpose of our research is to identify ways to form digital competence in literature lessons in high school through the use of digital technologies. Based on the set goal, we have identified the object and subject of the study. The object of the study is ICT in literature lessons. Subject of research: digital competencies formed through ICI in a literature lesson. Defining the essence of the concept of "digital competence", we identify some competencies that form "digital literacy". The paper also presents an analysis of the results of a survey of high school students (15-17 years old). Identifying the problem, we have proposed several platforms and types of tasks that can help in solving a didactic task. The main assistants of the teacher in the formation of digital competencies are information and communication technologies. The paper provides as an example several educational websites (platforms), ICT that can be used in the lesson of Russian literature, analyzes the ways of forming "digital competence".

A Systematic Review on Graph Neural Network-based Methods for Stock Market Forecasting

Financial technology (FinTech) is a field that uses artificial intelligence to automate financial services. One area of FinTech is stock analysis, which aims to predict future stock prices to develop investment strategies that maximize profits. Traditional methods of stock market prediction, such as time series analysis and machine learning, struggle to handle the non-linear, chaotic, and sudden changes in stock data and may not consider the interdependence between stocks. Recently, graph neural networks (GNNs) have been used in stock market forecasting to improve prediction accuracy by incorporating the interconnectedness of the market. GNNs can process non-Euclidean data in the form of a knowledge graph. However, financial knowledge graphs can have dynamic and complex interactions, which can be challenging for graph modeling technologies. This work presents a systematic review of graph-based approaches for stock market forecasting. This review covers different types of stock analysis tasks (classification, regression, and stock recommendation), a generalized framework for solving these tasks, and a review of various features, datasets, graph models, and evaluation metrics used in the stock market. The results of various studies are analyzed, and future directions for research are highlighted.

Effects of video game immersion and task interference on cognitive performance: a study on immediate and delayed recall and recognition accuracy.

This study investigates the cognitive impacts of video game immersion and task interference on immediate and delayed recall as well as recognition tasks. We enrolled 160 subjects aged 18 to 29, who were regular players of "shoot-em-up" video games for at least 3 years. Participants were assigned to one of three experimental groups or a control group. The experimental conditions varied in the timing and type of tasks: the first group performed a video game session between recall tasks, the second group multitasked with video games and recall tasks simultaneously, and the third group engaged in task switching from video games to recall tasks. Using the Rey Auditory Verbal Learning Test, we measured the effects of these conditions on cognitive performance, focusing on error types and recall accuracy. Results indicated that multitasking and task switching significantly affected the subjects' performance, with notable decrements in recall and recognition accuracy in conditions of high task interference. The study highlights the cognitive costs associated with multitasking in immersive digital games and provides insights into how task similarity and interference might increase error rates and affect memory performance.

Is the Frequency of a Targeted Neuromuscular Training Program a Factor in Modifying Knee Joint Loading During Typical Netball Landing Tasks?

Unplanned sidestep cutting and forward single-leg jump-landing contribute to non-contact anterior cruciate ligament (ACL) injuries in netball. Neuromuscular training programs (NMTPs) have shown promising results in reducing injury risk in certain populations when compliance is high. Compliance is easier to achieve when NMTPs are effective yet require minimal time for completion. Once- and thrice-weekly intervention groups would be equally effective in reducing knee abduction and internal rotation moments during forward single-leg jump landing and unplanned sidestep cutting. Randomized controlled trial. Level 3. External peak knee abduction and peak knee internal rotation moments during unplanned sidestep cutting and forward single-leg jump-landing were assessed pre- and post-intervention for 17 elite-level female netballers assigned randomly to either a once-weekly or thrice-weekly group. Regular netball training continued throughout the intervention, which lasted 6 weeks (30 minutes/session). One-way analysis of covariance (α = 0.05) was utilized to compare post-intervention peak knee abduction and peak knee internal rotation moments between groups, controlling for pre-intervention knee moments during the forward single-leg jump-landing and unplanned sidestep cut. Paired t tests were used to examine within-group changes in knee moments pre- versus post-intervention. For unplanned sidestep cuts on the right leg, both groups differed significantly, with the once-weekly group displaying a decrease in peak knee internal rotation moments [F(1,14) = 5.23; P = 0.04] whereas the thrice-weekly group did not. No other significant group interactions were found. A condensed NMTP with targeted exercises, performed once-weekly as part of regular training, shows potential to reduce peak knee internal rotation moments that are injurious to the ACL during unplanned sidestep cutting in adult female netballers. A once-weekly targeted NMTP would pose minimal disruption to a high-performing athlete's training schedule and likely increase compliance to ensure the success of the NMTP.

