BOL: Related items

Reference Sequence Resource!

LEGE — Wed, 15 Sep 2021 21:15:22 -0500

The ENCODE project uses Reference Genomes from NCBI or UCSC to provide a consistent framework for mapping high-throughput sequencing data. In general, ENCODE data are mapped consistently to 2 human (GRCH38, hg19) and 2 mouse (mm9/mm10) genomes for historical comparability. Drosophia melanogaster experiments are mapped to either dm3 or dm6 and Caenorhabdilis elegans experiments are mapped to ce10 or ce11. T

Address of the bookmark: https://www.encodeproject.org/data-standards/reference-sequences/

Large Language Models in Bioinformatics: Transforming Data Analysis and Interpretation

LEGE — Thu, 02 Jan 2025 11:26:29 -0600

The integration of artificial intelligence (AI) into bioinformatics has ushered in a new era of computational biology. Among the most transformative advancements are large language models (LLMs), such as GPT and BERT, which leverage deep learning to process and interpret vast amounts of text data. These models are reshaping bioinformatics by enhancing data analysis, hypothesis generation, and literature mining.

Understanding Large Language Models

LLMs are AI systems trained on extensive datasets of natural language. Their ability to model context, identify patterns, and generate coherent language has proven invaluable across domains, including bioinformatics. By fine-tuning these models on biological datasets, researchers can unlock insights into molecular biology, systems biology, and beyond.

Key Applications of LLMs in Bioinformatics

1. Annotating Biological Data

Annotating genomic and proteomic data is fundamental yet labor-intensive. LLMs streamline this process by extracting functional annotations from literature and databases, predicting gene and protein functions, and providing automated insights.

2. Mining Scientific Literature

The exponential growth of publications presents a challenge for researchers to stay updated. LLMs can process large volumes of text to extract key findings, summarize papers, and identify trends, thereby facilitating efficient literature reviews.

3. Predicting Gene and Protein Functions

By leveraging sequence data and annotations, LLMs can predict the functions of uncharacterized genes and proteins. This capability is particularly useful for studying non-model organisms and orphan genes.

4. Drug Discovery and Repurposing

LLMs enable pattern recognition across chemical, genomic, and clinical datasets, identifying novel drug candidates and repurposing existing drugs for new therapeutic targets. They can simulate interactions between drugs and biological molecules, accelerating the discovery pipeline.

5. Generating Hypotheses for Research

LLMs analyze complex datasets to propose testable hypotheses. For example, they can predict protein-protein interactions, identify regulatory motifs, or model evolutionary processes in genomes.

Advantages of LLMs in Bioinformatics

Scalability: LLMs process massive datasets rapidly, reducing the time required for data analysis.
Versatility: These models adapt to diverse bioinformatics tasks, from genomic annotation to network analysis.
Contextual Insights: By synthesizing information across disparate datasets, LLMs provide integrative insights into biological systems.

Challenges in Applying LLMs

Despite their promise, LLMs face limitations:

Data Quality and Bias: Inaccurate or biased datasets can affect model predictions, necessitating rigorous data curation.
Interpretability: Understanding the decision-making process of LLMs remains a critical challenge, especially in high-stakes fields like genomics and medicine.
Resource Intensity: Training and deploying LLMs require substantial computational power, which can limit accessibility.
Ethical Concerns: Handling sensitive genomic data raises privacy and security issues, emphasizing the need for ethical guidelines.

Future Prospects

The continued development of LLMs tailored for bioinformatics promises exciting advancements. Specialized models trained on omics data, open-access platforms, and interdisciplinary collaborations will expand the utility of LLMs. Moreover, integrating LLMs with other AI technologies, such as graph neural networks and reinforcement learning, can unlock deeper biological insights.

Conclusion

Large language models are revolutionizing bioinformatics by addressing longstanding challenges in data annotation, literature mining, and function prediction. Their ability to analyze complex biological datasets efficiently positions them as indispensable tools for modern research. As bioinformatics embraces AI, the synergy between LLMs and biological sciences holds the potential to unravel the complexities of life with unprecedented precision and scale.

Visual machine learning !!!

Jitendra Narayan — Wed, 29 Jul 2015 04:29:13 -0500

In machine learning, computers apply statistical learning techniques to automatically identify patterns in data. These techniques can be used to make highly accurate predictions.

More at http://www.r2d3.us/visual-intro-to-machine-learning-part-1/

Address of the bookmark: http://www.r2d3.us/visual-intro-to-machine-learning-part-1/

Free Books on Machine Learning and Artificial Intelligent !

