Sanjat Kanjilal
@sanjatkanjilal.bsky.social
Group leader | Dept of Medical Microbiology | Amsterdam University Medical Center @amsterdamumc.bsky.social | research machine learning for dx/tx/prevention of infectious diseases
It is hard to know what durations of treatment best prevent the selection of resistance at the population level; this is partly on the basis of data that suggests most people develop resistance post treatment through exogenous colonization of a damaged microbiome, rather than endogenous evolution.
November 24, 2025 at 10:37 AM
It is hard to know what durations of treatment best prevent the selection of resistance at the population level; this is partly on the basis of data that suggests most people develop resistance post treatment through exogenous colonization of a damaged microbiome, rather than endogenous evolution.
www.huffpost.com/entry/histor...
No easy solutions, but a lot of excellent points. It may be that tomorrow’s leaders will be those who have the courage to fail
No easy solutions, but a lot of excellent points. It may be that tomorrow’s leaders will be those who have the courage to fail
I Set A Trap To Catch My Students Cheating With AI. The Results Were Shocking.
"Students are not just undermining their ability to learn, but to someday lead."
www.huffpost.com
November 21, 2025 at 11:05 AM
www.huffpost.com/entry/histor...
No easy solutions, but a lot of excellent points. It may be that tomorrow’s leaders will be those who have the courage to fail
No easy solutions, but a lot of excellent points. It may be that tomorrow’s leaders will be those who have the courage to fail
Reposted by Sanjat Kanjilal
Now out in @natcomms.nature.com Kudos to @tylim.bsky.social and @jameshay.bsky.social for a huge effort and thanks to all the collaborators for their hard work. See the final version here: www.nature.com/articles/s41...
November 20, 2025 at 9:58 PM
Now out in @natcomms.nature.com Kudos to @tylim.bsky.social and @jameshay.bsky.social for a huge effort and thanks to all the collaborators for their hard work. See the final version here: www.nature.com/articles/s41...
Reposted by Sanjat Kanjilal
This week is World #AntimicrobialResistance Awareness week
This article collection spans the breadth of #AMR across pathogens (bacteria, viruses, fungi, parasites), covers epidemiological monitoring, diagnostics, treatment, etc
This article collection spans the breadth of #AMR across pathogens (bacteria, viruses, fungi, parasites), covers epidemiological monitoring, diagnostics, treatment, etc
Antimicrobial resistance: a silent pandemic
SPONSOR FEATURES
bit.ly
November 19, 2025 at 4:57 PM
This week is World #AntimicrobialResistance Awareness week
This article collection spans the breadth of #AMR across pathogens (bacteria, viruses, fungi, parasites), covers epidemiological monitoring, diagnostics, treatment, etc
This article collection spans the breadth of #AMR across pathogens (bacteria, viruses, fungi, parasites), covers epidemiological monitoring, diagnostics, treatment, etc
Reposted by Sanjat Kanjilal
The role of AI in infectious diseases is emerging—offering new opportunities for infection prevention, detection & control.
Explore developments & practical applications ⤵️
spkl.io/63323Ad83c @thelancetinfdis.bsky.social #WorldAMRAwarenessWeek
Explore developments & practical applications ⤵️
spkl.io/63323Ad83c @thelancetinfdis.bsky.social #WorldAMRAwarenessWeek
November 19, 2025 at 12:03 PM
The role of AI in infectious diseases is emerging—offering new opportunities for infection prevention, detection & control.
Explore developments & practical applications ⤵️
spkl.io/63323Ad83c @thelancetinfdis.bsky.social #WorldAMRAwarenessWeek
Explore developments & practical applications ⤵️
spkl.io/63323Ad83c @thelancetinfdis.bsky.social #WorldAMRAwarenessWeek
If successful for drug delivery, this could be really be helpful for minimizing adverse effects of treatment for infections… question is, can it get into a non-vascular space? (Ie abscesses or granulomas)…and can it be done cheaply so that we all can use it?
Researchers at ETH Zurich have developed a #Microrobot capable of transporting drugs to specific locations within the body, with the potential for use in #Hospitals in the near future.
———
Read the full article: ethz.ch/en/news-and-...
———
Read the full article: ethz.ch/en/news-and-...
November 15, 2025 at 8:03 AM
If successful for drug delivery, this could be really be helpful for minimizing adverse effects of treatment for infections… question is, can it get into a non-vascular space? (Ie abscesses or granulomas)…and can it be done cheaply so that we all can use it?