Spotting missing or wanted people: racial biases in prospective person memory

Searching for missing or wanted people is a crucial task in our society. Previous work on prospective person memory (PPM) has demonstrated that performance on this type of search task is worse relative to standard prospective memory tasks. Importantly, this process may be further affected by the race of the missing person, yet this has never been tested in laboratory settings. To test the effects of race on PPM, a convenience sample consisting primarily of self-identified Caucasian participants was asked to search for either a Caucasian or an Indian target person while judging the orientation of different Caucasian and Indian faces. Although the tasks were otherwise identical, 89% of Caucasian PPM targets were found while only 53% of Indian targets were found. Furthermore, relative to a control group with no PPM requirements, participants were slower and more error-prone when judging Indian faces relative to White faces, particularly if they were searching for an Indian face. We interpret these results as revealing other-race effects in prospective person memory, highlighting race as a critical factor for finding missing people. Importantly, this also emphasizes the need for real-world search efforts to factor in difficulty differences when people monitor for missing/wanted people from their own or different racial backgrounds. For example, media coverage of missing persons cases could perhaps be distributed more equitably by considering whether the missing person is from a racial minority in that region.

Variability in Vowel Space in Parkinson's Disease: Associations With Cognitive and Motor Impairment.

People with Parkinson's disease (PwP) typically experience impairments in vowel articulation; however, less is known about how this measure varies with speech task type and clinical characteristics such as cognitive impairment. We characterized vowel space in PwP with and without mild cognitive impairment (MCI) comparing performance across phonation, reading, and picture description tasks. We evaluated associations between vowel space and cognitive impairment, as well as motor symptom severity to elucidate the factors contributing to variability in this acoustic measure. PwP (n = 48) and age-matched controls (n = 15) performed sustained phonation of corner vowels, a reading passage, and a picture description task (Cookie Theft picture). PwP participants were classified as with normal cognition (PD-NC) or MCI (PD-MCI), and motor symptoms were assessed using the Movement Disorders Society Unified Parkingson's Disease Rating Scale Part III (MDS-UPDRS Part III). Vowel articulation index (VAI) for each task and mean difference in VAI between tasks was compared between the groups using linear mixed models adjusted for age, sex, and education. The impact of motor severity was assessed by additionally adjusting the model for MDS-UPDRS Part III score. In the adjusted mixed model, mean VAI was significantly lower in the PD-MCI group compared to the PD-NC group for all tasks. Within participants, adjusted mean differences demonstrated that all groups declined in VAI when sustained phonation was compared to either reading or picture description tasks. Adjustment for MDS-UPDRS Part III did not alter the results, suggesting no major association of motor impairment with vowel space variability within or between individuals or groups. Variability in vowel space is impacted by cognitive impairment and speech task in PwP. These findings are relevant to the further development of speech markers in PwP and other neurogenerative diseases that impact both cognitive and motor functions.

