Phil Fradkin
@phil_fradkin
Followers
274
Following
5K
Statuses
263
Born too late to explore the Earth Too early explore the Galaxy Just in time to study comp bio and climb some rocks PhD @VectorInst
Joined December 2015
RT @artemmoskalev: AI/ML Internships in Drug Discovery🚨 Our team is hiring PhD research interns for summer 2025 in the US. Come work with…
0
19
0
RT @pkoo562: [SAVE THE DATE] MLCB 2025 is happening Sep 10-11 at the NY Genome Center—NYC! Attend the premier conference at the intersecti…
0
43
0
@i000 @BrandesNadav Have people tried weighting the loss by some empirical metric like constraint or conservation? Just even in a small experiments only on human genome
2
0
2
@i000 @BrandesNadav Agreed - although the information signal in the UTRs is significantly more diffused than coding region. We actually have these results - the contrastive objective outperforms MLM on identical pre-training data just haven't made it into the pre-print yet
0
0
2
Each year MLCB is such a great experience and a great place for ML + Bio folks to meet and catch up!
0
1
5
RT @RexMa9: 1/ Really excited to see IntegrAO (Integrate Any Omics) 🧬, a multi-omics integration framework, has been published in Nature Ma…
0
3
0
RT @genophoria: A month ago we @vevo_ai announced that we have generated the largest single-cell perturbation atlas in history, Tahoe-100M.…
0
55
0
RT @lazar_atan: I had a blast working with such an amazing team! @martoskreto @bose_joey @AlexanderTong7 @k_neklyudov Check out our paper…
0
8
0
RT @k_neklyudov: 🧵(1/5) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new…
0
53
0
RT @nalidoust: I agree with this that many of the attempts at building an in silico model of cell will not soon lead to fundamental, new di…
0
1
0
RT @LNuzhna: Nature just published a piece on why probability doesn't exist. Lee Cronin said many times chemical reactions are not real. Yo…
0
743
0
Thanks to the FM4Science workshop at #Neurips for recognizing MolPhenix as best paper! We had so much fun working on this with Puria (co-first author), @karush_, Frederik and co-supervised by Maciej and @dom_beaini
@valence_ai @RecursionPharma
1
4
29
RT @ianshi3: Phil (@phil_fradkin) and I will be presenting Orthrus ( as a spotlight poster at the Workshop on AI fo…
0
2
0
Excited to be presenting Orthrus with @ianshi3 today! We will be presenting our spotlight at the workshop on AI for new drug modalities #NeurIPS2024 Come chat about a new approach to mRNA representation learning!
Phil (@phil_fradkin) and I will be presenting Orthrus ( as a spotlight poster at the Workshop on AI for New Drug Modalities at #NeurIPS2024! Our poster will be up starting 11:40AM in West Meeting Room 109, 110. Excited to be sharing some new results!
0
3
16
RT @hsu_jonny: How Molecules Impact Cells by the @valence_ai team happening now at East Hall! Can we find molecules that can reverse cell…
0
3
0
RT @vallisubasri: My first time @NeurIPSConf, and having so much fun presenting our work GV-Rep!! Great to see old faces and meet new ones…
0
2
0
2. Orthrus (spotlight @ AIDrugX): Contrastive learning for mRNA representations with biologically inspired augmentations Looking forward to seeing friends and meeting new folks. Happy to chat about these mythically named methods and other ideas for cellular rep. & gen. learning!
0
0
4