Affinity Relationships Research Articles

NCMNet: Neighbor Consistency Mining Network for Two-View Correspondence Pruning.

Correspondence pruning plays a crucial role in a variety of feature matching based tasks, which aims at identifying correct correspondences (inliers) from initial ones. Seeking consistent k-nearest neighbors in both coordinate and feature spaces is a prevalent strategy employed in previous approaches. However, the vicinity of an inlier contains numerous irregular false correspondences (outliers), which leads them to mistakenly become neighbors according to the similarity constraint of nearest neighbors. To tackle this issue, we propose a global-graph space to seek consistent neighbors with similar graph structures. This is achieved by using a global connected graph to explicitly render the affinity relationship between correspondences based on the spatial and feature consistency. Furthermore, to enhance the robustness of method for various matching scenes, we develop a neighbor consistency block to adequately leverage the potential of three types of neighbors. The consistency can be progressively mined by sequentially extracting intra-neighbor context and exploring inter-neighbor interactions. Ultimately, we present a Neighbor Consistency Mining Network (NCMNet) to estimate the parametric models and remove outliers. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on various benchmarks for two-view geometry estimation. Meanwhile, four extended tasks, including remote sensing image registration, point cloud registration, 3D reconstruction, and visual localization, are conducted to test the generalization ability.

INCOMPLETE multi-view clustering based on low-rank adaptive graph learning

The challenge of acquiring complete data has led to substantial progress in incomplete multi-view clustering (IMVC) methods. Because graph structures can be excellent representations of data structure relationships, exceptional performance in handling incomplete data is demonstrated by graph-based methods at present. However, these methods still have their limitations. Most incomplete multi-view algorithms primarily focus on local information, neglecting global information. Therefore, these methods cannot dynamically recover the structural relationships in incomplete data by harnessing potential information from multiple perspectives and overall structural information. In response to the aforementioned concerns, we introduced an IMVC based on low-rank adaptive graph learning (IMVC-LAGL). This method initially constructs an affinity matrix based on the inter-view adjacency relationships. It also utilizes tensor low-rank constraints and consensus representation learning to explore higher-order correlations among different views. Subsequently, it adaptively reconstructs the incomplete graph structure to ultimately obtain a complete affinity relationship. It leads to excellent clustering results by integrating relevant information within views, overall structural information and potential information from multiple perspectives. We conducted experiments comparing our algorithm with eight incomplete multi-view algorithms using five different evaluation metrics. The results show that our algorithm achieves the best clustering results across eight datasets with varying missing rates. Particularly in the BBCSport dataset and YaleB dataset, the clustering accuracy of our algorithm is improved by 19.83 % and 16.41 %, respectively, compared with the second-best algorithm, under a 50 % missing rate.

Intraday and daily dynamics of cryptocurrency

This paper examines and compares intraday and intraweek patterns in hourly and daily prices, returns, volumes and volatility of native cryptocurrencies, stablecoins and tokens traded on Bitstamp. We show that native cryptocurrencies and tokens share common intraday periodicity determined by the operating times of the NYSE, LSE and Hang Seng stock exchange markets. Periodic patterns are also documented in the returns on cryptocurrency market portfolio approximated by the PCA applied to intraday and intraweek cross-sectional correlation matrices of cryptocurrency returns. Stablecoins have distinct dynamics and their daily and hourly returns are uncorrelated with one another and with the returns on other cryptocurrencies. We introduce a functional CAPM to accommodate the periodic patterns and estimate it by regressing the functions of intraday and intraweek cryptocurrency returns on the market portfolio. We show that the return functions on Bitcoin, Ether, and Link satisfy affine relationships with the return functions of the market portfolio and their functional betas display periodic intraday and intraweek patterns.

Religious Involvement Is Associated With Higher Fertility and Lower Maternal Investment, but More Alloparental Support Among Gambian Mothers.