An exploratory study on second language learner engagement in different types of interactive tasks in video-chat and text-chat communication

Abstract This study investigated 48 Hong Kong English as a second language (ESL) learners’ engagement in three types of interactive tasks conducted via video chat or text chat. The learners, paired with their university friends, completed a descriptive task, a narrative task, and a decision-making task. They were randomly assigned to either the video-chat or text-chat group and were interviewed about their emotional engagement in each task immediately after task performance. The findings revealed that both groups of learners were behaviourally the least engaged but cognitively the most engaged in the decision-making task. They experienced positive emotions during the descriptive task, but fewer reported positive emotions in the other two tasks. The text-chat group was the most socially engaged in the decision-making task. Furthermore, the video-chat group was behaviourally and emotionally more engaged than the text-chat group. These findings have implications for task design and selection in computer-mediated communication.

Emotion-Driven Moral Evaluation: A Mechanistic Study Based on the Drift-Diffusion Model.

Moral evaluation is identified as the first stage in the theory of moral judgment, and academics believe that it may align with the social intuitionist model. This study aims to prove that the model's emotional dominance hypothesis applies to moral evaluation by presenting a computational decision-making model that mathematically formalizes this emotional dominance decision-making process. We also compared different types of valence evaluation tasks to test the emotional priority hypothesis. We used a convenience sampling method to randomly recruit 30 enrolled college students. The drift-diffusion model was employed to analyze reaction times for words with various emotional and moral valences Additionally, we designed different valence evaluation tasks based on the response relevance hypothesis and evaluated the processing order through reaction time comparisons. The analysis revealed that the emotional mechanism of immoral evaluation differs from moral evaluation. An increase in emotional valence accelerates the speed of evidence accumulation (v) for moral evaluation (M = 1.21, 0.2% < 0 < 99.8%) but lowers decision caution (a) in immoral evaluation (M = -0.64, 96.1% < 0 < 3.9%). In contrast, moral valence does not have a significant influence on evaluation processes (v, M = -0.28, 72.1% < 0 < 27.9%; a, M = -0.32, 79.3% < 0 < 20.7%). Furthermore, We found no significant difference in reaction times between moral and immoral words in the emotional evaluation task (F(1,29) = 0.55, p = 0.464, partial η2 = 0.02), but a significant difference existed in the moral evaluation task (F(1,29) = 17.99, p < 0.001, partial η2 = 0.38), indicating that the tendency of relatively fast immoral evaluation in emotional evaluation tasks may be caused by emotional priority. Our findings support the intuitive model's emotional dominance hypothesis and introduce a new emotional mechanism into moral evaluation. This study clarifies the distinct emotional processes in moral and immoral evaluations, fills a gap in the research on moral evaluation, and offers insights into human decision-making in moral contexts.

Affordances and Constraints of Automation and Augmentation

Human-AI collaboration is becoming increasingly prevalent in workplaces, and is considered to be an important model for the future of work. Consequently, AI is no longer seen merely as a tool but as a teammate working alongside humans. Currently, the design of AI in team collaboration, particularly human-AI collaboration patterns, has become a focal point for organizations. However, users' perceptions of the affordances and constraints of different collaboration patterns remain insufficient. Therefore, this study introduces a human-AI collaboration business simulation platform, used to simulate a future work environment that has two distinct human-AI collaboration patterns: automation and augmentation. In the unique context of the case enterprise platform, we further investigated the impact of task types (structured and unstructured tasks) on people's perceptions of automation and the influence of knowledge sources (AI designers' and end-users' knowledge-driven development) on people's perceptions of augmentation.

Meta-Analysis on the Impact of Different Channel Loads on Takeover Performance in Autonomous Driving under Non-Driving Tasks

Abstract Under conditions of high automation, drivers’ excessive engagement in non-driving related tasks can severely impact their takeover ability, posing a significant threat to road safety. Therefore, it’s essential to explore the channel resources occupied by non-driving related tasks to enhance driving safety. However, many studies have merely categorized different types of tasks in experiments without clarifying the relationship between the tasks and the channel resources they occupy. To determine whether different channel loads under non-driving related tasks have varying impacts on autonomous driving takeover performance, a meta-analysis was conducted on literature retrieved from January 2021 to January 2024. The results indicate that tasks occupying visual, auditory, motor, and cognitive channel resources during takeover all affect takeover performance. Among these, cognitive channel resource occupation significantly reduces takeover efficiency, followed by motor and auditory channels, with the visual channel having the least impact.

