Sanjyot Shenoy
@sanjyot.bsky.social
Doctoral Student at the Carnegie Mellon University - University of Pittsburgh Joint Ph.D. Program in Computational Biology (CPCB). Former - Mathematics, IIT Bombay
Pinned
Sanjyot Shenoy
@sanjyot.bsky.social
· Nov 17
Thanks @ramith.fyi for the invitation to join this better version of Twitter/X! Just for an introduction - I am a first year doctoral student at the CMU-Pitt Ph.D. Program in Computational Biology. I am interested in the intersection of Math, CS, ML and its applications to unraveling Biology!
Reposted by Sanjyot Shenoy
Since everyone wants to learn RL for language models now post DeepSeek, reminder that I've been working on this book quietly in the background for months.
Policy gradient chapter is coming together. Plugging away at the book every day now.
rlhfbook.com/c/11-policy-...
Policy gradient chapter is coming together. Plugging away at the book every day now.
rlhfbook.com/c/11-policy-...
February 1, 2025 at 10:05 PM
Since everyone wants to learn RL for language models now post DeepSeek, reminder that I've been working on this book quietly in the background for months.
Policy gradient chapter is coming together. Plugging away at the book every day now.
rlhfbook.com/c/11-policy-...
Policy gradient chapter is coming together. Plugging away at the book every day now.
rlhfbook.com/c/11-policy-...
Reposted by Sanjyot Shenoy
You only get the PhD when you finally truly accept that you will never actually know very much.
December 21, 2024 at 12:07 AM
You only get the PhD when you finally truly accept that you will never actually know very much.
Reposted by Sanjyot Shenoy
I could not be more thrilled to announce the Nature Methods @naturemethods.bsky.social Method of the Year is Spatial Proteomics! Please see our editorial as a roadmap to the fantastic content in this special issue! www.nature.com/articles/s41...
Method of the Year 2024: spatial proteomics - Nature Methods
Approaches for profiling the spatial proteome in tissues are the basis of atlas-scale projects that are delivering on their promise for understanding biological complexity in health and disease.
www.nature.com
December 6, 2024 at 8:52 PM
I could not be more thrilled to announce the Nature Methods @naturemethods.bsky.social Method of the Year is Spatial Proteomics! Please see our editorial as a roadmap to the fantastic content in this special issue! www.nature.com/articles/s41...
Reposted by Sanjyot Shenoy
Me rereading my own code from 2 months ago:
December 7, 2024 at 3:56 AM
Me rereading my own code from 2 months ago:
Reposted by Sanjyot Shenoy
Yes. This experiment will work if you make it your own. Customize your experience, build new ones, make a social network that can be controlled by the people who use it an idea we do not go back on.
The deep goal of bluesky is to decentralize the social internet so that every individual controls their experience of it rather than having it be controlled by 5 random billionaires. Everyone thinks they signed up for a demuskified twitter...we actually signed an exciting and bizarre experiment.
December 6, 2024 at 5:44 PM
Yes. This experiment will work if you make it your own. Customize your experience, build new ones, make a social network that can be controlled by the people who use it an idea we do not go back on.
A really informative thread. I also feel like presentations/online media should have more animation-based explain a lot more than static images/charts. Good data visualization is a difficult challenge but worth the investment (for yourself and others too!)
How to design your presentation?
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
Presentation is an essential skill for academics.
After attending so many meetings, prelims, thesis defenses, research talks, and lectures, I’ve realized that I may have been approaching it all wrong ...
Some (bitter) lessons I learned. 👇
December 7, 2024 at 7:50 AM
A really informative thread. I also feel like presentations/online media should have more animation-based explain a lot more than static images/charts. Good data visualization is a difficult challenge but worth the investment (for yourself and others too!)
Reposted by Sanjyot Shenoy
Hello, #MedSky community! We’re excited to begin our Bluesky journey.
Here is a sampling of the trusted, influential, and essential information you can expect when you follow us:
Here is a sampling of the trusted, influential, and essential information you can expect when you follow us:
December 6, 2024 at 8:24 PM
Hello, #MedSky community! We’re excited to begin our Bluesky journey.