Human childrearing is cooperative, with women often able to achieve relatively high fertility through help from many individuals. Previous work has documented tremendous socioecological variation in who supports women in childrearing, but less is known about the intracultural correlates of variation in allomaternal support. In the highly religious, high-fertility setting of The Gambia, we studied whether religious mothers have more children and receive more support with their children. We randomly sampled 395 mothers and 745 focal children enrolled in the Kiang West (The Gambia) Longitudinal Population Study cohort. Structured interviews asked mothers who and how often people invest in their children, and about their religious practices. Data were collected at participants' homes on electronic tablet-based long-form surveys and analyzed using the Bayesian hierarchical models. Religiosity was weakly associated with women's higher age-adjusted fertility. Maternal religiosity was negatively related to maternal investment in focal children, but positively associated with total allomaternal support. Specifically, a woman's religiosity was positively associated with allomaternal support from matrilineal kin, other offspring, and affinal kin, but unrelated to paternal, patrilineal, and non-kin investment. These results suggest that higher fertility among religious mothers may be supported by high levels of investment from biological and affinal kin. Matrilineal kin, other siblings, and affinal kin seem to be the most responsive to a woman's religiosity. Our findings cast doubt on interpretations of women's religious behaviorsas signals of fidelity, and instead suggest theymay be part of strategies to enable collective allomaternal resources and higher relative fertility.

MAC: Maximal Cliques for 3D Registration.

This paper presents a 3D registration method with maximal cliques (MAC) for 3D point cloud registration (PCR). The key insight is to loosen the previous maximum clique constraint and mine more local consensus information in a graph for accurate pose hypotheses generation: 1) A compatibility graph is constructed to render the affinity relationship between initial correspondences. 2) We search for maximal cliques in the graph, each representing a consensus set. 3) Transformation hypotheses are computed for the selected cliques by the SVD algorithm and the best hypothesis is used to perform registration. In addition, we present a variant of MAC if given overlap prior, called MAC-OP. Overlap prior further enhances MAC from many technical aspects, such as graph construction with re-weighted nodes, hypotheses generation from cliques with additional constraints, and hypothesis evaluation with overlap-aware weights. Extensive experiments demonstrate that both MAC and MAC-OP effectively increase registration recall, outperform various state-of-the-art methods, and boost the performance of deep-learned methods. For instance, MAC combined with GeoTransformer achieves a state-of-the-art registration recall of 95.7% / 78.9% on 3DMatch / 3DLoMatch. We perform synthetic experiments on 3DMatch-LIR / 3DLoMatch-LIR, a dataset with extremely low inlier ratios for 3D registration in ultra-challenging cases. Code will be available at: https://github.com/zhangxy0517/3D-Registration-with-Maximal-Cliques.

Virtual Screening and Validation of Affinity DNA Functional Ligands for IgG Fc Segment.

The effective attachment of antibodies to the immune sensing interface is a crucial factor that determines the detection performance of immunosensors. Therefore, this study aims to investigate a novel antibody immobilization material with low molecular weight, high stability, and excellent directional immobilization effect. In this study, we employed molecular docking technology based on the ZDOCK algorithm to virtually screen DNA functional ligands (DNAFL) for the Fc segment of antibodies. Through a comprehensive analysis of the key binding sites and contact propensities at the interface between DNAFL and IgG antibody, we have gained valuable insights into the affinity relationship, as well as the principles governing amino acid and nucleotide interactions at this interface. Furthermore, molecular affinity experiments and competitive binding experiments were conducted to validate both the binding ability of DNAFL to IgG antibody and its actual binding site. Through affinity experiments using multi-base sequences, we identified bases that significantly influence antibody-DNAFL binding and successfully obtained DNAFL with an enhanced affinity towards the IgG Fc segment. These findings provide a theoretical foundation for the targeted design of higher-affinity DNAFLs while also presenting a new technical approach for immunosensor preparation with potential applications in biodetection.

Investigating linguistic and genetic shifts in East Indian tribal groups

South Asia is home to almost a quarter of the world's total population and is home to significant ethnolinguistic diversity. Previous studies of linguistic and genetic affiliations of Indian populations suggest that the formation of these distinct groups was a protracted and complex phenomenon involving multiple waves of migration, cultural assimilation, and genetic admixture. The evolutionary processes of migration, mixing and merging of populations thus impact the culture and linguistic diversity of different groups, some of which may retain their linguistic affinities despite genetic admixture with other groups, or vice versa. Our study examines the relationship of genetic and linguistic affinities between Austroasiatic and Indo-European speakers in adjacent geographical regions of Eastern India. We analyzed 224 mitogenomes and 0.65 million SNP genotypes from 40 unrelated individuals belonging to the Bathudi, Bhumij, Ho, and Mahali ethnic groups from the Eastern Indian state of Odisha. These four groups are speakers of Austroasiatic languages who have adopted elements from Indo-European languages spoken in neighbouring regions. Our results suggest that these groups have the greatest maternal genetic affinity with other Austroasiatic-speaking groups in India. Allele frequency-based analyses, genome-wide SNPs, haplotype-based methods and IBD sharing further support the genetic similarity of these East Indian groups to Austroasiatic speakers of South Asia rather than regional populations speaking Indo-European and Dravidian languages. Our study shows that these populations experienced linguistic mixing, likely due to industrialization and modernization that brought them into close cultural contact with neighbouring Indo-European-speaking groups. However, linguistic change in these groups is not reflected in genetic mixing in these populations, as they appear to maintain strict genetic boundaries while simultaneously experiencing cultural mixing.