State of the Art of Brain Function Detection Technologies in Robot-Assisted Lower Limb Rehabilitation.

Background: With an aging population, the prevalence of neurological disorders is increasing, leading to a rise in lower limb movement disorders and, in turn, a growing need for rehabilitation training. Previous neuroimaging studies have shown a growing scientific interest in the study of brain mechanisms in robot-assisted lower limb rehabilitation (RALLR). Objective: This review aimed to determine differences in neural activity patterns during different RALLR tasks and the impact on neurofunctional plasticity. Methods: Sixty-five articles in the field of RALLR were selected and tested using three brain function detection technologies. Results: Most studies have focused on changes in activity in various regions of the cerebral cortex during different lower limb rehabilitation tasks but have also increasingly focused on functional changes in other cortical and deep subcortical structures. Our analysis also revealed a neglect of certain task types. Conclusion: We identify and discuss future research directions that may contribute to a clear understanding of neural functional plasticity under different RALLR tasks. Impact Statement The evaluation of robot-assisted lower limb rehabilitation based on brain function detection technology can assess the neurological changes of patients in the rehabilitation process by monitoring brain activities and can also provide more accurate guidance for robot-assisted lower limb rehabilitation. By monitoring the patient's brain activity, the robot can adjust according to the real-time status of the patient to achieve more effective rehabilitation training. This has potential impact on improving the rehabilitation effect and speeding up the rehabilitation process of patients.

Physiological and perceptual responses of firefighters wearing protective clothing under various training environment and activity conditions

To enhance operational capabilities of firefighters in live-fire scenarios, daily training is absolutely important which involves various types of training tasks in diverse thermal environments. Fire training in heat may impose severe heat stress on firefighters. Yet, the thermal burden associating with different training has rarely been studied. In this study, twelve healthy male firefighters performed 50 min of treadmill exercise while wearing firefighting protective clothing (FPC) in two environmental conditions (34°C and 37°C) with three training intensities (3 km/h, 4.5 km/h and 6 km/h). Results showed that in hot environments, training intensity exhibited a more pronounced effect on physiological responses than ambient temperature. Exposure to 37°C with heavy activity produced high level of core temperature (38.8±0.2°C), near maximal heart rate (164±18 bpm), increased energy expenditure (27.10±1.42 ml/min/kg) coupled with mild dehydration (2.08%±0.35%). The forehead, back and chest which showed the highest level of thermal sensation vote, wetness sensation vote and thermal comfort vote are suggested to be primarily considered when designing cooling strategies. Moreover, when providing recovery and cooling for firefighters working in extreme heat while wearing fully encapsulated FPC, the priority should be given to work intensity and duration, followed by environmental conditions.

Lexical retrieval difficulties in post-COVID-19 syndrome: Insights from verbal fluency and naming tasks.

