Clint Miller
@clintomics
Followers
2K
Following
4K
Media
50
Statuses
2K
Human genomicist, Assoc Prof @UVA. Deconvolving complex cardiovascular diseases using systems genetics and single-cell omics.
Charlottesville, VA
Joined April 2013
Latest news feature in @NatureBiotech on recent developments in spatial biology to unravel disease mechanisms, with insights from experts in field @aruthak @NeBanovich @AI4Pathology @PDulaiMD Jasmine Plummer, Amanda Orr etc
nature.com
Nature Biotechnology - As the next generation of spatial transcriptomics tools hits the market, researchers are uncovering previously unknown interactions that could transform clinical research.
0
2
10
RT @atvbahajournals: The 9p21 risk locus — the first and most impactful CAD genetic risk factor in humans — drives VSMCs to adopt an osteoc….
0
6
0
RT @valelosardo: Thrilled to share the🥇paper from the lab @atvbahajournals. Here we continue to unravel the mysteries of the 9p21.3 CAD loc….
ahajournals.org
BACKGROUND: Genome-wide association studies have identified common genetic variants at ≈300 human genomic loci linked to coronary artery disease susceptibility. Among these genomic regions, the most...
0
8
0
RT @atheroexpress: 🚀 Thrilled to announce our latest #preprint on intraplaque haemorrhage (IPH) quantification and molecular 🧬characterisat….
0
7
0
Huge congrats to PhD student @John_S_IV for successfully defending his thesis today! Thanks to the committee and everyone for their support. @shefflab @uva_bims @MedicineUVA
0
0
15
New model for multimodal spatial omics analysis, MISO, performs feature extraction, clustering and handles large-scale omics data. Includes extensive benchmarking and application to various cancer types. @DrMingyaoLi @naturemethods
nature.com
Nature Methods - MISO (MultI-modal Spatial Omics) integrates two or more spatial omics modalities, despite differences in data quality and spatial resolution for improved feature extraction and...
1
9
37
New expression foundation model, GET, predicts gene expression in unseen cell types and context specific TF interaction networks - pretrained on chromatin accessibility data from 213 human adult and fetal cell types. @nature @ericxing @RabadanColumbia
nature.com
Nature - A foundation model learns transcriptional regulatory syntax from chromatin accessibility and sequence data across a range of cell types to predict gene expression and transcription factor...
0
0
5
New generative model, IMPA, predicts cell morphology responses to genetic and drug perturbations, enhancing phenotypic screening and drug discovery. Corrects batch effects and models unseen perturbations. @NatureComms @mo_lotfollahi @fabian_theis .
nature.com
Nature Communications - Predicting morphological impacts of perturbations using computational methods can aid treatment discovery. Here, authors present IMPA, a generative model that predicts...
0
17
61
New single-cell analysis framework, LEMUR, disentangles covariates and latent cell states from multi-condition data to predict counterfactual gene expression and identify cell neighborhoods with similar DEGs without clustering. @NatureGenet @wolfgangkhuber.
nature.com
Nature Genetics - Latent embedding multivariate regression models multi-condition single-cell RNA-seq using a continuous latent space, enabling data integration, per-cell gene expression prediction...
4
18
89
Delineating the effective use of self-supervised learning in single-cell genomics @NatMachIntell @fabian_theis
nature.com
Nature Machine Intelligence - Self-supervised learning techniques are powerful assets for enabling deep insights into complex, unlabelled single-cell genomic data. Richter et al. here benchmark the...
1
18
86
Very grateful and humbled to receive promotion to tenure @MedicineUVA! . Huge thanks to my supportive mentors, colleagues, family, and talented trainees who continue to inspire me along this journey. Here’s to the work ahead!.
20
1
81
RT @shitov_happens: The number of cells in single-cell transcriptomics studies grew exponentially over the years. But what about the number….
nature.com
Nature Methods - This Review provides a comprehensive and detailed discussion about how to build and use single-cell atlases.
0
14
0
For simulation tasks scDesign3 outperformed scFMs in simulating reference based scRNA-seq datasets @SongDongyuan @jsb_ucla.
0
1
1
As expected the performance of scFMs is highly task specific. they perform well in certain tasks after fine tuning, eg cell annotation, but worse in gene regulatory networks.
1
0
1
Nice benchmarking study of 10 different foundation models for single cell data analysis. important best practices, limitations and insights to guide future applications @HongyuZhao2
2
29
118
RT @StephenQuake: Virtual cell models have the potential to transform biological research. Today @ChanZuckerberg released an initial set of….
chanzuckerberg.com
We’re making it easier for biologists and machine learning researchers to collaborate with cell models that are easy-to-use + build upon to accelerate the next big breakthrough.
0
58
0
New method CellANOVA recovers lost biological signals and evaluates global and gene level distortions introduced from common single-cell batch correction algorithms @NatureBiotech
github.com
CellANOVA: Cell State Space Analysis of Variance for signal recovery in single cell batch integration - Janezjz/cellanova
0
11
78
RT @junedh_amrute: We use Multiome and HiC to build a comprehensive single cell variant to enhancer to gene map for coronary artery disease….
medrxiv.org
Although genome wide association studies (GWAS) in large populations have identified hundreds of variants associated with common diseases such as coronary artery disease (CAD), most disease-associa...
0
11
0