Roberto Díaz @roberdp

Miguel Servet Researcher at @idis_research - @GMXenomics Immunogenomics/Autoimmunity/Rheumatology/Oncology/Bioinformatics. Santiago de Compostela Joined February 2011

Tweets

2K
Followers

398
Following

2K
Likes

2K

Jordi Martí @xarxatic

2 weeks ago

Otra noche de insomnio de las mías. Me estoy haciendo el primer café de la mañana, pienso en los horarios de Primaria de cualquier colegio y me dan ganas de llorar. Nos estamos cargando la base de los chavales con chorradas de escaparate. 🧵va...

123 963 3K 268K 382

View Details

Yuanhao Qu @YuanhaoQ

2 weeks ago

𝗖𝗮𝗻 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗽𝗲𝗿𝗳𝗼𝗿𝗺 𝗯𝗶𝗼𝗺𝗲𝗱𝗶𝗰𝗮𝗹 𝗱𝗮𝘁𝗮 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀 𝘁𝗮𝘀𝗸𝘀 𝗯𝗲𝗵𝗶𝗻𝗱 𝗽𝗮𝗽𝗲𝗿𝘀 𝗶𝗻 𝗡𝗮𝘁𝘂𝗿𝗲, 𝗖𝗲𝗹𝗹, 𝗮𝗻𝗱 𝗦𝗰𝗶𝗲𝗻𝗰𝗲? To find out, we built 𝗕𝗶𝗼𝗺𝗻𝗶𝗕𝗲𝗻𝗰𝗵, a benchmark we co-developed with the original paper authors and 5+year domain experts to grade AI agents the way a peer reviewer reads a paper: scrutinizing methods, reasoning, and every analytical choice, not just the final answer. As the first track of this benchmark, 𝗕𝗶𝗼𝗺𝗻𝗶𝗕𝗲𝗻𝗰𝗵-𝗗𝗮𝘁𝗮𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 contains 100 data-analysis tasks drawn directly from 21 published studies in Nature, Cell, Science, Nature Medicine, and other leading journals. Each task hands the agent a real dataset and a research question, then scores its full analytical trajectory against an expert-authored rubric. What's inside: - 𝟭𝟬𝟬 𝘁𝗮𝘀𝗸𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝟱 𝗱𝗶𝘀𝗲𝗮𝘀𝗲 𝗮𝗿𝗲𝗮𝘀 (𝗼𝗻𝗰𝗼𝗹𝗼𝗴𝘆, 𝗶𝗺𝗺𝘂𝗻𝗼𝗹𝗼𝗴𝘆, 𝗻𝗲𝘂𝗿𝗼𝗹𝗼𝗴𝘆, 𝗺𝗲𝘁𝗮𝗯𝗼𝗹𝗶𝗰 & 𝗲𝗻𝗱𝗼𝗰𝗿𝗶𝗻𝗲, 𝗰𝗮𝗿𝗱𝗶𝗼𝘃𝗮𝘀𝗰𝘂𝗹𝗮𝗿) 𝗽𝗹𝘂𝘀 𝗴𝗲𝗻𝗲𝗿𝗮𝗹 𝗯𝗶𝗼𝗹𝗼𝗴𝘆 - 𝟭𝟳 𝗮𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝗮𝗹 𝘁𝗮𝘀𝗸 𝘁𝘆𝗽𝗲𝘀 (𝗲.𝗴., 𝗚𝗪𝗔𝗦/𝗲𝗤𝗧𝗟 𝗰𝗼𝗹𝗼𝗰𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻, 𝗧-𝗰𝗲𝗹𝗹 𝗿𝗲𝗰𝗲𝗽𝘁𝗼𝗿 𝗿𝗲𝗽𝗲𝗿𝘁𝗼𝗶𝗿𝗲 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀, 𝗰𝗲𝗹𝗹-𝗰𝗲𝗹𝗹 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝗰𝗮𝘁𝗶𝗼𝗻) - 𝗔𝗻 𝗲𝘅𝗽𝗲𝗿𝘁-𝗰𝘂𝗿𝗮𝘁𝗲𝗱 𝗿𝘂𝗯𝗿𝗶𝗰 𝗳𝗼𝗿 𝗲𝘃𝗲𝗿𝘆 𝘁𝗮𝘀𝗸, 𝘀𝗰𝗼𝗿𝗶𝗻𝗴 𝟲 𝗱𝗶𝗺𝗲𝗻𝘀𝗶𝗼𝗻𝘀 𝗼𝗳 𝗮𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝗮𝗹 𝗾𝘂𝗮𝗹𝗶𝘁𝘆 - 𝗣𝗿𝗼𝗰𝗲𝘀𝘀-𝗹𝗲𝘃𝗲𝗹 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗼𝗳 𝟵 𝗳𝗿𝗼𝗻𝘁𝗶𝗲𝗿 𝗟𝗟𝗠𝘀 (𝗚𝗣𝗧-𝟱.𝟱, 𝗖𝗹𝗮𝘂𝗱𝗲 𝗢𝗽𝘂𝘀 𝟰.𝟳, 𝗮𝗺𝗼𝗻𝗴 𝗼𝘁𝗵𝗲𝗿𝘀) 𝗮𝗰𝗿𝗼𝘀𝘀 𝟰 𝗮𝗴𝗲𝗻𝘁 𝗵𝗮𝗿𝗻𝗲𝘀𝘀𝗲𝘀 (𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲, 𝗖𝗼𝗱𝗲𝘅 𝗖𝗟𝗜, 𝗧𝗲𝗿𝗺𝗶𝗻𝘂𝘀-𝟮, 𝗚𝗲𝗺𝗶𝗻𝗶 𝗖𝗟𝗜) Headline results: - 𝗙𝗿𝗼𝗻𝘁𝗶𝗲𝗿 𝗺𝗼𝗱𝗲𝗹𝘀 𝗹𝗲𝗮𝗱 𝗮𝘁 𝟳𝟯.𝟯/𝟭𝟬𝟬, 𝘄𝗶𝘁𝗵 𝘀𝘂𝗯𝘀𝘁𝗮𝗻𝘁𝗶𝗮𝗹 𝗵𝗲𝗮𝗱𝗿𝗼𝗼𝗺 𝘁𝗼 𝗶𝗺𝗽𝗿𝗼𝘃𝗲. - 𝗧𝗵𝗲 𝗮𝗴𝗲𝗻𝘁 𝗵𝗮𝗿𝗻𝗲𝘀𝘀 𝗺𝗮𝘁𝘁𝗲𝗿𝘀 𝗮𝘀 𝗺𝘂𝗰𝗵 𝗮𝘀 𝘁𝗵𝗲 𝗯𝗮𝘀𝗲 𝗺𝗼𝗱𝗲𝗹. - 𝗔𝗴𝗲𝗻𝘁𝘀 𝗳𝗮𝗹𝗹 𝘀𝗵𝗼𝗿𝘁 𝗼𝗻 𝗯𝗶𝗼𝗹𝗼𝗴𝗶𝗰𝗮𝗹 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝘁𝗶𝗼𝗻, 𝗺𝗲𝘁𝗵𝗼𝗱 𝘀𝗲𝗹𝗲𝗰𝘁𝗶𝗼𝗻, 𝗮𝗻𝗱 𝘀𝗰𝗶𝗲𝗻𝘁𝗶𝗳𝗶𝗰 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴. We hope to make 𝗕𝗶𝗼𝗺𝗻𝗶𝗕𝗲𝗻𝗰𝗵 the most helpful benchmark for biologists to understand how AI agents handle real-world biomedical tasks: where they can be trusted, and where they fall short. We're actively expanding our evaluation effort, and would love to engage the broader scientific community on what comes next. 📄 biorxiv.org/content/10.648… 🤗 huggingface.co/datasets/phylo… Thanks to our amazing @phylo_bio team (Minta Lu, @TuXinming , @serena2z , @TianweiShe , @lecong , @jure , @KexinHuang5 ) and our collaborators at @LaudeInstitute , @Stanford , @Harvard , @PKU1898 , @virginia_tech , Humanlaya Data Lab, Xbench: @alexgshaw , JOU-HO SHIH, Bingqing Zhao, Minjie Shen, Haochen Yang, Jielin Yan, Rongchuan Zhang, Xinze Wu, Tingting Li, Xiaobo Hu, Yuan Jiang, Jiayun Dong, Tao Peng.