Thank you @tedpak.bsky.social for publishing the code for the LLM medical concept extractor you built for our recent paper! 2 things make this significant: a) This isn’t done enough in translational research and b) it’s designed for general use (ie Dockerized). Superb!
github.com/tpaklab/llacie
github.com/tpaklab/llacie
GitHub - tpaklab/llacie: Large Language Model Clinical Information Extractor
Large Language Model Clinical Information Extractor - tpaklab/llacie
github.com
November 13, 2025 at 9:06 AM
Thank you @tedpak.bsky.social for publishing the code for the LLM medical concept extractor you built for our recent paper! 2 things make this significant: a) This isn’t done enough in translational research and b) it’s designed for general use (ie Dockerized). Superb!
github.com/tpaklab/llacie
github.com/tpaklab/llacie
Reposted by Sanjat Kanjilal
Our lab's paper describing the North American H5N1 epizootic is out now in Nature! So thrilled to have this out, and congratulations to @lambod50.bsky.social for all the fantastic work on this: www.nature.com/articles/s41...
Ecology and spread of the North American H5N1 epizootic - Nature
The panzootic of highly pathogenic H5N1 since 2021 was driven by around nine introductions into the Atlantic and Pacific flyways, followed by rapid dissemination through wild migratory birds, primaril...
www.nature.com
November 12, 2025 at 7:33 PM
Our lab's paper describing the North American H5N1 epizootic is out now in Nature! So thrilled to have this out, and congratulations to @lambod50.bsky.social for all the fantastic work on this: www.nature.com/articles/s41...
Sorry for the delayed reply; been a while since I thought of this but yes my recollection is that since BAL samples are ~50mls, we centrifuge prior to Gram staining and aliquot 0.01ml for quantitative culture. Happy to inquire with folks on the bench if that would be of help!
November 7, 2025 at 7:54 AM
Sorry for the delayed reply; been a while since I thought of this but yes my recollection is that since BAL samples are ~50mls, we centrifuge prior to Gram staining and aliquot 0.01ml for quantitative culture. Happy to inquire with folks on the bench if that would be of help!
Gave my 1st talk in NL: how to make multicenter data analysis with patient data actually work.
tl;dr: common data models (global interoperability) + LLMs (data harmonization, mapping, future-proofing) + federated learning (privacy)
Let me know what you think!
drive.google.com/file/d/1N3yk...
tl;dr: common data models (global interoperability) + LLMs (data harmonization, mapping, future-proofing) + federated learning (privacy)
Let me know what you think!
drive.google.com/file/d/1N3yk...
November 5, 2025 at 11:06 AM
Gave my 1st talk in NL: how to make multicenter data analysis with patient data actually work.
tl;dr: common data models (global interoperability) + LLMs (data harmonization, mapping, future-proofing) + federated learning (privacy)
Let me know what you think!
drive.google.com/file/d/1N3yk...
tl;dr: common data models (global interoperability) + LLMs (data harmonization, mapping, future-proofing) + federated learning (privacy)
Let me know what you think!
drive.google.com/file/d/1N3yk...
Last chance world! Application closes tomorrow!
Hey world, we have an opening for a PhD candidate in my lab! Come join our team in Amsterdam and help build an AI learning health system for infectious diseases (along the way eat some haring and get your bike game on)
werkenbij.amsterdamumc.org/nl/vacatures...
werkenbij.amsterdamumc.org/nl/vacatures...
Vacatures - PhD Innovatieve AI-toepassingen in het laboratorium Medische Microbiologie - Amsterdam UMC
Wil jij met AI bijdragen aan snellere en betere diagnostiek van infectieziekten? Ben je analytisch sterk en werk je graag in een multidisciplinair team? Ontdek jouw impact bij Amsterdam UMC.
werkenbij.amsterdamumc.org
November 3, 2025 at 8:58 PM
Last chance world! Application closes tomorrow!
Really happy to see this out! Congrats @tedpak.bsky.social on an important and top notch piece of research!
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...
Syndromic Analysis of Sepsis Cohorts Using Large Language Models
This cohort study compares the performance of a large language model against manual medical record review for extracting presenting signs and symptoms data from hospital admission notes and uses these...
jamanetwork.com
October 26, 2025 at 10:22 PM
Really happy to see this out! Congrats @tedpak.bsky.social on an important and top notch piece of research!
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...
