Mastodawn

Andrea Navas-Olive Mar 6, 2024

kari hoffman Mar 6, 2024

@LMPrida @perpl_lab @acnavasolive @saman @cogneurophys 🥳so happy this is out! I wasn’t sure how the ML models would perform, given the frequency shift in monkey (and human) SWRs, and the larger post-ripple wave compared to those in mice. But, a few models rose to the top straightaway and performed even better with modest “top up” training! 📈Now I’m curious how the #opensource toolbox will perform on human hippocampal data. ……..➡️👩‍🔬both senior authors and one lead author were #womenInSTEM working across two continents, and the original multi-model testing was formulated as a hackathon that included #diverserepresentation ! #neuroai #ann #cnn #neuroscience #hippocampus #HippocampalReplay #internationalwomensday

Andrea Navas-Olive Mar 6, 2024

Liset M de la Prida Mar 6, 2024

New 📝 @acnavasolive & Adrian Rubio in Comm Biol. A machine learning toolbox for the analysis of hippocampal ripples 🔗 https://www.nature.com/articles/s42003-024-05871-w AI models trained in 🐁 applied to 🙊 data obtained w similar types of electrodes. See best-models from each architecture & codes for retraining at our GitHub https://github.com/PridaLab/rippl-AI Monkey data thanks to our great collaborators @perpl_lab @karihoffman & @saman

A machine learning toolbox for the analysis of sharp-wave ripples reveals common waveform features across species - Communications Biology

Introducing machine-learning models for cross-species detection and analysis of hippocampal ripple oscillations, this userfriendly open-source toolbox streamlines standardized research and biomedical applications.

Nature

Andrea Navas-Olive Oct 3, 2023

Dan Goodman Oct 3, 2023

This week I read about a Nobel winner whose groundbreaking work didn't get funded and got her demoted, and about data fraud by two of the highest profile scientists who were lauded and mega funded. We have to stop rewarding short term flashy work and overproductive scientists.

It's fine and correct to talk about both incentives and individual responsibility. But if we scientists collectively decided to heavily downplay work without open, raw data and reproducible methods, and ignored journal title when evaluating scientists, this couldn't happen.

The system is absolutely broken and needs structural reform, yes. Journals need to go. Competitive grants are the wrong way to fund science. Scientific prizes are very problematic. But we also need to get better at reading and doing science and valuing what works in the long term.

That's the key point. If we let these things happen it means we are doing science badly.

Andrea Navas-Olive Oct 3, 2023

Officially starting my postdoc at ISTAustria, working with Peter Jonas & @TPVogels 😁🥳

Andrea Navas-Olive Sep 8, 2023

New paper out, & it's SO COOL!! 🤩 How different #metastasis affects 🧠 #LFP? We saw that each type have spectific signatures, so that they can be even classifed from the recordings! 😱 Thanks Alberto, Mariam, @LMPrida & Manuel Valiente for all 😊 https://www.sciencedirect.com/science/article/pii/S1535610823002507

Andrea Navas-Olive Sep 8, 2023

Liset M de la Prida Sep 4, 2023

New 📝 in @cellpress #cancercell! Together with Valiente Lab we look at the electrophysiological signatures of 🧠 metastasis, using multi-electrode recordings and #MachineLearning . By Alberto Sanchez-Aguilera, Mariam Masmudi @acnavasolive & many others👉🏼 📝 https://www.sciencedirect.com/science/article/pii/S1535610823002507 👇🏼🧵

Andrea Navas-Olive Jul 12, 2023

Liset M de la Prida May 30, 2023

Heading to the #SpringHippocampal to meet colleagues and friends who are passionate about the hippocampus! Looking forward to talk about our work with @Julio_EI and @JuanPQuinta on neuronal representations. #DeepCode project #caixaresearch

Andrea Navas-Olive Jul 12, 2023

Liset M de la Prida Jul 4, 2023

Our new @biorxivpreprint preprint 📝 is out!! https://www.biorxiv.org/content/10.1101/2023.07.02.547382v1 by Andrea Navas-Olive and Adrian Rubio. 👉🏼An opensource ML toolbox for sharp-wave ripple detection https://github.com/PridaLab/rippl-AI Trained with 🐭 data and applied to 🙊 in collaboration with @karihoffman and Sam Abbaspoor #DeepCode

Andrea Navas-Olive Jul 12, 2023

Show thread

kari hoffman Jul 4, 2023

@elduvelle @LMPrida @biorxivpreprint @cogneurophys I’m stoked that it worked out so well! The assessment followed closely the methods in Navas-Olive CNN paper https://elifesciences.org/articles/77772 using F1 (balanced accuracy) to reflect both precision and recall (i.e. sensitivity). So both FN and FPs count against the score, equally. The human raters were around .7 and the monkey data started at ~.5 and reached ~.6 (same as mouse levels!) after retraining. A pleasant surprise, given visible differences in the SWR phenotype between rodent and primate clades!

I think Andrea will post more details soon, but meanwhile, some relevant keywords for interested folks (can you think of others we should use?)

#neuroscience #MemoryReplay #learningandmemory #hippocampus #ripples #SWR #replay #cnn #lstm #openscience #hackathon #oscillations

Deep learning-based feature extraction for prediction and interpretation of sharp-wave ripples in the rodent hippocampus

A new method is described to identify sharp-wave ripples from the rodent hippocampus with deep learning techniques, which may help to identify and characterize previously undetected physiological events.

eLife