Alissa Hummer
@AlissaHummer
Followers
972
Following
1K
Statuses
276
PhD student @OPIGlets @UniofOxford in ML for antibody design | MPhil @MRC_LMB @Cambridge_Uni | Computational biochemist 💻🧬 || MD @NucleateHQ Oxford
Joined July 2020
Very excited to announce our new preprint, with my PhD work on deep learning to predict change in antibody-antigen binding affinity! Investigating the Volume and Diversity of Data Needed for Generalizable Antibody-Antigen ΔΔG Prediction 🧵⬇️
7
30
198
RT @Pranay_Shahh: I believe this call to build FROs in the UK with @Convergent_FROs is one of the most impactful opportunities to address s…
0
9
0
RT @KalliKappel: The Kappel Lab is opening soon at UCLA and we’re hiring Staff Scientists to help lead our wet-lab projects & to assist wit…
0
97
0
RT @RachaelKretsch: We discovered 3 RNA families that form homo-oligomeric RNA-only complexes! Studying nature continues to expand my wilde…
0
59
0
RT @OPIGlets: Happy 2025 from everyone at OPIG! DPhil student Isaac Ellmen has written a News & Views article for Nature Chemical Biology…
0
15
0
RT @LewisChinery: Happy to share that Humatch, @OPIGlets new humanisation tool, is now available at mAbs - Please…
0
7
0
RT @OPIGlets: Our paper describing AbLang2, an antibody-specific language model trained with focal loss to mitigate against germline bias,…
0
10
0
RT @OPIGlets: OPIG DPhil student @oliverturnbull1 and postdocs @AlissaHummer & @mijr12 contributed computational profiling to a comparative…
0
7
0
RT @StJudeResearch: St. Jude names M. Madan Babu, PhD, as Chief Data Scientist. He’ll lead the new Office of Data Science, advancing biomed…
0
19
0
RT @OPIGlets: OPIG DPhil student @GemmaLGordon led work to build and analyse "PLAbDab-nano: a database of camelid and shark nanobodies from…
0
17
0
RT @AlanNawzadAmin: Structure to sequence models like ProteinMPNN don’t fit their data; we tested! Come see our work at ICML Thursday after…
0
7
0
Understanding the reliability of bioML models is more important than ever! Learn more about our efforts to quantify reliability for structure-to-sequence models, led by @PierreGlaser 📌 ICML poster – booth #1800, happening now! 📰 Paper:
Given the energy spent improving predictive protein sequence models, can we find out how close they are to the ground truth? Log-likelihoods and RMSEs are no good for this, and can only be used for model comparison. (Deep) Kernel Methods to the rescue! (ICML 2024 Poster) 1/n
0
1
21
RT @ml4proteins: Next week, 7/23 @ 4 pm ET, we'll have @proteinrosh @EvoscaleAI present ESM3: Simulating 500 million years of evolution wit…
0
25
0
RT @julian_englert: Crowdsourcing better cancer drugs! At @adaptyvbio, we want to allow anyone to become a protein designer. Test your sk…
0
90
0
RT @workshopmlsb: The Machine Learning in Structural Biology workshop will be back at #NeurIPS for its 5th edition in December! Stay tuned…
0
19
0
RT @kosonocky: Announcing the BioML Challenge 2024: Bits to Binders! In this 5-week competition, teams will use AI methods to design prote…
0
67
0
RT @alexrives: We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming…
0
827
0
RT @ProteinBoston: for the folks who missed @sokrypton's excellent presentation and discussion of #AlphaFold3 last week, you can now check…
0
73
0
RT @ProteinBoston: Join us this Wednesday, June 12th at 7pm for a special session where @sokrypton will walk us through what we need to kno…
0
12
0
RT @H__Spinner: Marks Lab is HIRING!!! If you're a software engineer interested in biology, proteins, RNAs, viruses, genomes, etc etc and M…
0
13
0