Precise uncertain significance prediction using latent space matrix factorization models: genomics variant and heterogeneous clinical data-driven approaches

2020 ◽  
Author(s):  
Sina Abdollahi ◽  
Peng-Chan Lin ◽  
Meng-Ru Shen ◽  
Jung-Hsien Chiang
Keyword(s):  
Clinical Data ◽  
Matrix Factorization ◽  
High Accuracy ◽  
Vast Number ◽  
Variant Of Uncertain Significance ◽  
Factorization Model ◽  
Latent Space ◽  
Uncertain Significance ◽  
Space Matrix ◽  
Single Matrix

Abstract Several studies to date have proposed different types of interpreters for measuring the degree of pathogenicity of variants. However, in predicting the disease type and disease–gene associations, scholars face two essential challenges, namely the vast number of existing variants and the existence of variants which are recognized as variant of uncertain significance (VUS). To tackle these challenges, we propose algorithms to assign a significance to each gene rather than each variant, describing its degree of pathogenicity. Since the interpreters identified most of the variants as VUS, most of the gene scores were identified as uncertain significance. To predict the uncertain significance scores, we design two matrix factorization-based models: the common latent space model uses genomics variant data as well as heterogeneous clinical data, while the single-matrix factorization model can be used when heterogeneous clinical data are unavailable. We have managed to show that the models successfully predict the uncertain significance scores with low error and high accuracy. Moreover, to evaluate the effectiveness of our novel input features, we train five different multi-label classifiers including a feedforward neural network with the same feature set and show they all achieve high accuracy as the main impact of our approach comes from the features. Availability: The source code is freely available at https://github.com/sabdollahi/CoLaSpSMFM.

scholarly journals TrustRec: An effective approach to exploit implicit trust and distrust relationships along with explicitones for accurate recommendations

2020 ◽  
pp. 39-39
Author(s):  
Reyhani Hamedani ◽  
Irfan Ali ◽  
Jiwon Hong ◽  
Sang-Wook Kim
Keyword(s):  
Matrix Factorization ◽  
Computational Cost ◽  
Effective Solution ◽  
Trust Networks ◽  
Novel Approach ◽  
Factorization Model ◽  
Implicit Trust ◽  
The Matrix ◽  
Effectiveness And Efficiency ◽  
Single Matrix

Trust-aware recommendation approaches are widely used to mitigate the cold-start problem in recommender systems by utilizing trust networks. In this paper, we point out the problems of existing trust-aware recommendation approaches as follows: (P1) exploiting sparse explicit trust and distrust relationships; (P2) considering a misleading assumption that a user pair having a trust/distrust relationship certainly has a similar/dissimilar preference in practice; (P3) employing the transitivity of distrust relationships. Then, we propose TrustRec, a novel approach based on the matrix factorization that provides an effective solution to each of the afore mentioned problems and incorporates all of them in a single matrix factorization model. Furthermore, TrustRec exploits only top-k most similar trustees and dissimilar distrustees of each user to improve both the computational cost and accuracy. The results of our extensive experiments demonstrate that TructRec outperforms existing approaches in terms of both effectiveness and efficiency.

TrustSVD: A Novel Trust-Based Matrix Factorization Model with User Trust and Item Ratings

2017 ◽  
Vol 7 (11) ◽  
pp. 7 ◽  
Author(s):  
K Sobha Rani
Keyword(s):  
Matrix Factorization ◽  
Social Trust ◽  
State Of The Art ◽  
Data Sets ◽  
Real World Data ◽  
Recommendation Algorithm ◽  
Active User ◽  
Factorization Model ◽  
The Social ◽  
Matrix Factorization Technique

Collaborative filtering suffers from the problems of data sparsity and cold start, which dramatically degrade recommendation performance. To help resolve these issues, we propose TrustSVD, a trust-based matrix factorization technique. By analyzing the social trust data from four real-world data sets, we conclude that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. Hence, we build on top of a state-of-the-art recommendation algorithm SVD++ which inherently involves the explicit and implicit influence of rated items, by further incorporating both the explicit and implicit influence of trusted users on the prediction of items for an active user. To our knowledge, the work reported is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that our approach TrustSVD achieves better accuracy than other ten counterparts, and can better handle the concerned issues.