16 65 368 34K 95

View Details

Abdel Abdellaoui @dr_appie

3 weeks ago

Here are my four GWAS lectures of ~20 minutes each for the International Statistical Genetics Workshop 2026. They're part of the broader workshop curriculum but also work as standalone lectures covering the basics of GWAS from the ground up. Videos are below 👇🏽

1 34 142 11K 149

View Details

Eric Topol @EricTopol

3 months ago

The dogma about tumor necrosis factor (TNF) was wrong. cell.com/stem-cell-repo…

5 50 189 21K 94

View Details

Nature Biotechnology @NatureBiotech

3 months ago

Agentic AI and the rise of in silico team science in biomedical research - @moorejh go.nature.com/3ZRlP9v

3 39 150 13K 76

View Details

Iván Arias @ivdelaro

4 months ago

🧵 New in @bmj_rmdopen Multi-omics (transcriptomics + proteomics) can biologically stratify patients with axial spondyloarthritis (axSpA) and help predict radiographic progression. Here’s the thread 👇

1 3 3 135 0

View Details

ACR_Journals @ACR_Journals

4 months ago

PrismRA is a molecular signature response classifier shown to predict inadequate response to TNFi. In a prospective RA cohort, use of PrismRA to guide treatment selection was assoc. with significantly better clinical disease activity index scores AC&R doi.org/10.1002/acr.80…

0 3 5 841 4

View Details

American College of Rheumatology @ACRheum

6 months ago

The ACR Convergence 2025 Abstract Supplement in Arthritis & Rheumatology is now online! 📓 acr.tw/3MId6Tt 💻 You can also search the Convergence abstracts at acrabstracts.org