This article doesn't explicitly say what (I think) many of us who practice/d in the US implicitly understand / feel, which is that health disparities, inequity and sickness are a feature, not a byproduct, of the US healthcare system. They are highly profitable
www.thelancet.com/journals/lan...
www.thelancet.com/journals/lan...
Health care in the USA: money has become the mission
Despite extraordinary scientific and medical resources, the US health-care system
underperforms. In this Review we consider the damage wrought by decades of market-based
policies that have stimulated ...
www.thelancet.com
October 23, 2025 at 8:20 AM
This article doesn't explicitly say what (I think) many of us who practice/d in the US implicitly understand / feel, which is that health disparities, inequity and sickness are a feature, not a byproduct, of the US healthcare system. They are highly profitable
www.thelancet.com/journals/lan...
www.thelancet.com/journals/lan...
Hey world, we have an opening for a PhD candidate in my lab! Come join our team in Amsterdam and help build an AI learning health system for infectious diseases (along the way eat some haring and get your bike game on)
werkenbij.amsterdamumc.org/nl/vacatures...
werkenbij.amsterdamumc.org/nl/vacatures...
Vacatures - PhD Innovatieve AI-toepassingen in het laboratorium Medische Microbiologie - Amsterdam UMC
Wil jij met AI bijdragen aan snellere en betere diagnostiek van infectieziekten? Ben je analytisch sterk en werk je graag in een multidisciplinair team? Ontdek jouw impact bij Amsterdam UMC.
werkenbij.amsterdamumc.org
October 22, 2025 at 9:00 AM
Hey world, we have an opening for a PhD candidate in my lab! Come join our team in Amsterdam and help build an AI learning health system for infectious diseases (along the way eat some haring and get your bike game on)
werkenbij.amsterdamumc.org/nl/vacatures...
werkenbij.amsterdamumc.org/nl/vacatures...
D'Angelo's music oeuvre is incredible but it was his song Africa that changed my entire perspective about what is possible with music. The acoustic demo version lifted the song to a new level, which I didn't think was possible.
A true genius 🥲
www.youtube.com/watch?v=NlcA...
A true genius 🥲
www.youtube.com/watch?v=NlcA...
D'Angelo - Africa (Acoustic Demo)
YouTube video by MonBienCherAmi
www.youtube.com
October 14, 2025 at 6:41 PM
D'Angelo's music oeuvre is incredible but it was his song Africa that changed my entire perspective about what is possible with music. The acoustic demo version lifted the song to a new level, which I didn't think was possible.
A true genius 🥲
www.youtube.com/watch?v=NlcA...
A true genius 🥲
www.youtube.com/watch?v=NlcA...
It’s 2am. Do you know where your public health agency is?
October 11, 2025 at 8:08 AM
It’s 2am. Do you know where your public health agency is?
www.nature.com/articles/s41...
Awesome to be a part of this project to publish a huge EHR dataset of patients with/without AMR for the research community
An equally large *harmonized* EHR dataset from my previous center (Mass General Brigham) is forthcoming & will allow for multicenter validation!
Awesome to be a part of this project to publish a huge EHR dataset of patients with/without AMR for the research community
An equally large *harmonized* EHR dataset from my previous center (Mass General Brigham) is forthcoming & will allow for multicenter validation!
Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs - Scientific Data
Scientific Data - Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs
www.nature.com
October 9, 2025 at 9:01 AM
www.nature.com/articles/s41...
Awesome to be a part of this project to publish a huge EHR dataset of patients with/without AMR for the research community
An equally large *harmonized* EHR dataset from my previous center (Mass General Brigham) is forthcoming & will allow for multicenter validation!
Awesome to be a part of this project to publish a huge EHR dataset of patients with/without AMR for the research community
An equally large *harmonized* EHR dataset from my previous center (Mass General Brigham) is forthcoming & will allow for multicenter validation!
Journals and publishers crack down on research from open health data sets
www.science.org/content/arti...
There's a meta-story here about the generation of knowledge in the 21st century and the (immense) resources it takes to ensure it is of high quality. It is / should be an industry unto itself
www.science.org/content/arti...
There's a meta-story here about the generation of knowledge in the 21st century and the (immense) resources it takes to ensure it is of high quality. It is / should be an industry unto itself
Journals and publishers crack down on research from open health data sets
PLOS, Frontiers, and others announce policies trying to stem the tide of suspect research
www.science.org
October 9, 2025 at 7:29 AM
Journals and publishers crack down on research from open health data sets
www.science.org/content/arti...
