Biology subjects

McLean, C. Y.

Publications and source records attributed to McLean, C. Y..

9 recordsLinked to original sources

bioRxiv2025

Integrating Genomics into Multimodal EHR Foundation Models

AO_SCPLOWBSTRACTC_SCPLOWThis paper introduces an innovative Electronic Health Record (EHR) foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality, moving beyond traditional EHR-only approaches to build more holistic health profiles. Leveraging the extensive and diverse data from the All of Us (AoU) Research Program, this multimodal framework aims to learn complex relationships between clinical data and genetic predispositions. The methodology extends advancements in generative AI to the EHR foundation model space, enhancing predictive capabilities and interpretability. Evaluation on AoU data demonstrates the models predictive value for the onset of various conditions, particularly Type 2 Diabetes (T2D), and illustrates the interplay between PRS and EHR data. The work also explores transfer learning for custom classification tasks, showcasing the architectures versatility and efficiency. This approach is pivotal for unlocking new insights into disease prediction, proactive health management, risk stratification, and personalized treatment strategies, laying the groundwork for more personalized, equitable, and actionable real-world evidence generation in healthcare.

bioinformatics↗

bioRxiv2025

NucleoBench: A Large-Scale Benchmark of Neural Nucleic Acid DesignAlgorithms

We introduce GrAdaBeam, a hybrid model-based optimization algorithm that combines gradient-derived attention maps with an adaptive beam search to navigate complex nucleic acid fitness landscapes. By unifying the broad exploration of evolutionary methods with the precise guidance of gradient descent, GrAdaBeam overcomes a central limitation of existing approaches: no single optimization strategy performs robustly across the full spectrum of genomic design tasks. We rigorously evaluate GrAdaBeam and seven other design algorithms using NucleoBench, a novel benchmark covering 17 diverse genomic tasks that introduces a paired-start-sequence design for superior statistical comparisons. GrAdaBeam statistically outperforms all other algorithms across over 600,000 experiments, never ranking lower than second across all 17 benchmark tasks, while baseline methods often struggle on large models or long sequences. Critically, GrAdaBeam sequences generalize most reliably to independent predictive models and recover canonical transcription factor binding motifs de novo, providing evidence of biological signal capture beyond the optimization target. GrAdaBeam and NucleoBench are freely available as an open-source package.

genomics↗

bioRxiv2023

Accurate human genome analysis with Element Avidity sequencing

We investigate the new sequencing technology Avidity from Element Biosciences. We show that Element whole genome sequencing achieves higher mapping and variant calling accuracy compared to Illumina sequencing at the same coverage, with larger differences at lower coverages (20x-30x). We quantify base error rates of Element reads, finding lower error rates, especially in homopolymer and tandem repeat regions. We use Elements ability to generate paired end sequencing with longer insert sizes than typical short-read sequencing. We show that longer insert sizes result in even higher accuracy, with long insert Element sequencing giving noticeably more accurate genome analyses at all coverages.

bioinformatics↗

bioRxiv2022

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

Biological age, distinct from an individuals chronological age, has been studied extensively through predictive aging clocks. However, these clocks have limited accuracy in short time-scales. Deep learning approaches on imaging datasets of the eye have proven powerful for a variety of quantitative phenotype inference tasks and provide an opportunity to explore organismal aging and tissue health. Here we trained deep learning models on fundus images from the EyePACS dataset to predict individuals chronological age. These predictions led to the concept of a retinal aging clock, "eyeAge", which we employed for a series of downstream longitudinal analyses. eyeAge was used to predict chronological age on timescales under a year using longitudinal fundus imaging data from a subset of patients. To further validate the model, it was applied to a separate cohort from the UK Biobank. The difference between individuals eyeAge and their chronological age, hereafter "eyeAgeAccel", was computed and used for genome-wide association analysis (GWAS). EyeAge predicted chronological age more accurately than other aging clocks (mean absolute error of 2.86 and 3.30 years on quality-filtered data from EyePACS and UKBiobank, respectively). Additionally, eyeAgeAccel was highly independent of blood marker-based measures of biological age (e.g. "phenotypic age"), maintaining an all-cause mortality hazard ratio of 1.026 even in the presence of phenotypic age. Longitudinal studies showed that the resulting models were able to predict individuals aging, in time-scales less than a year, with 71% accuracy. The individual-specific component to this prediction was confirmed with the identification of multiple GWAS hits in the independent UK Biobank cohort. The knockdown of the fly homolog to the top hit, ALKAL2, which was previously shown to extend lifespan in flies, also slowed age-related decline in vision in flies. In conclusion, predicted age from retinal images can be used as a biomarker of biological aging that is independent from assessment based on blood markers. This study demonstrates the potential utility of a retinal aging clock for studying aging and age-related diseases and quantitatively measuring aging on very short time-scales, opening avenues for quick and actionable evaluation of gero-protective therapeutics.

bioinformatics↗

bioRxiv2021

DeepConsensus: Gap-Aware Sequence Transformers for Sequence Correction

Pacific BioScience (PacBio) circular consensus sequencing (CCS) generates long (10-25 kb), accurate "HiFi" reads by combining serial observations of a DNA molecule into a consensus sequence. The standard approach to consensus generation uses a hidden Markov model (pbccs). Here, we introduce DeepConsensus, which uses a unique alignment-based loss to train a gap-aware transformer-encoder (GATE) for sequence correction. Compared to pbccs, DeepConsensus reduces read errors in the same dataset by 42%. This increases the yield of PacBio HiFi reads at Q20 by 9%, at Q30 by 27%, and at Q40 by 90%. With two SMRT Cells of HG003, reads from DeepConsensus improve hifiasm assembly contiguity (NG50 4.9Mb to 17.2Mb), increase gene completeness (94% to 97%), reduce false gene duplication rate (1.1% to 0.5%), improve assembly base accuracy (Q43 to Q45), and also reduce variant calling errors by 24%.