Although considerable research has been conducted on post-COVID-19 syndrome (PCS), cognitive symptoms, particularly those related to language, are still not well understood. To provide a detailed quantitative and qualitative analysis of language performance in PCS patients using a comprehensive set of semantic and verbal production tasks. The study involved 195 PCS patients aged 26-64 years and 50 healthy controls aged 25-61 years. Participants were assessed using two semantic tasks, three naming tasks and four types of verbal fluency tasks, designed to evaluate different aspects of language processing. PCS patients demonstrated significantly poorer performance compared with controls across all verbal fluency tasks. This was evident in both the total number of words generated and their types, with patients tending to choose more easily accessible words. In naming tasks, the pattern of errors was similar in both groups, although patients showed a higher number of non-responses and made more errors, reflecting difficulties in word retrieval. The analysis highlighted the impact of factors such as stimulus availability, educational level and cognitive reserve on performance. Notably, younger patients performed worse than older, a paradoxical trend also observed in previous research. These findings reveal significant word retrieval difficulties in PCS patients, suggesting that cognitive impairment related to language may be more pronounced than previously understood. The results underscore the need for a thorough evaluation of language functions in PCS patients and the development of more targeted and individualized language rehabilitation strategies to address these specific challenges. What is already known on the subject Studies on the cognitive characteristics of CPS have focused mainly on broad-spectrum neuropsychological assessments covering all cognitive functions. However, there are very few studies analysing oral production with specific lexical and semantic system tasks. Furthermore, no work has specifically included tasks assessing semantic processing or conducted qualitative analyses of the psycholinguistic variables affecting performance. Such analyses could undoubtedly help clarify the nature of the language impairments in patients with PCS. What this paper adds to the existing knowledge This study explores in depth the evaluation and analysis of the oral production of patients with PCS using several lexical and semantic tasks. In addition, psycholinguistic variables are analysed that could undoubtedly help clarify the nature of the language impairments in patients with PCS. What are the potential or actual clinical implications of this work? The study allows the identification of specific lexical-semantic deficits in the spoken language in patients with this PCS. A more detailed assessment of the oral language of these patients, keeping in mind the psycholinguistic variables that may affect the performance, will facilitate the design of more efficient and individualized rehabilitation programmes.

DEVELOPMENT OF AN INTERACTIVE WEBSITE WITH DIDACTIC GAMES TO ENHANCE VOCABULARY IN YOUNG STUDENTS WITH INTELLECTUAL DISABILITIES

The article investigates the development of a website that includes interactive didactic games designed to improve the vocabulary of primary schoolchildren with intellectual disabilities. It describes the importance of developing vocabulary in children with intellectual disabilities and shows how the game approach can be an effective tool for teaching and developing speech in this category of children. The process of developing a website with didactic games is considered, which includes the selection of appropriate software, interface design, development of interactive tasks and games, as well as testing and improvement of the website. In particular, the article discusses methods and approaches to creating games aimed at developing lexical skills, expanding vocabulary and improving communication skills in children with intellectual disabilities. The advantages of using interactive didactic games in the educational process of junior schoolchildren with intellectual disabilities are highlighted. They stimulate children's interest in learning words and expanding their vocabulary, develop cognitive and speech skills, improve memory and concentration, and increase motivation and enjoyment of learning. A game-based approach can keep children interested, motivated, and effective, helping them to develop their language skills and achieve greater academic success. The website was created on the wix platform. The collection of didactic games was developed on the LearningApps platform. There are various types of tasks, for example quizzes, puzzles, crosswords, matching exercises, etc. Images for didactic games were generated by playground.ai artificial intelligence, which opens up new opportunities for creating visually appealing games and tasks. The importance of developing website with interactive didactic games for the development of vocabulary of younger students with intellectual disabilities is emphasized, they can become an effective tool for teaching and developing speech in children of this category, contributing to their success in learning and overall development.

Promoting Enrichment of Living Conditions: Indispensable Goal of all Individuals

The individuals, belonging to all occupations, communities, categories and socio-economic backgrounds have one of the major goals of individuals of promoting enrichment of living conditions. In order to achieve this goal, they are required to augment information in terms of different types of subjects and concepts. Furthermore, they are required to reinforce the traits of morality, ethics, diligence and conscientiousness. In addition, individuals need to understand that there are some job duties, which are carried out on an individual basis, whereas, there are others, which are implemented through working in co-ordination with other individuals. One of the important aspects that needs to be taken into account is, individuals should not be disheartened due to problems and challenging situations. One needs to ensure, they are aware in terms of different job duties and methodologies. In addition, they need to augment confidence levels and overcome the feelings of apprehensiveness and vulnerability. Furthermore, all types of problems and challenging situations need to be prevented from giving rise to impediments within the course of putting into operation different types of tasks and activities. Therefore, it is understood on a comprehensive basis that promoting enrichment of living conditions is an indispensable goal of all individuals. The main concepts that are taken into account in this research paper are, understanding the meaning and significance of promoting enrichment of living conditions, measures to be put into operation in promoting enrichment of living conditions and advantages of promoting enrichment of living conditions.

