The framework uses Google TensorFlow, along with scikit-learn, for expressing neural networks for deep learning.It also makes use of the RDKit python framework, for performing more basic operations on molecular data, such as converting SMILES strings into molecular graphs.The framework is now in the alpha stage, at version 0.1.As the framework develops, it will move toward implementing more models in TensorFlow, which use GPUs for training and inference.This new open source framework is poised to become an accelerating factor for innovation in drug discovery across industry and academia.

Another unique aspect of DeepChem is that it has incorporated a large amount of publicly-available chemical assay datasets, which are described in Table 1.

DeepChem Assay Datasets

Table 1:The current v0.1 DeepChem Framework includes the data sets in this table, along others which will be added to future versions.

Metrics

The squared Pearson Correleation Coefficient is used to quantify the quality of performance of a model trained on any of these regression datasets.Models trained on classification datasets have their predictive quality measured by the area under curve (AUC) for receiver operator characteristic (ROC) curves (AUC-ROC).Some datasets have more than one task, in which case the mean over all tasks is reported by the framework.

Data Splitting

DeepChem uses a number of methods for randomizing or reordering datasets so that models can be trained on sets which are more thoroughly randomized, in both the training and validation sets, for example.These methods are summarized in Table 2.

DeepChem Dataset Splitting Methods

Table 2:Various methods are available for splitting the dataset in order to avoid sampling bias.

Featurizations

DeepChem offers a number of featurization methods, summarized in Table 3.SMILES strings are unique representations of molecules, and can themselves can be used as a molecular feature.The use of SMILES strings has been explored in recent work.SMILES featurization will likely become a part of future versions of DeepChem.

Most machine learning methods, however, require more feature information than can be extracted from a SMILES string alone.

DeepChem Featurizers

Table 3:Various methods are available for splitting the dataset in order to avoid sampling bias.

Supported Models

Supported Models as of v0.1

Table 4: Model types supported by DeepChem 0.1

A Glimpse into the Tox21 Dataset and Deep Learning

The Toxicology in the 21st Century (Tox21) research initiative led to the creation of a public dataset which includes measurements of activation of stress response and nuclear receptor response pathways by 8,014 distinct molecules.Twelve response pathways were observed in total, with each having some association with toxicity.Table 5 summarizes the pathways investigated in the study.

Tox21 Assay Descriptions

Table 5:Biological pathway responses investigated in the Tox21 Machine Learning Challenge.

We used the Tox21 dataset to make predictions on molecular toxicity in DeepChem using the variations shown in Table 6.

Model Construction Parameter Variations Used

Table 6:Model construction parameter variations used in generating our predictions, as shown in Figure 1.

A .csv file containing SMILES strings for 8,014 molecules was used to first featurize each molecule by using either ECFP or molecular graph convolution.IUPAC names for each molecule were queried from NIH Cactus, and toxicity predictions were made, using a trained model, on a set of nine molecules randomly selected from the total tox21 data set.Nine results showing molecular structure (rendered by RDKit), IUPAC names, and predicted toxicity scores, across all 12 biochemical response pathways, described in Table 5, are shown in Figure 1.

Expect more from DeepChem in the Future

The DeepChem framework is undergoing rapid development, and is currently at the 0.1 release version.New models and features will be added, along with more data sets in future.You can download the DeepChem framework from github.There is also a website for framework documentation at deepchem.io.

Microway offers DeepChem pre-installed on our line of WhisperStation products for Deep Learning. Researchers interested in exploring deep learning applications with chemistry and drug discovery can browse our line of WhisperStation products.

References

1.) Subramanian, Govindan, et al. “Computational Modeling of β-secretase 1 (BACE-1) Inhibitors using Ligand Based Approaches.” Journal of Chemical Information and Modeling 56.10 (2016): 1936-1949.
2.) Altae-Tran, Han, et al. “Low Data Drug Discovery with One-shot Learning.” arXiv preprint arXiv:1611.03199 (2016).
3.) Wu, Zhenqin, et al. “MoleculeNet: A Benchmark for Molecular Machine Learning.” arXiv preprint arXiv:1703.00564 (2017).
4.) Gomes, Joseph, et al. “Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity.” arXiv preprint arXiv:1703.10603 (2017).
5.) Gómez-Bombarelli, Rafael, et al. “Automatic chemical design using a data-driven continuous representation of molecules.” arXiv preprint arXiv:1610.02415 (2016).
6.) Mayr, Andreas, et al. “DeepTox: toxicity prediction using deep learning.” Frontiers in Environmental Science 3 (2016): 80.

The post DeepChem – a Deep Learning Framework for Drug Discovery appeared first on Microway.

This is a tutorial on the usage of GPU-accelerated NAMD for molecular dynamics simulations. We make it simple to test your codes on the latest high-performance systems – you are free to use your own applications on our cluster and we also provide a variety of pre-installed applications with built-in GPU support. Our GPU Test Drive Cluster acts as a useful resource for demonstrating the increased application performance which can be achieved with NVIDIA Tesla GPUs.

This post describes the scalable molecular dynamics software NAMD, which comes out of the Theoretical and Computational Biophysics Group at the University of Illinois Urbana-Champaign. NAMD supports a variety of operational modes, including GPU-accelerated runs across large numbers of compute nodes. We’ll demonstrate how a single server with NVIDIA® Tesla®  K40 GPUs can deliver speedups over 4X!

Before continuing, please note that this post assumes you are familiar with NAMD. If you prefer a different molecular dynamics package (e.g., AMBER), read through the list of applications we have pre-installed. There may be no need for you to learn a new tool. If all of these tools are new to you, you will find a number of NAMD tutorials online.