bioinformatics↗

bioRxiv2020

Accurate, scalable cohort variant calls using DeepVariant and GLnexus

Population-scale sequenced cohorts are foundational resources for genetic analyses, but processing raw reads into analysis-ready variants remains challenging. Here we introduce an open-source cohort variant-calling method using the highly-accurate caller DeepVariant and scalable merging tool GLnexus. We optimized callset quality based on benchmark samples and Mendelian consistency across many sample sizes and sequencing specifications, resulting in substantial quality improvements and cost savings over existing best practices. We further evaluated our pipeline in the 1000 Genomes Project (1KGP) samples, showing superior quality metrics and imputation performance. We publicly release the 1KGP callset to foster development of broad studies of genetic variation.

genomics↗

bioRxiv2018

A deep learning approach to pattern recognition for short DNA sequences

MotivationInferring properties of biological sequences--such as determining the species-of-origin of a DNA sequence or the function of an amino-acid sequence--is a core task in many bioinformatics applications. These tasks are often solved using string-matching to map query sequences to labeled database sequences or via Hidden Markov Model-like pattern matching. In the current work we describe and assess an deep learning approach which trains a deep neural network (DNN) to predict database-derived labels directly from query sequences. ResultsWe demonstrate this DNN performs at state-of-the-art or above levels on a difficult, practically important problem: predicting species-of-origin from short reads of 16S ribosomal DNA. When trained on 16S sequences of over 13,000 distinct species, our DNN achieves read-level species classification accuracy within 2.0% of perfect memorization of training data, and produces more accurate genus-level assignments for reads from held-out species than k-mer, alignment, and taxonomic binning baselines. Moreover, our models exhibit greater robustness than these existing approaches to increasing noise in the query sequences. Finally, we show that these DNNs perform well on experimental 16S mock community dataset. Overall, our results constitute a first step towards our long-term goal of developing a general-purpose deep learning approach to predicting meaningful labels from short biological sequences. AvailabilityTensorFlow training code is available through GitHub (https://github.com/tensorflow/models/tree/master/research). Data in TensorFlow TFRecord format is available on Google Cloud Storage (gs://brain-genomics-public/research/seq2species/). Contactseq2species-interest@google.com Supplementary informationSupplementary data are available in a separate document.

bioinformatics↗

bioRxiv2018

Reproducible integration of multiple sequencing datasets to form high-confidence SNP, indel, and reference calls for five human genome reference materials

Benchmark small variant calls from the Genome in a Bottle Consortium (GIAB) for the CEPH/HapMap genome NA12878 (HG001) have been used extensively for developing, optimizing, and demonstrating performance of sequencing and bioinformatics methods. Here, we develop a reproducible, cloud-based pipeline to integrate multiple sequencing datasets and form benchmark calls, enabling application to arbitrary human genomes. We use these reproducible methods to form high-confidence calls with respect to GRCh37 and GRCh38 for HG001 and 4 additional broadly-consented genomes from the Personal Genome Project that are available as NIST Reference Materials. These new genomes broad, open consent with few restrictions on availability of samples and data is enabling a uniquely diverse array of applications. Our new methods produce 17% more high-confidence SNPs, 176% more indels, and 12% larger regions than our previously published calls. To demonstrate that these calls can be used for accurate benchmarking, we compare other high-quality callsets to ours (e.g., Illumina Platinum Genomes), and we demonstrate that the majority of discordant calls are errors in the other callsets, We also highlight challenges in interpreting performance metrics when benchmarking against imperfect high-confidence calls. We show that benchmarking tools from the Global Alliance for Genomics and Health can be used with our calls to stratify performance metrics by variant type and genome context and elucidate strengths and weaknesses of a method.

genomics↗

bioRxiv2016

Creating a universal SNP and small indel variant caller with deep neural networks

Next-generation sequencing (NGS) is a rapidly evolving set of technologies that can be used to determine the sequence of an individuals genome1 by calling genetic variants present in an individual using billions of short, errorful sequence reads2. Despite more than a decade of effort and thousands of dedicated researchers, the hand-crafted and parameterized statistical models used for variant calling still produce thousands of errors and missed variants in each genome3,4. Here we show that a deep convolutional neural network5 can call genetic variation in aligned next-generation sequencing read data by learning statistical relationships (likelihoods) between images of read pileups around putative variant sites and ground-truth genotype calls. This approach, called DeepVariant, outperforms existing tools, even winning the \"highest performance\" award for SNPs in a FDA-administered variant calling challenge. The learned model generalizes across genome builds and even to other mammalian species, allowing non-human sequencing projects to benefit from the wealth of human ground truth data. We further show that, unlike existing tools which perform well on only a specific technology, DeepVariant can learn to call variants in a variety of sequencing technologies and experimental designs, from deep whole genomes from 10X Genomics to Ion Ampliseq exomes. DeepVariant represents a significant step from expert-driven statistical modeling towards more automatic deep learning approaches for developing software to interpret biological instrumentation data.

genomics↗