Unified multimodal fusion transformer for few shot object detection for remote sensing images

Object detection is a fundamental computer vision task with wide applications in remote sensing, but traditional methods strongly rely on large annotated datasets which are difficult to obtain, especially for novel object classes. Few-shot object detection (FSOD) aims to address this by using detectors to learn from very limited labeled data. Recent work fuse multi-modalities like image–text pairs to tackle data scarcity but require external region proposal network (RPN) to align cross-modal pairs which leads to a bias towards base classes and insufficient cross-modal contextual learning. To address these problems, we propose a unified multi-modal fusion transformer (UMFT), which extracts visual features from ViT and textual encodings from BERT to align multi-modal representations in an end-to-end manner. Specifically, affinity-guided fusion (AFM) captures semantically related image–text pairs by modeling their affinity relationships to selectively combine most informative pairs. In addition, cross-modal correlation module (CCM) captures discriminative inter-modal patterns between image and text representations and filters out unrelated features to enhance cross-modal alignment. By leveraging AFM to focus on semantic relationships and CCM to refine inter-modal features, the model better aligns multimodal data without RPN. These representations are passed to detection decoder that predicts bounding boxes, probabilities of class and cross-modal attributes. Evaluation of UMFT on benchmark datasets NWPU VHR-10 and DIOR demonstrated its ability to leverage limited image–text training data via dynamic fusion, achieving new state-of-the-art mean average precision (mAP) for few-shot object detection. Our code will be publicly available at https://github.com/abdullah-azeem/umft.

Low-Rank Graph Completion-Based Incomplete Multiview Clustering.

In order to reduce the negative effect of missing data on clustering, incomplete multiview clustering (IMVC) has become an important research content in machine learning. At present, graph-based methods are widely used in IMVC, but these methods still have some defects. First, some of the methods overlook potential relationships across views. Second, most of the methods depend on local structure information and ignore the global structure information. Third, most of the methods cannot use both global structure information and potential information across views to adaptively recover the incomplete relationship structure. To address the above issues, we propose a unified optimization framework to learn reasonable affinity relationships, called low-rank graph completion-based IMVC (LRGR_IMVC). 1) Our method introduces adaptive graph embedding to effectively explore the potential relationship among views; 2) we append a low-rank constraint to adequately exploit the global structure information among views; and 3) this method unites related information within views, potential information across views, and global structure information to adaptively recover the incomplete graph structure and obtain complete affinity relationships. Experimental results on several commonly used datasets show that the proposed method achieves better clustering performance significantly than some of the most advanced methods.

Development of a Fluorescent Ligand for the Intracellular Allosteric Binding Site of the Neurotensin Receptor 1.

The membrane protein family of G protein-coupled receptors (GPCRs) represents a major class of drug targets. Over the last years, the presence of additional intracellular binding sites besides the canonical orthosteric binding pocket has been demonstrated for an increasing number of GPCRs. Allosteric modulators harnessing these pockets may represent valuable alternatives when targeting the orthosteric pocket is not successful for drug development. Starting from SBI-553, a recently discovered intracellular allosteric modulator for neurotensin receptor subtype 1 (NTSR1), we developed the fluorescent molecular probe 14. Compound 14 binds to NTSR1 with an affinity of 0.68 μM in the presence of the agonist NT(8-13). NanoBRET-based ligand binding assays with 14 were established to derive the affinity and structure-activity relationships for allosteric NTSR1 modulators in a direct and nonisotopic manner, thereby facilitating the search for and optimization of novel allosteric NTSR1 ligands. As a consequence of cooperativity between the ligands binding to the allosteric and orthosteric pocket, compound 14 can also be used to investigate orthosteric NTSR1 agonists and antagonists. Moreover, employing 14 as a probe in a drug library screening, we identified novel chemotypes as binders for the intracellular allosteric SBI-553 binding pocket of NTSR1 with single-digit micromolar affinity. These hits may serve as interesting starting points for the development of novel intracellular allosteric ligands for NTSR1 as a highly interesting yet unexploited drug target in the fields of pain and addiction disorder therapy.

