Dmitry Penzar
@dmitrypenzar
Followers
397
Following
4K
Media
51
Statuses
469
PhD in bioinformatics, ML researcher, teacher
Joined May 2016
(1/8)The LegNet paper is finally published Congrats to @halfacrocodile @WWenya @DariaNogina @ZinkevichA.
academic.oup.com
AbstractMotivation. The increasing volume of data from high-throughput experiments including parallel reporter assays facilitates the development of comple
3
16
59
RT @drklly: I'm excited to share work on a research direction my team has been advancing: connecting machine learning derived genetic varia….
biorxiv.org
Genome-wide association studies (GWAS) have identified thousands of trait-associated loci. Prioritizing causal variants within these loci is critical for characterizing trait biology. Statistical...
0
19
0
RT @keyonV: Can an AI model predict perfectly and still have a terrible world model?. What would that even mean?. Our new ICML paper formal….
0
1K
0
RT @anshulkundaje: Here's an idea. Generally in science, if something doesn't work, we say it doesn't work rather than claiming it does (mo….
0
8
0
RT @algobaker: @anshulkundaje The biggest meme is of course methods that don't compare to predicting basic baselines like 'mean perturbatio….
0
1
0
RT @jmschreiber91: This evaluation of DNA design methods is very well written. If you're interested in the field, you should def take a loo….
biorxiv.org
One outstanding open problem with high therapeutic value is how to design nucleic acid sequences with specific properties. Even just the 5’ UTR sequence admits 2 × 10120 possibilities, making...
0
8
0
RT @GallowayLabMIT: So you want to change transgene expression: just change your promoter, right? Changing the promoter increases RNA and t….
0
114
0
RT @kencan7749: Our paper is now accepted at Neural Networks!.This work builds on our previous threads, updated with deeper analyses. We r….
0
10
0
RT @pranamanam: What a way to end #ICLR2025 in Singapore 🇸🇬 with an acceptance for PepTune in #ICML2025 in Vancouver 🇨🇦! 🥳 So many congratu….
arxiv.org
We present PepTune, a multi-objective discrete diffusion model for simultaneous generation and optimization of therapeutic peptide SMILES. Built on the Masked Discrete Language Model (MDLM)...
0
3
0
RT @pranamanam: Most biological processes, like stem cell differentiation, branch into multiple fates, but current trajectory inference met….
0
32
0
RT @jmschreiber91: I wrote a quick application note on Tomtom-lite, a Python implementation of the Tomtom algorithm for comparing PWMs agai….
biorxiv.org
Summary Pairwise sequence similarity is a core operation in genomic analysis, yet most attention has been given to sequences made up of discrete characters. With the growing prevalence of machine...
0
8
0
RT @ElowitzLab: Synthetic biology could enable new types of programmable therapeutics. Our new preprint introduces synthetic protein circui….
biorxiv.org
Many targeted therapies indirectly suppress cancer cells by inhibiting oncogenic signaling pathways such as Ras[1][1]–[4][2]. This renders them susceptible to resistance and limits their long-term...
0
79
0
Really liked that reading.
0
0
1
RT @bettieliu: Delighted to share our latest work deciphering the landscape of chromatin accessibility and modeling the DNA sequence syntax….
biorxiv.org
Transcription factors (TFs) establish cell identity during development by binding regulatory DNA in a sequence-specific manner, often promoting local chromatin accessibility, and regulating gene...
0
65
0
It was very surprising to found that during Ribonanza competition. One way to counter this was using masked convolution.
@rgilman33 ALL the conv based arch with zero padding and enough layers WILL introduce implicit positional information.Bcuz the kernel is not symetric in each axis, and the zero padding provide the "edge/bound" info.
0
0
3
RT @CSProfKGD: @rgilman33 Position, Padding and Predictions:.A Deeper Look at Position Information in CNNs.
arxiv.org
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of...
0
3
0
RT @ben_szalai: Single-cell foundation models, trained on large-scale scRNA-seq datasets, are increasingly used for post-perturbation RNA-s….
bmcgenomics.biomedcentral.com
Accurately predicting cellular responses to perturbations is essential for understanding cell behaviour in both healthy and diseased states. While perturbation data is ideal for building such...
0
3
0
RT @olexandr: This is very irresponsible to give false promises like that to a millions of patients. If you are familiar with the complexit….
0
47
0
RT @_judewells: I really like this ProGen3 paper because, contrary to the title, I think it actually shows there is relatively little to be….
0
50
0
RT @genologos: Are AlphaFold3 and other protein-ligand structure predictors mostly memorizing their training data?. New study suggests yes.….
0
53
0