0 4 6 600 0

View Details

Sasha Gusev @SashaGusevPosts

6 months ago

I wrote a little bit about the "missing heritability" question and several recent studies that have brought it to a close. A short 🧵

10 98 459 194K 530

View Details

ACR_Journals @ACR_Journals

7 months ago

External validation of a genetic risk score (GRS) and combined risk score for identifying risk of RA-ILD. Combining a genetic risk score with clinical risk factors performed significantly better than the GRS alone Arthritis Care & Research doi.org/10.1002/acr.25…

2 11 14 2K 2

View Details

Manel Martínez @mmart659

2 years ago

🧵1/9 🔊 Comparteixo recurs acabat de sortir del forn! 100 cartes per treballar factorització / divisibilitat. drive.google.com/file/d/12Y-GYS… Són cartes per imprimir a doble cara (i plastificar). De mida estàndard 56x87 mm. #divisibilitat #recurs #1ESO

11 114 239 25K 125

View Details

Roberto Díaz @roberdp

7 months ago

Buscamos candidat@s para contratos predoctorales Perfiles: 1) Experiencia previa en análisis GWAS 2) Experiencia en análisis bioinformáticos relacionados con enfermedades autoinmunes Contacto: [email protected] @idis_research @GMXenomica

0 0 0 16 0

View Details

B.Palop @bpalop

8 months ago

¿Buscas buenos problemas para trabajar el Pensamiento Computacional? ¿Quieres conocer los retos seleccionados para el concurso (no competitivo) Bebras 2025? ¿Tienes 1h de clase con niños y niñas curiosones antes del 19/12/25? ¡INSCRÍBETE YA! forms.gle/y49pqi6Lm62Uws…

9 69 80 25K 46

View Details

ASHG @GeneticsSociety

8 months ago

Don’t miss the finale or these amazing papers: 📄 bit.ly/42Vm2dx 📄 bit.ly/3WfcVka #ASHG @AJHGNews

0 1 0 565 0

View Details

Javier Santoyo @jsantoyo

8 months ago

The Taiwan Precision Medicine Initiative provides a cohort for large-scale studies. #PopulationGenomics #Genomics @Nature nature.com/articles/s4158…

0 4 17 1K 6

View Details

Manel Esteller @ManelEsteller

8 months ago

Excited to introduce our Cell Reports Medicine @CellRepMed @CellPressNews article with the features of overextended #healthy #lifespan vs common #chronological #time: The story of a record-breaking #supercentenarian in a world burdened by #aging-related diseases. cell.com/cell-reports-m…

9 121 431 29K 132

View Details

SEMERGEN | Médicos de AP @SEMERGENap

8 months ago

🟠Ayer se celebró "#IBERICARDIO: VII Jornadas del Estudio IBERICAN”. Moderaron la sesión el Dr. @SergioCinza, Director de la Agencia de Investigación, y el Dr. @mitotatu y participaron como ponentes la Dra. Carmen Suárez, Dr. @rafamanuEl68, Dr. @alfonsobarquill y Dr. Roberto Díaz. Hilo 👇🧵

1 2 4 276 0

View Details

American College of Rheumatology @ACRheum

9 months ago

#ACR25 abstracts now online! 🎉 Browse over 3,100 abstracts representing the highest-impact research in the field of #rheum. NOTE: Information that goes beyond that contained in the abstract is under media embargo until Oct. 25 at 10:00 AM CT. View 👀 → acr.tw/30RaIzl

1 10 17 3K 2

View Details

Instituto de Invest. Sanitaria de Santiago (IDIS) @idis_research

9 months ago

Una investigación del grupo de Inmunogenética del #IDIS podría contribuir a optimizar la selección de fármacos para el tratamiento de la artritis reumatoide. El estudio acaba de ser publicado en Annals of the Rheumatic Diseases 🙌 Más información aquí 👇 idisantiago.es/una-investigac…

0 2 5 210 0

View Details

Paula Fraga @Paulafraga__

9 months ago

Hace unos años, compartí por aquí un aniversario de boda de mis padres. Hoy cumplen 45 años casados. En aquella ocasión, se generó una polémica consecuencia de lo absurdo de nuestro tiempo, con el clásico señalamiento de reaccionaria, tradicionalista, antifeminista y, lo crean o no, fasc1sta. Pues bien, entonces y hoy, afirmo que en una sociedad nihilista que «deconstruye» y aniquiIa todo vínculo comunitario, no hay nada más revolucionario que defender a la familia. En una sociedad posmoderna decadente que ha identificado libertad se×ual con encuentros fugaces y vacíos, nada más revolucionario que amor e intimidad genuinos. En una sociedad capitalista que promueve la deshumanización y el utilitarismo en las relaciones, colocándonos en escaparates como sujetos fácilmente intercambiables y sustituibles, no hay nada más revolucionario que elegir, cada día, a quien contigo construya un amor comprometido y sereno. Soy afortunada de observar este amor genuino en mi casa, porque son los hechos y el ejemplo los que guían para rechazar incompletudes y construir el amor auténtico que merecemos. Feliz aniversario a mis padres, orgullosa y agradecida 🤍.