Optimizing Image Recognition Efficiency using Sparse Representation Learning and Transfer Learning for Resource-Constrained Environments

Image recognition in resource-constrained environments is crucial for mobile devices, IoT, and embedded systems. It reduces the need for internet connectivity and enhances privacy and security. Real-time processing and decision-making are critical for applications such as facial recognition, object detection, and augmented reality. This approach is efficient, making it accessible in remote areas or situations with limited internet access. Our study proposes a novel approach using a network architecture with four modules, emphasizing sparse representation learning and transfer learning to improve image recognition efficiency in resource-constrained environments. The Domain-Adaptive Feature Extractor () facilitates effective sparse representation learning by projecting data from diverse domains into a shared space. The Transferable Affine Decoder () captures affine relationships between domains to facilitate knowledge transfer, while the Cross-Domain Correspondence Network () enforces pixel-level correspondence to extract shared intrinsic representations. The Efficient Classifier Network () enhances classification accuracy using efficient CNNs. The baseline model achieved an accuracy of 0.89. Improved Model 1, leveraging transfer learning, attained 0.92 accuracy, while Improved Model 2 with the Cross-Domain Correspondence Network reached 0.91. The Final Model, amalgamating all methodologies, excelled with the highest accuracy of 0.94. This holistic approach optimizes resource usage and enables real-time processing, thus empowering a diverse array of applications in resource-limited environments.

Strategies for Sustainable Rooting in Landscape: Arrangements between Architecture and the Ground

Contemporary environmental awareness requires new architectural practices to reformulate the relationship between buildings and the ground. Among these, the way in which buildings land on the site emerges as a key architectural condition that must be reviewed, focusing on generating new systems of articulation, more sensitive and attentive to the specific conditions of the grounds. Drawing on the ecological perspectives put forth by authors like Bruno Latour in recent years, this article presents a critical analysis of the rooting systems developed by some of the most significant architectural practices today. This case study provides a catalogue of various sustainable topographical strategies that prioritize the conservation and nurturing of soil properties. The discussion of these strategies enables the synthesis of a series of design guidelines to foster new relationships of affinity with the land, positioning architecture not as an imposition on the territory but as a facilitator of its natural development.

Abstract 6332: Evaluating the relationship of affinity, functional avidity, and in vivo potency in KIR-CAR T cells

Abstract Chimeric antigen receptors (CARs) targeting CD19 demonstrate remarkable clinical outcomes in patients (pts) with B-cell malignancies. Importantly, all four FDA-approved CD3ζ-based CAR T cell therapies use the same FMC63-derived single-chain variable fragment (scFv) to target CD19+ tumors. Although response rates are high in diffuse large B cell lymphoma, only ~40% of pts achieve durable, long-term remissions. Improved CAR T cell therapies are therefore needed. We have previously shown that a novel killer immunoglobulin receptor (KIR)-based CAR expressed in T cells as a multichain receptor with DAP12 (KIR-CAR T) has enhanced anti-tumor activity in several preclinical solid tumor models suggesting that this platform may show better activity in lymphoma. Some recent studies report that lower-affinity CD19 binders compared to the benchmark FMC63-scFv yield equivalent or increased anti-tumor activity of CAR T in pts, raising the question of optimal affinity for a KIR-based CAR. In this study, we aimed to evaluate the relationship of affinity, functional avidity, and in vivo potency of CD19 binders in a KIR-based CAR T cell. Using a highly-diverse 40-billion member canine scFv phage display library, we generated 19 unique human CD19-specific binders that compete with FMC63 binder supporting a similar binding epitope. Different KIR-CAR T cells were generated, and relative affinities were compared via binding to a recombinant (rec) CD19 protein. We found that although CAR receptor expression was similarly expressed, the concentration of soluble rec CD19 protein required to saturate the surface CAR varied more than 2-log among the different scFv binders suggesting a range of affinities relative to FMC63. We selected several scFvs with lower, and equivalent CD19 binding MFI compared to the FMC63-scFv and found that all scFvs could mediate similarly robust in vitro potency. In vivo anti-tumor efficacy was next assessed using the NSG xenograft mouse model of B-cell leukemia NALM6 cells. Interestingly, despite their comparable in vitro functions, some binders with relatively similar binding MFI failed to control the tumors. In contrast, two binders with an ~30-fold apparent affinity relative to FMC63 exhibited robust anti-tumor activity comparable to the benchmark scFv. These preliminary data suggest that the in vivo functional activity of chimeric KIR-based immunoreceptors is insensitive to binder affinity over a wide range of affinities. The failure of some scFvs with comparable affinity and binding epitope suggest that other, yet to be characterized attributes of the binder may be critical for optimal function. Further characterization of these binders is being conducted to understand the relationship between affinity, functional avidity, antigen density, and in vivo potency. This study paves the way for developing an improved CD19-specific KIR-CAR T cell therapy for treating pts with B-cell malignancies. Citation Format: Jun Xu, Selene Nunez-Cruz, John M. Leferovich, Gayathri Gulendran, Chune Zhang, Nora D. Yucel, Megan C. Blair, William S. Stanley, Laura A. Johnson, Don L. Siegel, Michael C. Milone. Evaluating the relationship of affinity, functional avidity, and in vivo potency in KIR-CAR T cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6332.

