Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt) header
Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt) profile picture

Bioinformatics, genetics, and cancer genomics @dkfz. I also tweet #Rstats #dataviz @baseRgraphics creator @grabstractio

Heidelberg
Joined April 2009
Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)Photo by Anand Mayakonda ๐Ÿ•‰๏ธ (@anand_mt)
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
#grabstract of the day A new HIV vaccine trained monkeys' immune systems to make rare antibodies that block many different strains of the virusโ€”a promising step toward a vaccine that could protect people. doi.org/10.1038/s41586-026-1โ€ฆ
2
1
147
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
#grabstract of the day A study of 7.3 million research papers found that by 2025, an estimated 57% showed signs of AI writing assistance, up from just 12% in 2023, with adoption varying widely across countries and institutions. doi.org/10.1073/pnas.2605754โ€ฆ
1
3
46
โ€œfastVEP annotates the complete GIAB HG002 clinical whole-genome sequencing benchmark (4.05 million high-confidence variants) against the full Ensembl GRCh38 gene model (508,530 transcripts) in 86 seconds.โ€ Finally! VEP is usable.
1
3
145
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
Processing hundreds of tumor samples per week now to train the largest cancer foundation models. AI will cure cancer.
123
252
39
3,107
137,691
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
Do you want to do your #postdoc with the most prestigious fellowship in Europe? Apply to DKFZ Marie Skล‚odowska Curie MasterClasses here: ๐Ÿ‘‰ t1p.de/nx6tu 26 Projects in #cancerresearch #cellandmolecularbiology #genomics #bioinformatics #immunology #medicaltechnology
4
7
1,169
Very interesting sales pitch for Mythos. Benchmarks show itโ€™s significantly good at coding but the marketing is geared at finding critical bugs and security.
We released Claude Opus 4.6 just two months ago. Today we're sharing some info on our new model, Claude Mythos Preview.
62
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
People often ask how breakthroughs occur in cancer biology-often the story is more complex - the survival plot for myeloma outcomes is extraordinary - improvements come about in incremental steps - in my lifetime treatment of Myeloma has almost transformed into a curable disease
25
256
29
1,008
205,990
When they say SaaS is dead - this is what it means. Itโ€™s faster to build one than to search for one.
Very interested in what the coming era of highly bespoke software might look like. Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over experiment duration of 8 weeks. The primary way to do this is to aspire to a certain sum total minute goals in Zone 2 cardio and 1 HIIT/week. 1 hour later I vibe coded this super custom dashboard for this very specific experiment that shows me how I'm tracking. Claude had to reverse engineer the Woodway treadmill cloud API to pull raw data, process, filter, debug it and create a web UI frontend to track the experiment. It wasn't a fully smooth experience and I had to notice and ask to fix bugs e.g. it screwed up metric vs. imperial system units and it screwed up on the calendar matching up days to dates etc. But I still feel like the overall direction is clear: 1) There will never be (and shouldn't be) a specific app on the app store for this kind of thing. I shouldn't have to look for, download and use some kind of a "Cardio experiment tracker", when this thing is ~300 lines of code that an LLM agent will give you in seconds. The idea of an "app store" of a long tail of discrete set of apps you choose from feels somehow wrong and outdated when LLM agents can improvise the app on the spot and just for you. 2) Second, the industry has to reconfigure into a set of services of sensors and actuators with agent native ergonomics. My Woodway treadmill is a sensor - it turns physical state into digital knowledge. It shouldn't maintain some human-readable frontend and my LLM agent shouldn't have to reverse engineer it, it should be an API/CLI easily usable by my agent. I'm a little bit disappointed (and my timelines are correspondingly slower) with how slowly this progression is happening in the industry overall. 99% of products/services still don't have an AI-native CLI yet. 99% of products/services maintain .html/.css docs like I won't immediately look for how to copy paste the whole thing to my agent to get something done. They give you a list of instructions on a webpage to open this or that url and click here or there to do a thing. In 2026. What am I a computer? You do it. Or have my agent do it. So anyway today I am impressed that this random thing took 1 hour (it would have been ~10 hours 2 years ago). But what excites me more is thinking through how this really should have been 1 minute tops. What has to be in place so that it would be 1 minute? So that I could simply say "Hi can you help me track my cardio over the next 8 weeks", and after a very brief Q&A the app would be up. The AI would already have a lot personal context, it would gather the extra needed data, it would reference and search related skill libraries, and maintain all my little apps/automations. TLDR the "app store" of a set of discrete apps that you choose from is an increasingly outdated concept all by itself. The future are services of AI-native sensors & actuators orchestrated via LLM glue into highly custom, ephemeral apps. It's just not here yet.
1
261
Claude just killed like a dozen startups.
