Sarvesh Nikumbh
@sarveshnikumbh
AI/ML + CompBio Past: PostDoc Scientist @MRC_LMS @imperialcollege, PhD from MPI-INF Interests: CS, ML, genomics, #rstats, and also cricket. Views are my own.
🥳🥳 SeqArchR is now available online in PLOS Comp Biol doi.org/10.1371/journa… - Give the article a read - Use seqArchR Bioconductor pkg - Appreciate simple but powerful NMF - Share feedback - Spread the knowledge 🙂🙂 @BorisLenhard @GroupLenhard @MRC_LMS @imperialcollege
Happy to introduce *seqArchR*, an approach using non-negative matrix factorisation (NMF) for de novo identification of promoter sequence architectures. 1/7 biorxiv.org/content/10.110…
We are hiring! We are looking for a candidate with expertise in bioinformatics, computational biology or Data science to work on a ICMR-funded project involving cancer genomics data analysis and build stat models for biomarker discovery. More info here: ncbs.res.in/jobportal/onli…
Absolutely recommend this if you are looking for a quality doctoral programme in computational biology in India!
We have extended our deadline to apply to our PhD programme in computational biology @IMScChennai by 12 days. Apply by May 12 if you have a mathematical bent of mind, biology interest, and necessary conditions met! (4-year or 5-year degree in STEM, any qualifying exam) More: 👇
Highly recommend this position! Details about the doctoral network here: danio-recode.eu
A PhD position in computational genomics is open in our group at Imperial/MRC LMS! 🌟 Join the DANIO-ReCODE Doctoral Network and work on gene regulation, evolution, development, and tissue regeneration. Deadline: 8 Jan 2025. t.ly/fDdDW
The fantastic Machine Learning in CompBio #MLCB2024 papers are up at proceedings.mlr.press/v261/ (thanks @lawrennd !) Reminder that all the talks are available on our yt channel youtube.com/@mlcbconf. Please RT!
Great place to do your PhD, nice set of prospective PhD advisors -- highly recommend @MRC_LMS!
A PhD position in computational genomics is open in our group at Imperial/MRC LMS! 🌟 Join the DANIO-ReCODE Doctoral Network and work on gene regulation, evolution, development, and tissue regeneration. Deadline: 8 Jan 2025. t.ly/fDdDW
The fantastic #MLCB2024 talks, spotlights, panel & keynotes are now up on our Youtube channel at youtube.com/watch?v=tWzIK1…. Please RT!
“My message to the young people is this: if I can get so close to the stars, you can too.” —Zhijian “James” Chen, 2024 #LaskerAward winner for his discovery of cGAS, an enzyme that senses self and foreign DNA #Lasker2024 #LaskerLaureate @UTSWMedCenter
#MLCB2024 will be streamed live from YouTube this week (Thursday and Friday). Get the link from here: mlcb.github.io
🎉 Excited to share the peer-reviewed version of our manuscript describing COBIND, a tool for revealing TF co-binding patterns using non-negative matrix factorization. Great work led by @IevaRau @NCMMnews @NordicEMBL @UniOslo_MED @UniOslo academic.oup.com/nar/advance-ar… @NAR_Open
Highly recommend!
Please RT: If you are excited to do a PhD in a vibrant place in Germany and interested in applications of ML in the context of bioinformatics please apply! Deadline 20.9.2024 schulzlab.github.io/Jobs/PosPhd202…
Interested in applying AI and ML to problems in medicine and healthcare? Join @aimlab_tum as a post-doctoral researcher! For more details check this out: portal.mytum.de/jobs/wissensch…
I am very happy to be a part of DANIO-ReCODE. We will be advertising PhD student positions on it soon, stay tuned!
📢 Exciting news 📢 Our MSCA Doctoral Network 🇪🇺 DANIO-ReCODE has just been funded: tinyurl.com/yv4adkat Excellent opportunities to work on vertebrate regenerative processes using advanced genomics tools in a highly international setting 🇬🇧🇩🇪🇦🇹🇭🇷🇸🇮🇪🇸 Stay tuned for more info!
Looks like an important and fun challenge! Modeling TF binding is surprisingly complex and despite many people having their favorite methods (myself included), I don't think we know which are best nor how to apply them to diverse data.
Join the IBIS Challenge: an open competition focused on the computational prediction of transcription factor binding motifs. IBIS aims to advance state-of-the-art methods for Inferring Binding Specificities of human transcription factors from diverse experimental data. (1/12)
💡 Want to leverage the power of foundation models in graphs? 🔥 Introducing Foundation-Informed Message-Passing (FIMP), a framework for applying any pre-trained transformer-based foundation model to Graph Neural Networks! arxiv.org/abs/2210.09475
One hell of a story! 1 person got vaccinated against SARS-CoV2 217 times within 29 months, yes 2 1 7 within 2 9, 29m!!! 😱🤯 N=1, so learnings not generalizable per se, but fascinating to study these rare cases.
Join the IBIS Challenge: an open competition focused on the computational prediction of transcription factor binding motifs. IBIS aims to advance state-of-the-art methods for Inferring Binding Specificities of human transcription factors from diverse experimental data. (1/12)
🧬🤖 Job Opportunity (RT plz)! @bayraktar_lab & I are on the hunt for passionate individuals at the crossroads of Machine Learning & Spatial Biology. Join us for innovative collaborations between labs at @sangerinstitute. Open to various levels: Postdoc/PhD & Predoc. Questions?…
print("here") 😁😁
“The most effective debugging tool is still careful thought, coupled with judiciously placed print statements.” — Brian Kernighan, co-creator of Unix
Looking for a postdoc in my group @NCMMnews @NordicEMBL @UniOslo_MED @unioslo_mn @unioslo_bioinfo to enhance computational resources for regulatory genomics (JASPAR & UniBind) with deep learning. Project in collaboration with @anshulkundaje & @WyWyWa jobbnorge.no/en/available-j…
This is my take as well. But I understand it coming from a tech background and starting to work on computational biology problems only a decade ago. FWIW, we need that 'ignorance is bliss' kinda enthusiasm/motivation for whatever push it can offer.
something I’ve noticed among the sf tech scene is a tendency to underestimate the complexity of biology in their overestimation of how fast AI will get us to “solving it” there seems to be this believe that we have all the data, we just don’t know how to interpret it yet