scholarly journals Adrenoleukodystrophy Newborn Screening in California Since 2016: Programmatic Outcomes and Follow-Up

2021 ◽  
Vol 7 (2) ◽  
pp. 22
Author(s):  
Jamie Matteson ◽  
Stanley Sciortino ◽  
Lisa Feuchtbaum ◽  
Tracey Bishop ◽  
Richard S. Olney ◽  
...  
Keyword(s):  
Newborn Screening ◽  
Program Implementation ◽  
Screening Program ◽  
Birth Prevalence ◽  
Variant Of Uncertain Significance ◽  
Implementation Challenges ◽  
Screening Programs ◽  
Uncertain Significance ◽  
Long Term Follow Up

X-linked adrenoleukodystrophy (ALD) is a recent addition to the Recommended Uniform Screening Panel, prompting many states to begin screening newborns for the disorder. We provide California’s experience with ALD newborn screening, highlighting the clinical and epidemiological outcomes observed as well as program implementation challenges. In this retrospective cohort study, we examine ALD newborn screening results and clinical outcomes for 1,854,631 newborns whose specimens were received by the California Genetic Disease Screening Program from 16 February 2016 through 15 February 2020. In the first four years of ALD newborn screening in California, 355 newborns screened positive for ALD, including 147 (41%) with an ABCD1 variant of uncertain significance (VUS) and 95 males diagnosed with ALD. After modifying cutoffs, we observed an ALD birth prevalence of 1 in 14,397 males. Long-term follow-up identified 14 males with signs of adrenal involvement. This study adds to a growing body of literature reporting on outcomes of newborn screening for ALD and offering a glimpse of what other large newborn screening programs can expect when adding ALD to their screening panel.

scholarly journals First report of X-linked hypohidrotic ectodermal dysplasia with a hemizygous c.1142G > C in the EDA gene: variant of uncertain significance or new pathogenic variant?

2021 ◽  
Vol 47 (1) ◽  
Author(s):  
Mario Tumminello ◽  
Antonella Gangemi ◽  
Federico Matina ◽  
Melania Guardino ◽  
Bianca Lea Giuffrè ◽  
...  
Keyword(s):  
Ectodermal Dysplasia ◽  
Genetic Disorder ◽  
Missense Variant ◽  
Pathogenic Variant ◽  
Hypohidrotic Ectodermal Dysplasia ◽  
Variant Of Uncertain Significance ◽  
Uncertain Significance ◽  
Clinical Potential ◽  
Genomic Variant ◽  
Eda Gene

Abstract Background Hypohidrotic Ectodermal Dysplasia (HED) is a genetic disorder which affects structures of ectodermal origin. X-linked hypohidrotic ectodermal dysplasia (XLHED) is the most common form of disease. XLHED is characterized by hypotrichosis, hypohydrosis and hypodontia. The cardinal features of classic HED become obvious during childhood. Identification of a hemizygous EDA pathogenic variant in an affected male confirms the diagnosis. Case presentation We report on a male newborn with the main clinical characteristics of the X-linked HED including hypotrichosis, hypodontia and hypohidrosis. Gene panel sequencing identified a new hemizygous missense variant of uncertain significance (VUS) c.1142G > C (p.Gly381Ala) in the EDA gene, located on the X chromosome and inherited from the healthy mother. Conclusion Despite the potential functional impact of VUS remains uncharacterized, our goal is to evaluate the clinical potential consequences of missense VUS on EDA gene. Even if the proband’s phenotype is characteristic for classic HED, further reports of patients with same clinical phenotype and the same genomic variant are needed to consider this novel VUS as responsible for the development of HED.

scholarly journals Revealing the Mutational Spectrum in Southern Africans With Amyotrophic Lateral Sclerosis

