Hannah Wayment-Steele
            
            @HWaymentSteele
Followers
                2K
              Following
                2K
              Media
                87
              Statuses
                577
              Biomolecular dynamics, big datasets, small boats. Asst prof @UWBiochem. Before: @JCCFund fellow with @DorotheeKern, PhD @Stanford https://t.co/73Od8N9ZYF
              
              Madison, WI
            
            
              
              Joined December 2015
            
            
           Protein dynamics was the first research to enchant me >10yrs ago, but I left in PhD bc I couldnt find big expt data to evaluate models. Today w @ginaelnesr, I'm thrilled to share the big dynamics data I've been dreaming of, and the mdl we trained: Dyna-1.  https://t.co/ZawXaGdCVw 
          
          
                
                4
              
              
                
                37
              
              
                
                170
              
             It’s that time of year where if I’m slow to respond to your email, it’s because I’m busy making pain faces on the Charles 
          
                
                3
              
              
                
                2
              
              
                
                89
              
             Join us on Oct. 6 for Biochemistry Colloquium with Brian Hie! @BrianHie's lab conducts research at the intersection of biology and machine learning. This seminar is sponsored by @thermofisher. More info:  https://t.co/fvHzsJ8rKF 
            @HWaymentSteele
          
          
                
                0
              
              
                
                2
              
              
                
                6
              
             Latest genomic AI models report near-perfect prediction of pathogenic variants (e.g. AUROC>0.97 for Evo2). We ran extensive independent evals and found these figures are true, but very misleading. A breakdown of our new preprint: 🧵 
          
                
                9
              
              
                
                118
              
              
                
                486
              
             Beautiful words from @RosettaCommons’s Jeff Gray kicking off @JohnsHopkins biophysics retreat. 
          
                
                0
              
              
                
                4
              
              
                
                22
              
             Happy to be here!! 
           Welcome to Hannah Wayment-Steele (@HWaymentSteele), who joins @UWBiochem this month as an assistant professor! Learn more about her research, interests, and lab: 
          
                
                0
              
              
                
                1
              
              
                
                42
              
             We are looking to fill the shoes of our lab manager/technician who is starting medical school Monday! If you know someone who might be interested and is passionate about the biology of aging, let them know they can apply here: 
          
                
                0
              
              
                
                16
              
              
                
                33
              
             The MLSB workshop will be in San Diego, CA (co-located with NeurIPS) this year for its 6th edition in December 🧬🔬 Stay tuned @workshopmlsb as we share details about the stellar lineup of speakers, the official call for papers, and other announcements!🌟 
          
                
                4
              
              
                
                49
              
              
                
                188
              
             This, all day. When I need a detox from just, like, existing in AI x bio, I go reread Platt’s 1964 “strong inference” essay: 
           Social media has truly warped science consumption. On one hand it has massively democratized it. On the other hand, it's become extremely easy to use hype to simply amplify things that are simply not true. 1/ 
          
                
                0
              
              
                
                4
              
              
                
                34
              
             Maybe it works out in the end cuz the hypers are usually also very intelligent & motivated. But it's getting increasingly difficult to calibrate to the current true state of the art unless u actually read papers, think critically, speak openly & have deep domain expertise. 4/ 
          
                
                1
              
              
                
                6
              
              
                
                40
              
             CASP is getting cut by NIH... 😢 (Anyone with extra funds wanna help support perhaps the most important competition of the century?)  https://t.co/mOuROZYJLh 
          
          
            
            science.org
              Agency silent on funding renewal for contest that inspired creation of AIs that predicted how proteins would fold
            
                
                20
              
              
                
                131
              
              
                
                349
              
             To say something obvious out loud with regards to science trainees: ChatGPT is a great tool, but it won't be there for you in thesis defense, or in job interview 
           It’s a hefty 206-page research paper, and the findings are concerning. "LLM users consistently underperformed at neural, linguistic, and behavioral levels" This study finds LLM dependence weakens the writer’s own neural and linguistic fingerprints. 🤔🤔 Relying only on EEG, 
            
                
                0
              
              
                
                3
              
              
                
                20
              
             Excited to be touching down in the Bay Area for the 2nd annual ensembles meetup put on by @stephanie_mul and @fraser_lab!  https://t.co/INKrYLldEj 
          
          
                
                0
              
              
                
                1
              
              
                
                5
              
             This, we need domain knowledge 🤝 ML knowledge to get places, they don't need to be at odds my optimistic hope is AI lit-reading tools could help more systematically inform model evaluation or catch incorrect claims?  https://t.co/c5qMESDX79 
          
          
            
            rachel.fast.ai
              an AI researcher going back to school for immunology
            
                
                3
              
              
                
                13
              
              
                
                96
              
             At Final Submission Deadline, numerous @kaggle notebooks outperform VFold human expert baseline in #RNA 3D structure prediction! Will these codes sustain performance on new targets released between now and Sep 2025? Join the discussion:  https://t.co/6wMz2E1UK4 
          
          
                
                0
              
              
                
                9
              
              
                
                31
              
             Happy Memorial Day! Today I harvested 10 kg of rhubarb! 
          
                
                2
              
              
                
                0
              
              
                
                12
              
             The W-S lab is seeking to hire a research scientist! This person will lead wet-lab innovations in our team as we combine AI and experiments to understand and design dynamics! Thanks for sharing/RTs!  https://t.co/aEkBSQ8gU1 
          
          
                
                1
              
              
                
                18
              
              
                
                46
              
             Designing proteins for multiple, often competing objectives is a major challenge. In our new preprint, we use deep learning + protein language models to design phages with higher activity, defined specificity, and generalizable infectivity—meeting 26 design goals across several 
          
                
                0
              
              
                
                13
              
              
                
                49