🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

M4 Mac Mini AI Cluster Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run LLMs distributed across 4 M4 Pro Mac Minis. The cluster is small (iPhone for reference). It’s running Nemotron 70B at 8 tok/sec and scales to Llama 405B (benchmarks soon).

A k-mer index for the entire SRA, finally.

A new Science study presents “Evo”—a machine learning model capable of decoding and designing DNA, RNA, and protein sequences, from molecular to genome scale, with unparalleled accuracy. Evo’s ability to predict, generate, and engineer entire genomic sequences could change the

Clair3-RNA: A deep learning-based small variant caller for long-read RNA sequencing data biorxiv.org/cgi/content/sh… #biorxiv_bioinfo

Can deep learning improve variant calling accuracy in long-read RNA sequencing data despite its inherent challenges like high error rates and uneven coverage? The University of Hong Kong Rice University bioRxiv "Clair3-RNA: A deep learning-based small variant caller for 2 long-read

The preprint of Clair3-RNA is now in bioRxiv 🔗biorxiv.org/content/10.110…. Phasing gives F1 another 5% jump, and is now available in v0.2.0. Great collaborating again with Fritz Sedlazeck.

I had my hopes to call it ClaiRR to make a pirate theme tool but Ruibang Laurent Luo stayed professional... what can I say it all started with Margaritas in Houston :) haha

🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team DeepSeek exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress with full transparency. These humble building blocks in our online service have been documented,

ClairS-TO: A deep-learning method for long-read tumor-only somatic small variant calling biorxiv.org/content/10.110… #biorxiv_bioinfo

The preprint of ClairS-TO is now in bioRxiv. 🔗biorxiv.org/content/10.110…

Clair3 now natively supports using GPU with CUDA or Apple Silicon to speed up calling in v1.2. using either a 4090, or a M3 Ultra, Clair3 can complete an ONT WGS 30x whole-genome variant calling in ~20min. A quick start is at 🔗github.com/HKU-BAL/Clair3…