The place and role of the civil sector in the inclusive education and development of children with Williams syndrome (also) through music

Williams syndrome (WS) is an extremely rare genetic disorder. Approximately 1 in every 20 000 people has WS. Because of this, most people have never even met a child with WS. WS occupies a unique place among genetic disorders because of the fact that, in addition to a unique mix of difficulties, symptoms and abnormalities, some of their abilities and performance in certain intellectual areas are adequate or average, and in many cases above average. Relatively high level of ability includes good communication skills, outstanding verbal skills, sociability and good musical abilities with highly sensitive hearing, good musical pitch and musicality, and a very positive attitude towards music. As is typically the case for rare disorders, the most important pillar of their advocacy is the civil sphere, where NGOs and foundations support WS children and families. The great affinity and positive relationship with music justifies that a prominent part of development and inclusion are specifically music-related activities, music therapy activities. The main objective of our research is to map NGOs in Europe and beyond whose activities focus on WS patients and their families. The basis for mapping the organizations is to summarize their aims, activities and achievements and to highlight their music-related activities in line with the mission of inclusion. Our main objective is to show that the development and rehabilitation of WS patients through music and musical activities is a significant and integral part of their care within the organized framework and possibilities of the civil sector.

Relationship of Thermostability and Binding Affinity in Metal-binding WW-Domain Minireceptors.

The design of metallo-miniproteins advances our understanding of the structural and functional roles of metals in proteins. We recently designed a metal-binding WW domain, WW-CA-Nle, which displays three histidine residues on its surface for coordination of divalent metals Ni(II), Zn(II) and Cu(II). However, WW-CA-Nle is a molten globule in the apo state and thus showed only moderate binding affinities with Kd values in the μM regime. In this report, we hypothesize that improved thermal stability of the apo state of the metal binding WW-domain scaffold should lead to improved preorganization of the metal-binding site and consequently to higher metal-binding affinities. By redesigning WW-CA-Nle, we obtained WW-CA variants, WW-CA-min and WW-CA-ANG, which were fully folded in the apo states and displayed moderate to excellent thermostabilities in the apo and holo states. We were able to show that the improved thermal stabilities led to improved metal binding, which was reflected in Kd values that were at least one order of magnitude lower compared to WW-CA-Nle. EPR spectroscopy and ITC measurements revealed a better defined and predisposed metal binding site in WW-CA-ANG.

