BOL: Related items

DeepHiC: A Generative Adversarial Network for Enhancing Hi-C Data Resolution

Rahul Nayak — Tue, 03 Mar 2020 01:12:47 -0600

DeepHiC is a GAN-based model for enhancing Hi-C data resolution. We developed this server for helping researchers to enhance their own low-resolution data by a few steps of clicks. Ab initio training could be performed according to our published code. We provided trained models for various depth of low-coverage sequencing Hi-C data. The depth of input data is estimated by its distribution comparing with those of the downsampled Hi-C data we used in training

Address of the bookmark: http://sysomics.com/deephic

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.

Frontend: Perl Web framework documentation - Andrej Sali Lab

Jit — Mon, 08 Jan 2018 22:32:03 -0600

The frontend is a set of Perl classes that displays the web interface, allowing a user to upload their input files, start a job, display a list of all jobs in the system, and get back job results. The main saliwebfrontend class must be subclassed for each web service. This class is then used to display the web pages using a set of CGI scripts that are set up automatically by the build system.

Address of the bookmark: https://saliweb.readthedocs.io/en/latest/frontend.html

PBSuite: Software for Long-Read Sequencing Data from PacBio

Jit — Mon, 27 Feb 2017 09:54:47 -0600

PBJelly - the genome upgrading tool.
PBHoney - the structural variation discovery tool

Both are contained within the PBSuite code found in downloads.

----- PBJelly -----
Read The Paper
http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0047768

PBJelly is a highly automated pipeline that aligns long sequencing reads (such as PacBio RS reads or long 454 reads in fasta format) to high-confidence draft assembles. PBJelly fills or reduces as many captured gaps as possible to produce upgraded draft genomes.

----- PBHoney -----
Read The Paper
http://www.biomedcentral.com/1471-2105/15/180/abstract

PBHoney is an implementation of two variant-identification approaches designed to exploit the high mappability of long reads (i.e., greater than 10,000 bp). PBHoney considers both intra-read discordance and soft-clipped tails of long reads to identify structural variants.

Address of the bookmark: https://sourceforge.net/projects/pb-jelly/

MashMap: a fast and approximate software for mapping long reads (PacBio/ONT) or assembly to reference genome(s)

Jit — Tue, 12 Dec 2017 17:23:31 -0600

MashMap is a fast and approximate software for mapping long reads (PacBio/ONT) or assembly to reference genome(s). It maps a query sequence against a reference region if and only if its estimated alignment identity is above a specified threshold. It does not compute the alignments explicitly, but rather estimates a k-mer based Jaccard similarity using a combination of Winnowing and MinHash. This is then converted to an estimate of sequence identity using the Mash distance. An appropriate k-mer sampling rate is automatically determined given minimum local alignment length and identity thresholds. The efficiency of the algorithm improves as both of these thresholds are increased.

Address of the bookmark: https://github.com/marbl/MashMap

The MARVEL assembler

Jit — Fri, 04 May 2018 19:18:41 -0500

MARVEL consists of a set of tools that facilitate the overlapping, patching, correction and assembly of noisy (not so noisy ones as well) long reads.

The assembly process can be summarized as follows:

overlap
patch reads
overlap (again)
scrubbing
assembly graph construction and touring
optional read correction
fasta file creation

Address of the bookmark: https://github.com/schloi/MARVEL

Hercules: a profile HMM-based hybrid error correction algorithm for long reads

Jit — Mon, 20 Aug 2018 14:14:11 -0500

Choosing whether to use second or third generation sequencing platforms can lead to trade-offs between accuracy and read length. Several studies require long and accurate reads including de novo assembly, fusion and structural variation detection. In such cases researchers often combine both technologies and the more erroneous long reads are corrected using the short reads. Current approaches rely on various graph based alignment techniques and do not take the error profile of the underlying technology into account. Memory- and time- efficient machine learning algorithms that address these shortcomings have the potential to achieve better and more accurate integration of these two technologies. Results: We designed and developed Hercules, the first machine learning-based long read error correction algorithm. The algorithm models every long read as a profile Hidden Markov Model with respect to the underlying platformtextquoterights error profile. The algorithm learns a posterior transition/emission probability distribution for each long read and uses this to correct errors in these reads. Using datasets from two DNA-seq BAC clones (CH17-157L1 and CH17-227A2), and human brain cerebellum polyA RNA-seq, we show that Hercules-corrected reads have the highest mapping rate among all competing algorithms and highest accuracy when most of the basepairs of a long read are covered with short reads. Availability:

Hercules source code is available at https://github.com/BilkentCompGen/Hercules

Address of the bookmark: https://github.com/BilkentCompGen/Hercules

Wtdbg2: a de novo sequence assembler for long noisy reads produced by PacBio or Oxford Nanopore

Neel — Fri, 19 Oct 2018 08:48:43 -0500

Wtdbg2 is a de novo sequence assembler for long noisy reads produced by PacBio or Oxford Nanopore Technologies (ONT). It assembles raw reads without error correction and then builds the consensus from intermediate assembly output. Wtdbg2 is able to assemble the human and even the 32Gb Axolotl genome at a speed tens of times faster than CANU and FALCONwhile producing contigs of comparable base accuracy.

Address of the bookmark: https://github.com/ruanjue/wtdbg2

AlignGraph2: similar genome-assisted reassembly pipeline for PacBio long reads

Rahul Nayak — Sun, 14 Mar 2021 09:42:47 -0500

AlignGraph2 is the second version of AlignGraph for PacBio long reads. It extends and refines contigs assembled from the long reads with a published genome similar to the sequencing genome.

More at https://academic.oup.com/bib/advance-article-abstract/doi/10.1093/bib/bbab022/6146772

Address of the bookmark: https://github.com/huangs001/AlignGraph2