2022 ◽  
Vol 8 (1) ◽  
pp. e654
Author(s):  
Melissa Nel ◽  
Amokelani C. Mahungu ◽  
Nomakhosazana Monnakgotla ◽  
Gerrit R. Botha ◽  
Nicola J. Mulder ◽  
...  
Keyword(s):  
Amyotrophic Lateral Sclerosis ◽  
Population Group ◽  
Genetic Ancestry ◽  
Familial Case ◽  
Data Sets ◽  
Variant Of Uncertain Significance ◽  
Pathogenic Variants ◽  
Sporadic Als ◽  
Uncertain Significance ◽  
Lateral Sclerosis

Background and ObjectivesTo perform the first screen of 44 amyotrophic lateral sclerosis (ALS) genes in a cohort of African genetic ancestry individuals with ALS using whole-genome sequencing (WGS) data.MethodsOne hundred three consecutive cases with probable/definite ALS (using the revised El Escorial criteria), and self-categorized as African genetic ancestry, underwent WGS using various Illumina platforms. As population controls, 238 samples from various African WGS data sets were included. Our analysis was restricted to 44 ALS genes, which were curated for rare sequence variants and classified according to the American College of Medical Genetics guidelines as likely benign, uncertain significance, likely pathogenic, or pathogenic variants.ResultsThirteen percent of 103 ALS cases harbored pathogenic variants; 5 different SOD1 variants (N87S, G94D, I114T, L145S, and L145F) in 5 individuals (5%, 1 familial case), pathogenic C9orf72 repeat expansions in 7 individuals (7%, 1 familial case) and a likely pathogenic ANXA11 (G38R) variant in 1 individual. Thirty individuals (29%) harbored ≥1 variant of uncertain significance; 10 of these variants had limited pathogenic evidence, although this was insufficient to permit confident classification as pathogenic.DiscussionOur findings show that known ALS genes can be expected to identify a genetic cause of disease in >11% of sporadic ALS cases of African genetic ancestry. Similar to European cohorts, the 2 most frequent genes harboring pathogenic variants in this population group are C9orf72 and SOD1.

scholarly journals LGLMF: Local Geographical Based Logistic Matrix Factorization Model for POI Recommendation

2020 ◽  
pp. 66-78 ◽  
Author(s):  
Hossein A. Rahmani ◽  
Mohammad Aliannejadi ◽  
Sajad Ahmadian ◽  
Mitra Baratchi ◽  
Mohsen Afsharchi ◽  
...  
Keyword(s):  
Matrix Factorization ◽  
Factorization Model ◽  
Poi Recommendation

scholarly journals AANMF: Attribute-Aware Attentional Neural Matrix Factorization

2019 ◽  
Vol 48 (4) ◽  
pp. 682-693
Author(s):  
Bo Zheng ◽  
Jinsong Hu
Keyword(s):  
Matrix Factorization ◽  
Recommendation System ◽  
Auxiliary Information ◽  
Inner Product ◽  
Data Sets ◽  
It Projects ◽  
Real World Data ◽  
Latent Space ◽  
Almost All ◽  
Novel Model

Matrix Factorization (MF) is one of the most intuitive and effective methods in the Recommendation System domain. It projects sparse (user, item) interactions into dense feature products which endues strong generality to the MF model. To leverage this interaction, recent works use auxiliary information of users and items. Despite effectiveness, irrationality still exists among these methods, since almost all of them simply add the feature of auxiliary information in dense latent space to the feature of the user or item. In this work, we propose a novel model named AANMF, short for Attribute-aware Attentional Neural Matrix Factorization. AANMF combines two main parts, namely, neural-network-based factorization architecture for modeling inner product and attention-mechanism-based attribute processing cell for attribute handling. Extensive experiments on two real-world data sets demonstrate the robust and stronger performance of our model. Notably, we show that our model can deal with the attributes of user or item more reasonably. Our implementation of AANMF is publicly available at https://github.com/Holy-Shine/AANMF.

Sign in / Sign up

Export Citation Format

Share Document