Here is a sampling of the trusted, influential, and essential information you can expect when you follow us:
Here is a sampling of the trusted, influential, and essential information you can expect when you follow us:
Reposted by Sanjyot Shenoy
scRNA-seq has revolutionized biology, but it’s not without challenges. We uncovered significant quality issues in widely used reference cell atlases like the Human Cell Atlas and Tabula Sapiens. Up to 85% of cells in some datasets are low-quality or misidentified!
2/8
2/8
December 3, 2024 at 8:38 AM
scRNA-seq has revolutionized biology, but it’s not without challenges. We uncovered significant quality issues in widely used reference cell atlases like the Human Cell Atlas and Tabula Sapiens. Up to 85% of cells in some datasets are low-quality or misidentified!
2/8
2/8
First real decent snow in Pittsburgh from this season.
December 5, 2024 at 5:17 AM
First real decent snow in Pittsburgh from this season.
Reposted by Sanjyot Shenoy
Finished teaching my new course on deep learning for computer vision. You can find the lecture notes here:
users.cecs.anu.edu.au/~sgould/pape...
users.cecs.anu.edu.au/~sgould/pape...
November 29, 2024 at 9:54 PM
Finished teaching my new course on deep learning for computer vision. You can find the lecture notes here:
users.cecs.anu.edu.au/~sgould/pape...
users.cecs.anu.edu.au/~sgould/pape...
This blog is what my ideal for blogs is. I'll try to some visualizations for my upcoming blog. Manim seems like a good tool for math related animations as far as I know.
November 27, 2024 at 7:45 AM
This blog is what my ideal for blogs is. I'll try to some visualizations for my upcoming blog. Manim seems like a good tool for math related animations as far as I know.
Reposted by Sanjyot Shenoy
Recovering screenshots of stuff that should be on bluesky
November 26, 2024 at 10:01 PM
Recovering screenshots of stuff that should be on bluesky
Reposted by Sanjyot Shenoy
A person on a bicycle is by far the most energy-efficient among animals and machines per distance traveled relative to body weight. The bicycle is magic.
www.jstor.org/stable/24923...
www.jstor.org/stable/24923...
November 24, 2024 at 11:12 PM
A person on a bicycle is by far the most energy-efficient among animals and machines per distance traveled relative to body weight. The bicycle is magic.
www.jstor.org/stable/24923...
www.jstor.org/stable/24923...
Reposted by Sanjyot Shenoy
We are happy to report that our journals and community sites now have Bluesky accounts. Follow them at:
@dev-journal.bsky.social
@jcellsci.bsky.social
@jexpbiol.bsky.social
@dmmjournal.bsky.social
@biologyopen.bsky.social
@the-node.bsky.social
@prelights.bsky.social
@focalplane.bsky.social
@dev-journal.bsky.social
@jcellsci.bsky.social
@jexpbiol.bsky.social
@dmmjournal.bsky.social
@biologyopen.bsky.social
@the-node.bsky.social
@prelights.bsky.social
@focalplane.bsky.social
November 25, 2024 at 2:44 PM
We are happy to report that our journals and community sites now have Bluesky accounts. Follow them at:
@dev-journal.bsky.social
@jcellsci.bsky.social
@jexpbiol.bsky.social
@dmmjournal.bsky.social
@biologyopen.bsky.social
@the-node.bsky.social
@prelights.bsky.social
@focalplane.bsky.social
@dev-journal.bsky.social
@jcellsci.bsky.social
@jexpbiol.bsky.social
@dmmjournal.bsky.social
@biologyopen.bsky.social
@the-node.bsky.social
@prelights.bsky.social
@focalplane.bsky.social
Reposted by Sanjyot Shenoy
Look who's here
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
November 25, 2024 at 1:47 PM
Look who's here
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
Reposted by Sanjyot Shenoy
Non-native English speakers need 50% more time to write a paper
When they do, they face a 2.5 times higher chance of being rejected because of language
journals.plos.org/plosbiology/...
When they do, they face a 2.5 times higher chance of being rejected because of language
journals.plos.org/plosbiology/...
November 24, 2024 at 4:43 AM
Non-native English speakers need 50% more time to write a paper
When they do, they face a 2.5 times higher chance of being rejected because of language
journals.plos.org/plosbiology/...
When they do, they face a 2.5 times higher chance of being rejected because of language
journals.plos.org/plosbiology/...
