Linh N Tran
@lntran.bsky.social
Postdoc @uwgenome 🐶
PhD Genetics @uarizona 🐱
BA Chemistry @brynmawrcollege 🦉
Population Genomics, Machine Learning, Cancer Evolution 🧬💻
📍Seattle, WA & Vancouver, BC
https://www.linkedin.com/in/linhnhtran/
PhD Genetics @uarizona 🐱
BA Chemistry @brynmawrcollege 🦉
Population Genomics, Machine Learning, Cancer Evolution 🧬💻
📍Seattle, WA & Vancouver, BC
https://www.linkedin.com/in/linhnhtran/
Reposted by Linh N Tran
@lntran.bsky.social @castellanoed.bsky.social @ryangutenkunst.bsky.social introduce a systematic permutation approach for interpreting haplotype matrix-based methods in population genomics.
🔗 doi.org/10.1093/molbev/msaf250
#evobio #molbio
🔗 doi.org/10.1093/molbev/msaf250
#evobio #molbio
Interpreting Supervised Machine Learning Inferences in Population Genomics Using Haplotype Matrix Permutations
Abstract. Supervised machine learning methods, such as convolutional neural networks (CNNs), that use haplotype matrices as input data have become powerful
doi.org
October 24, 2025 at 8:41 AM
@lntran.bsky.social @castellanoed.bsky.social @ryangutenkunst.bsky.social introduce a systematic permutation approach for interpreting haplotype matrix-based methods in population genomics.
🔗 doi.org/10.1093/molbev/msaf250
#evobio #molbio
🔗 doi.org/10.1093/molbev/msaf250
#evobio #molbio
Reposted by Linh N Tran
🧵1/
Excited to share our new paper in Molecular Biology & Evolution!
👉 [https://doi.org/10.1093/molbev/msaf250]
It started as a lab-meeting sanity check for another project — and ended up turning into a new way to interpret machine-learning models in population genomics.
Excited to share our new paper in Molecular Biology & Evolution!
👉 [https://doi.org/10.1093/molbev/msaf250]
It started as a lab-meeting sanity check for another project — and ended up turning into a new way to interpret machine-learning models in population genomics.
October 7, 2025 at 8:33 AM
🧵1/
Excited to share our new paper in Molecular Biology & Evolution!
👉 [https://doi.org/10.1093/molbev/msaf250]
It started as a lab-meeting sanity check for another project — and ended up turning into a new way to interpret machine-learning models in population genomics.
Excited to share our new paper in Molecular Biology & Evolution!
👉 [https://doi.org/10.1093/molbev/msaf250]
It started as a lab-meeting sanity check for another project — and ended up turning into a new way to interpret machine-learning models in population genomics.
Reposted by Linh N Tran
Really excited about this new work from Sam Hart (and joint with @kelleyharris.bsky.social) trying to disentangle mutational differences between groups of cancers. Check out Kelley's thread with the major results!
If you’ve ever wondered about the statistical significance of differences among mutational signature profiles, check out our new Aggregate Mutation Spectrum Distance (AMSD) preprint co-led by Sam Hart and @alisonfeder.bsky.social with @nalcala.bsky.social www.biorxiv.org/cgi/content/...
A signature-agnostic test for differences between tumor mutation spectra reveals carcinogen and ancestry effects
Mutational signatures contain valuable information about the mutational processes shaping cancer genomes. However, despite dozens of tools to identify signatures in cancer samples, there is not an est...
www.biorxiv.org
May 20, 2025 at 8:04 PM
Really excited about this new work from Sam Hart (and joint with @kelleyharris.bsky.social) trying to disentangle mutational differences between groups of cancers. Check out Kelley's thread with the major results!
Reposted by Linh N Tran
. @pnas.org just published the final version of our manuscript on how generation time and effective population size interact to shape vertebrate germline mutation rates, led by Luke Zhu and Annabel Beichman: www.pnas.org/doi/10.1073/...