There's a meta-story here about the generation of knowledge in the 21st century and the (immense) resources it takes to ensure it is of high quality. It is / should be an industry unto itself
www.science.org/content/arti...
There's a meta-story here about the generation of knowledge in the 21st century and the (immense) resources it takes to ensure it is of high quality. It is / should be an industry unto itself
The dawn of the post-literate society
And the end of civilisation
open.substack.com
October 7, 2025 at 5:23 PM
Reposted by Sanjat Kanjilal
Imagine we could travel back in time ⏪⌛️to explore the world of bacterial pathogens before humans discovered and industrialised antibiotics
We just did that to study the history of #AMR spread @science.org
doi.org/10.1126/scie...
If you like time travel & biology, this 🧵is for you👇
We just did that to study the history of #AMR spread @science.org
doi.org/10.1126/scie...
If you like time travel & biology, this 🧵is for you👇
Pre- and postantibiotic epoch: The historical spread of antimicrobial resistance
Plasmids are now the primary vectors of antimicrobial resistance, but our understanding of how human industrialisation of antibiotics influenced their evolution is limited by a paucity of data predati...
doi.org
October 6, 2025 at 10:42 AM
Imagine we could travel back in time ⏪⌛️to explore the world of bacterial pathogens before humans discovered and industrialised antibiotics
We just did that to study the history of #AMR spread @science.org
doi.org/10.1126/scie...
If you like time travel & biology, this 🧵is for you👇
We just did that to study the history of #AMR spread @science.org
doi.org/10.1126/scie...
If you like time travel & biology, this 🧵is for you👇
Science is fun, but the history of science is even...funner!
-Originally considered by Allied scientists in World War II, it proved so intractable that...the problem was proposed to be dropped over Germany so that German scientists could also waste their time on it
en.wikipedia.org/w/index.php?...
-Originally considered by Allied scientists in World War II, it proved so intractable that...the problem was proposed to be dropped over Germany so that German scientists could also waste their time on it
en.wikipedia.org/w/index.php?...
Multi-armed bandit - Wikipedia
en.wikipedia.org
October 6, 2025 at 7:10 AM
Science is fun, but the history of science is even...funner!
-Originally considered by Allied scientists in World War II, it proved so intractable that...the problem was proposed to be dropped over Germany so that German scientists could also waste their time on it
en.wikipedia.org/w/index.php?...
-Originally considered by Allied scientists in World War II, it proved so intractable that...the problem was proposed to be dropped over Germany so that German scientists could also waste their time on it
en.wikipedia.org/w/index.php?...
A stroll around the new hood
October 3, 2025 at 12:46 PM
A stroll around the new hood
Reposted by Sanjat Kanjilal
Historically, viruses were thought to primarily use host cell's translational machinery. New work from @harvardcellbio.bsky.social faculty Amy Lee reveals that a giant DNA virus encodes its own IF4F initiation complex, suggesting an unexpected evolutionary innovation. www.biorxiv.org/content/10.1...
Giant DNA viruses encode a hallmark translation initiation complex of eukaryotic life
In contrast to living organisms, viruses were long thought to lack protein synthesis machinery and instead depend on host factors to translate viral transcripts. Here, we discover that giant DNA virus...
www.biorxiv.org
October 2, 2025 at 6:10 PM
Historically, viruses were thought to primarily use host cell's translational machinery. New work from @harvardcellbio.bsky.social faculty Amy Lee reveals that a giant DNA virus encodes its own IF4F initiation complex, suggesting an unexpected evolutionary innovation. www.biorxiv.org/content/10.1...
arcinstitute.org/news/hie-kin...
Besides the really cool biology, it's also a very nice lay summary of their bioRxiv preprint...good precedent for the rest of us
Besides the really cool biology, it's also a very nice lay summary of their bioRxiv preprint...good precedent for the rest of us
How We Built the First AI-Generated Genomes | Arc Institute
Going from designing individual genes to complete genomes is an incredibly challenging problem. We have previously shown that the genomic foundation models like the Evo series can generate single prot...
arcinstitute.org
September 23, 2025 at 7:39 AM
arcinstitute.org/news/hie-kin...
Besides the really cool biology, it's also a very nice lay summary of their bioRxiv preprint...good precedent for the rest of us
Besides the really cool biology, it's also a very nice lay summary of their bioRxiv preprint...good precedent for the rest of us