Access the Tesla GPU-accelerated Cluster

Getting started with our GPU Benchmark cluster is fast and easy – fill out this short form to sign up for GPU benchmarking. Although we will send you an e-mail with a general list of commands when your request is accepted, this post goes into further detail.

First, you need to log in to the GPU cluster using SSH. Don’t worry if you haven’t used SSH before – we will send you step-by-step login instructions. Windows users have to perform one additional step, but SSH is built-in on Linux and MacOS.

Run CPU and GPU-accelerated versions of NAMD

Once you’re logged in, it’s easy to compare CPU and GPU performance: enter the NAMD directory and run the NAMD batch script which we have pre-written for you:

cd namd
sbatch run-namd-on-TeslaK40.sh

Waiting for your NAMD job to finish

Our cluster uses SLURM to manage users’ jobs. You can use the squeue command to keep track of your jobs. For real-time information on your job, run: watch squeue (hit CTRL+c to exit). Alternatively, the cluster can e-mail you when your job is finished if you update the NAMD batch script file (although this must be done before submitting your job). Run:

nano run-namd-on-TeslaK40.sh

Within this file, add the following two lines to the #SBATCH section (changing the e-mail address to your own):

#SBATCH --mail-user=yourname@example.com
#SBATCH --mail-type=END

If you would like to closely monitor the compute node which is running your job, check the output of squeue and take note of which compute node your job is running on. Log into that node with SSH and then use one of the following tools to keep an eye on GPU and system status:

ssh node2
nvidia-smi
htop

(hit q to exit htop)

Check the speedup of NAMD on GPUs vs. CPUs

The results from the NAMD batch script will be placed in an output file named namd-K40.xxxx.output.log – below is a sample of the output running on CPUs:

======================================================
= Run CPU only stmv
======================================================
Info: Benchmark time: 20 CPUs 0.531318 s/step 6.14951 days/ns 4769.63 MB memory

and with NAMD running on two GPUs (demonstrating over 4X speed-up):

======================================================
= Run Tesla_K40m GPU-accelerated stmv
======================================================
Info: Benchmark time: 18 CPUs 0.112677 s/step 1.30413 days/ns 2475.9 MB memory

Should you require further details on a particular run, you will see that a separate log file has been created for each of the inputs (e.g., stmv.20_cpu_cores.output). The NAMD output files are available in the benchmarks/ directory (with a separate subdirectory for each test case). If your job has any problems, the errors will be logged to the file namd-K40.xxxx.output.errors

The following chart shows the performance improvements for a CPU-only NAMD run (on two 10-core Ivy Bridge Intel Xeon CPUs) versus a GPU-accelerated NAMD run (on two NVIDIA Tesla K40 GPUs):

Running your own NAMD inputs on GPUs

If you’re familiar with BASH you can write your own batch script from scratch, but we recommend using the run-namd-your-files.sh file as a template when you’d like to try your own simulations. For most NAMD runs, the batch script will only reference a single input file (e.g., the stmv.namd script). This input script will reference any other input files which NAMD might require:

• Structure file (e.g., stmv.psf)
• Coordinates file (e.g., stmv.pdb)
• Input parameters file (e.g., par_all27_prot_na.inp)

You can upload existing inputs from your own workstation/laptop or you can assemble an input job on the cluster. If you opt for the latter, you need to load the appropriate software packages by running:

module load cuda gcc namd

Once your files are in place in your namd/ directory, you’ll need to ensure that the batch script is referencing the correct .namd input file. The relevant lines of the run-namd-your-files.sh file are:

echo "==============================================================="
echo "= Run CPU-only"
echo "==============================================================="

namd2 +p $num_cores_cpu input_file.namd > namd_output__cpu_run.txt
grep Benchmark namd_output__cpu_run.txt

and for execution on GPUs:

echo "==============================================================="
echo "= Run GPU-Accelerated"
echo "==============================================================="

namd2 +p $num_cores_gpu +devices $CUDA_VISIBLE_DEVICES +idlepoll input_file.namd > namd_output__gpu_run.txt
grep Benchmark namd_output__gpu_run.txt

As is hopefully clear, both the CPU and GPU runs use the same input file (input_file.namd). They will each output to a separate log file (namd_output__cpu_run.txt and namd_output__gpu_run.txt). The final line of each section uses the grep utility to print the performance of each run in days per nanosecond (where a lower number indicates better performance).

If you’d like to visualize your results, you will need an SSH client which properly forwards your X-session. You are welcome to contact us if you’re uncertain of this step. Once that’s done, the VMD visualization tool can be run:

module load vmd
vmd

Ready to try GPUs?

Once properly configured (which we’ve already done for you), running NAMD on a GPU cluster isn’t much more difficult than running it on your own workstation. This makes it easy to compare NAMD simulations running on CPUs and GPUs. If you’d like to give it a try, contact one of our experts or sign up for a GPU Test Drive today!

Citations for NAMD:

“NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign.”

James C. Phillips, Rosemary Braun, Wei Wang, James Gumbart, Emad Tajkhorshid, Elizabeth Villa, Christophe Chipot, Robert D. Skeel, Laxmikant Kale, and Klaus Schulten. Scalable molecular dynamics with NAMD. Journal of Computational Chemistry, 26:1781-1802, 2005. abstract, journal
https://www.ks.uiuc.edu/Research/namd/

Featured Illustration:

Molecular Dynamics of Viruses – Satellite Tobacco Mosaic Virus (STMV)

Citation for VMD:

Humphrey, W., Dalke, A. and Schulten, K., “VMD – Visual Molecular Dynamics” J. Molec. Graphics 1996, 14.1, 33-38
https://www.ks.uiuc.edu/Research/vmd/

The post Benchmarking NAMD on a GPU-Accelerated HPC Cluster with NVIDIA Tesla K40 appeared first on Microway.