Graph Convolution Based Efficient Re-Ranking for Visual Retrieval

Visual retrieval tasks such as image retrieval and person re-identification (Re-ID) aim at effectively and thoroughly searching images with similar content or the same identity. After obtaining retrieved examples, re-ranking is a widely adopted post-processing step to reorder and improve the initial retrieval results by making use of the contextual information from semantically neighboring samples. Prevailing re-ranking approaches update distance metrics and mostly rely on inefficient crosscheck set comparison operations while computing expanded neighbors based distances. In this work, we present an efficient re-ranking method which refines initial retrieval results by updating features. Specifically, we reformulate re-ranking based on Graph Convolution Networks (GCN) and propose a novel Graph Convolution based Re-ranking (GCR) for visual retrieval tasks via feature propagation. To accelerate computation for large-scale retrieval, a decentralized and synchronous feature propagation algorithm which supports parallel or distributed computing is introduced. In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras. It is also extended for video-based retrieval, and Graph Convolution based Re-ranking for Video (GCRV) is proposed by mathematically deriving a novel profile vector generation method for the tracklet. Without bells and whistles, the proposed approaches achieve state-of-the-art performances on seven benchmark datasets from three different tasks, i.e., image retrieval, person Re-ID and video-based person Re-ID. Code is publicly available: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">github.com/WesleyZhang1991/GCN rerank</uri> .

Kin Term Borrowings in the World’s Languages

Abstract The universality of kinship terms means they are regarded, like much basic vocabulary, as resistant to borrowing. Kin term borrowings are documented at varying frequencies, but their role in the dynamics of change in this core social domain is understudied. We investigated the dimensions and the sociolinguistic contexts of kinship borrowings with 50 kinship categories from a global sample of 32 languages, a subset extracted from the World Loanword Database. We found that more borrowings take place in affinal kin categories and in generations denoting relatives older than ego. Close kin categories also have borrowings, but the borrowed items usually coexist with other, presumably non-borrowed variants. Colonisation and the spread of cultures and religions were main inducing forces for kin term borrowings; new terms often enter a language via bilingualism. These tentative patterns can be studied further with larger datasets in future systematic studies of kinship borrowings.

Who gets the treat: Interspecific interactions between red squirrels and corvids in an urban park

AbstractSquirrels and some corvids have successfully adapted to urban conditions. Their populations are often more abundant in city parks than in rural areas. These species may compete, especially in terms of food resources. We studied interactions between corvids (hooded crows and rooks) and red squirrels inhabiting urban park, mostly in relation to supplementary food utilisation in Poland. The study included the following: (a) feeding trials, when squirrels were offered hazelnuts and all stealing attempts by other animals were noted; (b) direct observations of groups of animals (at least one squirrel and one corvid species) with all behaviours being recorded. During the feeding trial, and with constant corvid presence, corvids tried to steal almost every third nut cached by squirrels. Regardless of the season, the share of nuts that corvids tried to steal was similar. When the feeding trial proceeded, more squirrels joined in order to obtain food. On the contrary, the presence of corvids seemed to refrain other corvids from joining the trial. The presence of a bird/squirrel audience did not result in more deceptive caches. During direct observations, squirrels interacted mostly with corvids, and less often with people or other squirrels. The most frequent interaction of squirrels with other animals was flight and chasing away; for corvids, it was chasing and following or attempting to steal food. Overall, we showed that corvids can be food competitors and kleptoparasites for red squirrels. Red squirrels, with whom people often have affinity relationships, benefited from direct supplementary feeding. Corvids, in turn, learnt to follow red squirrels to steal human-delivered nuts.

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (aFusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model's understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.

Affinity for technology and group cohesion link to mental health during social isolation in Italy and Japan

Social group cohesion and social support are critical for positive mental health. People may use technology to maintain existing, or even create new, social groups – particularly when in-person contact is limited. During the global COVID-19 pandemic, countries mandated various stay-at-home orders; for many people worldwide, this was their first experience of extended periods of social isolation. To better understand the relationship of affinity for technology, group cohesion, and mental health depending on change in social isolation, we surveyed people based on country. We studied Italy because of its relatively large increase in social isolation, and we studied Japan because of its relatively small increase in social isolation. We surveyed participants about existing and new social groups in a country that strongly socially isolated (Study 1: Italy, n = 426) and one with few changes from normal (Study 2: Japan, n = 280). We collected data in June 2020, several months after the onset of the COVID-19 pandemic. Affinity for technology related to increased group cohesion and mental health depending on country and on whether groups were new or existing. Dimensions of group cohesion had varied effects on mental health. We synthesize results from this work and a prior study in the United States (U.S., n = 276), which had a very mixed approach to dealing with COVID-19 that differed from approaches in Italy and Japan. Finally, we discuss overall patterns across all three countries.