PNAS
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...
www.pnas.org
May 21, 2025 at 7:33 PM
. @pnas.org just published the final version of our manuscript on how generation time and effective population size interact to shape vertebrate germline mutation rates, led by Luke Zhu and Annabel Beichman: www.pnas.org/doi/10.1073/...
Reposted by Linh N Tran
If you’ve ever wondered about the statistical significance of differences among mutational signature profiles, check out our new Aggregate Mutation Spectrum Distance (AMSD) preprint co-led by Sam Hart and @alisonfeder.bsky.social with @nalcala.bsky.social www.biorxiv.org/cgi/content/...
A signature-agnostic test for differences between tumor mutation spectra reveals carcinogen and ancestry effects
Mutational signatures contain valuable information about the mutational processes shaping cancer genomes. However, despite dozens of tools to identify signatures in cancer samples, there is not an est...
www.biorxiv.org
May 20, 2025 at 4:58 PM
If you’ve ever wondered about the statistical significance of differences among mutational signature profiles, check out our new Aggregate Mutation Spectrum Distance (AMSD) preprint co-led by Sam Hart and @alisonfeder.bsky.social with @nalcala.bsky.social www.biorxiv.org/cgi/content/...
Reposted by Linh N Tran
🚨 New preprint alert! 🚨 We introduce ConfuseNN, a method to interpret convolutional neural network (CNN) inferences in population genomics using data shuffling. Curious about how CNNs make decisions in genomic analyses? Check it out! 🧵👇https://www.biorxiv.org/content/10.1101/2025.03.24.644668v1
March 27, 2025 at 1:09 PM
🚨 New preprint alert! 🚨 We introduce ConfuseNN, a method to interpret convolutional neural network (CNN) inferences in population genomics using data shuffling. Curious about how CNNs make decisions in genomic analyses? Check it out! 🧵👇https://www.biorxiv.org/content/10.1101/2025.03.24.644668v1
Reposted by Linh N Tran
We are excited to share our new preprint describing the inclusion of selection models to stdpopsim, our community-maintained library with an extensive catalog of population genetic models. 1/n
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
www.biorxiv.org
March 24, 2025 at 4:47 PM
We are excited to share our new preprint describing the inclusion of selection models to stdpopsim, our community-maintained library with an extensive catalog of population genetic models. 1/n
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Reposted by Linh N Tran
Amid the chaos, it was great to share results from the first Genomic History Inference Strategies Tournament at ProbGen25. Watch the talk to learn about the future of GHIST and @andrewhvaughn.bsky.social's nefarious metagaming of demographic inference. 😀 www.youtube.com/watch?v=3_dv...
Talk describing the results of GHIST1 at ProbGen 25.
YouTube video by Ryan Gutenkunst
www.youtube.com
March 17, 2025 at 3:53 PM
Amid the chaos, it was great to share results from the first Genomic History Inference Strategies Tournament at ProbGen25. Watch the talk to learn about the future of GHIST and @andrewhvaughn.bsky.social's nefarious metagaming of demographic inference. 😀 www.youtube.com/watch?v=3_dv...
Reposted by Linh N Tran
I'm looking forward to Evolution this summer! I'll be leading a *free* workshop on the Genomic History Inference Strategies Tournament (ghi.st) during the Monday lunch break. Sign up during registration and join this fun community event. In an hour, you'll analyze data to make your first submission!
February 13, 2025 at 3:29 PM
I'm looking forward to Evolution this summer! I'll be leading a *free* workshop on the Genomic History Inference Strategies Tournament (ghi.st) during the Monday lunch break. Sign up during registration and join this fun community event. In an hour, you'll analyze data to make your first submission!
Reposted by Linh N Tran
Our paper on fitting population genetic models to low-pass sequencing data is now out in Molecular Biology and Evolution! doi.org/10.1093/molb...
January 24, 2025 at 7:52 PM
Our paper on fitting population genetic models to low-pass sequencing data is now out in Molecular Biology and Evolution! doi.org/10.1093/molb...