Time reference in French-speaking people with fluent and non-fluent aphasia (part I): tense dissociations, task effects and cognitive predictors

ABSTRACT Background People with fluent and non-fluent aphasia frequently have time reference deficits, which could be more pronounced for the past than for the present and future tenses. However, this performance pattern (past < non-past) is not consensual and might depend on the type of task used. Furthermore, the influence of cognitive processes on time reference deficits remains little explored, as does the origin of these difficulties (e.g. pre-phonological, morpho-phonological). Aims The primary aims of the study were (1) to identify time reference deficits and (2) dissociations between tenses in French speakers with fluent and non-fluent aphasia and (3) to specify the effect of tasks on performance and tense dissociations. Secondly, our study also aimed to determine whether time reference deficits were (4) influenced by cognitive functions and (5) explained by pre-phonological or morpho-phonological deficits. Methods & procedures Twenty-one French-speaking participants with fluent and non-fluent aphasia and 21 matched control subjects performed three tasks assessing time reference (verb inflection production, verb inflection selection, and adverb selection) and five neuropsychological tests (verbal and non-verbal working memory, inhibition, flexibility, and temporality). Quantitative and qualitative analyses were conducted. Outcomes & results Participants with fluent and non-fluent aphasia had worse performances than controls on the three time-reference tasks. The performance of the participants with fluent and non-fluent aphasia was quantitatively similar but qualitatively different on the verb inflection production task (i.e. different error types). A main task effect was also found: the verb inflection production task was the only one to show worse performances in the past than in the present and future. Regarding cognitive predictors, verbal working memory and temporality were linked to the three tasks assessing time reference. In contrast, non-verbal working memory was associated only with the two selection tasks, possibly related to the mental timeline. Finally, task analysis suggested a pre-phonological (encoding of diacritic features deficit) rather than a morpho-phonological origin. Conclusions Our study is the first to replicate time reference deficit in French speakers with aphasia. It suggests that the type of task might influence the performance profiles observed and help to shed light on the origin of the difficulties. Cognitive functions that have rarely been investigated before may also influence performance. These results have important clinical implications by questioning the tasks used to assess time reference. They also underline the importance of identifying the origin of difficulties in proposing targeted treatment.

PMSFF: Improved Protein Binding Residues Prediction through Multi-Scale Sequence-Based Feature Fusion Strategy.

Proteins perform different biological functions through binding with various molecules which are mediated by a few key residues and accurate prediction of such protein binding residues (PBRs) is crucial for understanding cellular processes and for designing new drugs. Many computational prediction approaches have been proposed to identify PBRs with sequence-based features. However, these approaches face two main challenges: (1) these methods only concatenate residue feature vectors with a simple sliding window strategy, and (2) it is challenging to find a uniform sliding window size suitable for learning embeddings across different types of PBRs. In this study, we propose one novel framework that could apply multiple types of PBRs Prediciton task through Multi-scale Sequence-based Feature Fusion (PMSFF) strategy. Firstly, PMSFF employs a pre-trained language model named ProtT5, to encode amino acid residues in protein sequences. Then, it generates multi-scale residue embeddings by applying multi-size windows to capture effective neighboring residues and multi-size kernels to learn information across different scales. Additionally, the proposed model treats protein sequences as sentences, employing a bidirectional GRU to learn global context. We also collect benchmark datasets encompassing various PBRs types and evaluate our PMSFF approach to these datasets. Compared with state-of-the-art methods, PMSFF demonstrates superior performance on most PBRs prediction tasks.