BioStar — Thu, 16 Mar 2023 00:10:24 -0500

An Introduction to Statistical Learning
This book provides a broad and less technical treatment of key topics in statistical learning. Each chapter includes an R lab. This book is appropriate for anyone who wishes to use contemporary tools for data analysis.

https://hastie.su.domains/ISLR2/ISLRv2_website.pdf

Python Data Science Handbook
You’ll learn how to use the core libraries essential for working with data in Python: particularly IPython, NumPy, Pandas, Matplotlib, Scikit-Learn, and related packages. This resource is perfect for tackling day-to-day issues such as cleaning, manipulating, and transforming data — or building machine learning models.

https://jakevdp.github.io/PythonDataScienceHandbook/

Dive into Deep Learning
Interactive deep learning book with code, math, and discussions. Implemented with PyTorch, NumPy/MXNet, JAX, and TensorFlow. Adopted at 400 universities from 60 countries

https://d2l.ai/

Approaching (Almost) Any Machine Learning Problem
This book is for people who have some theoretical knowledge of machine learning and deep learning and want to dive into applied machine learning. The book is more oriented towards how and what should you use to solve machine learning and deep learning problems. The book is for you if you are looking for guidance on approaching machine learning problems.

https://github.com/abhishekkrthakur/approachingalmost/blob/master/AAAMLP.pdf

NGSymposium in Computational Biology

Mon, 09 Mar 2020 06:00:30 -0500

We have a great pleasure to invite you to the NGSymposium in Computational Biology to celebrate the 5th anniversary of the NGSchool Summer Schools. This international conference will make way for exchanging knowledge and experiences between experienced and early-stage researchers as well as bioinformaticians. The meeting will be held on 31.07 - 1.08.2020 in Warsaw. It will be a satellite event to the #NGSchool2020: Statistical Learning in Genomics. It will cover a wide range of topics from basic and applied biomedical sciences: bioinformatics, genomics, transcriptomics, computational biology, Machine Learning.

Registration of active participants will be open from February, 27 12 PM CET to April 17, 23:59 CET. In registration forms you will be asked for providing us with some basic information about yourself. You will also be able to submit your abstract. You can save your registration form after filling it partially and come back later to supply more data e.g. upload an abstract. Your registration will be completed only with the payment of the registration fee reaching our accounts - please make sure to transfer the money in advance!

Registration of passive participants will be open after closing of registration of active participants.

Details an registration: https://ngschool.eu/conference/

Automatic Filtering, Trimming, Error Removing and Quality Control for fastq data

Rahul Nayak — Mon, 13 Nov 2017 05:10:23 -0600

Automatic Filtering, Trimming, Error Removing and Quality Control for fastq data
AfterQC can simply go through all fastq files in a folder and then output three folders: good, bad and QC folders, which contains good reads, bad reads and the QC results of each fastq file/pair.
Currently it supports processing data from HiSeq 2000/2500/3000/4000, Nextseq 500/550, MiniSeq...and other Illumina 1.8 or newer formats

Address of the bookmark: https://github.com/OpenGene/AfterQC

MinION_GC: An R script to do some QC on MinION data

Radha Agarkar — Sun, 03 Dec 2017 15:19:18 -0600

Other tools focus on getting data out of the fastq or fast5 files, which is slow and computationally intensive. The benefit of this approach is that it works on a single, small, .txt summary file. So it's a lot quicker than most other things out there: it takes about a minute to analyse a 4GB flowcell on my laptop.

https://github.com/roblanf/minion_qc

Address of the bookmark: https://github.com/roblanf/minion_qc

MIX: Combining multiple assemblies from NGS data

Rahul Nayak — Tue, 08 May 2018 04:58:05 -0500

Mix is a tool that combines two or more draft assemblies, without relying on a reference genome and has the goal to reduce contig fragmentation and thus speed-up genome finishing. The proposed algorithm builds an extension graph where vertices represent extremities of contigs and edges represent existing alignments between these extremities. These alignment edges are used for contig extension. The resulting output assembly corresponds to a path in the extension graph that maximizes the cumulative contig length.

The Mix algorithm, approach and results were published in BMC bioinformatics : http://www.biomedcentral.com/1471-2105/14/S15/S16.

Address of the bookmark: https://github.com/cbib/MIX

NextSV: a meta-caller for structural variants from low-coverage long-read sequencing data

Jit — Mon, 06 Aug 2018 17:24:53 -0500

NextSV, a meta SV caller and a computational pipeline to perform SV calling from low coverage long-read sequencing data. NextSV integrates three aligners and three SV callers and generates two integrated call sets (sensitive/stringent) for different analysis purpose. The output of NextSV is in ANNOVAR-compatible bed format. Users can easily perform downstream annotation using ANNOVAR and disease gene discovery using Phenolyzer.

Address of the bookmark: https://github.com/Nextomics/NextSV

BamView: a free interactive display of read alignments in BAM data files

Neel — Fri, 09 Nov 2018 13:43:22 -0600

To run the application on UNIX from the downloaded jar file run the UNIX:

java -mx512m -jar BamView.jar

and extra command line options are given when '-h' is used:

java -jar BamView.jar -h

BAM files can be specified on the command line with the '-a' option:

java -mx512m -jar BamView.jar -a pathToFile/sorted.bam

If a BAM filename is not given on the command line BamView will prompt for a file to be entered. The BAM index file should have the same name as the BAM file but with a '.bai' suffix. Multiple BAM files can be loaded and overlaid in the viewer. To make this easier BamView will read in files that contain a list of filenames.

Address of the bookmark: http://bamview.sourceforge.net/