Akshay S.
@tricksterin.bsky.social
PhD student - Structural Bioinformatics / Molecular Dynamics simulations / Machine Learning
Reposted by Akshay S.
The limiting factor for MRI based prediction of behavioral traits may be neither the imaging nor the pipeline or learning algorith but rather the reliability of the target phenotypes
Thought provoking work my Martin Gell et al:
www.nature.com/articles/s41...
Thought provoking work my Martin Gell et al:
www.nature.com/articles/s41...
How measurement noise limits the accuracy of brain-behaviour predictions - Nature Communications
Our ability to identify associations between behaviour and brain imaging is important for uncovering markers of cognition and disease. Here, the authors illustrate the importance of the reliability of...
www.nature.com
December 13, 2024 at 11:24 PM
The limiting factor for MRI based prediction of behavioral traits may be neither the imaging nor the pipeline or learning algorith but rather the reliability of the target phenotypes
Thought provoking work my Martin Gell et al:
www.nature.com/articles/s41...
Thought provoking work my Martin Gell et al:
www.nature.com/articles/s41...
Reposted by Akshay S.
If an #H5N1 pandemic starts tomorrow or in three months, there will be little mystery as to how it happened. The conditions are all there. They have been for a while.
So in some ways the more interesting question to me at the moment is: Why aren’t we in a pandemic yet?
Story here, 🧵 to come:
🧪#IDSky
So in some ways the more interesting question to me at the moment is: Why aren’t we in a pandemic yet?
Story here, 🧵 to come:
🧪#IDSky
Why hasn’t the bird flu pandemic started?
Some scientists examining mutations found in H5N1 viruses fear major outbreak is imminent but others says pathogen remains unpredictable
www.science.org
December 6, 2024 at 12:54 PM
If an #H5N1 pandemic starts tomorrow or in three months, there will be little mystery as to how it happened. The conditions are all there. They have been for a while.
So in some ways the more interesting question to me at the moment is: Why aren’t we in a pandemic yet?
Story here, 🧵 to come:
🧪#IDSky
So in some ways the more interesting question to me at the moment is: Why aren’t we in a pandemic yet?
Story here, 🧵 to come:
🧪#IDSky
Reposted by Akshay S.
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
December 6, 2024 at 8:39 AM
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Reposted by Akshay S.
Diffusion models create beautiful novel images, but they can also memorize samples from the training set. How does this blending of features allow creating novel patterns? Our new work in Sci4DL workshop #neurips2024 shows that diffusion models behave like Dense Associative Memory networks.
December 5, 2024 at 5:29 PM
Diffusion models create beautiful novel images, but they can also memorize samples from the training set. How does this blending of features allow creating novel patterns? Our new work in Sci4DL workshop #neurips2024 shows that diffusion models behave like Dense Associative Memory networks.
Reposted by Akshay S.
The next generation of probabilistic machine learning for weather called GenCast is published in @natureportfolio.bsky.social today 🥳. Amazing to see the collective progress in ML for weather as a field over the last 5 years. 🏖️ www.nature.com/articles/s41...
Probabilistic weather forecasting with machine learning - Nature
GenCast, a probabilistic weather model using artificial intelligence for weather forecasting, has greater skill and speed than the top operational medium-range weather forecast in the world and provid...
www.nature.com
December 4, 2024 at 7:30 PM
The next generation of probabilistic machine learning for weather called GenCast is published in @natureportfolio.bsky.social today 🥳. Amazing to see the collective progress in ML for weather as a field over the last 5 years. 🏖️ www.nature.com/articles/s41...
Reposted by Akshay S.
Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
Learning on compressed molecular representations
Last year, a preprint gained notoriety, proposing that a k-nearest neighbour classifier is able to outperform large-language models using compressed text as input and normalised compression distance (...
pubs.rsc.org
November 21, 2024 at 12:58 PM
Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
Reposted by Akshay S.
Not checking nuclear markers like MALAT1 or intronic reads in your scRNA-seq data?🚨
We show their power to flag low-quality cells—even in top public datasets. It’s time to prioritize better QC for cleaner, more reliable genomics research!
Read more: bmcgenomics.biomedcentral.com/articles/10....
1/8
High content of nuclei-free low-quality cells in reference single-cell atlases: a call for more stringent quality control using nuclear fraction - BMC Genomics
The advent of droplet-based single-cell RNA-sequencing (scRNA-seq) has dramatically increased data throughput, enabling the release of a diverse array of tissue cell atlases to the public. However, we...
bmcgenomics.biomedcentral.com
December 3, 2024 at 8:38 AM
Not checking nuclear markers like MALAT1 or intronic reads in your scRNA-seq data?🚨
We show their power to flag low-quality cells—even in top public datasets. It’s time to prioritize better QC for cleaner, more reliable genomics research!
Read more: bmcgenomics.biomedcentral.com/articles/10....
1/8
Reposted by Akshay S.
First post on bsky to highlight our latest work on smell receptors (www.nature.com/articles/s41...). Odorant receptors are notoriously challenging to work with - we used a classic strategy from protein engineering to get a peek into how these receptors recognize such a diversity of smells.
December 4, 2024 at 4:59 AM
First post on bsky to highlight our latest work on smell receptors (www.nature.com/articles/s41...). Odorant receptors are notoriously challenging to work with - we used a classic strategy from protein engineering to get a peek into how these receptors recognize such a diversity of smells.
Reposted by Akshay S.
"Global emergence of regional heatwave hotspots outpaces climate model simulations"
Yeeah, that's not good
www.pnas.org/doi/10.1073/...
Yeeah, that's not good
www.pnas.org/doi/10.1073/...
November 27, 2024 at 7:47 PM
"Global emergence of regional heatwave hotspots outpaces climate model simulations"
Yeeah, that's not good
www.pnas.org/doi/10.1073/...
Yeeah, that's not good
www.pnas.org/doi/10.1073/...