Reposted by Sanjyot Shenoy
Real science:
1. Is not correlated with the amount of funding
2. Progresses slowly, usually taking many years
3. Leads to more questions than it answers
4. Advances when we disengage & in improvisational discussions
5. Is too important a thing to be done in a non-playful way
1. Is not correlated with the amount of funding
2. Progresses slowly, usually taking many years
3. Leads to more questions than it answers
4. Advances when we disengage & in improvisational discussions
5. Is too important a thing to be done in a non-playful way
November 24, 2024 at 11:37 PM
Real science:
1. Is not correlated with the amount of funding
2. Progresses slowly, usually taking many years
3. Leads to more questions than it answers
4. Advances when we disengage & in improvisational discussions
5. Is too important a thing to be done in a non-playful way
1. Is not correlated with the amount of funding
2. Progresses slowly, usually taking many years
3. Leads to more questions than it answers
4. Advances when we disengage & in improvisational discussions
5. Is too important a thing to be done in a non-playful way
Looking at this makes me happy, even though it's dark and gloomy outside.
November 23, 2024 at 3:03 PM
Looking at this makes me happy, even though it's dark and gloomy outside.
Most elite starter pack
November 23, 2024 at 2:33 AM
Most elite starter pack
Reposted by Sanjyot Shenoy
The Royal Society is on Bluesky! We are the independent scientific academy of the UK, founded in 1660 and dedicated to promoting excellence in science for the benefit of humanity. Follow us for the latest research, fascinating looks at science history, events and more: royalsociety.org
Welcome to the Royal Society | Royal Society
The Royal Society is a Fellowship of many of the world's most eminent scientists and is the oldest scientific academy in continuous existence.
royalsociety.org
November 18, 2024 at 3:47 PM
The Royal Society is on Bluesky! We are the independent scientific academy of the UK, founded in 1660 and dedicated to promoting excellence in science for the benefit of humanity. Follow us for the latest research, fascinating looks at science history, events and more: royalsociety.org
Reposted by Sanjyot Shenoy
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
November 22, 2024 at 1:33 AM
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
Reposted by Sanjyot Shenoy
bro, so to run a program, i "execute" it, but to stop it i "kill" it? computers are barbaric, bro
November 22, 2024 at 10:20 PM
bro, so to run a program, i "execute" it, but to stop it i "kill" it? computers are barbaric, bro
Reposted by Sanjyot Shenoy
#MedSky #IDSky
Surprise! Your friends (& your friends’ friends) shape your microbiome! Scientists found that bacteria in your 💩 were a better predictor than demographics like age group, gender, or wealth, of who you’re friends with: www.nature.com/articles/s41.... 🤯
www.nature.com/articles/d41...
Surprise! Your friends (& your friends’ friends) shape your microbiome! Scientists found that bacteria in your 💩 were a better predictor than demographics like age group, gender, or wealth, of who you’re friends with: www.nature.com/articles/s41.... 🤯
www.nature.com/articles/d41...
Your friends shape your microbiome — and so do their friends
Analysis of nearly 2,000 people living in remote villages in Honduras reveals who’s spreading gut microorganisms to whom.
www.nature.com
November 21, 2024 at 9:14 PM
#MedSky #IDSky
Surprise! Your friends (& your friends’ friends) shape your microbiome! Scientists found that bacteria in your 💩 were a better predictor than demographics like age group, gender, or wealth, of who you’re friends with: www.nature.com/articles/s41.... 🤯
www.nature.com/articles/d41...
Surprise! Your friends (& your friends’ friends) shape your microbiome! Scientists found that bacteria in your 💩 were a better predictor than demographics like age group, gender, or wealth, of who you’re friends with: www.nature.com/articles/s41.... 🤯
www.nature.com/articles/d41...
I have created a starter pack with help of @ramith.fyi for all Joint CMU-Pitt Computational Biology program folks. Let me know if I missed out on you!
go.bsky.app/Kh3aRx5
go.bsky.app/Kh3aRx5
November 21, 2024 at 6:19 PM
I have created a starter pack with help of @ramith.fyi for all Joint CMU-Pitt Computational Biology program folks. Let me know if I missed out on you!
go.bsky.app/Kh3aRx5
go.bsky.app/Kh3aRx5