Claude in Excel is now available on Pro plans. Claude now accepts multiple files via drag and drop, avoids overwriting your existing cells, and handles longer sessions with auto compaction. Get started: claude.com/claude-in-excel
107
Anthropic is killing it in bioinformatics and comp bio. ๐Ÿ‘๐Ÿ‘
Since launching our AI for Science program, weโ€™ve been working with scientists to understand how AI is accelerating progress. We spoke with 3 labs where Claude is reshaping researchโ€”and starting to point towards novel scientific insights and discoveries. anthropic.com/news/acceleratโ€ฆ
131
I wonder the status of bioinformatic toolsmithing in 2026. The technical barrier is now minimal with coding agents (Claude code for ex.). Anyone with a problem and curiosity can now ship. This is transformative but the question is will journals restrict tools built with AI?
1
2
545
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
This splash-resistant cup borrows properties from nature to minimize spilling and sloshing. Learn more in @ScienceAdvances: scim.ag/49g8oFq
8
47
9
236
36,325
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
#grabstract can now add citations to your manuscript. Just paste your text; AI finds relevant PubMed citations and formats them to 100+ journal styles. It's like EndNote or Zotero on autopilot. Try it for free at grabstract.io
1
132
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
Online Now: Advancing CNS tumor diagnostics with expanded DNA methylation-based classification dlvr.it/TPfTYR
14
1
45
6,145
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
How to convert research paper to slides in 1 minute? First, very quickly, why do we need to do this? โž We often need to convert papers to slides โž To present the paper in a conference โž To present our research to our supervisors โž To pitch our research for funding, and so on Creating slides manually takes a lot of time. Now, you can create slides in under a minute. How? You can do this with @grabstractio It is a tool that converts research into visuals. ๐‡๐จ๐ฐ ๐†๐ซ๐š๐›๐ฌ๐ญ๐ซ๐š๐œ๐ญ ๐ฐ๐จ๐ซ๐ค๐ฌ? 1. Go to grabstract.io and log in. 2. Upload your paper and click on Analyze PDF. 3. Now youโ€™ll see the following for your paper โ†ณ Metadata of your paper โ†ณ Structure of your paper โ†ณ PDF Mindmap of your paper 4. Further, you will see the following options โ†ณ Summary โ†ณ Journal Club โ†ณ PDF Poster โ†ณ Billboard โ†ณ Podcast โ†ณ PDF Chat โ†ณ Manuspect 5. To create slides, click on Billboard, & click Generate 6. It will create one visual with various slides in it. 7. You can copy and paste these as a separate slides ๐–๐ก๐š๐ญ ๐ˆ ๐ฅ๐ข๐ค๐ž๐ ๐š๐›๐จ๐ฎ๐ญ ๐ข๐ญ? โž I think the information on slides is very relevant. โž It only picks the most important information โž The slides are perfect for presenting your paper ๐Ž๐ง๐ž ๐ญ๐ก๐ข๐ง๐  ๐ญ๐ก๐š๐ญ ๐œ๐š๐ง ๐›๐ž ๐ข๐ฆ๐ฉ๐ซ๐จ๐ฏ๐ž๐ โžThe slides are not editable โž A researcher should be able to edit these slides Try Grabstract here: grabstract.io Itโ€™s very powerful tool for visualizing your research Anything you'd like to add?
2
45
1
189
10,037
This is amazing! If youโ€™re looking for something to edit and organize your manuscript figures and panels - here it is. Completely free. ๐Ÿ™Œ
It's finally time to announce what we've been working on. Welcome to the all new Affinity. Download now from affin.link/28b5 - welcome to the start of creative freedom for all, totally free. Forever.
1
131
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
Thrilled to announce our new paper, "Pipeline Olympics," is finally out in @NAR_OpenAccess! This was a massive effort, co-led with @pavlo_lutsik . We present a gold-standard benchmark for DNA methylation sequencing workflows. Check it out: academic.oup.com/nar/articleโ€ฆ
1
2
7
131
๐Ÿ‘๐Ÿ‘๐Ÿ‘
Weโ€™re building tools to support research in the life sciences, from early discovery through to commercialization. With Claude for Life Sciences, weโ€™ve added connectors to scientific tools, Skills, and new partnerships to make Claude more useful for scientific work.
2
109
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
๐Ÿšจ The older the sperm, the more likely it is to cause autism Sequencing sperm using nearly error-free sequencing โ†’ measure % sperm carrying disease-causing mutations: 2% at age 30 โ†’ 4.5% at 70 Most were autism genes New paper in @Nature today ๐Ÿงต
133
600
172
2,480
895,106
Anand Mayakonda ๐Ÿ•‰๏ธ retweeted
#grabstract of the day Single Vaccine, Triple Protection. Scientists create a trivalent vaccine for three deadly brain viruses. @MarkSlifka doi.org/10.1126/scitranslmedโ€ฆ
1
1
124